Upload model files
Browse files- .gitattributes +1 -0
- .ipynb_checkpoints/README-checkpoint.md +212 -0
- README.md +212 -0
- added_tokens.json +3 -0
- all_results.json +8 -0
- chat_template.jinja +1 -0
- config.json +55 -0
- generation_config.json +12 -0
- model.safetensors +3 -0
- special_tokens_map.json +49 -0
- tokenizer.json +3 -0
- tokenizer.model +3 -0
- tokenizer_config.json +0 -0
- train_results.json +8 -0
- trainer_log.jsonl +485 -0
- trainer_state.json +3431 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
.ipynb_checkpoints/README-checkpoint.md
ADDED
|
@@ -0,0 +1,212 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: gemma
|
| 3 |
+
datasets:
|
| 4 |
+
- lianghsun/tw-instruct-500k-rephrase
|
| 5 |
+
language:
|
| 6 |
+
- zh
|
| 7 |
+
- en
|
| 8 |
+
base_model:
|
| 9 |
+
- lianghsun/gemma-3-270m-tw
|
| 10 |
+
library_name: transformers
|
| 11 |
+
tags:
|
| 12 |
+
- Taiwan
|
| 13 |
+
- ROC
|
| 14 |
+
- zhtw
|
| 15 |
+
- chat
|
| 16 |
+
- Twinkle.AI
|
| 17 |
+
---
|
| 18 |
+
|
| 19 |
+
# Model Card for gemma-3-270m-it-cpt-annealing-sft-251126
|
| 20 |
+
|
| 21 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 22 |
+
|
| 23 |
+
This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).
|
| 24 |
+
|
| 25 |
+
## Model Details
|
| 26 |
+
|
| 27 |
+
### Model Description
|
| 28 |
+
|
| 29 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 30 |
+
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
- **Developed by:** [More Information Needed]
|
| 34 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 35 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 36 |
+
- **Model type:** [More Information Needed]
|
| 37 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 38 |
+
- **License:** [More Information Needed]
|
| 39 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 40 |
+
|
| 41 |
+
### Model Sources [optional]
|
| 42 |
+
|
| 43 |
+
<!-- Provide the basic links for the model. -->
|
| 44 |
+
|
| 45 |
+
- **Repository:** [More Information Needed]
|
| 46 |
+
- **Paper [optional]:** [More Information Needed]
|
| 47 |
+
- **Demo [optional]:** [More Information Needed]
|
| 48 |
+
|
| 49 |
+
## Uses
|
| 50 |
+
|
| 51 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 52 |
+
|
| 53 |
+
### Direct Use
|
| 54 |
+
|
| 55 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 56 |
+
|
| 57 |
+
[More Information Needed]
|
| 58 |
+
|
| 59 |
+
### Downstream Use [optional]
|
| 60 |
+
|
| 61 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 62 |
+
|
| 63 |
+
[More Information Needed]
|
| 64 |
+
|
| 65 |
+
### Out-of-Scope Use
|
| 66 |
+
|
| 67 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 68 |
+
|
| 69 |
+
[More Information Needed]
|
| 70 |
+
|
| 71 |
+
## Bias, Risks, and Limitations
|
| 72 |
+
|
| 73 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 74 |
+
|
| 75 |
+
[More Information Needed]
|
| 76 |
+
|
| 77 |
+
### Recommendations
|
| 78 |
+
|
| 79 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 80 |
+
|
| 81 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 82 |
+
|
| 83 |
+
## How to Get Started with the Model
|
| 84 |
+
|
| 85 |
+
Use the code below to get started with the model.
|
| 86 |
+
|
| 87 |
+
[More Information Needed]
|
| 88 |
+
|
| 89 |
+
## Training Details
|
| 90 |
+
|
| 91 |
+
### Training Data
|
| 92 |
+
|
| 93 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 94 |
+
|
| 95 |
+
[More Information Needed]
|
| 96 |
+
|
| 97 |
+
### Training Procedure
|
| 98 |
+
|
| 99 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 100 |
+
|
| 101 |
+
#### Preprocessing [optional]
|
| 102 |
+
|
| 103 |
+
[More Information Needed]
|
| 104 |
+
|
| 105 |
+
|
| 106 |
+
#### Training Hyperparameters
|
| 107 |
+
|
| 108 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 109 |
+
|
| 110 |
+
#### Speeds, Sizes, Times [optional]
|
| 111 |
+
|
| 112 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 113 |
+
|
| 114 |
+
[More Information Needed]
|
| 115 |
+
|
| 116 |
+
## Evaluation
|
| 117 |
+
|
| 118 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 119 |
+
|
| 120 |
+
### Testing Data, Factors & Metrics
|
| 121 |
+
|
| 122 |
+
#### Testing Data
|
| 123 |
+
|
| 124 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 125 |
+
|
| 126 |
+
[More Information Needed]
|
| 127 |
+
|
| 128 |
+
#### Factors
|
| 129 |
+
|
| 130 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 131 |
+
|
| 132 |
+
[More Information Needed]
|
| 133 |
+
|
| 134 |
+
#### Metrics
|
| 135 |
+
|
| 136 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 137 |
+
|
| 138 |
+
[More Information Needed]
|
| 139 |
+
|
| 140 |
+
### Results
|
| 141 |
+
|
| 142 |
+
[More Information Needed]
|
| 143 |
+
|
| 144 |
+
#### Summary
|
| 145 |
+
|
| 146 |
+
|
| 147 |
+
|
| 148 |
+
## Model Examination [optional]
|
| 149 |
+
|
| 150 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 151 |
+
|
| 152 |
+
[More Information Needed]
|
| 153 |
+
|
| 154 |
+
## Environmental Impact
|
| 155 |
+
|
| 156 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 157 |
+
|
| 158 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 159 |
+
|
| 160 |
+
- **Hardware Type:** [More Information Needed]
|
| 161 |
+
- **Hours used:** [More Information Needed]
|
| 162 |
+
- **Cloud Provider:** [More Information Needed]
|
| 163 |
+
- **Compute Region:** [More Information Needed]
|
| 164 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 165 |
+
|
| 166 |
+
## Technical Specifications [optional]
|
| 167 |
+
|
| 168 |
+
### Model Architecture and Objective
|
| 169 |
+
|
| 170 |
+
[More Information Needed]
|
| 171 |
+
|
| 172 |
+
### Compute Infrastructure
|
| 173 |
+
|
| 174 |
+
[More Information Needed]
|
| 175 |
+
|
| 176 |
+
#### Hardware
|
| 177 |
+
|
| 178 |
+
[More Information Needed]
|
| 179 |
+
|
| 180 |
+
#### Software
|
| 181 |
+
|
| 182 |
+
[More Information Needed]
|
| 183 |
+
|
| 184 |
+
## Citation [optional]
|
| 185 |
+
|
| 186 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 187 |
+
|
| 188 |
+
**BibTeX:**
|
| 189 |
+
|
| 190 |
+
[More Information Needed]
|
| 191 |
+
|
| 192 |
+
**APA:**
|
| 193 |
+
|
| 194 |
+
[More Information Needed]
|
| 195 |
+
|
| 196 |
+
## Glossary [optional]
|
| 197 |
+
|
| 198 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 199 |
+
|
| 200 |
+
[More Information Needed]
|
| 201 |
+
|
| 202 |
+
## More Information [optional]
|
| 203 |
+
|
| 204 |
+
[More Information Needed]
|
| 205 |
+
|
| 206 |
+
## Model Card Authors [optional]
|
| 207 |
+
|
| 208 |
+
[More Information Needed]
|
| 209 |
+
|
| 210 |
+
## Model Card Contact
|
| 211 |
+
|
| 212 |
+
[More Information Needed]
|
README.md
ADDED
|
@@ -0,0 +1,212 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: gemma
|
| 3 |
+
datasets:
|
| 4 |
+
- lianghsun/tw-instruct-500k-rephrase
|
| 5 |
+
language:
|
| 6 |
+
- zh
|
| 7 |
+
- en
|
| 8 |
+
base_model:
|
| 9 |
+
- lianghsun/gemma-3-270m-tw
|
| 10 |
+
library_name: transformers
|
| 11 |
+
tags:
|
| 12 |
+
- Taiwan
|
| 13 |
+
- ROC
|
| 14 |
+
- zhtw
|
| 15 |
+
- chat
|
| 16 |
+
- Twinkle.AI
|
| 17 |
+
---
|
| 18 |
+
|
| 19 |
+
# Model Card for gemma-3-270m-it-cpt-annealing-sft-251126
|
| 20 |
+
|
| 21 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 22 |
+
|
| 23 |
+
This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).
|
| 24 |
+
|
| 25 |
+
## Model Details
|
| 26 |
+
|
| 27 |
+
### Model Description
|
| 28 |
+
|
| 29 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 30 |
+
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
- **Developed by:** [More Information Needed]
|
| 34 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 35 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 36 |
+
- **Model type:** [More Information Needed]
|
| 37 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 38 |
+
- **License:** [More Information Needed]
|
| 39 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 40 |
+
|
| 41 |
+
### Model Sources [optional]
|
| 42 |
+
|
| 43 |
+
<!-- Provide the basic links for the model. -->
|
| 44 |
+
|
| 45 |
+
- **Repository:** [More Information Needed]
|
| 46 |
+
- **Paper [optional]:** [More Information Needed]
|
| 47 |
+
- **Demo [optional]:** [More Information Needed]
|
| 48 |
+
|
| 49 |
+
## Uses
|
| 50 |
+
|
| 51 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 52 |
+
|
| 53 |
+
### Direct Use
|
| 54 |
+
|
| 55 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 56 |
+
|
| 57 |
+
[More Information Needed]
|
| 58 |
+
|
| 59 |
+
### Downstream Use [optional]
|
| 60 |
+
|
| 61 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 62 |
+
|
| 63 |
+
[More Information Needed]
|
| 64 |
+
|
| 65 |
+
### Out-of-Scope Use
|
| 66 |
+
|
| 67 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 68 |
+
|
| 69 |
+
[More Information Needed]
|
| 70 |
+
|
| 71 |
+
## Bias, Risks, and Limitations
|
| 72 |
+
|
| 73 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 74 |
+
|
| 75 |
+
[More Information Needed]
|
| 76 |
+
|
| 77 |
+
### Recommendations
|
| 78 |
+
|
| 79 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 80 |
+
|
| 81 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 82 |
+
|
| 83 |
+
## How to Get Started with the Model
|
| 84 |
+
|
| 85 |
+
Use the code below to get started with the model.
|
| 86 |
+
|
| 87 |
+
[More Information Needed]
|
| 88 |
+
|
| 89 |
+
## Training Details
|
| 90 |
+
|
| 91 |
+
### Training Data
|
| 92 |
+
|
| 93 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 94 |
+
|
| 95 |
+
[More Information Needed]
|
| 96 |
+
|
| 97 |
+
### Training Procedure
|
| 98 |
+
|
| 99 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 100 |
+
|
| 101 |
+
#### Preprocessing [optional]
|
| 102 |
+
|
| 103 |
+
[More Information Needed]
|
| 104 |
+
|
| 105 |
+
|
| 106 |
+
#### Training Hyperparameters
|
| 107 |
+
|
| 108 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 109 |
+
|
| 110 |
+
#### Speeds, Sizes, Times [optional]
|
| 111 |
+
|
| 112 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 113 |
+
|
| 114 |
+
[More Information Needed]
|
| 115 |
+
|
| 116 |
+
## Evaluation
|
| 117 |
+
|
| 118 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 119 |
+
|
| 120 |
+
### Testing Data, Factors & Metrics
|
| 121 |
+
|
| 122 |
+
#### Testing Data
|
| 123 |
+
|
| 124 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 125 |
+
|
| 126 |
+
[More Information Needed]
|
| 127 |
+
|
| 128 |
+
#### Factors
|
| 129 |
+
|
| 130 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 131 |
+
|
| 132 |
+
[More Information Needed]
|
| 133 |
+
|
| 134 |
+
#### Metrics
|
| 135 |
+
|
| 136 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 137 |
+
|
| 138 |
+
[More Information Needed]
|
| 139 |
+
|
| 140 |
+
### Results
|
| 141 |
+
|
| 142 |
+
[More Information Needed]
|
| 143 |
+
|
| 144 |
+
#### Summary
|
| 145 |
+
|
| 146 |
+
|
| 147 |
+
|
| 148 |
+
## Model Examination [optional]
|
| 149 |
+
|
| 150 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 151 |
+
|
| 152 |
+
[More Information Needed]
|
| 153 |
+
|
| 154 |
+
## Environmental Impact
|
| 155 |
+
|
| 156 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 157 |
+
|
| 158 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 159 |
+
|
| 160 |
+
- **Hardware Type:** [More Information Needed]
|
| 161 |
+
- **Hours used:** [More Information Needed]
|
| 162 |
+
- **Cloud Provider:** [More Information Needed]
|
| 163 |
+
- **Compute Region:** [More Information Needed]
|
| 164 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 165 |
+
|
| 166 |
+
## Technical Specifications [optional]
|
| 167 |
+
|
| 168 |
+
### Model Architecture and Objective
|
| 169 |
+
|
| 170 |
+
[More Information Needed]
|
| 171 |
+
|
| 172 |
+
### Compute Infrastructure
|
| 173 |
+
|
| 174 |
+
[More Information Needed]
|
| 175 |
+
|
| 176 |
+
#### Hardware
|
| 177 |
+
|
| 178 |
+
[More Information Needed]
|
| 179 |
+
|
| 180 |
+
#### Software
|
| 181 |
+
|
| 182 |
+
[More Information Needed]
|
| 183 |
+
|
| 184 |
+
## Citation [optional]
|
| 185 |
+
|
| 186 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 187 |
+
|
| 188 |
+
**BibTeX:**
|
| 189 |
+
|
| 190 |
+
[More Information Needed]
|
| 191 |
+
|
| 192 |
+
**APA:**
|
| 193 |
+
|
| 194 |
+
[More Information Needed]
|
| 195 |
+
|
| 196 |
+
## Glossary [optional]
|
| 197 |
+
|
| 198 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 199 |
+
|
| 200 |
+
[More Information Needed]
|
| 201 |
+
|
| 202 |
+
## More Information [optional]
|
| 203 |
+
|
| 204 |
+
[More Information Needed]
|
| 205 |
+
|
| 206 |
+
## Model Card Authors [optional]
|
| 207 |
+
|
| 208 |
+
[More Information Needed]
|
| 209 |
+
|
| 210 |
+
## Model Card Contact
|
| 211 |
+
|
| 212 |
+
[More Information Needed]
|
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<image_soft_token>": 262144
|
| 3 |
+
}
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"total_flos": 3.051681632621691e+17,
|
| 4 |
+
"train_loss": 1.9266295598065557,
|
| 5 |
+
"train_runtime": 872.3743,
|
| 6 |
+
"train_samples_per_second": 283.775,
|
| 7 |
+
"train_steps_per_second": 0.555
|
| 8 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ content }}{% elif message['role'] == 'assistant' %}{{ content }}{% endif %}{% endfor %}
|
config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_sliding_window_pattern": 6,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Gemma3ForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"attn_logit_softcapping": null,
|
| 9 |
+
"bos_token_id": 2,
|
| 10 |
+
"dtype": "bfloat16",
|
| 11 |
+
"eos_token_id": 1,
|
| 12 |
+
"final_logit_softcapping": null,
|
| 13 |
+
"head_dim": 256,
|
| 14 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
| 15 |
+
"hidden_size": 640,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 2048,
|
| 18 |
+
"layer_types": [
|
| 19 |
+
"sliding_attention",
|
| 20 |
+
"sliding_attention",
|
| 21 |
+
"sliding_attention",
|
| 22 |
+
"sliding_attention",
|
| 23 |
+
"sliding_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"sliding_attention",
|
| 26 |
+
"sliding_attention",
|
| 27 |
+
"sliding_attention",
|
| 28 |
+
"sliding_attention",
|
| 29 |
+
"sliding_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"sliding_attention",
|
| 32 |
+
"sliding_attention",
|
| 33 |
+
"sliding_attention",
|
| 34 |
+
"sliding_attention",
|
| 35 |
+
"sliding_attention",
|
| 36 |
+
"full_attention"
|
| 37 |
+
],
|
| 38 |
+
"max_position_embeddings": 32768,
|
| 39 |
+
"model_type": "gemma3_text",
|
| 40 |
+
"num_attention_heads": 4,
|
| 41 |
+
"num_hidden_layers": 18,
|
| 42 |
+
"num_key_value_heads": 1,
|
| 43 |
+
"pad_token_id": 0,
|
| 44 |
+
"query_pre_attn_scalar": 256,
|
| 45 |
+
"rms_norm_eps": 1e-06,
|
| 46 |
+
"rope_local_base_freq": 10000.0,
|
| 47 |
+
"rope_scaling": null,
|
| 48 |
+
"rope_theta": 1000000.0,
|
| 49 |
+
"sliding_window": 512,
|
| 50 |
+
"torch_dtype": "bfloat16",
|
| 51 |
+
"transformers_version": "4.55.2",
|
| 52 |
+
"use_bidirectional_attention": false,
|
| 53 |
+
"use_cache": false,
|
| 54 |
+
"vocab_size": 262144
|
| 55 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 2,
|
| 3 |
+
"cache_implementation": "hybrid",
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": [
|
| 6 |
+
1
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 0,
|
| 9 |
+
"top_k": 64,
|
| 10 |
+
"top_p": 0.95,
|
| 11 |
+
"transformers_version": "4.55.2"
|
| 12 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ddb50607dac1c03703c4e817374b4598e2805dd76f4fc3548d604e1dfba5c9bf
|
| 3 |
+
size 871767464
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
{
|
| 4 |
+
"content": "<eos>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
{
|
| 11 |
+
"content": "<end_of_turn>",
|
| 12 |
+
"lstrip": false,
|
| 13 |
+
"normalized": false,
|
| 14 |
+
"rstrip": false,
|
| 15 |
+
"single_word": false
|
| 16 |
+
}
|
| 17 |
+
],
|
| 18 |
+
"boi_token": "<start_of_image>",
|
| 19 |
+
"bos_token": {
|
| 20 |
+
"content": "<bos>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false
|
| 25 |
+
},
|
| 26 |
+
"eoi_token": "<end_of_image>",
|
| 27 |
+
"eos_token": {
|
| 28 |
+
"content": "<eos>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false
|
| 33 |
+
},
|
| 34 |
+
"image_token": "<image_soft_token>",
|
| 35 |
+
"pad_token": {
|
| 36 |
+
"content": "<pad>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false
|
| 41 |
+
},
|
| 42 |
+
"unk_token": {
|
| 43 |
+
"content": "<unk>",
|
| 44 |
+
"lstrip": false,
|
| 45 |
+
"normalized": false,
|
| 46 |
+
"rstrip": false,
|
| 47 |
+
"single_word": false
|
| 48 |
+
}
|
| 49 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
|
| 3 |
+
size 33384568
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
|
| 3 |
+
size 4689074
|
tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"total_flos": 3.051681632621691e+17,
|
| 4 |
+
"train_loss": 1.9266295598065557,
|
| 5 |
+
"train_runtime": 872.3743,
|
| 6 |
+
"train_samples_per_second": 283.775,
|
| 7 |
+
"train_steps_per_second": 0.555
|
| 8 |
+
}
|
trainer_log.jsonl
ADDED
|
@@ -0,0 +1,485 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 1, "total_steps": 484, "loss": 2.4364, "lr": 0.0, "epoch": 0.004134366925064599, "percentage": 0.21, "elapsed_time": "0:00:04", "remaining_time": "0:34:09"}
|
| 2 |
+
{"current_steps": 2, "total_steps": 484, "loss": 2.3816, "lr": 5e-06, "epoch": 0.008268733850129198, "percentage": 0.41, "elapsed_time": "0:00:06", "remaining_time": "0:27:14"}
|
| 3 |
+
{"current_steps": 3, "total_steps": 484, "loss": 2.3568, "lr": 1e-05, "epoch": 0.012403100775193798, "percentage": 0.62, "elapsed_time": "0:00:09", "remaining_time": "0:25:12"}
|
| 4 |
+
{"current_steps": 4, "total_steps": 484, "loss": 2.383, "lr": 1.5e-05, "epoch": 0.016537467700258397, "percentage": 0.83, "elapsed_time": "0:00:11", "remaining_time": "0:23:06"}
|
| 5 |
+
{"current_steps": 5, "total_steps": 484, "loss": 2.3899, "lr": 2e-05, "epoch": 0.020671834625323, "percentage": 1.03, "elapsed_time": "0:00:13", "remaining_time": "0:21:10"}
|
| 6 |
+
{"current_steps": 6, "total_steps": 484, "loss": 2.3397, "lr": 2.5e-05, "epoch": 0.024806201550387597, "percentage": 1.24, "elapsed_time": "0:00:15", "remaining_time": "0:20:51"}
|
| 7 |
+
{"current_steps": 7, "total_steps": 484, "loss": 2.2792, "lr": 3e-05, "epoch": 0.028940568475452195, "percentage": 1.45, "elapsed_time": "0:00:17", "remaining_time": "0:20:00"}
|
| 8 |
+
{"current_steps": 8, "total_steps": 484, "loss": 2.3072, "lr": 3.5e-05, "epoch": 0.03307493540051679, "percentage": 1.65, "elapsed_time": "0:00:19", "remaining_time": "0:19:18"}
|
| 9 |
+
{"current_steps": 9, "total_steps": 484, "loss": 2.2655, "lr": 4e-05, "epoch": 0.037209302325581395, "percentage": 1.86, "elapsed_time": "0:00:21", "remaining_time": "0:19:05"}
|
| 10 |
+
{"current_steps": 10, "total_steps": 484, "loss": 2.312, "lr": 4.5e-05, "epoch": 0.041343669250646, "percentage": 2.07, "elapsed_time": "0:00:23", "remaining_time": "0:18:44"}
|
| 11 |
+
{"current_steps": 11, "total_steps": 484, "loss": 2.2325, "lr": 5e-05, "epoch": 0.04547803617571059, "percentage": 2.27, "elapsed_time": "0:00:25", "remaining_time": "0:18:21"}
|
| 12 |
+
{"current_steps": 12, "total_steps": 484, "loss": 2.253, "lr": 4.99994508999475e-05, "epoch": 0.04961240310077519, "percentage": 2.48, "elapsed_time": "0:00:27", "remaining_time": "0:18:05"}
|
| 13 |
+
{"current_steps": 13, "total_steps": 484, "loss": 2.1965, "lr": 4.999780362391087e-05, "epoch": 0.053746770025839795, "percentage": 2.69, "elapsed_time": "0:00:29", "remaining_time": "0:17:41"}
|
| 14 |
+
{"current_steps": 14, "total_steps": 484, "loss": 2.2547, "lr": 4.9995058244251644e-05, "epoch": 0.05788113695090439, "percentage": 2.89, "elapsed_time": "0:00:31", "remaining_time": "0:17:24"}
|
| 15 |
+
{"current_steps": 15, "total_steps": 484, "loss": 2.1849, "lr": 4.999121488156888e-05, "epoch": 0.06201550387596899, "percentage": 3.1, "elapsed_time": "0:00:32", "remaining_time": "0:17:08"}
|
| 16 |
+
{"current_steps": 16, "total_steps": 484, "loss": 2.1757, "lr": 4.9986273704693843e-05, "epoch": 0.06614987080103359, "percentage": 3.31, "elapsed_time": "0:00:34", "remaining_time": "0:16:54"}
|
| 17 |
+
{"current_steps": 17, "total_steps": 484, "loss": 2.1872, "lr": 4.9980234930682546e-05, "epoch": 0.0702842377260982, "percentage": 3.51, "elapsed_time": "0:00:36", "remaining_time": "0:16:42"}
|
| 18 |
+
{"current_steps": 18, "total_steps": 484, "loss": 2.142, "lr": 4.99730988248063e-05, "epoch": 0.07441860465116279, "percentage": 3.72, "elapsed_time": "0:00:38", "remaining_time": "0:16:30"}
|
| 19 |
+
{"current_steps": 19, "total_steps": 484, "loss": 2.1978, "lr": 4.9964865700539986e-05, "epoch": 0.07855297157622738, "percentage": 3.93, "elapsed_time": "0:00:39", "remaining_time": "0:16:17"}
|
| 20 |
+
{"current_steps": 20, "total_steps": 484, "loss": 2.1625, "lr": 4.995553591954832e-05, "epoch": 0.082687338501292, "percentage": 4.13, "elapsed_time": "0:00:41", "remaining_time": "0:16:05"}
|
| 21 |
+
{"current_steps": 21, "total_steps": 484, "loss": 2.1432, "lr": 4.994510989166997e-05, "epoch": 0.08682170542635659, "percentage": 4.34, "elapsed_time": "0:00:43", "remaining_time": "0:15:57"}
|
| 22 |
+
{"current_steps": 22, "total_steps": 484, "loss": 2.1673, "lr": 4.993358807489953e-05, "epoch": 0.09095607235142118, "percentage": 4.55, "elapsed_time": "0:00:45", "remaining_time": "0:15:51"}
|
| 23 |
+
{"current_steps": 23, "total_steps": 484, "loss": 2.1788, "lr": 4.99209709753674e-05, "epoch": 0.09509043927648579, "percentage": 4.75, "elapsed_time": "0:00:46", "remaining_time": "0:15:40"}
|
| 24 |
+
{"current_steps": 24, "total_steps": 484, "loss": 2.1548, "lr": 4.990725914731759e-05, "epoch": 0.09922480620155039, "percentage": 4.96, "elapsed_time": "0:00:48", "remaining_time": "0:15:31"}
|
| 25 |
+
{"current_steps": 25, "total_steps": 484, "loss": 2.1585, "lr": 4.989245319308335e-05, "epoch": 0.10335917312661498, "percentage": 5.17, "elapsed_time": "0:00:50", "remaining_time": "0:15:23"}
|
| 26 |
+
{"current_steps": 26, "total_steps": 484, "loss": 2.1397, "lr": 4.9876553763060684e-05, "epoch": 0.10749354005167959, "percentage": 5.37, "elapsed_time": "0:00:52", "remaining_time": "0:15:16"}
|
| 27 |
+
{"current_steps": 27, "total_steps": 484, "loss": 2.1242, "lr": 4.985956155567984e-05, "epoch": 0.11162790697674418, "percentage": 5.58, "elapsed_time": "0:00:53", "remaining_time": "0:15:11"}
|
| 28 |
+
{"current_steps": 28, "total_steps": 484, "loss": 2.1153, "lr": 4.984147731737455e-05, "epoch": 0.11576227390180878, "percentage": 5.79, "elapsed_time": "0:00:55", "remaining_time": "0:15:04"}
|
| 29 |
+
{"current_steps": 29, "total_steps": 484, "loss": 2.0822, "lr": 4.982230184254933e-05, "epoch": 0.11989664082687339, "percentage": 5.99, "elapsed_time": "0:00:57", "remaining_time": "0:15:03"}
|
| 30 |
+
{"current_steps": 30, "total_steps": 484, "loss": 2.1242, "lr": 4.9802035973544525e-05, "epoch": 0.12403100775193798, "percentage": 6.2, "elapsed_time": "0:00:59", "remaining_time": "0:15:03"}
|
| 31 |
+
{"current_steps": 31, "total_steps": 484, "loss": 2.129, "lr": 4.978068060059929e-05, "epoch": 0.1281653746770026, "percentage": 6.4, "elapsed_time": "0:01:01", "remaining_time": "0:14:57"}
|
| 32 |
+
{"current_steps": 32, "total_steps": 484, "loss": 2.0808, "lr": 4.975823666181255e-05, "epoch": 0.13229974160206717, "percentage": 6.61, "elapsed_time": "0:01:03", "remaining_time": "0:14:53"}
|
| 33 |
+
{"current_steps": 33, "total_steps": 484, "loss": 2.1064, "lr": 4.973470514310175e-05, "epoch": 0.13643410852713178, "percentage": 6.82, "elapsed_time": "0:01:04", "remaining_time": "0:14:48"}
|
| 34 |
+
{"current_steps": 34, "total_steps": 484, "loss": 2.089, "lr": 4.971008707815952e-05, "epoch": 0.1405684754521964, "percentage": 7.02, "elapsed_time": "0:01:06", "remaining_time": "0:14:42"}
|
| 35 |
+
{"current_steps": 35, "total_steps": 484, "loss": 2.0706, "lr": 4.968438354840834e-05, "epoch": 0.14470284237726097, "percentage": 7.23, "elapsed_time": "0:01:08", "remaining_time": "0:14:36"}
|
| 36 |
+
{"current_steps": 36, "total_steps": 484, "loss": 2.1003, "lr": 4.9657595682952965e-05, "epoch": 0.14883720930232558, "percentage": 7.44, "elapsed_time": "0:01:10", "remaining_time": "0:14:33"}
|
| 37 |
+
{"current_steps": 37, "total_steps": 484, "loss": 2.0789, "lr": 4.962972465853086e-05, "epoch": 0.1529715762273902, "percentage": 7.64, "elapsed_time": "0:01:11", "remaining_time": "0:14:27"}
|
| 38 |
+
{"current_steps": 38, "total_steps": 484, "loss": 2.1034, "lr": 4.960077169946052e-05, "epoch": 0.15710594315245477, "percentage": 7.85, "elapsed_time": "0:01:13", "remaining_time": "0:14:22"}
|
| 39 |
+
{"current_steps": 39, "total_steps": 484, "loss": 2.0912, "lr": 4.957073807758763e-05, "epoch": 0.16124031007751938, "percentage": 8.06, "elapsed_time": "0:01:15", "remaining_time": "0:14:20"}
|
| 40 |
+
{"current_steps": 40, "total_steps": 484, "loss": 2.1084, "lr": 4.953962511222927e-05, "epoch": 0.165374677002584, "percentage": 8.26, "elapsed_time": "0:01:17", "remaining_time": "0:14:17"}
|
| 41 |
+
{"current_steps": 41, "total_steps": 484, "loss": 2.0232, "lr": 4.950743417011591e-05, "epoch": 0.16950904392764857, "percentage": 8.47, "elapsed_time": "0:01:18", "remaining_time": "0:14:12"}
|
| 42 |
+
{"current_steps": 42, "total_steps": 484, "loss": 2.1171, "lr": 4.9474166665331385e-05, "epoch": 0.17364341085271318, "percentage": 8.68, "elapsed_time": "0:01:20", "remaining_time": "0:14:11"}
|
| 43 |
+
{"current_steps": 43, "total_steps": 484, "loss": 2.0441, "lr": 4.9439824059250794e-05, "epoch": 0.17777777777777778, "percentage": 8.88, "elapsed_time": "0:01:23", "remaining_time": "0:14:11"}
|
| 44 |
+
{"current_steps": 44, "total_steps": 484, "loss": 2.0278, "lr": 4.940440786047628e-05, "epoch": 0.18191214470284237, "percentage": 9.09, "elapsed_time": "0:01:24", "remaining_time": "0:14:07"}
|
| 45 |
+
{"current_steps": 45, "total_steps": 484, "loss": 2.0489, "lr": 4.936791962477076e-05, "epoch": 0.18604651162790697, "percentage": 9.3, "elapsed_time": "0:01:26", "remaining_time": "0:14:03"}
|
| 46 |
+
{"current_steps": 46, "total_steps": 484, "loss": 2.04, "lr": 4.9330360954989616e-05, "epoch": 0.19018087855297158, "percentage": 9.5, "elapsed_time": "0:01:28", "remaining_time": "0:13:59"}
|
| 47 |
+
{"current_steps": 47, "total_steps": 484, "loss": 2.0356, "lr": 4.929173350101025e-05, "epoch": 0.19431524547803616, "percentage": 9.71, "elapsed_time": "0:01:29", "remaining_time": "0:13:55"}
|
| 48 |
+
{"current_steps": 48, "total_steps": 484, "loss": 1.995, "lr": 4.925203895965963e-05, "epoch": 0.19844961240310077, "percentage": 9.92, "elapsed_time": "0:01:31", "remaining_time": "0:13:52"}
|
| 49 |
+
{"current_steps": 49, "total_steps": 484, "loss": 2.0618, "lr": 4.921127907463972e-05, "epoch": 0.20258397932816538, "percentage": 10.12, "elapsed_time": "0:01:33", "remaining_time": "0:13:48"}
|
| 50 |
+
{"current_steps": 50, "total_steps": 484, "loss": 2.0819, "lr": 4.9169455636450935e-05, "epoch": 0.20671834625322996, "percentage": 10.33, "elapsed_time": "0:01:34", "remaining_time": "0:13:43"}
|
| 51 |
+
{"current_steps": 51, "total_steps": 484, "loss": 1.9812, "lr": 4.9126570482313424e-05, "epoch": 0.21085271317829457, "percentage": 10.54, "elapsed_time": "0:01:36", "remaining_time": "0:13:39"}
|
| 52 |
+
{"current_steps": 52, "total_steps": 484, "loss": 2.0449, "lr": 4.908262549608644e-05, "epoch": 0.21498708010335918, "percentage": 10.74, "elapsed_time": "0:01:38", "remaining_time": "0:13:36"}
|
| 53 |
+
{"current_steps": 53, "total_steps": 484, "loss": 2.0348, "lr": 4.903762260818551e-05, "epoch": 0.21912144702842376, "percentage": 10.95, "elapsed_time": "0:01:40", "remaining_time": "0:13:34"}
|
| 54 |
+
{"current_steps": 54, "total_steps": 484, "loss": 2.0152, "lr": 4.899156379549769e-05, "epoch": 0.22325581395348837, "percentage": 11.16, "elapsed_time": "0:01:41", "remaining_time": "0:13:30"}
|
| 55 |
+
{"current_steps": 55, "total_steps": 484, "loss": 2.0087, "lr": 4.8944451081294697e-05, "epoch": 0.22739018087855298, "percentage": 11.36, "elapsed_time": "0:01:43", "remaining_time": "0:13:27"}
|
| 56 |
+
{"current_steps": 56, "total_steps": 484, "loss": 2.025, "lr": 4.889628653514402e-05, "epoch": 0.23152454780361756, "percentage": 11.57, "elapsed_time": "0:01:45", "remaining_time": "0:13:24"}
|
| 57 |
+
{"current_steps": 57, "total_steps": 484, "loss": 2.0748, "lr": 4.8847072272818076e-05, "epoch": 0.23565891472868217, "percentage": 11.78, "elapsed_time": "0:01:46", "remaining_time": "0:13:20"}
|
| 58 |
+
{"current_steps": 58, "total_steps": 484, "loss": 2.0116, "lr": 4.879681045620115e-05, "epoch": 0.23979328165374678, "percentage": 11.98, "elapsed_time": "0:01:48", "remaining_time": "0:13:17"}
|
| 59 |
+
{"current_steps": 59, "total_steps": 484, "loss": 2.034, "lr": 4.874550329319457e-05, "epoch": 0.24392764857881136, "percentage": 12.19, "elapsed_time": "0:01:50", "remaining_time": "0:13:13"}
|
| 60 |
+
{"current_steps": 60, "total_steps": 484, "loss": 2.061, "lr": 4.869315303761959e-05, "epoch": 0.24806201550387597, "percentage": 12.4, "elapsed_time": "0:01:51", "remaining_time": "0:13:10"}
|
| 61 |
+
{"current_steps": 61, "total_steps": 484, "loss": 1.9944, "lr": 4.863976198911845e-05, "epoch": 0.25219638242894055, "percentage": 12.6, "elapsed_time": "0:01:53", "remaining_time": "0:13:07"}
|
| 62 |
+
{"current_steps": 62, "total_steps": 484, "loss": 1.9977, "lr": 4.8585332493053364e-05, "epoch": 0.2563307493540052, "percentage": 12.81, "elapsed_time": "0:01:55", "remaining_time": "0:13:06"}
|
| 63 |
+
{"current_steps": 63, "total_steps": 484, "loss": 2.0503, "lr": 4.852986694040347e-05, "epoch": 0.26046511627906976, "percentage": 13.02, "elapsed_time": "0:01:57", "remaining_time": "0:13:03"}
|
| 64 |
+
{"current_steps": 64, "total_steps": 484, "loss": 1.948, "lr": 4.847336776765978e-05, "epoch": 0.26459948320413434, "percentage": 13.22, "elapsed_time": "0:01:59", "remaining_time": "0:13:01"}
|
| 65 |
+
{"current_steps": 65, "total_steps": 484, "loss": 1.9868, "lr": 4.84158374567182e-05, "epoch": 0.268733850129199, "percentage": 13.43, "elapsed_time": "0:02:00", "remaining_time": "0:12:57"}
|
| 66 |
+
{"current_steps": 66, "total_steps": 484, "loss": 2.0067, "lr": 4.8357278534770475e-05, "epoch": 0.27286821705426356, "percentage": 13.64, "elapsed_time": "0:02:02", "remaining_time": "0:12:54"}
|
| 67 |
+
{"current_steps": 67, "total_steps": 484, "loss": 2.0112, "lr": 4.829769357419317e-05, "epoch": 0.27700258397932814, "percentage": 13.84, "elapsed_time": "0:02:03", "remaining_time": "0:12:51"}
|
| 68 |
+
{"current_steps": 68, "total_steps": 484, "loss": 2.0049, "lr": 4.8237085192434676e-05, "epoch": 0.2811369509043928, "percentage": 14.05, "elapsed_time": "0:02:05", "remaining_time": "0:12:49"}
|
| 69 |
+
{"current_steps": 69, "total_steps": 484, "loss": 2.046, "lr": 4.8175456051900256e-05, "epoch": 0.28527131782945736, "percentage": 14.26, "elapsed_time": "0:02:07", "remaining_time": "0:12:46"}
|
| 70 |
+
{"current_steps": 70, "total_steps": 484, "loss": 2.0587, "lr": 4.8112808859835044e-05, "epoch": 0.28940568475452194, "percentage": 14.46, "elapsed_time": "0:02:09", "remaining_time": "0:12:43"}
|
| 71 |
+
{"current_steps": 71, "total_steps": 484, "loss": 2.0167, "lr": 4.804914636820517e-05, "epoch": 0.2935400516795866, "percentage": 14.67, "elapsed_time": "0:02:10", "remaining_time": "0:12:40"}
|
| 72 |
+
{"current_steps": 72, "total_steps": 484, "loss": 2.0274, "lr": 4.798447137357681e-05, "epoch": 0.29767441860465116, "percentage": 14.88, "elapsed_time": "0:02:12", "remaining_time": "0:12:37"}
|
| 73 |
+
{"current_steps": 73, "total_steps": 484, "loss": 2.0141, "lr": 4.791878671699342e-05, "epoch": 0.30180878552971574, "percentage": 15.08, "elapsed_time": "0:02:13", "remaining_time": "0:12:33"}
|
| 74 |
+
{"current_steps": 74, "total_steps": 484, "loss": 2.0168, "lr": 4.7852095283850866e-05, "epoch": 0.3059431524547804, "percentage": 15.29, "elapsed_time": "0:02:15", "remaining_time": "0:12:31"}
|
| 75 |
+
{"current_steps": 75, "total_steps": 484, "loss": 2.0016, "lr": 4.77844000037707e-05, "epoch": 0.31007751937984496, "percentage": 15.5, "elapsed_time": "0:02:17", "remaining_time": "0:12:28"}
|
| 76 |
+
{"current_steps": 76, "total_steps": 484, "loss": 1.9748, "lr": 4.771570385047147e-05, "epoch": 0.31421188630490954, "percentage": 15.7, "elapsed_time": "0:02:18", "remaining_time": "0:12:25"}
|
| 77 |
+
{"current_steps": 77, "total_steps": 484, "loss": 2.0023, "lr": 4.764600984163808e-05, "epoch": 0.3183462532299742, "percentage": 15.91, "elapsed_time": "0:02:20", "remaining_time": "0:12:22"}
|
| 78 |
+
{"current_steps": 78, "total_steps": 484, "loss": 2.021, "lr": 4.757532103878925e-05, "epoch": 0.32248062015503876, "percentage": 16.12, "elapsed_time": "0:02:22", "remaining_time": "0:12:19"}
|
| 79 |
+
{"current_steps": 79, "total_steps": 484, "loss": 1.9658, "lr": 4.750364054714302e-05, "epoch": 0.32661498708010334, "percentage": 16.32, "elapsed_time": "0:02:23", "remaining_time": "0:12:17"}
|
| 80 |
+
{"current_steps": 80, "total_steps": 484, "loss": 2.0258, "lr": 4.743097151548031e-05, "epoch": 0.330749354005168, "percentage": 16.53, "elapsed_time": "0:02:25", "remaining_time": "0:12:15"}
|
| 81 |
+
{"current_steps": 81, "total_steps": 484, "loss": 2.0056, "lr": 4.735731713600665e-05, "epoch": 0.33488372093023255, "percentage": 16.74, "elapsed_time": "0:02:27", "remaining_time": "0:12:13"}
|
| 82 |
+
{"current_steps": 82, "total_steps": 484, "loss": 1.9784, "lr": 4.7282680644211944e-05, "epoch": 0.33901808785529713, "percentage": 16.94, "elapsed_time": "0:02:29", "remaining_time": "0:12:11"}
|
| 83 |
+
{"current_steps": 83, "total_steps": 484, "loss": 1.9203, "lr": 4.72070653187283e-05, "epoch": 0.34315245478036177, "percentage": 17.15, "elapsed_time": "0:02:31", "remaining_time": "0:12:09"}
|
| 84 |
+
{"current_steps": 84, "total_steps": 484, "loss": 1.9825, "lr": 4.713047448118606e-05, "epoch": 0.34728682170542635, "percentage": 17.36, "elapsed_time": "0:02:32", "remaining_time": "0:12:07"}
|
| 85 |
+
{"current_steps": 85, "total_steps": 484, "loss": 2.0026, "lr": 4.705291149606786e-05, "epoch": 0.35142118863049093, "percentage": 17.56, "elapsed_time": "0:02:34", "remaining_time": "0:12:04"}
|
| 86 |
+
{"current_steps": 86, "total_steps": 484, "loss": 1.958, "lr": 4.6974379770560846e-05, "epoch": 0.35555555555555557, "percentage": 17.77, "elapsed_time": "0:02:36", "remaining_time": "0:12:02"}
|
| 87 |
+
{"current_steps": 87, "total_steps": 484, "loss": 2.0069, "lr": 4.689488275440697e-05, "epoch": 0.35968992248062015, "percentage": 17.98, "elapsed_time": "0:02:37", "remaining_time": "0:12:00"}
|
| 88 |
+
{"current_steps": 88, "total_steps": 484, "loss": 2.0372, "lr": 4.68144239397515e-05, "epoch": 0.36382428940568473, "percentage": 18.18, "elapsed_time": "0:02:39", "remaining_time": "0:11:57"}
|
| 89 |
+
{"current_steps": 89, "total_steps": 484, "loss": 1.9789, "lr": 4.673300686098957e-05, "epoch": 0.36795865633074937, "percentage": 18.39, "elapsed_time": "0:02:41", "remaining_time": "0:11:56"}
|
| 90 |
+
{"current_steps": 90, "total_steps": 484, "loss": 2.0055, "lr": 4.665063509461097e-05, "epoch": 0.37209302325581395, "percentage": 18.6, "elapsed_time": "0:02:43", "remaining_time": "0:11:53"}
|
| 91 |
+
{"current_steps": 91, "total_steps": 484, "loss": 2.017, "lr": 4.6567312259043e-05, "epoch": 0.37622739018087853, "percentage": 18.8, "elapsed_time": "0:02:44", "remaining_time": "0:11:51"}
|
| 92 |
+
{"current_steps": 92, "total_steps": 484, "loss": 1.9536, "lr": 4.648304201449153e-05, "epoch": 0.38036175710594317, "percentage": 19.01, "elapsed_time": "0:02:46", "remaining_time": "0:11:49"}
|
| 93 |
+
{"current_steps": 93, "total_steps": 484, "loss": 1.9638, "lr": 4.639782806278021e-05, "epoch": 0.38449612403100775, "percentage": 19.21, "elapsed_time": "0:02:48", "remaining_time": "0:11:47"}
|
| 94 |
+
{"current_steps": 94, "total_steps": 484, "loss": 2.0001, "lr": 4.631167414718788e-05, "epoch": 0.3886304909560723, "percentage": 19.42, "elapsed_time": "0:02:49", "remaining_time": "0:11:45"}
|
| 95 |
+
{"current_steps": 95, "total_steps": 484, "loss": 1.9628, "lr": 4.6224584052284106e-05, "epoch": 0.39276485788113696, "percentage": 19.63, "elapsed_time": "0:02:51", "remaining_time": "0:11:42"}
|
| 96 |
+
{"current_steps": 96, "total_steps": 484, "loss": 2.0396, "lr": 4.6136561603762925e-05, "epoch": 0.39689922480620154, "percentage": 19.83, "elapsed_time": "0:02:53", "remaining_time": "0:11:40"}
|
| 97 |
+
{"current_steps": 97, "total_steps": 484, "loss": 1.9954, "lr": 4.6047610668274846e-05, "epoch": 0.4010335917312661, "percentage": 20.04, "elapsed_time": "0:02:54", "remaining_time": "0:11:37"}
|
| 98 |
+
{"current_steps": 98, "total_steps": 484, "loss": 1.9253, "lr": 4.5957735153256915e-05, "epoch": 0.40516795865633076, "percentage": 20.25, "elapsed_time": "0:02:56", "remaining_time": "0:11:35"}
|
| 99 |
+
{"current_steps": 99, "total_steps": 484, "loss": 1.9543, "lr": 4.586693900676116e-05, "epoch": 0.40930232558139534, "percentage": 20.45, "elapsed_time": "0:02:58", "remaining_time": "0:11:33"}
|
| 100 |
+
{"current_steps": 100, "total_steps": 484, "loss": 1.9897, "lr": 4.577522621728106e-05, "epoch": 0.4134366925064599, "percentage": 20.66, "elapsed_time": "0:02:59", "remaining_time": "0:11:31"}
|
| 101 |
+
{"current_steps": 101, "total_steps": 484, "loss": 1.9997, "lr": 4.5682600813576435e-05, "epoch": 0.41757105943152456, "percentage": 20.87, "elapsed_time": "0:03:01", "remaining_time": "0:11:28"}
|
| 102 |
+
{"current_steps": 102, "total_steps": 484, "loss": 1.9706, "lr": 4.55890668644964e-05, "epoch": 0.42170542635658914, "percentage": 21.07, "elapsed_time": "0:03:03", "remaining_time": "0:11:26"}
|
| 103 |
+
{"current_steps": 103, "total_steps": 484, "loss": 1.9759, "lr": 4.549462847880066e-05, "epoch": 0.4258397932816537, "percentage": 21.28, "elapsed_time": "0:03:04", "remaining_time": "0:11:24"}
|
| 104 |
+
{"current_steps": 104, "total_steps": 484, "loss": 1.9579, "lr": 4.539928980497903e-05, "epoch": 0.42997416020671836, "percentage": 21.49, "elapsed_time": "0:03:06", "remaining_time": "0:11:21"}
|
| 105 |
+
{"current_steps": 105, "total_steps": 484, "loss": 1.9803, "lr": 4.530305503106916e-05, "epoch": 0.43410852713178294, "percentage": 21.69, "elapsed_time": "0:03:08", "remaining_time": "0:11:19"}
|
| 106 |
+
{"current_steps": 106, "total_steps": 484, "loss": 1.9267, "lr": 4.5205928384472616e-05, "epoch": 0.4382428940568475, "percentage": 21.9, "elapsed_time": "0:03:09", "remaining_time": "0:11:17"}
|
| 107 |
+
{"current_steps": 107, "total_steps": 484, "loss": 1.9855, "lr": 4.510791413176912e-05, "epoch": 0.44237726098191216, "percentage": 22.11, "elapsed_time": "0:03:11", "remaining_time": "0:11:14"}
|
| 108 |
+
{"current_steps": 108, "total_steps": 484, "loss": 2.0313, "lr": 4.5009016578529194e-05, "epoch": 0.44651162790697674, "percentage": 22.31, "elapsed_time": "0:03:13", "remaining_time": "0:11:12"}
|
| 109 |
+
{"current_steps": 109, "total_steps": 484, "loss": 1.9745, "lr": 4.4909240069124966e-05, "epoch": 0.4506459948320413, "percentage": 22.52, "elapsed_time": "0:03:15", "remaining_time": "0:11:11"}
|
| 110 |
+
{"current_steps": 110, "total_steps": 484, "loss": 1.9208, "lr": 4.480858898653936e-05, "epoch": 0.45478036175710596, "percentage": 22.73, "elapsed_time": "0:03:16", "remaining_time": "0:11:08"}
|
| 111 |
+
{"current_steps": 111, "total_steps": 484, "loss": 1.9365, "lr": 4.470706775217355e-05, "epoch": 0.45891472868217054, "percentage": 22.93, "elapsed_time": "0:03:18", "remaining_time": "0:11:06"}
|
| 112 |
+
{"current_steps": 112, "total_steps": 484, "loss": 1.9509, "lr": 4.4604680825652753e-05, "epoch": 0.4630490956072351, "percentage": 23.14, "elapsed_time": "0:03:20", "remaining_time": "0:11:05"}
|
| 113 |
+
{"current_steps": 113, "total_steps": 484, "loss": 1.9406, "lr": 4.4501432704630305e-05, "epoch": 0.46718346253229975, "percentage": 23.35, "elapsed_time": "0:03:22", "remaining_time": "0:11:03"}
|
| 114 |
+
{"current_steps": 114, "total_steps": 484, "loss": 1.9809, "lr": 4.43973279245901e-05, "epoch": 0.47131782945736433, "percentage": 23.55, "elapsed_time": "0:03:23", "remaining_time": "0:11:01"}
|
| 115 |
+
{"current_steps": 115, "total_steps": 484, "loss": 1.9638, "lr": 4.4292371058647345e-05, "epoch": 0.4754521963824289, "percentage": 23.76, "elapsed_time": "0:03:25", "remaining_time": "0:10:59"}
|
| 116 |
+
{"current_steps": 116, "total_steps": 484, "loss": 1.9621, "lr": 4.41865667173477e-05, "epoch": 0.47958656330749355, "percentage": 23.97, "elapsed_time": "0:03:27", "remaining_time": "0:10:57"}
|
| 117 |
+
{"current_steps": 117, "total_steps": 484, "loss": 1.9688, "lr": 4.407991954846471e-05, "epoch": 0.48372093023255813, "percentage": 24.17, "elapsed_time": "0:03:28", "remaining_time": "0:10:55"}
|
| 118 |
+
{"current_steps": 118, "total_steps": 484, "loss": 1.9179, "lr": 4.3972434236795656e-05, "epoch": 0.4878552971576227, "percentage": 24.38, "elapsed_time": "0:03:30", "remaining_time": "0:10:53"}
|
| 119 |
+
{"current_steps": 119, "total_steps": 484, "loss": 1.9979, "lr": 4.386411550395576e-05, "epoch": 0.49198966408268735, "percentage": 24.59, "elapsed_time": "0:03:32", "remaining_time": "0:10:51"}
|
| 120 |
+
{"current_steps": 120, "total_steps": 484, "loss": 1.9072, "lr": 4.3754968108170766e-05, "epoch": 0.49612403100775193, "percentage": 24.79, "elapsed_time": "0:03:34", "remaining_time": "0:10:49"}
|
| 121 |
+
{"current_steps": 121, "total_steps": 484, "loss": 1.9378, "lr": 4.3644996844067955e-05, "epoch": 0.5002583979328166, "percentage": 25.0, "elapsed_time": "0:03:36", "remaining_time": "0:10:48"}
|
| 122 |
+
{"current_steps": 122, "total_steps": 484, "loss": 1.9835, "lr": 4.353420654246546e-05, "epoch": 0.5043927648578811, "percentage": 25.21, "elapsed_time": "0:03:37", "remaining_time": "0:10:46"}
|
| 123 |
+
{"current_steps": 123, "total_steps": 484, "loss": 1.9278, "lr": 4.342260207016012e-05, "epoch": 0.5085271317829457, "percentage": 25.41, "elapsed_time": "0:03:39", "remaining_time": "0:10:44"}
|
| 124 |
+
{"current_steps": 124, "total_steps": 484, "loss": 2.0604, "lr": 4.3310188329713665e-05, "epoch": 0.5126614987080104, "percentage": 25.62, "elapsed_time": "0:03:41", "remaining_time": "0:10:42"}
|
| 125 |
+
{"current_steps": 125, "total_steps": 484, "loss": 2.0045, "lr": 4.319697025923736e-05, "epoch": 0.5167958656330749, "percentage": 25.83, "elapsed_time": "0:03:43", "remaining_time": "0:10:40"}
|
| 126 |
+
{"current_steps": 126, "total_steps": 484, "loss": 1.9651, "lr": 4.308295283217507e-05, "epoch": 0.5209302325581395, "percentage": 26.03, "elapsed_time": "0:03:44", "remaining_time": "0:10:38"}
|
| 127 |
+
{"current_steps": 127, "total_steps": 484, "loss": 1.9391, "lr": 4.296814105708482e-05, "epoch": 0.5250645994832042, "percentage": 26.24, "elapsed_time": "0:03:46", "remaining_time": "0:10:37"}
|
| 128 |
+
{"current_steps": 128, "total_steps": 484, "loss": 1.9325, "lr": 4.285253997741875e-05, "epoch": 0.5291989664082687, "percentage": 26.45, "elapsed_time": "0:03:48", "remaining_time": "0:10:35"}
|
| 129 |
+
{"current_steps": 129, "total_steps": 484, "loss": 2.0234, "lr": 4.2736154671301556e-05, "epoch": 0.5333333333333333, "percentage": 26.65, "elapsed_time": "0:03:50", "remaining_time": "0:10:33"}
|
| 130 |
+
{"current_steps": 130, "total_steps": 484, "loss": 1.9127, "lr": 4.261899025130748e-05, "epoch": 0.537467700258398, "percentage": 26.86, "elapsed_time": "0:03:52", "remaining_time": "0:10:32"}
|
| 131 |
+
{"current_steps": 131, "total_steps": 484, "loss": 1.9703, "lr": 4.2501051864235636e-05, "epoch": 0.5416020671834625, "percentage": 27.07, "elapsed_time": "0:03:53", "remaining_time": "0:10:29"}
|
| 132 |
+
{"current_steps": 132, "total_steps": 484, "loss": 1.999, "lr": 4.238234469088399e-05, "epoch": 0.5457364341085271, "percentage": 27.27, "elapsed_time": "0:03:55", "remaining_time": "0:10:27"}
|
| 133 |
+
{"current_steps": 133, "total_steps": 484, "loss": 1.9527, "lr": 4.2262873945821754e-05, "epoch": 0.5498708010335918, "percentage": 27.48, "elapsed_time": "0:03:56", "remaining_time": "0:10:25"}
|
| 134 |
+
{"current_steps": 134, "total_steps": 484, "loss": 1.985, "lr": 4.214264487716033e-05, "epoch": 0.5540051679586563, "percentage": 27.69, "elapsed_time": "0:03:58", "remaining_time": "0:10:22"}
|
| 135 |
+
{"current_steps": 135, "total_steps": 484, "loss": 1.9307, "lr": 4.2021662766322736e-05, "epoch": 0.5581395348837209, "percentage": 27.89, "elapsed_time": "0:04:00", "remaining_time": "0:10:20"}
|
| 136 |
+
{"current_steps": 136, "total_steps": 484, "loss": 1.9159, "lr": 4.189993292781165e-05, "epoch": 0.5622739018087856, "percentage": 28.1, "elapsed_time": "0:04:01", "remaining_time": "0:10:19"}
|
| 137 |
+
{"current_steps": 137, "total_steps": 484, "loss": 1.9684, "lr": 4.177746070897592e-05, "epoch": 0.5664082687338501, "percentage": 28.31, "elapsed_time": "0:04:03", "remaining_time": "0:10:16"}
|
| 138 |
+
{"current_steps": 138, "total_steps": 484, "loss": 1.939, "lr": 4.165425148977571e-05, "epoch": 0.5705426356589147, "percentage": 28.51, "elapsed_time": "0:04:05", "remaining_time": "0:10:14"}
|
| 139 |
+
{"current_steps": 139, "total_steps": 484, "loss": 1.9246, "lr": 4.15303106825461e-05, "epoch": 0.5746770025839794, "percentage": 28.72, "elapsed_time": "0:04:07", "remaining_time": "0:10:13"}
|
| 140 |
+
{"current_steps": 140, "total_steps": 484, "loss": 1.9766, "lr": 4.140564373175939e-05, "epoch": 0.5788113695090439, "percentage": 28.93, "elapsed_time": "0:04:08", "remaining_time": "0:10:11"}
|
| 141 |
+
{"current_steps": 141, "total_steps": 484, "loss": 1.9565, "lr": 4.128025611378594e-05, "epoch": 0.5829457364341085, "percentage": 29.13, "elapsed_time": "0:04:10", "remaining_time": "0:10:09"}
|
| 142 |
+
{"current_steps": 142, "total_steps": 484, "loss": 1.9158, "lr": 4.1154153336653534e-05, "epoch": 0.5870801033591732, "percentage": 29.34, "elapsed_time": "0:04:12", "remaining_time": "0:10:07"}
|
| 143 |
+
{"current_steps": 143, "total_steps": 484, "loss": 1.9419, "lr": 4.10273409398055e-05, "epoch": 0.5912144702842377, "percentage": 29.55, "elapsed_time": "0:04:13", "remaining_time": "0:10:05"}
|
| 144 |
+
{"current_steps": 144, "total_steps": 484, "loss": 1.9824, "lr": 4.089982449385736e-05, "epoch": 0.5953488372093023, "percentage": 29.75, "elapsed_time": "0:04:15", "remaining_time": "0:10:03"}
|
| 145 |
+
{"current_steps": 145, "total_steps": 484, "loss": 1.9677, "lr": 4.077160960035207e-05, "epoch": 0.599483204134367, "percentage": 29.96, "elapsed_time": "0:04:17", "remaining_time": "0:10:01"}
|
| 146 |
+
{"current_steps": 146, "total_steps": 484, "loss": 1.9844, "lr": 4.0642701891514e-05, "epoch": 0.6036175710594315, "percentage": 30.17, "elapsed_time": "0:04:18", "remaining_time": "0:09:59"}
|
| 147 |
+
{"current_steps": 147, "total_steps": 484, "loss": 1.9424, "lr": 4.0513107030001544e-05, "epoch": 0.6077519379844961, "percentage": 30.37, "elapsed_time": "0:04:20", "remaining_time": "0:09:57"}
|
| 148 |
+
{"current_steps": 148, "total_steps": 484, "loss": 1.9885, "lr": 4.0382830708658316e-05, "epoch": 0.6118863049095608, "percentage": 30.58, "elapsed_time": "0:04:22", "remaining_time": "0:09:56"}
|
| 149 |
+
{"current_steps": 149, "total_steps": 484, "loss": 1.9332, "lr": 4.025187865026311e-05, "epoch": 0.6160206718346253, "percentage": 30.79, "elapsed_time": "0:04:24", "remaining_time": "0:09:54"}
|
| 150 |
+
{"current_steps": 150, "total_steps": 484, "loss": 1.9403, "lr": 4.012025660727849e-05, "epoch": 0.6201550387596899, "percentage": 30.99, "elapsed_time": "0:04:26", "remaining_time": "0:09:52"}
|
| 151 |
+
{"current_steps": 151, "total_steps": 484, "loss": 2.0081, "lr": 3.998797036159812e-05, "epoch": 0.6242894056847546, "percentage": 31.2, "elapsed_time": "0:04:27", "remaining_time": "0:09:50"}
|
| 152 |
+
{"current_steps": 152, "total_steps": 484, "loss": 1.9237, "lr": 3.985502572429276e-05, "epoch": 0.6284237726098191, "percentage": 31.4, "elapsed_time": "0:04:29", "remaining_time": "0:09:49"}
|
| 153 |
+
{"current_steps": 153, "total_steps": 484, "loss": 2.0038, "lr": 3.972142853535499e-05, "epoch": 0.6325581395348837, "percentage": 31.61, "elapsed_time": "0:04:31", "remaining_time": "0:09:47"}
|
| 154 |
+
{"current_steps": 154, "total_steps": 484, "loss": 1.9428, "lr": 3.958718466344269e-05, "epoch": 0.6366925064599483, "percentage": 31.82, "elapsed_time": "0:04:33", "remaining_time": "0:09:45"}
|
| 155 |
+
{"current_steps": 155, "total_steps": 484, "loss": 1.9459, "lr": 3.945230000562121e-05, "epoch": 0.6408268733850129, "percentage": 32.02, "elapsed_time": "0:04:34", "remaining_time": "0:09:43"}
|
| 156 |
+
{"current_steps": 156, "total_steps": 484, "loss": 1.9787, "lr": 3.931678048710439e-05, "epoch": 0.6449612403100775, "percentage": 32.23, "elapsed_time": "0:04:36", "remaining_time": "0:09:41"}
|
| 157 |
+
{"current_steps": 157, "total_steps": 484, "loss": 1.9787, "lr": 3.91806320609942e-05, "epoch": 0.6490956072351421, "percentage": 32.44, "elapsed_time": "0:04:38", "remaining_time": "0:09:39"}
|
| 158 |
+
{"current_steps": 158, "total_steps": 484, "loss": 1.9134, "lr": 3.9043860708019273e-05, "epoch": 0.6532299741602067, "percentage": 32.64, "elapsed_time": "0:04:40", "remaining_time": "0:09:37"}
|
| 159 |
+
{"current_steps": 159, "total_steps": 484, "loss": 2.025, "lr": 3.890647243627218e-05, "epoch": 0.6573643410852713, "percentage": 32.85, "elapsed_time": "0:04:42", "remaining_time": "0:09:36"}
|
| 160 |
+
{"current_steps": 160, "total_steps": 484, "loss": 1.9579, "lr": 3.876847328094549e-05, "epoch": 0.661498708010336, "percentage": 33.06, "elapsed_time": "0:04:43", "remaining_time": "0:09:34"}
|
| 161 |
+
{"current_steps": 161, "total_steps": 484, "loss": 1.9624, "lr": 3.862986930406669e-05, "epoch": 0.6656330749354005, "percentage": 33.26, "elapsed_time": "0:04:45", "remaining_time": "0:09:32"}
|
| 162 |
+
{"current_steps": 162, "total_steps": 484, "loss": 1.9392, "lr": 3.849066659423186e-05, "epoch": 0.6697674418604651, "percentage": 33.47, "elapsed_time": "0:04:47", "remaining_time": "0:09:30"}
|
| 163 |
+
{"current_steps": 163, "total_steps": 484, "loss": 1.9173, "lr": 3.835087126633821e-05, "epoch": 0.6739018087855297, "percentage": 33.68, "elapsed_time": "0:04:48", "remaining_time": "0:09:28"}
|
| 164 |
+
{"current_steps": 164, "total_steps": 484, "loss": 1.9504, "lr": 3.821048946131549e-05, "epoch": 0.6780361757105943, "percentage": 33.88, "elapsed_time": "0:04:50", "remaining_time": "0:09:27"}
|
| 165 |
+
{"current_steps": 165, "total_steps": 484, "loss": 1.9375, "lr": 3.806952734585623e-05, "epoch": 0.6821705426356589, "percentage": 34.09, "elapsed_time": "0:04:52", "remaining_time": "0:09:25"}
|
| 166 |
+
{"current_steps": 166, "total_steps": 484, "loss": 1.9579, "lr": 3.792799111214483e-05, "epoch": 0.6863049095607235, "percentage": 34.3, "elapsed_time": "0:04:54", "remaining_time": "0:09:23"}
|
| 167 |
+
{"current_steps": 167, "total_steps": 484, "loss": 1.945, "lr": 3.778588697758556e-05, "epoch": 0.6904392764857881, "percentage": 34.5, "elapsed_time": "0:04:55", "remaining_time": "0:09:21"}
|
| 168 |
+
{"current_steps": 168, "total_steps": 484, "loss": 1.8605, "lr": 3.764322118452943e-05, "epoch": 0.6945736434108527, "percentage": 34.71, "elapsed_time": "0:04:57", "remaining_time": "0:09:20"}
|
| 169 |
+
{"current_steps": 169, "total_steps": 484, "loss": 1.9562, "lr": 3.7500000000000003e-05, "epoch": 0.6987080103359173, "percentage": 34.92, "elapsed_time": "0:04:59", "remaining_time": "0:09:18"}
|
| 170 |
+
{"current_steps": 170, "total_steps": 484, "loss": 1.9373, "lr": 3.7356229715418074e-05, "epoch": 0.7028423772609819, "percentage": 35.12, "elapsed_time": "0:05:01", "remaining_time": "0:09:16"}
|
| 171 |
+
{"current_steps": 171, "total_steps": 484, "loss": 1.8931, "lr": 3.721191664632531e-05, "epoch": 0.7069767441860465, "percentage": 35.33, "elapsed_time": "0:05:02", "remaining_time": "0:09:14"}
|
| 172 |
+
{"current_steps": 172, "total_steps": 484, "loss": 1.9028, "lr": 3.7067067132106815e-05, "epoch": 0.7111111111111111, "percentage": 35.54, "elapsed_time": "0:05:04", "remaining_time": "0:09:12"}
|
| 173 |
+
{"current_steps": 173, "total_steps": 484, "loss": 1.9441, "lr": 3.6921687535712656e-05, "epoch": 0.7152454780361757, "percentage": 35.74, "elapsed_time": "0:05:06", "remaining_time": "0:09:10"}
|
| 174 |
+
{"current_steps": 174, "total_steps": 484, "loss": 1.8995, "lr": 3.6775784243378354e-05, "epoch": 0.7193798449612403, "percentage": 35.95, "elapsed_time": "0:05:07", "remaining_time": "0:09:08"}
|
| 175 |
+
{"current_steps": 175, "total_steps": 484, "loss": 1.9544, "lr": 3.662936366434434e-05, "epoch": 0.7235142118863049, "percentage": 36.16, "elapsed_time": "0:05:10", "remaining_time": "0:09:07"}
|
| 176 |
+
{"current_steps": 176, "total_steps": 484, "loss": 1.9965, "lr": 3.6482432230574446e-05, "epoch": 0.7276485788113695, "percentage": 36.36, "elapsed_time": "0:05:11", "remaining_time": "0:09:05"}
|
| 177 |
+
{"current_steps": 177, "total_steps": 484, "loss": 1.9837, "lr": 3.63349963964733e-05, "epoch": 0.7317829457364341, "percentage": 36.57, "elapsed_time": "0:05:13", "remaining_time": "0:09:03"}
|
| 178 |
+
{"current_steps": 178, "total_steps": 484, "loss": 1.9656, "lr": 3.618706263860284e-05, "epoch": 0.7359173126614987, "percentage": 36.78, "elapsed_time": "0:05:14", "remaining_time": "0:09:01"}
|
| 179 |
+
{"current_steps": 179, "total_steps": 484, "loss": 1.9108, "lr": 3.60386374553978e-05, "epoch": 0.7400516795865633, "percentage": 36.98, "elapsed_time": "0:05:16", "remaining_time": "0:08:59"}
|
| 180 |
+
{"current_steps": 180, "total_steps": 484, "loss": 1.9317, "lr": 3.5889727366880256e-05, "epoch": 0.7441860465116279, "percentage": 37.19, "elapsed_time": "0:05:18", "remaining_time": "0:08:57"}
|
| 181 |
+
{"current_steps": 181, "total_steps": 484, "loss": 1.9307, "lr": 3.57403389143732e-05, "epoch": 0.7483204134366925, "percentage": 37.4, "elapsed_time": "0:05:20", "remaining_time": "0:08:56"}
|
| 182 |
+
{"current_steps": 182, "total_steps": 484, "loss": 1.9501, "lr": 3.5590478660213214e-05, "epoch": 0.7524547803617571, "percentage": 37.6, "elapsed_time": "0:05:22", "remaining_time": "0:08:54"}
|
| 183 |
+
{"current_steps": 183, "total_steps": 484, "loss": 1.9188, "lr": 3.5440153187462145e-05, "epoch": 0.7565891472868217, "percentage": 37.81, "elapsed_time": "0:05:23", "remaining_time": "0:08:52"}
|
| 184 |
+
{"current_steps": 184, "total_steps": 484, "loss": 1.9035, "lr": 3.528936909961801e-05, "epoch": 0.7607235142118863, "percentage": 38.02, "elapsed_time": "0:05:25", "remaining_time": "0:08:50"}
|
| 185 |
+
{"current_steps": 185, "total_steps": 484, "loss": 1.8984, "lr": 3.5138133020324845e-05, "epoch": 0.7648578811369509, "percentage": 38.22, "elapsed_time": "0:05:27", "remaining_time": "0:08:48"}
|
| 186 |
+
{"current_steps": 186, "total_steps": 484, "loss": 1.8889, "lr": 3.498645159308179e-05, "epoch": 0.7689922480620155, "percentage": 38.43, "elapsed_time": "0:05:28", "remaining_time": "0:08:46"}
|
| 187 |
+
{"current_steps": 187, "total_steps": 484, "loss": 1.9199, "lr": 3.483433148095121e-05, "epoch": 0.7731266149870801, "percentage": 38.64, "elapsed_time": "0:05:30", "remaining_time": "0:08:44"}
|
| 188 |
+
{"current_steps": 188, "total_steps": 484, "loss": 2.0003, "lr": 3.468177936626603e-05, "epoch": 0.7772609819121447, "percentage": 38.84, "elapsed_time": "0:05:32", "remaining_time": "0:08:43"}
|
| 189 |
+
{"current_steps": 189, "total_steps": 484, "loss": 1.8989, "lr": 3.4528801950336174e-05, "epoch": 0.7813953488372093, "percentage": 39.05, "elapsed_time": "0:05:33", "remaining_time": "0:08:41"}
|
| 190 |
+
{"current_steps": 190, "total_steps": 484, "loss": 1.9181, "lr": 3.437540595315423e-05, "epoch": 0.7855297157622739, "percentage": 39.26, "elapsed_time": "0:05:35", "remaining_time": "0:08:39"}
|
| 191 |
+
{"current_steps": 191, "total_steps": 484, "loss": 1.9343, "lr": 3.4221598113100195e-05, "epoch": 0.7896640826873385, "percentage": 39.46, "elapsed_time": "0:05:37", "remaining_time": "0:08:37"}
|
| 192 |
+
{"current_steps": 192, "total_steps": 484, "loss": 1.9097, "lr": 3.406738518664552e-05, "epoch": 0.7937984496124031, "percentage": 39.67, "elapsed_time": "0:05:38", "remaining_time": "0:08:35"}
|
| 193 |
+
{"current_steps": 193, "total_steps": 484, "loss": 1.8665, "lr": 3.3912773948056274e-05, "epoch": 0.7979328165374677, "percentage": 39.88, "elapsed_time": "0:05:40", "remaining_time": "0:08:33"}
|
| 194 |
+
{"current_steps": 194, "total_steps": 484, "loss": 1.9451, "lr": 3.375777118909561e-05, "epoch": 0.8020671834625323, "percentage": 40.08, "elapsed_time": "0:05:42", "remaining_time": "0:08:31"}
|
| 195 |
+
{"current_steps": 195, "total_steps": 484, "loss": 1.944, "lr": 3.360238371872536e-05, "epoch": 0.8062015503875969, "percentage": 40.29, "elapsed_time": "0:05:43", "remaining_time": "0:08:29"}
|
| 196 |
+
{"current_steps": 196, "total_steps": 484, "loss": 1.9652, "lr": 3.344661836280699e-05, "epoch": 0.8103359173126615, "percentage": 40.5, "elapsed_time": "0:05:45", "remaining_time": "0:08:27"}
|
| 197 |
+
{"current_steps": 197, "total_steps": 484, "loss": 1.9728, "lr": 3.32904819638017e-05, "epoch": 0.814470284237726, "percentage": 40.7, "elapsed_time": "0:05:47", "remaining_time": "0:08:26"}
|
| 198 |
+
{"current_steps": 198, "total_steps": 484, "loss": 1.9231, "lr": 3.313398138046987e-05, "epoch": 0.8186046511627907, "percentage": 40.91, "elapsed_time": "0:05:49", "remaining_time": "0:08:24"}
|
| 199 |
+
{"current_steps": 199, "total_steps": 484, "loss": 1.9545, "lr": 3.297712348756982e-05, "epoch": 0.8227390180878553, "percentage": 41.12, "elapsed_time": "0:05:50", "remaining_time": "0:08:22"}
|
| 200 |
+
{"current_steps": 200, "total_steps": 484, "loss": 1.9332, "lr": 3.2819915175555684e-05, "epoch": 0.8268733850129198, "percentage": 41.32, "elapsed_time": "0:05:52", "remaining_time": "0:08:20"}
|
| 201 |
+
{"current_steps": 201, "total_steps": 484, "loss": 1.9518, "lr": 3.266236335027487e-05, "epoch": 0.8310077519379845, "percentage": 41.53, "elapsed_time": "0:05:54", "remaining_time": "0:08:18"}
|
| 202 |
+
{"current_steps": 202, "total_steps": 484, "loss": 1.9011, "lr": 3.250447493266463e-05, "epoch": 0.8351421188630491, "percentage": 41.74, "elapsed_time": "0:05:55", "remaining_time": "0:08:16"}
|
| 203 |
+
{"current_steps": 203, "total_steps": 484, "loss": 1.9257, "lr": 3.234625685844803e-05, "epoch": 0.8392764857881136, "percentage": 41.94, "elapsed_time": "0:05:57", "remaining_time": "0:08:14"}
|
| 204 |
+
{"current_steps": 204, "total_steps": 484, "loss": 1.9172, "lr": 3.218771607782929e-05, "epoch": 0.8434108527131783, "percentage": 42.15, "elapsed_time": "0:05:59", "remaining_time": "0:08:13"}
|
| 205 |
+
{"current_steps": 205, "total_steps": 484, "loss": 1.9632, "lr": 3.202885955518849e-05, "epoch": 0.8475452196382429, "percentage": 42.36, "elapsed_time": "0:06:00", "remaining_time": "0:08:11"}
|
| 206 |
+
{"current_steps": 206, "total_steps": 484, "loss": 1.9568, "lr": 3.186969426877563e-05, "epoch": 0.8516795865633074, "percentage": 42.56, "elapsed_time": "0:06:02", "remaining_time": "0:08:09"}
|
| 207 |
+
{"current_steps": 207, "total_steps": 484, "loss": 1.9168, "lr": 3.171022721040409e-05, "epoch": 0.8558139534883721, "percentage": 42.77, "elapsed_time": "0:06:04", "remaining_time": "0:08:07"}
|
| 208 |
+
{"current_steps": 208, "total_steps": 484, "loss": 1.9243, "lr": 3.1550465385143455e-05, "epoch": 0.8599483204134367, "percentage": 42.98, "elapsed_time": "0:06:06", "remaining_time": "0:08:05"}
|
| 209 |
+
{"current_steps": 209, "total_steps": 484, "loss": 1.8235, "lr": 3.139041581101187e-05, "epoch": 0.8640826873385012, "percentage": 43.18, "elapsed_time": "0:06:07", "remaining_time": "0:08:04"}
|
| 210 |
+
{"current_steps": 210, "total_steps": 484, "loss": 1.9092, "lr": 3.12300855186677e-05, "epoch": 0.8682170542635659, "percentage": 43.39, "elapsed_time": "0:06:09", "remaining_time": "0:08:02"}
|
| 211 |
+
{"current_steps": 211, "total_steps": 484, "loss": 1.9501, "lr": 3.1069481551100695e-05, "epoch": 0.8723514211886305, "percentage": 43.6, "elapsed_time": "0:06:11", "remaining_time": "0:08:00"}
|
| 212 |
+
{"current_steps": 212, "total_steps": 484, "loss": 1.9308, "lr": 3.090861096332263e-05, "epoch": 0.876485788113695, "percentage": 43.8, "elapsed_time": "0:06:12", "remaining_time": "0:07:58"}
|
| 213 |
+
{"current_steps": 213, "total_steps": 484, "loss": 1.9279, "lr": 3.074748082205734e-05, "epoch": 0.8806201550387597, "percentage": 44.01, "elapsed_time": "0:06:14", "remaining_time": "0:07:56"}
|
| 214 |
+
{"current_steps": 214, "total_steps": 484, "loss": 1.9227, "lr": 3.0586098205430355e-05, "epoch": 0.8847545219638243, "percentage": 44.21, "elapsed_time": "0:06:16", "remaining_time": "0:07:54"}
|
| 215 |
+
{"current_steps": 215, "total_steps": 484, "loss": 1.9263, "lr": 3.042447020265795e-05, "epoch": 0.8888888888888888, "percentage": 44.42, "elapsed_time": "0:06:18", "remaining_time": "0:07:53"}
|
| 216 |
+
{"current_steps": 216, "total_steps": 484, "loss": 1.9113, "lr": 3.02626039137357e-05, "epoch": 0.8930232558139535, "percentage": 44.63, "elapsed_time": "0:06:19", "remaining_time": "0:07:51"}
|
| 217 |
+
{"current_steps": 217, "total_steps": 484, "loss": 1.9546, "lr": 3.010050644912662e-05, "epoch": 0.8971576227390181, "percentage": 44.83, "elapsed_time": "0:06:21", "remaining_time": "0:07:49"}
|
| 218 |
+
{"current_steps": 218, "total_steps": 484, "loss": 1.8975, "lr": 2.993818492944882e-05, "epoch": 0.9012919896640826, "percentage": 45.04, "elapsed_time": "0:06:23", "remaining_time": "0:07:47"}
|
| 219 |
+
{"current_steps": 219, "total_steps": 484, "loss": 1.9315, "lr": 2.9775646485162694e-05, "epoch": 0.9054263565891473, "percentage": 45.25, "elapsed_time": "0:06:25", "remaining_time": "0:07:45"}
|
| 220 |
+
{"current_steps": 220, "total_steps": 484, "loss": 1.9024, "lr": 2.9612898256257716e-05, "epoch": 0.9095607235142119, "percentage": 45.45, "elapsed_time": "0:06:26", "remaining_time": "0:07:44"}
|
| 221 |
+
{"current_steps": 221, "total_steps": 484, "loss": 1.9726, "lr": 2.9449947391938766e-05, "epoch": 0.9136950904392764, "percentage": 45.66, "elapsed_time": "0:06:28", "remaining_time": "0:07:42"}
|
| 222 |
+
{"current_steps": 222, "total_steps": 484, "loss": 1.9322, "lr": 2.9286801050312078e-05, "epoch": 0.9178294573643411, "percentage": 45.87, "elapsed_time": "0:06:30", "remaining_time": "0:07:40"}
|
| 223 |
+
{"current_steps": 223, "total_steps": 484, "loss": 1.9033, "lr": 2.9123466398070852e-05, "epoch": 0.9219638242894057, "percentage": 46.07, "elapsed_time": "0:06:32", "remaining_time": "0:07:39"}
|
| 224 |
+
{"current_steps": 224, "total_steps": 484, "loss": 1.9108, "lr": 2.8959950610180374e-05, "epoch": 0.9260981912144702, "percentage": 46.28, "elapsed_time": "0:06:34", "remaining_time": "0:07:37"}
|
| 225 |
+
{"current_steps": 225, "total_steps": 484, "loss": 1.9964, "lr": 2.8796260869562863e-05, "epoch": 0.9302325581395349, "percentage": 46.49, "elapsed_time": "0:06:35", "remaining_time": "0:07:35"}
|
| 226 |
+
{"current_steps": 226, "total_steps": 484, "loss": 1.934, "lr": 2.8632404366781924e-05, "epoch": 0.9343669250645995, "percentage": 46.69, "elapsed_time": "0:06:37", "remaining_time": "0:07:34"}
|
| 227 |
+
{"current_steps": 227, "total_steps": 484, "loss": 1.9087, "lr": 2.8468388299726712e-05, "epoch": 0.938501291989664, "percentage": 46.9, "elapsed_time": "0:06:39", "remaining_time": "0:07:32"}
|
| 228 |
+
{"current_steps": 228, "total_steps": 484, "loss": 1.9168, "lr": 2.830421987329569e-05, "epoch": 0.9426356589147287, "percentage": 47.11, "elapsed_time": "0:06:41", "remaining_time": "0:07:30"}
|
| 229 |
+
{"current_steps": 229, "total_steps": 484, "loss": 1.9262, "lr": 2.8139906299080203e-05, "epoch": 0.9467700258397933, "percentage": 47.31, "elapsed_time": "0:06:42", "remaining_time": "0:07:28"}
|
| 230 |
+
{"current_steps": 230, "total_steps": 484, "loss": 1.9458, "lr": 2.7975454795047622e-05, "epoch": 0.9509043927648578, "percentage": 47.52, "elapsed_time": "0:06:44", "remaining_time": "0:07:26"}
|
| 231 |
+
{"current_steps": 231, "total_steps": 484, "loss": 1.8954, "lr": 2.7810872585224308e-05, "epoch": 0.9550387596899225, "percentage": 47.73, "elapsed_time": "0:06:46", "remaining_time": "0:07:24"}
|
| 232 |
+
{"current_steps": 232, "total_steps": 484, "loss": 1.8969, "lr": 2.7646166899378255e-05, "epoch": 0.9591731266149871, "percentage": 47.93, "elapsed_time": "0:06:47", "remaining_time": "0:07:23"}
|
| 233 |
+
{"current_steps": 233, "total_steps": 484, "loss": 1.8251, "lr": 2.7481344972701545e-05, "epoch": 0.9633074935400516, "percentage": 48.14, "elapsed_time": "0:06:49", "remaining_time": "0:07:21"}
|
| 234 |
+
{"current_steps": 234, "total_steps": 484, "loss": 1.8961, "lr": 2.7316414045492445e-05, "epoch": 0.9674418604651163, "percentage": 48.35, "elapsed_time": "0:06:51", "remaining_time": "0:07:19"}
|
| 235 |
+
{"current_steps": 235, "total_steps": 484, "loss": 1.8999, "lr": 2.7151381362837426e-05, "epoch": 0.9715762273901809, "percentage": 48.55, "elapsed_time": "0:06:52", "remaining_time": "0:07:17"}
|
| 236 |
+
{"current_steps": 236, "total_steps": 484, "loss": 1.9217, "lr": 2.6986254174292862e-05, "epoch": 0.9757105943152454, "percentage": 48.76, "elapsed_time": "0:06:54", "remaining_time": "0:07:15"}
|
| 237 |
+
{"current_steps": 237, "total_steps": 484, "loss": 1.9375, "lr": 2.682103973356659e-05, "epoch": 0.9798449612403101, "percentage": 48.97, "elapsed_time": "0:06:56", "remaining_time": "0:07:13"}
|
| 238 |
+
{"current_steps": 238, "total_steps": 484, "loss": 1.8848, "lr": 2.6655745298199253e-05, "epoch": 0.9839793281653747, "percentage": 49.17, "elapsed_time": "0:06:57", "remaining_time": "0:07:11"}
|
| 239 |
+
{"current_steps": 239, "total_steps": 484, "loss": 1.9268, "lr": 2.6490378129245498e-05, "epoch": 0.9881136950904392, "percentage": 49.38, "elapsed_time": "0:06:59", "remaining_time": "0:07:10"}
|
| 240 |
+
{"current_steps": 240, "total_steps": 484, "loss": 1.9187, "lr": 2.6324945490955027e-05, "epoch": 0.9922480620155039, "percentage": 49.59, "elapsed_time": "0:07:01", "remaining_time": "0:07:08"}
|
| 241 |
+
{"current_steps": 241, "total_steps": 484, "loss": 1.9676, "lr": 2.6159454650453463e-05, "epoch": 0.9963824289405685, "percentage": 49.79, "elapsed_time": "0:07:03", "remaining_time": "0:07:06"}
|
| 242 |
+
{"current_steps": 242, "total_steps": 484, "loss": 1.8618, "lr": 2.599391287742315e-05, "epoch": 1.0, "percentage": 50.0, "elapsed_time": "0:07:04", "remaining_time": "0:07:04"}
|
| 243 |
+
{"current_steps": 243, "total_steps": 484, "loss": 1.8551, "lr": 2.582832744378377e-05, "epoch": 1.0041343669250646, "percentage": 50.21, "elapsed_time": "0:07:16", "remaining_time": "0:07:13"}
|
| 244 |
+
{"current_steps": 244, "total_steps": 484, "loss": 1.8274, "lr": 2.5662705623372967e-05, "epoch": 1.0082687338501293, "percentage": 50.41, "elapsed_time": "0:07:18", "remaining_time": "0:07:11"}
|
| 245 |
+
{"current_steps": 245, "total_steps": 484, "loss": 1.9035, "lr": 2.5497054691626753e-05, "epoch": 1.012403100775194, "percentage": 50.62, "elapsed_time": "0:07:20", "remaining_time": "0:07:09"}
|
| 246 |
+
{"current_steps": 246, "total_steps": 484, "loss": 1.8652, "lr": 2.5331381925259968e-05, "epoch": 1.0165374677002583, "percentage": 50.83, "elapsed_time": "0:07:22", "remaining_time": "0:07:07"}
|
| 247 |
+
{"current_steps": 247, "total_steps": 484, "loss": 1.8787, "lr": 2.5165694601946565e-05, "epoch": 1.020671834625323, "percentage": 51.03, "elapsed_time": "0:07:24", "remaining_time": "0:07:06"}
|
| 248 |
+
{"current_steps": 248, "total_steps": 484, "loss": 1.8937, "lr": 2.5e-05, "epoch": 1.0248062015503876, "percentage": 51.24, "elapsed_time": "0:07:25", "remaining_time": "0:07:04"}
|
| 249 |
+
{"current_steps": 249, "total_steps": 484, "loss": 1.8592, "lr": 2.483430539805344e-05, "epoch": 1.0289405684754522, "percentage": 51.45, "elapsed_time": "0:07:27", "remaining_time": "0:07:02"}
|
| 250 |
+
{"current_steps": 250, "total_steps": 484, "loss": 1.8266, "lr": 2.4668618074740045e-05, "epoch": 1.0330749354005169, "percentage": 51.65, "elapsed_time": "0:07:29", "remaining_time": "0:07:01"}
|
| 251 |
+
{"current_steps": 251, "total_steps": 484, "loss": 1.8778, "lr": 2.4502945308373246e-05, "epoch": 1.0372093023255813, "percentage": 51.86, "elapsed_time": "0:07:31", "remaining_time": "0:06:59"}
|
| 252 |
+
{"current_steps": 252, "total_steps": 484, "loss": 1.8661, "lr": 2.433729437662704e-05, "epoch": 1.041343669250646, "percentage": 52.07, "elapsed_time": "0:07:33", "remaining_time": "0:06:57"}
|
| 253 |
+
{"current_steps": 253, "total_steps": 484, "loss": 1.8583, "lr": 2.4171672556216234e-05, "epoch": 1.0454780361757106, "percentage": 52.27, "elapsed_time": "0:07:34", "remaining_time": "0:06:55"}
|
| 254 |
+
{"current_steps": 254, "total_steps": 484, "loss": 1.8805, "lr": 2.4006087122576863e-05, "epoch": 1.0496124031007752, "percentage": 52.48, "elapsed_time": "0:07:36", "remaining_time": "0:06:53"}
|
| 255 |
+
{"current_steps": 255, "total_steps": 484, "loss": 1.8467, "lr": 2.3840545349546536e-05, "epoch": 1.0537467700258398, "percentage": 52.69, "elapsed_time": "0:07:38", "remaining_time": "0:06:51"}
|
| 256 |
+
{"current_steps": 256, "total_steps": 484, "loss": 1.886, "lr": 2.3675054509044976e-05, "epoch": 1.0578811369509045, "percentage": 52.89, "elapsed_time": "0:07:40", "remaining_time": "0:06:49"}
|
| 257 |
+
{"current_steps": 257, "total_steps": 484, "loss": 1.8698, "lr": 2.3509621870754505e-05, "epoch": 1.062015503875969, "percentage": 53.1, "elapsed_time": "0:07:42", "remaining_time": "0:06:48"}
|
| 258 |
+
{"current_steps": 258, "total_steps": 484, "loss": 1.8819, "lr": 2.3344254701800756e-05, "epoch": 1.0661498708010335, "percentage": 53.31, "elapsed_time": "0:07:43", "remaining_time": "0:06:46"}
|
| 259 |
+
{"current_steps": 259, "total_steps": 484, "loss": 1.9108, "lr": 2.317896026643341e-05, "epoch": 1.0702842377260982, "percentage": 53.51, "elapsed_time": "0:07:45", "remaining_time": "0:06:44"}
|
| 260 |
+
{"current_steps": 260, "total_steps": 484, "loss": 1.8473, "lr": 2.301374582570714e-05, "epoch": 1.0744186046511628, "percentage": 53.72, "elapsed_time": "0:07:47", "remaining_time": "0:06:42"}
|
| 261 |
+
{"current_steps": 261, "total_steps": 484, "loss": 1.8351, "lr": 2.2848618637162584e-05, "epoch": 1.0785529715762274, "percentage": 53.93, "elapsed_time": "0:07:48", "remaining_time": "0:06:40"}
|
| 262 |
+
{"current_steps": 262, "total_steps": 484, "loss": 1.8416, "lr": 2.268358595450756e-05, "epoch": 1.082687338501292, "percentage": 54.13, "elapsed_time": "0:07:50", "remaining_time": "0:06:38"}
|
| 263 |
+
{"current_steps": 263, "total_steps": 484, "loss": 1.9227, "lr": 2.2518655027298464e-05, "epoch": 1.0868217054263565, "percentage": 54.34, "elapsed_time": "0:07:52", "remaining_time": "0:06:36"}
|
| 264 |
+
{"current_steps": 264, "total_steps": 484, "loss": 1.8309, "lr": 2.2353833100621747e-05, "epoch": 1.0909560723514211, "percentage": 54.55, "elapsed_time": "0:07:54", "remaining_time": "0:06:35"}
|
| 265 |
+
{"current_steps": 265, "total_steps": 484, "loss": 1.8799, "lr": 2.2189127414775698e-05, "epoch": 1.0950904392764857, "percentage": 54.75, "elapsed_time": "0:07:55", "remaining_time": "0:06:33"}
|
| 266 |
+
{"current_steps": 266, "total_steps": 484, "loss": 1.8673, "lr": 2.2024545204952383e-05, "epoch": 1.0992248062015504, "percentage": 54.96, "elapsed_time": "0:07:57", "remaining_time": "0:06:31"}
|
| 267 |
+
{"current_steps": 267, "total_steps": 484, "loss": 1.8612, "lr": 2.1860093700919803e-05, "epoch": 1.103359173126615, "percentage": 55.17, "elapsed_time": "0:07:59", "remaining_time": "0:06:29"}
|
| 268 |
+
{"current_steps": 268, "total_steps": 484, "loss": 1.8742, "lr": 2.169578012670431e-05, "epoch": 1.1074935400516797, "percentage": 55.37, "elapsed_time": "0:08:01", "remaining_time": "0:06:27"}
|
| 269 |
+
{"current_steps": 269, "total_steps": 484, "loss": 1.8515, "lr": 2.1531611700273297e-05, "epoch": 1.1116279069767443, "percentage": 55.58, "elapsed_time": "0:08:02", "remaining_time": "0:06:25"}
|
| 270 |
+
{"current_steps": 270, "total_steps": 484, "loss": 1.8439, "lr": 2.1367595633218082e-05, "epoch": 1.1157622739018087, "percentage": 55.79, "elapsed_time": "0:08:04", "remaining_time": "0:06:23"}
|
| 271 |
+
{"current_steps": 271, "total_steps": 484, "loss": 1.8407, "lr": 2.1203739130437146e-05, "epoch": 1.1198966408268733, "percentage": 55.99, "elapsed_time": "0:08:06", "remaining_time": "0:06:22"}
|
| 272 |
+
{"current_steps": 272, "total_steps": 484, "loss": 1.862, "lr": 2.104004938981963e-05, "epoch": 1.124031007751938, "percentage": 56.2, "elapsed_time": "0:08:07", "remaining_time": "0:06:20"}
|
| 273 |
+
{"current_steps": 273, "total_steps": 484, "loss": 1.852, "lr": 2.087653360192915e-05, "epoch": 1.1281653746770026, "percentage": 56.4, "elapsed_time": "0:08:09", "remaining_time": "0:06:18"}
|
| 274 |
+
{"current_steps": 274, "total_steps": 484, "loss": 1.8953, "lr": 2.0713198949687924e-05, "epoch": 1.1322997416020673, "percentage": 56.61, "elapsed_time": "0:08:11", "remaining_time": "0:06:16"}
|
| 275 |
+
{"current_steps": 275, "total_steps": 484, "loss": 1.8498, "lr": 2.055005260806125e-05, "epoch": 1.1364341085271317, "percentage": 56.82, "elapsed_time": "0:08:13", "remaining_time": "0:06:14"}
|
| 276 |
+
{"current_steps": 276, "total_steps": 484, "loss": 1.8367, "lr": 2.0387101743742293e-05, "epoch": 1.1405684754521963, "percentage": 57.02, "elapsed_time": "0:08:14", "remaining_time": "0:06:13"}
|
| 277 |
+
{"current_steps": 277, "total_steps": 484, "loss": 1.8657, "lr": 2.0224353514837305e-05, "epoch": 1.144702842377261, "percentage": 57.23, "elapsed_time": "0:08:16", "remaining_time": "0:06:11"}
|
| 278 |
+
{"current_steps": 278, "total_steps": 484, "loss": 1.878, "lr": 2.0061815070551186e-05, "epoch": 1.1488372093023256, "percentage": 57.44, "elapsed_time": "0:08:18", "remaining_time": "0:06:09"}
|
| 279 |
+
{"current_steps": 279, "total_steps": 484, "loss": 1.9105, "lr": 1.989949355087339e-05, "epoch": 1.1529715762273902, "percentage": 57.64, "elapsed_time": "0:08:19", "remaining_time": "0:06:07"}
|
| 280 |
+
{"current_steps": 280, "total_steps": 484, "loss": 1.8895, "lr": 1.9737396086264313e-05, "epoch": 1.1571059431524549, "percentage": 57.85, "elapsed_time": "0:08:21", "remaining_time": "0:06:05"}
|
| 281 |
+
{"current_steps": 281, "total_steps": 484, "loss": 1.839, "lr": 1.957552979734205e-05, "epoch": 1.1612403100775195, "percentage": 58.06, "elapsed_time": "0:08:23", "remaining_time": "0:06:03"}
|
| 282 |
+
{"current_steps": 282, "total_steps": 484, "loss": 1.9009, "lr": 1.9413901794569644e-05, "epoch": 1.165374677002584, "percentage": 58.26, "elapsed_time": "0:08:25", "remaining_time": "0:06:01"}
|
| 283 |
+
{"current_steps": 283, "total_steps": 484, "loss": 1.8245, "lr": 1.9252519177942667e-05, "epoch": 1.1695090439276485, "percentage": 58.47, "elapsed_time": "0:08:26", "remaining_time": "0:06:00"}
|
| 284 |
+
{"current_steps": 284, "total_steps": 484, "loss": 1.8063, "lr": 1.9091389036677382e-05, "epoch": 1.1736434108527132, "percentage": 58.68, "elapsed_time": "0:08:28", "remaining_time": "0:05:58"}
|
| 285 |
+
{"current_steps": 285, "total_steps": 484, "loss": 1.8572, "lr": 1.8930518448899304e-05, "epoch": 1.1777777777777778, "percentage": 58.88, "elapsed_time": "0:08:30", "remaining_time": "0:05:56"}
|
| 286 |
+
{"current_steps": 286, "total_steps": 484, "loss": 1.7977, "lr": 1.8769914481332303e-05, "epoch": 1.1819121447028424, "percentage": 59.09, "elapsed_time": "0:08:32", "remaining_time": "0:05:54"}
|
| 287 |
+
{"current_steps": 287, "total_steps": 484, "loss": 1.8664, "lr": 1.8609584188988136e-05, "epoch": 1.1860465116279069, "percentage": 59.3, "elapsed_time": "0:08:33", "remaining_time": "0:05:52"}
|
| 288 |
+
{"current_steps": 288, "total_steps": 484, "loss": 1.8977, "lr": 1.8449534614856558e-05, "epoch": 1.1901808785529715, "percentage": 59.5, "elapsed_time": "0:08:35", "remaining_time": "0:05:50"}
|
| 289 |
+
{"current_steps": 289, "total_steps": 484, "loss": 1.8771, "lr": 1.8289772789595917e-05, "epoch": 1.1943152454780361, "percentage": 59.71, "elapsed_time": "0:08:37", "remaining_time": "0:05:48"}
|
| 290 |
+
{"current_steps": 290, "total_steps": 484, "loss": 1.8976, "lr": 1.813030573122437e-05, "epoch": 1.1984496124031008, "percentage": 59.92, "elapsed_time": "0:08:38", "remaining_time": "0:05:47"}
|
| 291 |
+
{"current_steps": 291, "total_steps": 484, "loss": 1.7874, "lr": 1.7971140444811513e-05, "epoch": 1.2025839793281654, "percentage": 60.12, "elapsed_time": "0:08:40", "remaining_time": "0:05:45"}
|
| 292 |
+
{"current_steps": 292, "total_steps": 484, "loss": 1.8486, "lr": 1.7812283922170718e-05, "epoch": 1.20671834625323, "percentage": 60.33, "elapsed_time": "0:08:42", "remaining_time": "0:05:43"}
|
| 293 |
+
{"current_steps": 293, "total_steps": 484, "loss": 1.8403, "lr": 1.7653743141551983e-05, "epoch": 1.2108527131782947, "percentage": 60.54, "elapsed_time": "0:08:43", "remaining_time": "0:05:41"}
|
| 294 |
+
{"current_steps": 294, "total_steps": 484, "loss": 1.8939, "lr": 1.749552506733537e-05, "epoch": 1.214987080103359, "percentage": 60.74, "elapsed_time": "0:08:45", "remaining_time": "0:05:39"}
|
| 295 |
+
{"current_steps": 295, "total_steps": 484, "loss": 1.8646, "lr": 1.733763664972513e-05, "epoch": 1.2191214470284237, "percentage": 60.95, "elapsed_time": "0:08:47", "remaining_time": "0:05:38"}
|
| 296 |
+
{"current_steps": 296, "total_steps": 484, "loss": 1.8722, "lr": 1.7180084824444325e-05, "epoch": 1.2232558139534884, "percentage": 61.16, "elapsed_time": "0:08:49", "remaining_time": "0:05:36"}
|
| 297 |
+
{"current_steps": 297, "total_steps": 484, "loss": 1.8458, "lr": 1.7022876512430197e-05, "epoch": 1.227390180878553, "percentage": 61.36, "elapsed_time": "0:08:50", "remaining_time": "0:05:34"}
|
| 298 |
+
{"current_steps": 298, "total_steps": 484, "loss": 1.8117, "lr": 1.6866018619530123e-05, "epoch": 1.2315245478036176, "percentage": 61.57, "elapsed_time": "0:08:52", "remaining_time": "0:05:32"}
|
| 299 |
+
{"current_steps": 299, "total_steps": 484, "loss": 1.8317, "lr": 1.6709518036198308e-05, "epoch": 1.235658914728682, "percentage": 61.78, "elapsed_time": "0:08:54", "remaining_time": "0:05:30"}
|
| 300 |
+
{"current_steps": 300, "total_steps": 484, "loss": 1.8655, "lr": 1.6553381637193018e-05, "epoch": 1.2397932816537467, "percentage": 61.98, "elapsed_time": "0:08:56", "remaining_time": "0:05:28"}
|
| 301 |
+
{"current_steps": 301, "total_steps": 484, "loss": 1.8391, "lr": 1.639761628127465e-05, "epoch": 1.2439276485788113, "percentage": 62.19, "elapsed_time": "0:08:58", "remaining_time": "0:05:27"}
|
| 302 |
+
{"current_steps": 302, "total_steps": 484, "loss": 1.8665, "lr": 1.6242228810904392e-05, "epoch": 1.248062015503876, "percentage": 62.4, "elapsed_time": "0:08:59", "remaining_time": "0:05:25"}
|
| 303 |
+
{"current_steps": 303, "total_steps": 484, "loss": 1.8349, "lr": 1.6087226051943728e-05, "epoch": 1.2521963824289406, "percentage": 62.6, "elapsed_time": "0:09:01", "remaining_time": "0:05:23"}
|
| 304 |
+
{"current_steps": 304, "total_steps": 484, "loss": 1.8874, "lr": 1.5932614813354486e-05, "epoch": 1.2563307493540052, "percentage": 62.81, "elapsed_time": "0:09:03", "remaining_time": "0:05:21"}
|
| 305 |
+
{"current_steps": 305, "total_steps": 484, "loss": 1.8545, "lr": 1.5778401886899807e-05, "epoch": 1.2604651162790699, "percentage": 63.02, "elapsed_time": "0:09:05", "remaining_time": "0:05:19"}
|
| 306 |
+
{"current_steps": 306, "total_steps": 484, "loss": 1.8512, "lr": 1.5624594046845777e-05, "epoch": 1.2645994832041343, "percentage": 63.22, "elapsed_time": "0:09:07", "remaining_time": "0:05:18"}
|
| 307 |
+
{"current_steps": 307, "total_steps": 484, "loss": 1.8466, "lr": 1.547119804966382e-05, "epoch": 1.268733850129199, "percentage": 63.43, "elapsed_time": "0:09:08", "remaining_time": "0:05:16"}
|
| 308 |
+
{"current_steps": 308, "total_steps": 484, "loss": 1.8543, "lr": 1.5318220633733978e-05, "epoch": 1.2728682170542636, "percentage": 63.64, "elapsed_time": "0:09:10", "remaining_time": "0:05:14"}
|
| 309 |
+
{"current_steps": 309, "total_steps": 484, "loss": 1.863, "lr": 1.5165668519048799e-05, "epoch": 1.2770025839793282, "percentage": 63.84, "elapsed_time": "0:09:12", "remaining_time": "0:05:12"}
|
| 310 |
+
{"current_steps": 310, "total_steps": 484, "loss": 1.8448, "lr": 1.5013548406918215e-05, "epoch": 1.2811369509043928, "percentage": 64.05, "elapsed_time": "0:09:14", "remaining_time": "0:05:10"}
|
| 311 |
+
{"current_steps": 311, "total_steps": 484, "loss": 1.801, "lr": 1.4861866979675154e-05, "epoch": 1.2852713178294572, "percentage": 64.26, "elapsed_time": "0:09:15", "remaining_time": "0:05:09"}
|
| 312 |
+
{"current_steps": 312, "total_steps": 484, "loss": 1.847, "lr": 1.4710630900382e-05, "epoch": 1.2894056847545219, "percentage": 64.46, "elapsed_time": "0:09:17", "remaining_time": "0:05:07"}
|
| 313 |
+
{"current_steps": 313, "total_steps": 484, "loss": 1.8623, "lr": 1.455984681253787e-05, "epoch": 1.2935400516795865, "percentage": 64.67, "elapsed_time": "0:09:19", "remaining_time": "0:05:05"}
|
| 314 |
+
{"current_steps": 314, "total_steps": 484, "loss": 1.8888, "lr": 1.4409521339786808e-05, "epoch": 1.2976744186046512, "percentage": 64.88, "elapsed_time": "0:09:21", "remaining_time": "0:05:04"}
|
| 315 |
+
{"current_steps": 315, "total_steps": 484, "loss": 1.8331, "lr": 1.4259661085626801e-05, "epoch": 1.3018087855297158, "percentage": 65.08, "elapsed_time": "0:09:23", "remaining_time": "0:05:02"}
|
| 316 |
+
{"current_steps": 316, "total_steps": 484, "loss": 1.8092, "lr": 1.4110272633119753e-05, "epoch": 1.3059431524547804, "percentage": 65.29, "elapsed_time": "0:09:25", "remaining_time": "0:05:00"}
|
| 317 |
+
{"current_steps": 317, "total_steps": 484, "loss": 1.8703, "lr": 1.3961362544602213e-05, "epoch": 1.310077519379845, "percentage": 65.5, "elapsed_time": "0:09:27", "remaining_time": "0:04:58"}
|
| 318 |
+
{"current_steps": 318, "total_steps": 484, "loss": 1.872, "lr": 1.3812937361397165e-05, "epoch": 1.3142118863049095, "percentage": 65.7, "elapsed_time": "0:09:28", "remaining_time": "0:04:56"}
|
| 319 |
+
{"current_steps": 319, "total_steps": 484, "loss": 1.8474, "lr": 1.3665003603526705e-05, "epoch": 1.3183462532299741, "percentage": 65.91, "elapsed_time": "0:09:30", "remaining_time": "0:04:55"}
|
| 320 |
+
{"current_steps": 320, "total_steps": 484, "loss": 1.8529, "lr": 1.3517567769425548e-05, "epoch": 1.3224806201550388, "percentage": 66.12, "elapsed_time": "0:09:32", "remaining_time": "0:04:53"}
|
| 321 |
+
{"current_steps": 321, "total_steps": 484, "loss": 1.8471, "lr": 1.3370636335655656e-05, "epoch": 1.3266149870801034, "percentage": 66.32, "elapsed_time": "0:09:34", "remaining_time": "0:04:51"}
|
| 322 |
+
{"current_steps": 322, "total_steps": 484, "loss": 1.8375, "lr": 1.3224215756621652e-05, "epoch": 1.330749354005168, "percentage": 66.53, "elapsed_time": "0:09:36", "remaining_time": "0:04:49"}
|
| 323 |
+
{"current_steps": 323, "total_steps": 484, "loss": 1.8213, "lr": 1.3078312464287353e-05, "epoch": 1.3348837209302324, "percentage": 66.74, "elapsed_time": "0:09:37", "remaining_time": "0:04:48"}
|
| 324 |
+
{"current_steps": 324, "total_steps": 484, "loss": 1.8426, "lr": 1.2932932867893189e-05, "epoch": 1.339018087855297, "percentage": 66.94, "elapsed_time": "0:09:39", "remaining_time": "0:04:46"}
|
| 325 |
+
{"current_steps": 325, "total_steps": 484, "loss": 1.8597, "lr": 1.2788083353674693e-05, "epoch": 1.3431524547803617, "percentage": 67.15, "elapsed_time": "0:09:40", "remaining_time": "0:04:44"}
|
| 326 |
+
{"current_steps": 326, "total_steps": 484, "loss": 1.8445, "lr": 1.2643770284581929e-05, "epoch": 1.3472868217054264, "percentage": 67.36, "elapsed_time": "0:09:42", "remaining_time": "0:04:42"}
|
| 327 |
+
{"current_steps": 327, "total_steps": 484, "loss": 1.8973, "lr": 1.2500000000000006e-05, "epoch": 1.351421188630491, "percentage": 67.56, "elapsed_time": "0:09:44", "remaining_time": "0:04:40"}
|
| 328 |
+
{"current_steps": 328, "total_steps": 484, "loss": 1.8589, "lr": 1.2356778815470573e-05, "epoch": 1.3555555555555556, "percentage": 67.77, "elapsed_time": "0:09:46", "remaining_time": "0:04:38"}
|
| 329 |
+
{"current_steps": 329, "total_steps": 484, "loss": 1.8268, "lr": 1.2214113022414448e-05, "epoch": 1.3596899224806203, "percentage": 67.98, "elapsed_time": "0:09:48", "remaining_time": "0:04:37"}
|
| 330 |
+
{"current_steps": 330, "total_steps": 484, "loss": 1.864, "lr": 1.2072008887855174e-05, "epoch": 1.3638242894056847, "percentage": 68.18, "elapsed_time": "0:09:50", "remaining_time": "0:04:35"}
|
| 331 |
+
{"current_steps": 331, "total_steps": 484, "loss": 1.8236, "lr": 1.1930472654143776e-05, "epoch": 1.3679586563307493, "percentage": 68.39, "elapsed_time": "0:09:51", "remaining_time": "0:04:33"}
|
| 332 |
+
{"current_steps": 332, "total_steps": 484, "loss": 1.8804, "lr": 1.1789510538684523e-05, "epoch": 1.372093023255814, "percentage": 68.6, "elapsed_time": "0:09:53", "remaining_time": "0:04:31"}
|
| 333 |
+
{"current_steps": 333, "total_steps": 484, "loss": 1.8574, "lr": 1.1649128733661802e-05, "epoch": 1.3762273901808786, "percentage": 68.8, "elapsed_time": "0:09:55", "remaining_time": "0:04:29"}
|
| 334 |
+
{"current_steps": 334, "total_steps": 484, "loss": 1.9211, "lr": 1.1509333405768152e-05, "epoch": 1.3803617571059432, "percentage": 69.01, "elapsed_time": "0:09:56", "remaining_time": "0:04:28"}
|
| 335 |
+
{"current_steps": 335, "total_steps": 484, "loss": 1.8639, "lr": 1.1370130695933318e-05, "epoch": 1.3844961240310076, "percentage": 69.21, "elapsed_time": "0:09:58", "remaining_time": "0:04:26"}
|
| 336 |
+
{"current_steps": 336, "total_steps": 484, "loss": 1.8409, "lr": 1.123152671905451e-05, "epoch": 1.3886304909560723, "percentage": 69.42, "elapsed_time": "0:10:00", "remaining_time": "0:04:24"}
|
| 337 |
+
{"current_steps": 337, "total_steps": 484, "loss": 1.8612, "lr": 1.1093527563727827e-05, "epoch": 1.392764857881137, "percentage": 69.63, "elapsed_time": "0:10:02", "remaining_time": "0:04:22"}
|
| 338 |
+
{"current_steps": 338, "total_steps": 484, "loss": 1.8504, "lr": 1.0956139291980727e-05, "epoch": 1.3968992248062015, "percentage": 69.83, "elapsed_time": "0:10:04", "remaining_time": "0:04:21"}
|
| 339 |
+
{"current_steps": 339, "total_steps": 484, "loss": 1.8497, "lr": 1.08193679390058e-05, "epoch": 1.4010335917312662, "percentage": 70.04, "elapsed_time": "0:10:06", "remaining_time": "0:04:19"}
|
| 340 |
+
{"current_steps": 340, "total_steps": 484, "loss": 1.8579, "lr": 1.0683219512895612e-05, "epoch": 1.4051679586563308, "percentage": 70.25, "elapsed_time": "0:10:07", "remaining_time": "0:04:17"}
|
| 341 |
+
{"current_steps": 341, "total_steps": 484, "loss": 1.8193, "lr": 1.0547699994378787e-05, "epoch": 1.4093023255813955, "percentage": 70.45, "elapsed_time": "0:10:09", "remaining_time": "0:04:15"}
|
| 342 |
+
{"current_steps": 342, "total_steps": 484, "loss": 1.8528, "lr": 1.0412815336557316e-05, "epoch": 1.4134366925064599, "percentage": 70.66, "elapsed_time": "0:10:11", "remaining_time": "0:04:13"}
|
| 343 |
+
{"current_steps": 343, "total_steps": 484, "loss": 1.8185, "lr": 1.0278571464645011e-05, "epoch": 1.4175710594315245, "percentage": 70.87, "elapsed_time": "0:10:13", "remaining_time": "0:04:12"}
|
| 344 |
+
{"current_steps": 344, "total_steps": 484, "loss": 1.8597, "lr": 1.0144974275707241e-05, "epoch": 1.4217054263565891, "percentage": 71.07, "elapsed_time": "0:10:15", "remaining_time": "0:04:10"}
|
| 345 |
+
{"current_steps": 345, "total_steps": 484, "loss": 1.8352, "lr": 1.001202963840187e-05, "epoch": 1.4258397932816538, "percentage": 71.28, "elapsed_time": "0:10:16", "remaining_time": "0:04:08"}
|
| 346 |
+
{"current_steps": 346, "total_steps": 484, "loss": 1.8801, "lr": 9.879743392721506e-06, "epoch": 1.4299741602067184, "percentage": 71.49, "elapsed_time": "0:10:18", "remaining_time": "0:04:06"}
|
| 347 |
+
{"current_steps": 347, "total_steps": 484, "loss": 1.8583, "lr": 9.748121349736892e-06, "epoch": 1.4341085271317828, "percentage": 71.69, "elapsed_time": "0:10:20", "remaining_time": "0:04:04"}
|
| 348 |
+
{"current_steps": 348, "total_steps": 484, "loss": 1.875, "lr": 9.617169291341689e-06, "epoch": 1.4382428940568475, "percentage": 71.9, "elapsed_time": "0:10:21", "remaining_time": "0:04:03"}
|
| 349 |
+
{"current_steps": 349, "total_steps": 484, "loss": 1.8851, "lr": 9.486892969998465e-06, "epoch": 1.442377260981912, "percentage": 72.11, "elapsed_time": "0:10:23", "remaining_time": "0:04:01"}
|
| 350 |
+
{"current_steps": 350, "total_steps": 484, "loss": 1.8454, "lr": 9.357298108486003e-06, "epoch": 1.4465116279069767, "percentage": 72.31, "elapsed_time": "0:10:25", "remaining_time": "0:03:59"}
|
| 351 |
+
{"current_steps": 351, "total_steps": 484, "loss": 1.8602, "lr": 9.228390399647943e-06, "epoch": 1.4506459948320414, "percentage": 72.52, "elapsed_time": "0:10:27", "remaining_time": "0:03:57"}
|
| 352 |
+
{"current_steps": 352, "total_steps": 484, "loss": 1.8836, "lr": 9.10017550614265e-06, "epoch": 1.454780361757106, "percentage": 72.73, "elapsed_time": "0:10:29", "remaining_time": "0:03:55"}
|
| 353 |
+
{"current_steps": 353, "total_steps": 484, "loss": 1.8628, "lr": 8.972659060194506e-06, "epoch": 1.4589147286821706, "percentage": 72.93, "elapsed_time": "0:10:31", "remaining_time": "0:03:54"}
|
| 354 |
+
{"current_steps": 354, "total_steps": 484, "loss": 1.8457, "lr": 8.845846663346472e-06, "epoch": 1.463049095607235, "percentage": 73.14, "elapsed_time": "0:10:32", "remaining_time": "0:03:52"}
|
| 355 |
+
{"current_steps": 355, "total_steps": 484, "loss": 1.8254, "lr": 8.71974388621407e-06, "epoch": 1.4671834625322997, "percentage": 73.35, "elapsed_time": "0:10:34", "remaining_time": "0:03:50"}
|
| 356 |
+
{"current_steps": 356, "total_steps": 484, "loss": 1.8711, "lr": 8.594356268240616e-06, "epoch": 1.4713178294573643, "percentage": 73.55, "elapsed_time": "0:10:36", "remaining_time": "0:03:48"}
|
| 357 |
+
{"current_steps": 357, "total_steps": 484, "loss": 1.8553, "lr": 8.469689317453908e-06, "epoch": 1.475452196382429, "percentage": 73.76, "elapsed_time": "0:10:38", "remaining_time": "0:03:47"}
|
| 358 |
+
{"current_steps": 358, "total_steps": 484, "loss": 1.8525, "lr": 8.345748510224299e-06, "epoch": 1.4795865633074936, "percentage": 73.97, "elapsed_time": "0:10:40", "remaining_time": "0:03:45"}
|
| 359 |
+
{"current_steps": 359, "total_steps": 484, "loss": 1.9113, "lr": 8.222539291024078e-06, "epoch": 1.483720930232558, "percentage": 74.17, "elapsed_time": "0:10:41", "remaining_time": "0:03:43"}
|
| 360 |
+
{"current_steps": 360, "total_steps": 484, "loss": 1.8571, "lr": 8.100067072188356e-06, "epoch": 1.4878552971576227, "percentage": 74.38, "elapsed_time": "0:10:43", "remaining_time": "0:03:41"}
|
| 361 |
+
{"current_steps": 361, "total_steps": 484, "loss": 1.8458, "lr": 7.978337233677268e-06, "epoch": 1.4919896640826873, "percentage": 74.59, "elapsed_time": "0:10:45", "remaining_time": "0:03:39"}
|
| 362 |
+
{"current_steps": 362, "total_steps": 484, "loss": 1.8726, "lr": 7.857355122839675e-06, "epoch": 1.496124031007752, "percentage": 74.79, "elapsed_time": "0:10:47", "remaining_time": "0:03:38"}
|
| 363 |
+
{"current_steps": 363, "total_steps": 484, "loss": 1.8668, "lr": 7.737126054178237e-06, "epoch": 1.5002583979328166, "percentage": 75.0, "elapsed_time": "0:10:49", "remaining_time": "0:03:36"}
|
| 364 |
+
{"current_steps": 364, "total_steps": 484, "loss": 1.8788, "lr": 7.617655309116009e-06, "epoch": 1.5043927648578812, "percentage": 75.21, "elapsed_time": "0:10:50", "remaining_time": "0:03:34"}
|
| 365 |
+
{"current_steps": 365, "total_steps": 484, "loss": 1.8416, "lr": 7.4989481357643694e-06, "epoch": 1.5085271317829458, "percentage": 75.41, "elapsed_time": "0:10:52", "remaining_time": "0:03:32"}
|
| 366 |
+
{"current_steps": 366, "total_steps": 484, "loss": 1.8633, "lr": 7.381009748692527e-06, "epoch": 1.5126614987080105, "percentage": 75.62, "elapsed_time": "0:10:54", "remaining_time": "0:03:31"}
|
| 367 |
+
{"current_steps": 367, "total_steps": 484, "loss": 1.8743, "lr": 7.26384532869844e-06, "epoch": 1.516795865633075, "percentage": 75.83, "elapsed_time": "0:10:56", "remaining_time": "0:03:29"}
|
| 368 |
+
{"current_steps": 368, "total_steps": 484, "loss": 1.8014, "lr": 7.147460022581257e-06, "epoch": 1.5209302325581395, "percentage": 76.03, "elapsed_time": "0:10:58", "remaining_time": "0:03:27"}
|
| 369 |
+
{"current_steps": 369, "total_steps": 484, "loss": 1.8386, "lr": 7.031858942915187e-06, "epoch": 1.5250645994832042, "percentage": 76.24, "elapsed_time": "0:10:59", "remaining_time": "0:03:25"}
|
| 370 |
+
{"current_steps": 370, "total_steps": 484, "loss": 1.8405, "lr": 6.917047167824939e-06, "epoch": 1.5291989664082686, "percentage": 76.45, "elapsed_time": "0:11:01", "remaining_time": "0:03:23"}
|
| 371 |
+
{"current_steps": 371, "total_steps": 484, "loss": 1.83, "lr": 6.803029740762648e-06, "epoch": 1.5333333333333332, "percentage": 76.65, "elapsed_time": "0:11:03", "remaining_time": "0:03:22"}
|
| 372 |
+
{"current_steps": 372, "total_steps": 484, "loss": 1.8482, "lr": 6.689811670286342e-06, "epoch": 1.5374677002583979, "percentage": 76.86, "elapsed_time": "0:11:04", "remaining_time": "0:03:20"}
|
| 373 |
+
{"current_steps": 373, "total_steps": 484, "loss": 1.8653, "lr": 6.57739792983989e-06, "epoch": 1.5416020671834625, "percentage": 77.07, "elapsed_time": "0:11:06", "remaining_time": "0:03:18"}
|
| 374 |
+
{"current_steps": 374, "total_steps": 484, "loss": 1.8693, "lr": 6.465793457534553e-06, "epoch": 1.5457364341085271, "percentage": 77.27, "elapsed_time": "0:11:08", "remaining_time": "0:03:16"}
|
| 375 |
+
{"current_steps": 375, "total_steps": 484, "loss": 1.8395, "lr": 6.355003155932052e-06, "epoch": 1.5498708010335918, "percentage": 77.48, "elapsed_time": "0:11:10", "remaining_time": "0:03:14"}
|
| 376 |
+
{"current_steps": 376, "total_steps": 484, "loss": 1.8553, "lr": 6.245031891829237e-06, "epoch": 1.5540051679586564, "percentage": 77.69, "elapsed_time": "0:11:11", "remaining_time": "0:03:12"}
|
| 377 |
+
{"current_steps": 377, "total_steps": 484, "loss": 1.8392, "lr": 6.135884496044244e-06, "epoch": 1.558139534883721, "percentage": 77.89, "elapsed_time": "0:11:13", "remaining_time": "0:03:11"}
|
| 378 |
+
{"current_steps": 378, "total_steps": 484, "loss": 1.8382, "lr": 6.0275657632043485e-06, "epoch": 1.5622739018087857, "percentage": 78.1, "elapsed_time": "0:11:15", "remaining_time": "0:03:09"}
|
| 379 |
+
{"current_steps": 379, "total_steps": 484, "loss": 1.8157, "lr": 5.920080451535295e-06, "epoch": 1.56640826873385, "percentage": 78.31, "elapsed_time": "0:11:17", "remaining_time": "0:03:07"}
|
| 380 |
+
{"current_steps": 380, "total_steps": 484, "loss": 1.8271, "lr": 5.813433282652298e-06, "epoch": 1.5705426356589147, "percentage": 78.51, "elapsed_time": "0:11:18", "remaining_time": "0:03:05"}
|
| 381 |
+
{"current_steps": 381, "total_steps": 484, "loss": 1.8964, "lr": 5.7076289413526554e-06, "epoch": 1.5746770025839794, "percentage": 78.72, "elapsed_time": "0:11:20", "remaining_time": "0:03:04"}
|
| 382 |
+
{"current_steps": 382, "total_steps": 484, "loss": 1.83, "lr": 5.602672075409904e-06, "epoch": 1.5788113695090438, "percentage": 78.93, "elapsed_time": "0:11:22", "remaining_time": "0:03:02"}
|
| 383 |
+
{"current_steps": 383, "total_steps": 484, "loss": 1.8695, "lr": 5.4985672953697e-06, "epoch": 1.5829457364341084, "percentage": 79.13, "elapsed_time": "0:11:24", "remaining_time": "0:03:00"}
|
| 384 |
+
{"current_steps": 384, "total_steps": 484, "loss": 1.8578, "lr": 5.395319174347244e-06, "epoch": 1.587080103359173, "percentage": 79.34, "elapsed_time": "0:11:26", "remaining_time": "0:02:58"}
|
| 385 |
+
{"current_steps": 385, "total_steps": 484, "loss": 1.8401, "lr": 5.292932247826449e-06, "epoch": 1.5912144702842377, "percentage": 79.55, "elapsed_time": "0:11:28", "remaining_time": "0:02:56"}
|
| 386 |
+
{"current_steps": 386, "total_steps": 484, "loss": 1.8087, "lr": 5.191411013460645e-06, "epoch": 1.5953488372093023, "percentage": 79.75, "elapsed_time": "0:11:29", "remaining_time": "0:02:55"}
|
| 387 |
+
{"current_steps": 387, "total_steps": 484, "loss": 1.8407, "lr": 5.090759930875039e-06, "epoch": 1.599483204134367, "percentage": 79.96, "elapsed_time": "0:11:31", "remaining_time": "0:02:53"}
|
| 388 |
+
{"current_steps": 388, "total_steps": 484, "loss": 1.8525, "lr": 4.990983421470813e-06, "epoch": 1.6036175710594316, "percentage": 80.17, "elapsed_time": "0:11:33", "remaining_time": "0:02:51"}
|
| 389 |
+
{"current_steps": 389, "total_steps": 484, "loss": 1.9135, "lr": 4.892085868230881e-06, "epoch": 1.6077519379844962, "percentage": 80.37, "elapsed_time": "0:11:35", "remaining_time": "0:02:49"}
|
| 390 |
+
{"current_steps": 390, "total_steps": 484, "loss": 1.8808, "lr": 4.794071615527393e-06, "epoch": 1.6118863049095609, "percentage": 80.58, "elapsed_time": "0:11:37", "remaining_time": "0:02:48"}
|
| 391 |
+
{"current_steps": 391, "total_steps": 484, "loss": 1.822, "lr": 4.696944968930847e-06, "epoch": 1.6160206718346253, "percentage": 80.79, "elapsed_time": "0:11:39", "remaining_time": "0:02:46"}
|
| 392 |
+
{"current_steps": 392, "total_steps": 484, "loss": 1.8732, "lr": 4.600710195020982e-06, "epoch": 1.62015503875969, "percentage": 80.99, "elapsed_time": "0:11:40", "remaining_time": "0:02:44"}
|
| 393 |
+
{"current_steps": 393, "total_steps": 484, "loss": 1.8418, "lr": 4.505371521199342e-06, "epoch": 1.6242894056847546, "percentage": 81.2, "elapsed_time": "0:11:42", "remaining_time": "0:02:42"}
|
| 394 |
+
{"current_steps": 394, "total_steps": 484, "loss": 1.815, "lr": 4.4109331355036085e-06, "epoch": 1.628423772609819, "percentage": 81.4, "elapsed_time": "0:11:44", "remaining_time": "0:02:40"}
|
| 395 |
+
{"current_steps": 395, "total_steps": 484, "loss": 1.8274, "lr": 4.317399186423574e-06, "epoch": 1.6325581395348836, "percentage": 81.61, "elapsed_time": "0:11:46", "remaining_time": "0:02:39"}
|
| 396 |
+
{"current_steps": 396, "total_steps": 484, "loss": 1.7943, "lr": 4.2247737827189435e-06, "epoch": 1.6366925064599482, "percentage": 81.82, "elapsed_time": "0:11:48", "remaining_time": "0:02:37"}
|
| 397 |
+
{"current_steps": 397, "total_steps": 484, "loss": 1.8355, "lr": 4.1330609932388495e-06, "epoch": 1.6408268733850129, "percentage": 82.02, "elapsed_time": "0:11:49", "remaining_time": "0:02:35"}
|
| 398 |
+
{"current_steps": 398, "total_steps": 484, "loss": 1.8786, "lr": 4.042264846743085e-06, "epoch": 1.6449612403100775, "percentage": 82.23, "elapsed_time": "0:11:51", "remaining_time": "0:02:33"}
|
| 399 |
+
{"current_steps": 399, "total_steps": 484, "loss": 1.8485, "lr": 3.952389331725162e-06, "epoch": 1.6490956072351421, "percentage": 82.44, "elapsed_time": "0:11:53", "remaining_time": "0:02:31"}
|
| 400 |
+
{"current_steps": 400, "total_steps": 484, "loss": 1.8068, "lr": 3.863438396237082e-06, "epoch": 1.6532299741602068, "percentage": 82.64, "elapsed_time": "0:11:54", "remaining_time": "0:02:30"}
|
| 401 |
+
{"current_steps": 401, "total_steps": 484, "loss": 1.7877, "lr": 3.775415947715899e-06, "epoch": 1.6573643410852714, "percentage": 82.85, "elapsed_time": "0:11:56", "remaining_time": "0:02:28"}
|
| 402 |
+
{"current_steps": 402, "total_steps": 484, "loss": 1.8659, "lr": 3.6883258528121188e-06, "epoch": 1.661498708010336, "percentage": 83.06, "elapsed_time": "0:11:58", "remaining_time": "0:02:26"}
|
| 403 |
+
{"current_steps": 403, "total_steps": 484, "loss": 1.8661, "lr": 3.602171937219789e-06, "epoch": 1.6656330749354005, "percentage": 83.26, "elapsed_time": "0:12:00", "remaining_time": "0:02:24"}
|
| 404 |
+
{"current_steps": 404, "total_steps": 484, "loss": 1.8701, "lr": 3.516957985508476e-06, "epoch": 1.669767441860465, "percentage": 83.47, "elapsed_time": "0:12:01", "remaining_time": "0:02:22"}
|
| 405 |
+
{"current_steps": 405, "total_steps": 484, "loss": 1.8656, "lr": 3.432687740957008e-06, "epoch": 1.6739018087855297, "percentage": 83.68, "elapsed_time": "0:12:03", "remaining_time": "0:02:21"}
|
| 406 |
+
{"current_steps": 406, "total_steps": 484, "loss": 1.8797, "lr": 3.3493649053890326e-06, "epoch": 1.6780361757105942, "percentage": 83.88, "elapsed_time": "0:12:05", "remaining_time": "0:02:19"}
|
| 407 |
+
{"current_steps": 407, "total_steps": 484, "loss": 1.8763, "lr": 3.266993139010438e-06, "epoch": 1.6821705426356588, "percentage": 84.09, "elapsed_time": "0:12:06", "remaining_time": "0:02:17"}
|
| 408 |
+
{"current_steps": 408, "total_steps": 484, "loss": 1.8886, "lr": 3.185576060248513e-06, "epoch": 1.6863049095607234, "percentage": 84.3, "elapsed_time": "0:12:08", "remaining_time": "0:02:15"}
|
| 409 |
+
{"current_steps": 409, "total_steps": 484, "loss": 1.827, "lr": 3.1051172455930394e-06, "epoch": 1.690439276485788, "percentage": 84.5, "elapsed_time": "0:12:10", "remaining_time": "0:02:13"}
|
| 410 |
+
{"current_steps": 410, "total_steps": 484, "loss": 1.83, "lr": 3.0256202294391577e-06, "epoch": 1.6945736434108527, "percentage": 84.71, "elapsed_time": "0:12:12", "remaining_time": "0:02:12"}
|
| 411 |
+
{"current_steps": 411, "total_steps": 484, "loss": 1.9031, "lr": 2.9470885039321356e-06, "epoch": 1.6987080103359173, "percentage": 84.92, "elapsed_time": "0:12:14", "remaining_time": "0:02:10"}
|
| 412 |
+
{"current_steps": 412, "total_steps": 484, "loss": 1.8421, "lr": 2.8695255188139426e-06, "epoch": 1.702842377260982, "percentage": 85.12, "elapsed_time": "0:12:15", "remaining_time": "0:02:08"}
|
| 413 |
+
{"current_steps": 413, "total_steps": 484, "loss": 1.799, "lr": 2.792934681271708e-06, "epoch": 1.7069767441860466, "percentage": 85.33, "elapsed_time": "0:12:17", "remaining_time": "0:02:06"}
|
| 414 |
+
{"current_steps": 414, "total_steps": 484, "loss": 1.8414, "lr": 2.7173193557880615e-06, "epoch": 1.7111111111111112, "percentage": 85.54, "elapsed_time": "0:12:19", "remaining_time": "0:02:04"}
|
| 415 |
+
{"current_steps": 415, "total_steps": 484, "loss": 1.8484, "lr": 2.6426828639933536e-06, "epoch": 1.7152454780361757, "percentage": 85.74, "elapsed_time": "0:12:21", "remaining_time": "0:02:03"}
|
| 416 |
+
{"current_steps": 416, "total_steps": 484, "loss": 1.8877, "lr": 2.5690284845196923e-06, "epoch": 1.7193798449612403, "percentage": 85.95, "elapsed_time": "0:12:22", "remaining_time": "0:02:01"}
|
| 417 |
+
{"current_steps": 417, "total_steps": 484, "loss": 1.8535, "lr": 2.4963594528569833e-06, "epoch": 1.723514211886305, "percentage": 86.16, "elapsed_time": "0:12:24", "remaining_time": "0:01:59"}
|
| 418 |
+
{"current_steps": 418, "total_steps": 484, "loss": 1.8502, "lr": 2.424678961210747e-06, "epoch": 1.7276485788113694, "percentage": 86.36, "elapsed_time": "0:12:26", "remaining_time": "0:01:57"}
|
| 419 |
+
{"current_steps": 419, "total_steps": 484, "loss": 1.8292, "lr": 2.3539901583619185e-06, "epoch": 1.731782945736434, "percentage": 86.57, "elapsed_time": "0:12:28", "remaining_time": "0:01:56"}
|
| 420 |
+
{"current_steps": 420, "total_steps": 484, "loss": 1.8694, "lr": 2.2842961495285335e-06, "epoch": 1.7359173126614986, "percentage": 86.78, "elapsed_time": "0:12:29", "remaining_time": "0:01:54"}
|
| 421 |
+
{"current_steps": 421, "total_steps": 484, "loss": 1.7625, "lr": 2.2155999962293033e-06, "epoch": 1.7400516795865633, "percentage": 86.98, "elapsed_time": "0:12:31", "remaining_time": "0:01:52"}
|
| 422 |
+
{"current_steps": 422, "total_steps": 484, "loss": 1.8017, "lr": 2.147904716149135e-06, "epoch": 1.744186046511628, "percentage": 87.19, "elapsed_time": "0:12:33", "remaining_time": "0:01:50"}
|
| 423 |
+
{"current_steps": 423, "total_steps": 484, "loss": 1.8337, "lr": 2.081213283006575e-06, "epoch": 1.7483204134366925, "percentage": 87.4, "elapsed_time": "0:12:35", "remaining_time": "0:01:48"}
|
| 424 |
+
{"current_steps": 424, "total_steps": 484, "loss": 1.8175, "lr": 2.0155286264231856e-06, "epoch": 1.7524547803617572, "percentage": 87.6, "elapsed_time": "0:12:36", "remaining_time": "0:01:47"}
|
| 425 |
+
{"current_steps": 425, "total_steps": 484, "loss": 1.8493, "lr": 1.9508536317948357e-06, "epoch": 1.7565891472868218, "percentage": 87.81, "elapsed_time": "0:12:38", "remaining_time": "0:01:45"}
|
| 426 |
+
{"current_steps": 426, "total_steps": 484, "loss": 1.8613, "lr": 1.887191140164954e-06, "epoch": 1.7607235142118864, "percentage": 88.02, "elapsed_time": "0:12:40", "remaining_time": "0:01:43"}
|
| 427 |
+
{"current_steps": 427, "total_steps": 484, "loss": 1.8511, "lr": 1.8245439480997439e-06, "epoch": 1.7648578811369509, "percentage": 88.22, "elapsed_time": "0:12:41", "remaining_time": "0:01:41"}
|
| 428 |
+
{"current_steps": 428, "total_steps": 484, "loss": 1.8711, "lr": 1.7629148075653245e-06, "epoch": 1.7689922480620155, "percentage": 88.43, "elapsed_time": "0:12:43", "remaining_time": "0:01:39"}
|
| 429 |
+
{"current_steps": 429, "total_steps": 484, "loss": 1.8665, "lr": 1.7023064258068377e-06, "epoch": 1.7731266149870801, "percentage": 88.64, "elapsed_time": "0:12:45", "remaining_time": "0:01:38"}
|
| 430 |
+
{"current_steps": 430, "total_steps": 484, "loss": 1.8085, "lr": 1.6427214652295326e-06, "epoch": 1.7772609819121445, "percentage": 88.84, "elapsed_time": "0:12:47", "remaining_time": "0:01:36"}
|
| 431 |
+
{"current_steps": 431, "total_steps": 484, "loss": 1.8855, "lr": 1.5841625432818057e-06, "epoch": 1.7813953488372092, "percentage": 89.05, "elapsed_time": "0:12:48", "remaining_time": "0:01:34"}
|
| 432 |
+
{"current_steps": 432, "total_steps": 484, "loss": 1.9024, "lr": 1.5266322323402277e-06, "epoch": 1.7855297157622738, "percentage": 89.26, "elapsed_time": "0:12:50", "remaining_time": "0:01:32"}
|
| 433 |
+
{"current_steps": 433, "total_steps": 484, "loss": 1.864, "lr": 1.4701330595965402e-06, "epoch": 1.7896640826873385, "percentage": 89.46, "elapsed_time": "0:12:52", "remaining_time": "0:01:31"}
|
| 434 |
+
{"current_steps": 434, "total_steps": 484, "loss": 1.8587, "lr": 1.4146675069466403e-06, "epoch": 1.793798449612403, "percentage": 89.67, "elapsed_time": "0:12:54", "remaining_time": "0:01:29"}
|
| 435 |
+
{"current_steps": 435, "total_steps": 484, "loss": 1.8191, "lr": 1.3602380108815537e-06, "epoch": 1.7979328165374677, "percentage": 89.88, "elapsed_time": "0:12:56", "remaining_time": "0:01:27"}
|
| 436 |
+
{"current_steps": 436, "total_steps": 484, "loss": 1.8353, "lr": 1.3068469623804176e-06, "epoch": 1.8020671834625324, "percentage": 90.08, "elapsed_time": "0:12:58", "remaining_time": "0:01:25"}
|
| 437 |
+
{"current_steps": 437, "total_steps": 484, "loss": 1.824, "lr": 1.2544967068054332e-06, "epoch": 1.806201550387597, "percentage": 90.29, "elapsed_time": "0:12:59", "remaining_time": "0:01:23"}
|
| 438 |
+
{"current_steps": 438, "total_steps": 484, "loss": 1.8875, "lr": 1.2031895437988493e-06, "epoch": 1.8103359173126616, "percentage": 90.5, "elapsed_time": "0:13:01", "remaining_time": "0:01:22"}
|
| 439 |
+
{"current_steps": 439, "total_steps": 484, "loss": 1.8507, "lr": 1.152927727181935e-06, "epoch": 1.814470284237726, "percentage": 90.7, "elapsed_time": "0:13:03", "remaining_time": "0:01:20"}
|
| 440 |
+
{"current_steps": 440, "total_steps": 484, "loss": 1.867, "lr": 1.1037134648559794e-06, "epoch": 1.8186046511627907, "percentage": 90.91, "elapsed_time": "0:13:05", "remaining_time": "0:01:18"}
|
| 441 |
+
{"current_steps": 441, "total_steps": 484, "loss": 1.8777, "lr": 1.0555489187053096e-06, "epoch": 1.8227390180878553, "percentage": 91.12, "elapsed_time": "0:13:07", "remaining_time": "0:01:16"}
|
| 442 |
+
{"current_steps": 442, "total_steps": 484, "loss": 1.8892, "lr": 1.008436204502311e-06, "epoch": 1.8268733850129197, "percentage": 91.32, "elapsed_time": "0:13:08", "remaining_time": "0:01:14"}
|
| 443 |
+
{"current_steps": 443, "total_steps": 484, "loss": 1.7744, "lr": 9.623773918144897e-07, "epoch": 1.8310077519379844, "percentage": 91.53, "elapsed_time": "0:13:10", "remaining_time": "0:01:13"}
|
| 444 |
+
{"current_steps": 444, "total_steps": 484, "loss": 1.8433, "lr": 9.173745039135622e-07, "epoch": 1.835142118863049, "percentage": 91.74, "elapsed_time": "0:13:12", "remaining_time": "0:01:11"}
|
| 445 |
+
{"current_steps": 445, "total_steps": 484, "loss": 1.8294, "lr": 8.734295176865747e-07, "epoch": 1.8392764857881136, "percentage": 91.94, "elapsed_time": "0:13:14", "remaining_time": "0:01:09"}
|
| 446 |
+
{"current_steps": 446, "total_steps": 484, "loss": 1.8404, "lr": 8.305443635490711e-07, "epoch": 1.8434108527131783, "percentage": 92.15, "elapsed_time": "0:13:15", "remaining_time": "0:01:07"}
|
| 447 |
+
{"current_steps": 447, "total_steps": 484, "loss": 1.8432, "lr": 7.887209253602839e-07, "epoch": 1.847545219638243, "percentage": 92.36, "elapsed_time": "0:13:17", "remaining_time": "0:01:06"}
|
| 448 |
+
{"current_steps": 448, "total_steps": 484, "loss": 1.8492, "lr": 7.479610403403781e-07, "epoch": 1.8516795865633076, "percentage": 92.56, "elapsed_time": "0:13:19", "remaining_time": "0:01:04"}
|
| 449 |
+
{"current_steps": 449, "total_steps": 484, "loss": 1.8722, "lr": 7.082664989897487e-07, "epoch": 1.8558139534883722, "percentage": 92.77, "elapsed_time": "0:13:21", "remaining_time": "0:01:02"}
|
| 450 |
+
{"current_steps": 450, "total_steps": 484, "loss": 1.8855, "lr": 6.696390450103867e-07, "epoch": 1.8599483204134368, "percentage": 92.98, "elapsed_time": "0:13:22", "remaining_time": "0:01:00"}
|
| 451 |
+
{"current_steps": 451, "total_steps": 484, "loss": 1.8698, "lr": 6.320803752292464e-07, "epoch": 1.8640826873385012, "percentage": 93.18, "elapsed_time": "0:13:24", "remaining_time": "0:00:58"}
|
| 452 |
+
{"current_steps": 452, "total_steps": 484, "loss": 1.8963, "lr": 5.955921395237318e-07, "epoch": 1.8682170542635659, "percentage": 93.39, "elapsed_time": "0:13:26", "remaining_time": "0:00:57"}
|
| 453 |
+
{"current_steps": 453, "total_steps": 484, "loss": 1.8047, "lr": 5.601759407492107e-07, "epoch": 1.8723514211886305, "percentage": 93.6, "elapsed_time": "0:13:28", "remaining_time": "0:00:55"}
|
| 454 |
+
{"current_steps": 454, "total_steps": 484, "loss": 1.7953, "lr": 5.258333346686211e-07, "epoch": 1.876485788113695, "percentage": 93.8, "elapsed_time": "0:13:29", "remaining_time": "0:00:53"}
|
| 455 |
+
{"current_steps": 455, "total_steps": 484, "loss": 1.8466, "lr": 4.925658298840979e-07, "epoch": 1.8806201550387596, "percentage": 94.01, "elapsed_time": "0:13:31", "remaining_time": "0:00:51"}
|
| 456 |
+
{"current_steps": 456, "total_steps": 484, "loss": 1.8405, "lr": 4.603748877707342e-07, "epoch": 1.8847545219638242, "percentage": 94.21, "elapsed_time": "0:13:33", "remaining_time": "0:00:49"}
|
| 457 |
+
{"current_steps": 457, "total_steps": 484, "loss": 1.875, "lr": 4.2926192241237175e-07, "epoch": 1.8888888888888888, "percentage": 94.42, "elapsed_time": "0:13:34", "remaining_time": "0:00:48"}
|
| 458 |
+
{"current_steps": 458, "total_steps": 484, "loss": 1.8635, "lr": 3.992283005394837e-07, "epoch": 1.8930232558139535, "percentage": 94.63, "elapsed_time": "0:13:36", "remaining_time": "0:00:46"}
|
| 459 |
+
{"current_steps": 459, "total_steps": 484, "loss": 1.8324, "lr": 3.7027534146913676e-07, "epoch": 1.8971576227390181, "percentage": 94.83, "elapsed_time": "0:13:38", "remaining_time": "0:00:44"}
|
| 460 |
+
{"current_steps": 460, "total_steps": 484, "loss": 1.8829, "lr": 3.424043170470376e-07, "epoch": 1.9012919896640827, "percentage": 95.04, "elapsed_time": "0:13:40", "remaining_time": "0:00:42"}
|
| 461 |
+
{"current_steps": 461, "total_steps": 484, "loss": 1.8715, "lr": 3.1561645159166597e-07, "epoch": 1.9054263565891474, "percentage": 95.25, "elapsed_time": "0:13:42", "remaining_time": "0:00:41"}
|
| 462 |
+
{"current_steps": 462, "total_steps": 484, "loss": 1.8551, "lr": 2.89912921840485e-07, "epoch": 1.909560723514212, "percentage": 95.45, "elapsed_time": "0:13:43", "remaining_time": "0:00:39"}
|
| 463 |
+
{"current_steps": 463, "total_steps": 484, "loss": 1.8608, "lr": 2.6529485689825997e-07, "epoch": 1.9136950904392764, "percentage": 95.66, "elapsed_time": "0:13:45", "remaining_time": "0:00:37"}
|
| 464 |
+
{"current_steps": 464, "total_steps": 484, "loss": 1.8855, "lr": 2.417633381874534e-07, "epoch": 1.917829457364341, "percentage": 95.87, "elapsed_time": "0:13:47", "remaining_time": "0:00:35"}
|
| 465 |
+
{"current_steps": 465, "total_steps": 484, "loss": 1.8424, "lr": 2.1931939940071366e-07, "epoch": 1.9219638242894057, "percentage": 96.07, "elapsed_time": "0:13:48", "remaining_time": "0:00:33"}
|
| 466 |
+
{"current_steps": 466, "total_steps": 484, "loss": 1.8745, "lr": 1.9796402645547995e-07, "epoch": 1.9260981912144701, "percentage": 96.28, "elapsed_time": "0:13:50", "remaining_time": "0:00:32"}
|
| 467 |
+
{"current_steps": 467, "total_steps": 484, "loss": 1.8746, "lr": 1.7769815745066475e-07, "epoch": 1.9302325581395348, "percentage": 96.49, "elapsed_time": "0:13:52", "remaining_time": "0:00:30"}
|
| 468 |
+
{"current_steps": 468, "total_steps": 484, "loss": 1.8308, "lr": 1.5852268262544768e-07, "epoch": 1.9343669250645994, "percentage": 96.69, "elapsed_time": "0:13:54", "remaining_time": "0:00:28"}
|
| 469 |
+
{"current_steps": 469, "total_steps": 484, "loss": 1.8205, "lr": 1.4043844432016506e-07, "epoch": 1.938501291989664, "percentage": 96.9, "elapsed_time": "0:13:56", "remaining_time": "0:00:26"}
|
| 470 |
+
{"current_steps": 470, "total_steps": 484, "loss": 1.8457, "lr": 1.234462369393147e-07, "epoch": 1.9426356589147287, "percentage": 97.11, "elapsed_time": "0:13:58", "remaining_time": "0:00:24"}
|
| 471 |
+
{"current_steps": 471, "total_steps": 484, "loss": 1.8358, "lr": 1.0754680691665298e-07, "epoch": 1.9467700258397933, "percentage": 97.31, "elapsed_time": "0:13:59", "remaining_time": "0:00:23"}
|
| 472 |
+
{"current_steps": 472, "total_steps": 484, "loss": 1.8508, "lr": 9.274085268241028e-08, "epoch": 1.950904392764858, "percentage": 97.52, "elapsed_time": "0:14:01", "remaining_time": "0:00:21"}
|
| 473 |
+
{"current_steps": 473, "total_steps": 484, "loss": 1.7873, "lr": 7.90290246326042e-08, "epoch": 1.9550387596899226, "percentage": 97.73, "elapsed_time": "0:14:03", "remaining_time": "0:00:19"}
|
| 474 |
+
{"current_steps": 474, "total_steps": 484, "loss": 1.8693, "lr": 6.641192510047634e-08, "epoch": 1.9591731266149872, "percentage": 97.93, "elapsed_time": "0:14:04", "remaining_time": "0:00:17"}
|
| 475 |
+
{"current_steps": 475, "total_steps": 484, "loss": 1.7866, "lr": 5.489010833002739e-08, "epoch": 1.9633074935400516, "percentage": 98.14, "elapsed_time": "0:14:06", "remaining_time": "0:00:16"}
|
| 476 |
+
{"current_steps": 476, "total_steps": 484, "loss": 1.8249, "lr": 4.4464080451675494e-08, "epoch": 1.9674418604651163, "percentage": 98.35, "elapsed_time": "0:14:08", "remaining_time": "0:00:14"}
|
| 477 |
+
{"current_steps": 477, "total_steps": 484, "loss": 1.8257, "lr": 3.51342994600129e-08, "epoch": 1.971576227390181, "percentage": 98.55, "elapsed_time": "0:14:09", "remaining_time": "0:00:12"}
|
| 478 |
+
{"current_steps": 478, "total_steps": 484, "loss": 1.7818, "lr": 2.6901175193699835e-08, "epoch": 1.9757105943152453, "percentage": 98.76, "elapsed_time": "0:14:11", "remaining_time": "0:00:10"}
|
| 479 |
+
{"current_steps": 479, "total_steps": 484, "loss": 1.8652, "lr": 1.976506931745392e-08, "epoch": 1.97984496124031, "percentage": 98.97, "elapsed_time": "0:14:13", "remaining_time": "0:00:08"}
|
| 480 |
+
{"current_steps": 480, "total_steps": 484, "loss": 1.8704, "lr": 1.3726295306162873e-08, "epoch": 1.9839793281653746, "percentage": 99.17, "elapsed_time": "0:14:14", "remaining_time": "0:00:07"}
|
| 481 |
+
{"current_steps": 481, "total_steps": 484, "loss": 1.8785, "lr": 8.785118431120509e-09, "epoch": 1.9881136950904392, "percentage": 99.38, "elapsed_time": "0:14:16", "remaining_time": "0:00:05"}
|
| 482 |
+
{"current_steps": 482, "total_steps": 484, "loss": 1.8445, "lr": 4.941755748361088e-09, "epoch": 1.9922480620155039, "percentage": 99.59, "elapsed_time": "0:14:18", "remaining_time": "0:00:03"}
|
| 483 |
+
{"current_steps": 483, "total_steps": 484, "loss": 1.8895, "lr": 2.1963760891391407e-09, "epoch": 1.9963824289405685, "percentage": 99.79, "elapsed_time": "0:14:20", "remaining_time": "0:00:01"}
|
| 484 |
+
{"current_steps": 484, "total_steps": 484, "loss": 1.813, "lr": 5.491000525020828e-10, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:14:21", "remaining_time": "0:00:00"}
|
| 485 |
+
{"current_steps": 484, "total_steps": 484, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:14:31", "remaining_time": "0:00:00"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3431 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 484,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.004134366925064599,
|
| 14 |
+
"grad_norm": 2.4449265003204346,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"loss": 2.4364,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.008268733850129198,
|
| 21 |
+
"grad_norm": 2.5834848880767822,
|
| 22 |
+
"learning_rate": 5e-06,
|
| 23 |
+
"loss": 2.3816,
|
| 24 |
+
"step": 2
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.012403100775193798,
|
| 28 |
+
"grad_norm": 2.8045172691345215,
|
| 29 |
+
"learning_rate": 1e-05,
|
| 30 |
+
"loss": 2.3568,
|
| 31 |
+
"step": 3
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.016537467700258397,
|
| 35 |
+
"grad_norm": 1.875626564025879,
|
| 36 |
+
"learning_rate": 1.5e-05,
|
| 37 |
+
"loss": 2.383,
|
| 38 |
+
"step": 4
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.020671834625323,
|
| 42 |
+
"grad_norm": 2.4247257709503174,
|
| 43 |
+
"learning_rate": 2e-05,
|
| 44 |
+
"loss": 2.3899,
|
| 45 |
+
"step": 5
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.024806201550387597,
|
| 49 |
+
"grad_norm": 3.0779945850372314,
|
| 50 |
+
"learning_rate": 2.5e-05,
|
| 51 |
+
"loss": 2.3397,
|
| 52 |
+
"step": 6
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.028940568475452195,
|
| 56 |
+
"grad_norm": 2.628978729248047,
|
| 57 |
+
"learning_rate": 3e-05,
|
| 58 |
+
"loss": 2.2792,
|
| 59 |
+
"step": 7
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.03307493540051679,
|
| 63 |
+
"grad_norm": 2.2071683406829834,
|
| 64 |
+
"learning_rate": 3.5e-05,
|
| 65 |
+
"loss": 2.3072,
|
| 66 |
+
"step": 8
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.037209302325581395,
|
| 70 |
+
"grad_norm": 1.4800362586975098,
|
| 71 |
+
"learning_rate": 4e-05,
|
| 72 |
+
"loss": 2.2655,
|
| 73 |
+
"step": 9
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.041343669250646,
|
| 77 |
+
"grad_norm": 1.8521326780319214,
|
| 78 |
+
"learning_rate": 4.5e-05,
|
| 79 |
+
"loss": 2.312,
|
| 80 |
+
"step": 10
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.04547803617571059,
|
| 84 |
+
"grad_norm": 1.5628751516342163,
|
| 85 |
+
"learning_rate": 5e-05,
|
| 86 |
+
"loss": 2.2325,
|
| 87 |
+
"step": 11
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.04961240310077519,
|
| 91 |
+
"grad_norm": 1.5056865215301514,
|
| 92 |
+
"learning_rate": 4.99994508999475e-05,
|
| 93 |
+
"loss": 2.253,
|
| 94 |
+
"step": 12
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.053746770025839795,
|
| 98 |
+
"grad_norm": 1.4171890020370483,
|
| 99 |
+
"learning_rate": 4.999780362391087e-05,
|
| 100 |
+
"loss": 2.1965,
|
| 101 |
+
"step": 13
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.05788113695090439,
|
| 105 |
+
"grad_norm": 1.1090164184570312,
|
| 106 |
+
"learning_rate": 4.9995058244251644e-05,
|
| 107 |
+
"loss": 2.2547,
|
| 108 |
+
"step": 14
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.06201550387596899,
|
| 112 |
+
"grad_norm": 1.2201741933822632,
|
| 113 |
+
"learning_rate": 4.999121488156888e-05,
|
| 114 |
+
"loss": 2.1849,
|
| 115 |
+
"step": 15
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.06614987080103359,
|
| 119 |
+
"grad_norm": 1.028005838394165,
|
| 120 |
+
"learning_rate": 4.9986273704693843e-05,
|
| 121 |
+
"loss": 2.1757,
|
| 122 |
+
"step": 16
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.0702842377260982,
|
| 126 |
+
"grad_norm": 0.9961190819740295,
|
| 127 |
+
"learning_rate": 4.9980234930682546e-05,
|
| 128 |
+
"loss": 2.1872,
|
| 129 |
+
"step": 17
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.07441860465116279,
|
| 133 |
+
"grad_norm": 0.9829438924789429,
|
| 134 |
+
"learning_rate": 4.99730988248063e-05,
|
| 135 |
+
"loss": 2.142,
|
| 136 |
+
"step": 18
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.07855297157622738,
|
| 140 |
+
"grad_norm": 0.904361367225647,
|
| 141 |
+
"learning_rate": 4.9964865700539986e-05,
|
| 142 |
+
"loss": 2.1978,
|
| 143 |
+
"step": 19
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.082687338501292,
|
| 147 |
+
"grad_norm": 0.8257375955581665,
|
| 148 |
+
"learning_rate": 4.995553591954832e-05,
|
| 149 |
+
"loss": 2.1625,
|
| 150 |
+
"step": 20
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.08682170542635659,
|
| 154 |
+
"grad_norm": 0.8695998787879944,
|
| 155 |
+
"learning_rate": 4.994510989166997e-05,
|
| 156 |
+
"loss": 2.1432,
|
| 157 |
+
"step": 21
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.09095607235142118,
|
| 161 |
+
"grad_norm": 0.8254109621047974,
|
| 162 |
+
"learning_rate": 4.993358807489953e-05,
|
| 163 |
+
"loss": 2.1673,
|
| 164 |
+
"step": 22
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.09509043927648579,
|
| 168 |
+
"grad_norm": 0.9864363074302673,
|
| 169 |
+
"learning_rate": 4.99209709753674e-05,
|
| 170 |
+
"loss": 2.1788,
|
| 171 |
+
"step": 23
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.09922480620155039,
|
| 175 |
+
"grad_norm": 0.8983305096626282,
|
| 176 |
+
"learning_rate": 4.990725914731759e-05,
|
| 177 |
+
"loss": 2.1548,
|
| 178 |
+
"step": 24
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.10335917312661498,
|
| 182 |
+
"grad_norm": 0.8856174349784851,
|
| 183 |
+
"learning_rate": 4.989245319308335e-05,
|
| 184 |
+
"loss": 2.1585,
|
| 185 |
+
"step": 25
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.10749354005167959,
|
| 189 |
+
"grad_norm": 0.9101842641830444,
|
| 190 |
+
"learning_rate": 4.9876553763060684e-05,
|
| 191 |
+
"loss": 2.1397,
|
| 192 |
+
"step": 26
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.11162790697674418,
|
| 196 |
+
"grad_norm": 0.8508126735687256,
|
| 197 |
+
"learning_rate": 4.985956155567984e-05,
|
| 198 |
+
"loss": 2.1242,
|
| 199 |
+
"step": 27
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.11576227390180878,
|
| 203 |
+
"grad_norm": 0.8094877600669861,
|
| 204 |
+
"learning_rate": 4.984147731737455e-05,
|
| 205 |
+
"loss": 2.1153,
|
| 206 |
+
"step": 28
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.11989664082687339,
|
| 210 |
+
"grad_norm": 0.8883515000343323,
|
| 211 |
+
"learning_rate": 4.982230184254933e-05,
|
| 212 |
+
"loss": 2.0822,
|
| 213 |
+
"step": 29
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.12403100775193798,
|
| 217 |
+
"grad_norm": 0.8447825908660889,
|
| 218 |
+
"learning_rate": 4.9802035973544525e-05,
|
| 219 |
+
"loss": 2.1242,
|
| 220 |
+
"step": 30
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.1281653746770026,
|
| 224 |
+
"grad_norm": 0.7655540704727173,
|
| 225 |
+
"learning_rate": 4.978068060059929e-05,
|
| 226 |
+
"loss": 2.129,
|
| 227 |
+
"step": 31
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.13229974160206717,
|
| 231 |
+
"grad_norm": 0.868387758731842,
|
| 232 |
+
"learning_rate": 4.975823666181255e-05,
|
| 233 |
+
"loss": 2.0808,
|
| 234 |
+
"step": 32
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.13643410852713178,
|
| 238 |
+
"grad_norm": 0.814836859703064,
|
| 239 |
+
"learning_rate": 4.973470514310175e-05,
|
| 240 |
+
"loss": 2.1064,
|
| 241 |
+
"step": 33
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.1405684754521964,
|
| 245 |
+
"grad_norm": 0.8349934816360474,
|
| 246 |
+
"learning_rate": 4.971008707815952e-05,
|
| 247 |
+
"loss": 2.089,
|
| 248 |
+
"step": 34
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.14470284237726097,
|
| 252 |
+
"grad_norm": 0.8028632998466492,
|
| 253 |
+
"learning_rate": 4.968438354840834e-05,
|
| 254 |
+
"loss": 2.0706,
|
| 255 |
+
"step": 35
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.14883720930232558,
|
| 259 |
+
"grad_norm": 0.833337664604187,
|
| 260 |
+
"learning_rate": 4.9657595682952965e-05,
|
| 261 |
+
"loss": 2.1003,
|
| 262 |
+
"step": 36
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.1529715762273902,
|
| 266 |
+
"grad_norm": 0.7648825645446777,
|
| 267 |
+
"learning_rate": 4.962972465853086e-05,
|
| 268 |
+
"loss": 2.0789,
|
| 269 |
+
"step": 37
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.15710594315245477,
|
| 273 |
+
"grad_norm": 0.7566452622413635,
|
| 274 |
+
"learning_rate": 4.960077169946052e-05,
|
| 275 |
+
"loss": 2.1034,
|
| 276 |
+
"step": 38
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.16124031007751938,
|
| 280 |
+
"grad_norm": 1.0385154485702515,
|
| 281 |
+
"learning_rate": 4.957073807758763e-05,
|
| 282 |
+
"loss": 2.0912,
|
| 283 |
+
"step": 39
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.165374677002584,
|
| 287 |
+
"grad_norm": 0.7650123238563538,
|
| 288 |
+
"learning_rate": 4.953962511222927e-05,
|
| 289 |
+
"loss": 2.1084,
|
| 290 |
+
"step": 40
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.16950904392764857,
|
| 294 |
+
"grad_norm": 0.8287901878356934,
|
| 295 |
+
"learning_rate": 4.950743417011591e-05,
|
| 296 |
+
"loss": 2.0232,
|
| 297 |
+
"step": 41
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.17364341085271318,
|
| 301 |
+
"grad_norm": 0.8501759171485901,
|
| 302 |
+
"learning_rate": 4.9474166665331385e-05,
|
| 303 |
+
"loss": 2.1171,
|
| 304 |
+
"step": 42
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.17777777777777778,
|
| 308 |
+
"grad_norm": 0.8050918579101562,
|
| 309 |
+
"learning_rate": 4.9439824059250794e-05,
|
| 310 |
+
"loss": 2.0441,
|
| 311 |
+
"step": 43
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.18191214470284237,
|
| 315 |
+
"grad_norm": 0.9413315653800964,
|
| 316 |
+
"learning_rate": 4.940440786047628e-05,
|
| 317 |
+
"loss": 2.0278,
|
| 318 |
+
"step": 44
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.18604651162790697,
|
| 322 |
+
"grad_norm": 0.8258485198020935,
|
| 323 |
+
"learning_rate": 4.936791962477076e-05,
|
| 324 |
+
"loss": 2.0489,
|
| 325 |
+
"step": 45
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.19018087855297158,
|
| 329 |
+
"grad_norm": 0.7860682606697083,
|
| 330 |
+
"learning_rate": 4.9330360954989616e-05,
|
| 331 |
+
"loss": 2.04,
|
| 332 |
+
"step": 46
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.19431524547803616,
|
| 336 |
+
"grad_norm": 1.176941990852356,
|
| 337 |
+
"learning_rate": 4.929173350101025e-05,
|
| 338 |
+
"loss": 2.0356,
|
| 339 |
+
"step": 47
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.19844961240310077,
|
| 343 |
+
"grad_norm": 0.8738293051719666,
|
| 344 |
+
"learning_rate": 4.925203895965963e-05,
|
| 345 |
+
"loss": 1.995,
|
| 346 |
+
"step": 48
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.20258397932816538,
|
| 350 |
+
"grad_norm": 0.835989236831665,
|
| 351 |
+
"learning_rate": 4.921127907463972e-05,
|
| 352 |
+
"loss": 2.0618,
|
| 353 |
+
"step": 49
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.20671834625322996,
|
| 357 |
+
"grad_norm": 0.8307858109474182,
|
| 358 |
+
"learning_rate": 4.9169455636450935e-05,
|
| 359 |
+
"loss": 2.0819,
|
| 360 |
+
"step": 50
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.21085271317829457,
|
| 364 |
+
"grad_norm": 0.778562068939209,
|
| 365 |
+
"learning_rate": 4.9126570482313424e-05,
|
| 366 |
+
"loss": 1.9812,
|
| 367 |
+
"step": 51
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.21498708010335918,
|
| 371 |
+
"grad_norm": 1.0076038837432861,
|
| 372 |
+
"learning_rate": 4.908262549608644e-05,
|
| 373 |
+
"loss": 2.0449,
|
| 374 |
+
"step": 52
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.21912144702842376,
|
| 378 |
+
"grad_norm": 0.8014701008796692,
|
| 379 |
+
"learning_rate": 4.903762260818551e-05,
|
| 380 |
+
"loss": 2.0348,
|
| 381 |
+
"step": 53
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.22325581395348837,
|
| 385 |
+
"grad_norm": 0.799463152885437,
|
| 386 |
+
"learning_rate": 4.899156379549769e-05,
|
| 387 |
+
"loss": 2.0152,
|
| 388 |
+
"step": 54
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.22739018087855298,
|
| 392 |
+
"grad_norm": 0.816827654838562,
|
| 393 |
+
"learning_rate": 4.8944451081294697e-05,
|
| 394 |
+
"loss": 2.0087,
|
| 395 |
+
"step": 55
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.23152454780361756,
|
| 399 |
+
"grad_norm": 0.8588879108428955,
|
| 400 |
+
"learning_rate": 4.889628653514402e-05,
|
| 401 |
+
"loss": 2.025,
|
| 402 |
+
"step": 56
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.23565891472868217,
|
| 406 |
+
"grad_norm": 0.8005595803260803,
|
| 407 |
+
"learning_rate": 4.8847072272818076e-05,
|
| 408 |
+
"loss": 2.0748,
|
| 409 |
+
"step": 57
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.23979328165374678,
|
| 413 |
+
"grad_norm": 0.8273265957832336,
|
| 414 |
+
"learning_rate": 4.879681045620115e-05,
|
| 415 |
+
"loss": 2.0116,
|
| 416 |
+
"step": 58
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.24392764857881136,
|
| 420 |
+
"grad_norm": 0.7770358324050903,
|
| 421 |
+
"learning_rate": 4.874550329319457e-05,
|
| 422 |
+
"loss": 2.034,
|
| 423 |
+
"step": 59
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.24806201550387597,
|
| 427 |
+
"grad_norm": 0.8438355922698975,
|
| 428 |
+
"learning_rate": 4.869315303761959e-05,
|
| 429 |
+
"loss": 2.061,
|
| 430 |
+
"step": 60
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.25219638242894055,
|
| 434 |
+
"grad_norm": 0.9614850282669067,
|
| 435 |
+
"learning_rate": 4.863976198911845e-05,
|
| 436 |
+
"loss": 1.9944,
|
| 437 |
+
"step": 61
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.2563307493540052,
|
| 441 |
+
"grad_norm": 0.8549639582633972,
|
| 442 |
+
"learning_rate": 4.8585332493053364e-05,
|
| 443 |
+
"loss": 1.9977,
|
| 444 |
+
"step": 62
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.26046511627906976,
|
| 448 |
+
"grad_norm": 0.7411041259765625,
|
| 449 |
+
"learning_rate": 4.852986694040347e-05,
|
| 450 |
+
"loss": 2.0503,
|
| 451 |
+
"step": 63
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.26459948320413434,
|
| 455 |
+
"grad_norm": 1.0129224061965942,
|
| 456 |
+
"learning_rate": 4.847336776765978e-05,
|
| 457 |
+
"loss": 1.948,
|
| 458 |
+
"step": 64
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.268733850129199,
|
| 462 |
+
"grad_norm": 0.8144932985305786,
|
| 463 |
+
"learning_rate": 4.84158374567182e-05,
|
| 464 |
+
"loss": 1.9868,
|
| 465 |
+
"step": 65
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.27286821705426356,
|
| 469 |
+
"grad_norm": 0.725849449634552,
|
| 470 |
+
"learning_rate": 4.8357278534770475e-05,
|
| 471 |
+
"loss": 2.0067,
|
| 472 |
+
"step": 66
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.27700258397932814,
|
| 476 |
+
"grad_norm": 0.7719712853431702,
|
| 477 |
+
"learning_rate": 4.829769357419317e-05,
|
| 478 |
+
"loss": 2.0112,
|
| 479 |
+
"step": 67
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.2811369509043928,
|
| 483 |
+
"grad_norm": 0.8452929854393005,
|
| 484 |
+
"learning_rate": 4.8237085192434676e-05,
|
| 485 |
+
"loss": 2.0049,
|
| 486 |
+
"step": 68
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.28527131782945736,
|
| 490 |
+
"grad_norm": 0.757272481918335,
|
| 491 |
+
"learning_rate": 4.8175456051900256e-05,
|
| 492 |
+
"loss": 2.046,
|
| 493 |
+
"step": 69
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.28940568475452194,
|
| 497 |
+
"grad_norm": 0.76349276304245,
|
| 498 |
+
"learning_rate": 4.8112808859835044e-05,
|
| 499 |
+
"loss": 2.0587,
|
| 500 |
+
"step": 70
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.2935400516795866,
|
| 504 |
+
"grad_norm": 0.7980454564094543,
|
| 505 |
+
"learning_rate": 4.804914636820517e-05,
|
| 506 |
+
"loss": 2.0167,
|
| 507 |
+
"step": 71
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.29767441860465116,
|
| 511 |
+
"grad_norm": 0.7534277439117432,
|
| 512 |
+
"learning_rate": 4.798447137357681e-05,
|
| 513 |
+
"loss": 2.0274,
|
| 514 |
+
"step": 72
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.30180878552971574,
|
| 518 |
+
"grad_norm": 0.7189844250679016,
|
| 519 |
+
"learning_rate": 4.791878671699342e-05,
|
| 520 |
+
"loss": 2.0141,
|
| 521 |
+
"step": 73
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.3059431524547804,
|
| 525 |
+
"grad_norm": 0.7738127708435059,
|
| 526 |
+
"learning_rate": 4.7852095283850866e-05,
|
| 527 |
+
"loss": 2.0168,
|
| 528 |
+
"step": 74
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.31007751937984496,
|
| 532 |
+
"grad_norm": 0.8310754299163818,
|
| 533 |
+
"learning_rate": 4.77844000037707e-05,
|
| 534 |
+
"loss": 2.0016,
|
| 535 |
+
"step": 75
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.31421188630490954,
|
| 539 |
+
"grad_norm": 0.7218735218048096,
|
| 540 |
+
"learning_rate": 4.771570385047147e-05,
|
| 541 |
+
"loss": 1.9748,
|
| 542 |
+
"step": 76
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.3183462532299742,
|
| 546 |
+
"grad_norm": 0.7458547353744507,
|
| 547 |
+
"learning_rate": 4.764600984163808e-05,
|
| 548 |
+
"loss": 2.0023,
|
| 549 |
+
"step": 77
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.32248062015503876,
|
| 553 |
+
"grad_norm": 0.78424471616745,
|
| 554 |
+
"learning_rate": 4.757532103878925e-05,
|
| 555 |
+
"loss": 2.021,
|
| 556 |
+
"step": 78
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.32661498708010334,
|
| 560 |
+
"grad_norm": 0.8354324698448181,
|
| 561 |
+
"learning_rate": 4.750364054714302e-05,
|
| 562 |
+
"loss": 1.9658,
|
| 563 |
+
"step": 79
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.330749354005168,
|
| 567 |
+
"grad_norm": 0.7179548740386963,
|
| 568 |
+
"learning_rate": 4.743097151548031e-05,
|
| 569 |
+
"loss": 2.0258,
|
| 570 |
+
"step": 80
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.33488372093023255,
|
| 574 |
+
"grad_norm": 0.7219117283821106,
|
| 575 |
+
"learning_rate": 4.735731713600665e-05,
|
| 576 |
+
"loss": 2.0056,
|
| 577 |
+
"step": 81
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.33901808785529713,
|
| 581 |
+
"grad_norm": 0.7525460124015808,
|
| 582 |
+
"learning_rate": 4.7282680644211944e-05,
|
| 583 |
+
"loss": 1.9784,
|
| 584 |
+
"step": 82
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.34315245478036177,
|
| 588 |
+
"grad_norm": 0.731530487537384,
|
| 589 |
+
"learning_rate": 4.72070653187283e-05,
|
| 590 |
+
"loss": 1.9203,
|
| 591 |
+
"step": 83
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.34728682170542635,
|
| 595 |
+
"grad_norm": 0.8921816349029541,
|
| 596 |
+
"learning_rate": 4.713047448118606e-05,
|
| 597 |
+
"loss": 1.9825,
|
| 598 |
+
"step": 84
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.35142118863049093,
|
| 602 |
+
"grad_norm": 0.7859289050102234,
|
| 603 |
+
"learning_rate": 4.705291149606786e-05,
|
| 604 |
+
"loss": 2.0026,
|
| 605 |
+
"step": 85
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.35555555555555557,
|
| 609 |
+
"grad_norm": 0.7696364521980286,
|
| 610 |
+
"learning_rate": 4.6974379770560846e-05,
|
| 611 |
+
"loss": 1.958,
|
| 612 |
+
"step": 86
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.35968992248062015,
|
| 616 |
+
"grad_norm": 0.7473434805870056,
|
| 617 |
+
"learning_rate": 4.689488275440697e-05,
|
| 618 |
+
"loss": 2.0069,
|
| 619 |
+
"step": 87
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.36382428940568473,
|
| 623 |
+
"grad_norm": 0.7674610614776611,
|
| 624 |
+
"learning_rate": 4.68144239397515e-05,
|
| 625 |
+
"loss": 2.0372,
|
| 626 |
+
"step": 88
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.36795865633074937,
|
| 630 |
+
"grad_norm": 0.72877037525177,
|
| 631 |
+
"learning_rate": 4.673300686098957e-05,
|
| 632 |
+
"loss": 1.9789,
|
| 633 |
+
"step": 89
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.37209302325581395,
|
| 637 |
+
"grad_norm": 0.8508046865463257,
|
| 638 |
+
"learning_rate": 4.665063509461097e-05,
|
| 639 |
+
"loss": 2.0055,
|
| 640 |
+
"step": 90
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.37622739018087853,
|
| 644 |
+
"grad_norm": 0.694132387638092,
|
| 645 |
+
"learning_rate": 4.6567312259043e-05,
|
| 646 |
+
"loss": 2.017,
|
| 647 |
+
"step": 91
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.38036175710594317,
|
| 651 |
+
"grad_norm": 0.8397891521453857,
|
| 652 |
+
"learning_rate": 4.648304201449153e-05,
|
| 653 |
+
"loss": 1.9536,
|
| 654 |
+
"step": 92
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.38449612403100775,
|
| 658 |
+
"grad_norm": 0.7123363018035889,
|
| 659 |
+
"learning_rate": 4.639782806278021e-05,
|
| 660 |
+
"loss": 1.9638,
|
| 661 |
+
"step": 93
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.3886304909560723,
|
| 665 |
+
"grad_norm": 0.7163733839988708,
|
| 666 |
+
"learning_rate": 4.631167414718788e-05,
|
| 667 |
+
"loss": 2.0001,
|
| 668 |
+
"step": 94
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.39276485788113696,
|
| 672 |
+
"grad_norm": 0.7076818346977234,
|
| 673 |
+
"learning_rate": 4.6224584052284106e-05,
|
| 674 |
+
"loss": 1.9628,
|
| 675 |
+
"step": 95
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.39689922480620154,
|
| 679 |
+
"grad_norm": 0.7508699893951416,
|
| 680 |
+
"learning_rate": 4.6136561603762925e-05,
|
| 681 |
+
"loss": 2.0396,
|
| 682 |
+
"step": 96
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.4010335917312661,
|
| 686 |
+
"grad_norm": 0.7641069293022156,
|
| 687 |
+
"learning_rate": 4.6047610668274846e-05,
|
| 688 |
+
"loss": 1.9954,
|
| 689 |
+
"step": 97
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.40516795865633076,
|
| 693 |
+
"grad_norm": 0.8162916302680969,
|
| 694 |
+
"learning_rate": 4.5957735153256915e-05,
|
| 695 |
+
"loss": 1.9253,
|
| 696 |
+
"step": 98
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.40930232558139534,
|
| 700 |
+
"grad_norm": 0.8505280613899231,
|
| 701 |
+
"learning_rate": 4.586693900676116e-05,
|
| 702 |
+
"loss": 1.9543,
|
| 703 |
+
"step": 99
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.4134366925064599,
|
| 707 |
+
"grad_norm": 0.7581599354743958,
|
| 708 |
+
"learning_rate": 4.577522621728106e-05,
|
| 709 |
+
"loss": 1.9897,
|
| 710 |
+
"step": 100
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.41757105943152456,
|
| 714 |
+
"grad_norm": 0.7437825202941895,
|
| 715 |
+
"learning_rate": 4.5682600813576435e-05,
|
| 716 |
+
"loss": 1.9997,
|
| 717 |
+
"step": 101
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.42170542635658914,
|
| 721 |
+
"grad_norm": 0.8151077628135681,
|
| 722 |
+
"learning_rate": 4.55890668644964e-05,
|
| 723 |
+
"loss": 1.9706,
|
| 724 |
+
"step": 102
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.4258397932816537,
|
| 728 |
+
"grad_norm": 0.7886041402816772,
|
| 729 |
+
"learning_rate": 4.549462847880066e-05,
|
| 730 |
+
"loss": 1.9759,
|
| 731 |
+
"step": 103
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.42997416020671836,
|
| 735 |
+
"grad_norm": 1.0506982803344727,
|
| 736 |
+
"learning_rate": 4.539928980497903e-05,
|
| 737 |
+
"loss": 1.9579,
|
| 738 |
+
"step": 104
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.43410852713178294,
|
| 742 |
+
"grad_norm": 0.7806780934333801,
|
| 743 |
+
"learning_rate": 4.530305503106916e-05,
|
| 744 |
+
"loss": 1.9803,
|
| 745 |
+
"step": 105
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.4382428940568475,
|
| 749 |
+
"grad_norm": 0.7416555285453796,
|
| 750 |
+
"learning_rate": 4.5205928384472616e-05,
|
| 751 |
+
"loss": 1.9267,
|
| 752 |
+
"step": 106
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.44237726098191216,
|
| 756 |
+
"grad_norm": 0.7598101496696472,
|
| 757 |
+
"learning_rate": 4.510791413176912e-05,
|
| 758 |
+
"loss": 1.9855,
|
| 759 |
+
"step": 107
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.44651162790697674,
|
| 763 |
+
"grad_norm": 0.795430600643158,
|
| 764 |
+
"learning_rate": 4.5009016578529194e-05,
|
| 765 |
+
"loss": 2.0313,
|
| 766 |
+
"step": 108
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.4506459948320413,
|
| 770 |
+
"grad_norm": 0.8061582446098328,
|
| 771 |
+
"learning_rate": 4.4909240069124966e-05,
|
| 772 |
+
"loss": 1.9745,
|
| 773 |
+
"step": 109
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.45478036175710596,
|
| 777 |
+
"grad_norm": 0.7706458568572998,
|
| 778 |
+
"learning_rate": 4.480858898653936e-05,
|
| 779 |
+
"loss": 1.9208,
|
| 780 |
+
"step": 110
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.45891472868217054,
|
| 784 |
+
"grad_norm": 0.7505202293395996,
|
| 785 |
+
"learning_rate": 4.470706775217355e-05,
|
| 786 |
+
"loss": 1.9365,
|
| 787 |
+
"step": 111
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.4630490956072351,
|
| 791 |
+
"grad_norm": 0.7764873504638672,
|
| 792 |
+
"learning_rate": 4.4604680825652753e-05,
|
| 793 |
+
"loss": 1.9509,
|
| 794 |
+
"step": 112
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.46718346253229975,
|
| 798 |
+
"grad_norm": 0.7258660793304443,
|
| 799 |
+
"learning_rate": 4.4501432704630305e-05,
|
| 800 |
+
"loss": 1.9406,
|
| 801 |
+
"step": 113
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.47131782945736433,
|
| 805 |
+
"grad_norm": 0.70240718126297,
|
| 806 |
+
"learning_rate": 4.43973279245901e-05,
|
| 807 |
+
"loss": 1.9809,
|
| 808 |
+
"step": 114
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.4754521963824289,
|
| 812 |
+
"grad_norm": 0.8790384531021118,
|
| 813 |
+
"learning_rate": 4.4292371058647345e-05,
|
| 814 |
+
"loss": 1.9638,
|
| 815 |
+
"step": 115
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.47958656330749355,
|
| 819 |
+
"grad_norm": 0.8162893652915955,
|
| 820 |
+
"learning_rate": 4.41865667173477e-05,
|
| 821 |
+
"loss": 1.9621,
|
| 822 |
+
"step": 116
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.48372093023255813,
|
| 826 |
+
"grad_norm": 0.7459295988082886,
|
| 827 |
+
"learning_rate": 4.407991954846471e-05,
|
| 828 |
+
"loss": 1.9688,
|
| 829 |
+
"step": 117
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.4878552971576227,
|
| 833 |
+
"grad_norm": 0.7379862070083618,
|
| 834 |
+
"learning_rate": 4.3972434236795656e-05,
|
| 835 |
+
"loss": 1.9179,
|
| 836 |
+
"step": 118
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.49198966408268735,
|
| 840 |
+
"grad_norm": 0.7245668768882751,
|
| 841 |
+
"learning_rate": 4.386411550395576e-05,
|
| 842 |
+
"loss": 1.9979,
|
| 843 |
+
"step": 119
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.49612403100775193,
|
| 847 |
+
"grad_norm": 0.7252455353736877,
|
| 848 |
+
"learning_rate": 4.3754968108170766e-05,
|
| 849 |
+
"loss": 1.9072,
|
| 850 |
+
"step": 120
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.5002583979328166,
|
| 854 |
+
"grad_norm": 0.6954511404037476,
|
| 855 |
+
"learning_rate": 4.3644996844067955e-05,
|
| 856 |
+
"loss": 1.9378,
|
| 857 |
+
"step": 121
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.5043927648578811,
|
| 861 |
+
"grad_norm": 0.6904546618461609,
|
| 862 |
+
"learning_rate": 4.353420654246546e-05,
|
| 863 |
+
"loss": 1.9835,
|
| 864 |
+
"step": 122
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.5085271317829457,
|
| 868 |
+
"grad_norm": 0.6972026228904724,
|
| 869 |
+
"learning_rate": 4.342260207016012e-05,
|
| 870 |
+
"loss": 1.9278,
|
| 871 |
+
"step": 123
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.5126614987080104,
|
| 875 |
+
"grad_norm": 0.7186058759689331,
|
| 876 |
+
"learning_rate": 4.3310188329713665e-05,
|
| 877 |
+
"loss": 2.0604,
|
| 878 |
+
"step": 124
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.5167958656330749,
|
| 882 |
+
"grad_norm": 0.7146493792533875,
|
| 883 |
+
"learning_rate": 4.319697025923736e-05,
|
| 884 |
+
"loss": 2.0045,
|
| 885 |
+
"step": 125
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.5209302325581395,
|
| 889 |
+
"grad_norm": 0.7462325096130371,
|
| 890 |
+
"learning_rate": 4.308295283217507e-05,
|
| 891 |
+
"loss": 1.9651,
|
| 892 |
+
"step": 126
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.5250645994832042,
|
| 896 |
+
"grad_norm": 0.6708013415336609,
|
| 897 |
+
"learning_rate": 4.296814105708482e-05,
|
| 898 |
+
"loss": 1.9391,
|
| 899 |
+
"step": 127
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.5291989664082687,
|
| 903 |
+
"grad_norm": 0.7074844241142273,
|
| 904 |
+
"learning_rate": 4.285253997741875e-05,
|
| 905 |
+
"loss": 1.9325,
|
| 906 |
+
"step": 128
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.5333333333333333,
|
| 910 |
+
"grad_norm": 0.7078781127929688,
|
| 911 |
+
"learning_rate": 4.2736154671301556e-05,
|
| 912 |
+
"loss": 2.0234,
|
| 913 |
+
"step": 129
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.537467700258398,
|
| 917 |
+
"grad_norm": 0.7044352293014526,
|
| 918 |
+
"learning_rate": 4.261899025130748e-05,
|
| 919 |
+
"loss": 1.9127,
|
| 920 |
+
"step": 130
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.5416020671834625,
|
| 924 |
+
"grad_norm": 0.7831200361251831,
|
| 925 |
+
"learning_rate": 4.2501051864235636e-05,
|
| 926 |
+
"loss": 1.9703,
|
| 927 |
+
"step": 131
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.5457364341085271,
|
| 931 |
+
"grad_norm": 0.7024598121643066,
|
| 932 |
+
"learning_rate": 4.238234469088399e-05,
|
| 933 |
+
"loss": 1.999,
|
| 934 |
+
"step": 132
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.5498708010335918,
|
| 938 |
+
"grad_norm": 0.6917828321456909,
|
| 939 |
+
"learning_rate": 4.2262873945821754e-05,
|
| 940 |
+
"loss": 1.9527,
|
| 941 |
+
"step": 133
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.5540051679586563,
|
| 945 |
+
"grad_norm": 0.7841182947158813,
|
| 946 |
+
"learning_rate": 4.214264487716033e-05,
|
| 947 |
+
"loss": 1.985,
|
| 948 |
+
"step": 134
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.5581395348837209,
|
| 952 |
+
"grad_norm": 0.805595874786377,
|
| 953 |
+
"learning_rate": 4.2021662766322736e-05,
|
| 954 |
+
"loss": 1.9307,
|
| 955 |
+
"step": 135
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.5622739018087856,
|
| 959 |
+
"grad_norm": 0.8467949032783508,
|
| 960 |
+
"learning_rate": 4.189993292781165e-05,
|
| 961 |
+
"loss": 1.9159,
|
| 962 |
+
"step": 136
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.5664082687338501,
|
| 966 |
+
"grad_norm": 0.7130942940711975,
|
| 967 |
+
"learning_rate": 4.177746070897592e-05,
|
| 968 |
+
"loss": 1.9684,
|
| 969 |
+
"step": 137
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.5705426356589147,
|
| 973 |
+
"grad_norm": 0.7865200638771057,
|
| 974 |
+
"learning_rate": 4.165425148977571e-05,
|
| 975 |
+
"loss": 1.939,
|
| 976 |
+
"step": 138
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.5746770025839794,
|
| 980 |
+
"grad_norm": 0.748938262462616,
|
| 981 |
+
"learning_rate": 4.15303106825461e-05,
|
| 982 |
+
"loss": 1.9246,
|
| 983 |
+
"step": 139
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.5788113695090439,
|
| 987 |
+
"grad_norm": 0.9481565356254578,
|
| 988 |
+
"learning_rate": 4.140564373175939e-05,
|
| 989 |
+
"loss": 1.9766,
|
| 990 |
+
"step": 140
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.5829457364341085,
|
| 994 |
+
"grad_norm": 0.7311868667602539,
|
| 995 |
+
"learning_rate": 4.128025611378594e-05,
|
| 996 |
+
"loss": 1.9565,
|
| 997 |
+
"step": 141
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.5870801033591732,
|
| 1001 |
+
"grad_norm": 0.7198468446731567,
|
| 1002 |
+
"learning_rate": 4.1154153336653534e-05,
|
| 1003 |
+
"loss": 1.9158,
|
| 1004 |
+
"step": 142
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.5912144702842377,
|
| 1008 |
+
"grad_norm": 0.7481444478034973,
|
| 1009 |
+
"learning_rate": 4.10273409398055e-05,
|
| 1010 |
+
"loss": 1.9419,
|
| 1011 |
+
"step": 143
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.5953488372093023,
|
| 1015 |
+
"grad_norm": 0.7872593402862549,
|
| 1016 |
+
"learning_rate": 4.089982449385736e-05,
|
| 1017 |
+
"loss": 1.9824,
|
| 1018 |
+
"step": 144
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.599483204134367,
|
| 1022 |
+
"grad_norm": 0.7807745933532715,
|
| 1023 |
+
"learning_rate": 4.077160960035207e-05,
|
| 1024 |
+
"loss": 1.9677,
|
| 1025 |
+
"step": 145
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.6036175710594315,
|
| 1029 |
+
"grad_norm": 0.732774019241333,
|
| 1030 |
+
"learning_rate": 4.0642701891514e-05,
|
| 1031 |
+
"loss": 1.9844,
|
| 1032 |
+
"step": 146
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.6077519379844961,
|
| 1036 |
+
"grad_norm": 0.7809471487998962,
|
| 1037 |
+
"learning_rate": 4.0513107030001544e-05,
|
| 1038 |
+
"loss": 1.9424,
|
| 1039 |
+
"step": 147
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.6118863049095608,
|
| 1043 |
+
"grad_norm": 0.7766205668449402,
|
| 1044 |
+
"learning_rate": 4.0382830708658316e-05,
|
| 1045 |
+
"loss": 1.9885,
|
| 1046 |
+
"step": 148
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.6160206718346253,
|
| 1050 |
+
"grad_norm": 0.7303252220153809,
|
| 1051 |
+
"learning_rate": 4.025187865026311e-05,
|
| 1052 |
+
"loss": 1.9332,
|
| 1053 |
+
"step": 149
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.6201550387596899,
|
| 1057 |
+
"grad_norm": 0.7558519840240479,
|
| 1058 |
+
"learning_rate": 4.012025660727849e-05,
|
| 1059 |
+
"loss": 1.9403,
|
| 1060 |
+
"step": 150
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.6242894056847546,
|
| 1064 |
+
"grad_norm": 0.7559822797775269,
|
| 1065 |
+
"learning_rate": 3.998797036159812e-05,
|
| 1066 |
+
"loss": 2.0081,
|
| 1067 |
+
"step": 151
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.6284237726098191,
|
| 1071 |
+
"grad_norm": 0.6652326583862305,
|
| 1072 |
+
"learning_rate": 3.985502572429276e-05,
|
| 1073 |
+
"loss": 1.9237,
|
| 1074 |
+
"step": 152
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.6325581395348837,
|
| 1078 |
+
"grad_norm": 0.7019279599189758,
|
| 1079 |
+
"learning_rate": 3.972142853535499e-05,
|
| 1080 |
+
"loss": 2.0038,
|
| 1081 |
+
"step": 153
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.6366925064599483,
|
| 1085 |
+
"grad_norm": 0.7089804410934448,
|
| 1086 |
+
"learning_rate": 3.958718466344269e-05,
|
| 1087 |
+
"loss": 1.9428,
|
| 1088 |
+
"step": 154
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.6408268733850129,
|
| 1092 |
+
"grad_norm": 0.6618722677230835,
|
| 1093 |
+
"learning_rate": 3.945230000562121e-05,
|
| 1094 |
+
"loss": 1.9459,
|
| 1095 |
+
"step": 155
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.6449612403100775,
|
| 1099 |
+
"grad_norm": 0.6605201959609985,
|
| 1100 |
+
"learning_rate": 3.931678048710439e-05,
|
| 1101 |
+
"loss": 1.9787,
|
| 1102 |
+
"step": 156
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.6490956072351421,
|
| 1106 |
+
"grad_norm": 0.7129101157188416,
|
| 1107 |
+
"learning_rate": 3.91806320609942e-05,
|
| 1108 |
+
"loss": 1.9787,
|
| 1109 |
+
"step": 157
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.6532299741602067,
|
| 1113 |
+
"grad_norm": 0.6954473257064819,
|
| 1114 |
+
"learning_rate": 3.9043860708019273e-05,
|
| 1115 |
+
"loss": 1.9134,
|
| 1116 |
+
"step": 158
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.6573643410852713,
|
| 1120 |
+
"grad_norm": 0.7614483833312988,
|
| 1121 |
+
"learning_rate": 3.890647243627218e-05,
|
| 1122 |
+
"loss": 2.025,
|
| 1123 |
+
"step": 159
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.661498708010336,
|
| 1127 |
+
"grad_norm": 0.7437235713005066,
|
| 1128 |
+
"learning_rate": 3.876847328094549e-05,
|
| 1129 |
+
"loss": 1.9579,
|
| 1130 |
+
"step": 160
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.6656330749354005,
|
| 1134 |
+
"grad_norm": 0.6715400218963623,
|
| 1135 |
+
"learning_rate": 3.862986930406669e-05,
|
| 1136 |
+
"loss": 1.9624,
|
| 1137 |
+
"step": 161
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.6697674418604651,
|
| 1141 |
+
"grad_norm": 0.7101289629936218,
|
| 1142 |
+
"learning_rate": 3.849066659423186e-05,
|
| 1143 |
+
"loss": 1.9392,
|
| 1144 |
+
"step": 162
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.6739018087855297,
|
| 1148 |
+
"grad_norm": 0.7018868923187256,
|
| 1149 |
+
"learning_rate": 3.835087126633821e-05,
|
| 1150 |
+
"loss": 1.9173,
|
| 1151 |
+
"step": 163
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.6780361757105943,
|
| 1155 |
+
"grad_norm": 0.7128501534461975,
|
| 1156 |
+
"learning_rate": 3.821048946131549e-05,
|
| 1157 |
+
"loss": 1.9504,
|
| 1158 |
+
"step": 164
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.6821705426356589,
|
| 1162 |
+
"grad_norm": 0.7460259199142456,
|
| 1163 |
+
"learning_rate": 3.806952734585623e-05,
|
| 1164 |
+
"loss": 1.9375,
|
| 1165 |
+
"step": 165
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.6863049095607235,
|
| 1169 |
+
"grad_norm": 0.7216957211494446,
|
| 1170 |
+
"learning_rate": 3.792799111214483e-05,
|
| 1171 |
+
"loss": 1.9579,
|
| 1172 |
+
"step": 166
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.6904392764857881,
|
| 1176 |
+
"grad_norm": 0.7324910163879395,
|
| 1177 |
+
"learning_rate": 3.778588697758556e-05,
|
| 1178 |
+
"loss": 1.945,
|
| 1179 |
+
"step": 167
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.6945736434108527,
|
| 1183 |
+
"grad_norm": 0.7266360521316528,
|
| 1184 |
+
"learning_rate": 3.764322118452943e-05,
|
| 1185 |
+
"loss": 1.8605,
|
| 1186 |
+
"step": 168
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.6987080103359173,
|
| 1190 |
+
"grad_norm": 0.8365564346313477,
|
| 1191 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 1192 |
+
"loss": 1.9562,
|
| 1193 |
+
"step": 169
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.7028423772609819,
|
| 1197 |
+
"grad_norm": 0.7650736570358276,
|
| 1198 |
+
"learning_rate": 3.7356229715418074e-05,
|
| 1199 |
+
"loss": 1.9373,
|
| 1200 |
+
"step": 170
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.7069767441860465,
|
| 1204 |
+
"grad_norm": 0.8527212738990784,
|
| 1205 |
+
"learning_rate": 3.721191664632531e-05,
|
| 1206 |
+
"loss": 1.8931,
|
| 1207 |
+
"step": 171
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.7111111111111111,
|
| 1211 |
+
"grad_norm": 0.8237689137458801,
|
| 1212 |
+
"learning_rate": 3.7067067132106815e-05,
|
| 1213 |
+
"loss": 1.9028,
|
| 1214 |
+
"step": 172
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.7152454780361757,
|
| 1218 |
+
"grad_norm": 0.7969968914985657,
|
| 1219 |
+
"learning_rate": 3.6921687535712656e-05,
|
| 1220 |
+
"loss": 1.9441,
|
| 1221 |
+
"step": 173
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.7193798449612403,
|
| 1225 |
+
"grad_norm": 0.7200686931610107,
|
| 1226 |
+
"learning_rate": 3.6775784243378354e-05,
|
| 1227 |
+
"loss": 1.8995,
|
| 1228 |
+
"step": 174
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.7235142118863049,
|
| 1232 |
+
"grad_norm": 0.7550849318504333,
|
| 1233 |
+
"learning_rate": 3.662936366434434e-05,
|
| 1234 |
+
"loss": 1.9544,
|
| 1235 |
+
"step": 175
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.7276485788113695,
|
| 1239 |
+
"grad_norm": 0.6668141484260559,
|
| 1240 |
+
"learning_rate": 3.6482432230574446e-05,
|
| 1241 |
+
"loss": 1.9965,
|
| 1242 |
+
"step": 176
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.7317829457364341,
|
| 1246 |
+
"grad_norm": 0.710862398147583,
|
| 1247 |
+
"learning_rate": 3.63349963964733e-05,
|
| 1248 |
+
"loss": 1.9837,
|
| 1249 |
+
"step": 177
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.7359173126614987,
|
| 1253 |
+
"grad_norm": 0.6771061420440674,
|
| 1254 |
+
"learning_rate": 3.618706263860284e-05,
|
| 1255 |
+
"loss": 1.9656,
|
| 1256 |
+
"step": 178
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.7400516795865633,
|
| 1260 |
+
"grad_norm": 0.6792022585868835,
|
| 1261 |
+
"learning_rate": 3.60386374553978e-05,
|
| 1262 |
+
"loss": 1.9108,
|
| 1263 |
+
"step": 179
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.7441860465116279,
|
| 1267 |
+
"grad_norm": 0.6902000904083252,
|
| 1268 |
+
"learning_rate": 3.5889727366880256e-05,
|
| 1269 |
+
"loss": 1.9317,
|
| 1270 |
+
"step": 180
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.7483204134366925,
|
| 1274 |
+
"grad_norm": 0.6956230998039246,
|
| 1275 |
+
"learning_rate": 3.57403389143732e-05,
|
| 1276 |
+
"loss": 1.9307,
|
| 1277 |
+
"step": 181
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.7524547803617571,
|
| 1281 |
+
"grad_norm": 0.7050280570983887,
|
| 1282 |
+
"learning_rate": 3.5590478660213214e-05,
|
| 1283 |
+
"loss": 1.9501,
|
| 1284 |
+
"step": 182
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.7565891472868217,
|
| 1288 |
+
"grad_norm": 0.6987014412879944,
|
| 1289 |
+
"learning_rate": 3.5440153187462145e-05,
|
| 1290 |
+
"loss": 1.9188,
|
| 1291 |
+
"step": 183
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.7607235142118863,
|
| 1295 |
+
"grad_norm": 0.7244204878807068,
|
| 1296 |
+
"learning_rate": 3.528936909961801e-05,
|
| 1297 |
+
"loss": 1.9035,
|
| 1298 |
+
"step": 184
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.7648578811369509,
|
| 1302 |
+
"grad_norm": 1.0021049976348877,
|
| 1303 |
+
"learning_rate": 3.5138133020324845e-05,
|
| 1304 |
+
"loss": 1.8984,
|
| 1305 |
+
"step": 185
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.7689922480620155,
|
| 1309 |
+
"grad_norm": 0.7401679158210754,
|
| 1310 |
+
"learning_rate": 3.498645159308179e-05,
|
| 1311 |
+
"loss": 1.8889,
|
| 1312 |
+
"step": 186
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.7731266149870801,
|
| 1316 |
+
"grad_norm": 0.6945346593856812,
|
| 1317 |
+
"learning_rate": 3.483433148095121e-05,
|
| 1318 |
+
"loss": 1.9199,
|
| 1319 |
+
"step": 187
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.7772609819121447,
|
| 1323 |
+
"grad_norm": 0.7187919616699219,
|
| 1324 |
+
"learning_rate": 3.468177936626603e-05,
|
| 1325 |
+
"loss": 2.0003,
|
| 1326 |
+
"step": 188
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.7813953488372093,
|
| 1330 |
+
"grad_norm": 0.7584187984466553,
|
| 1331 |
+
"learning_rate": 3.4528801950336174e-05,
|
| 1332 |
+
"loss": 1.8989,
|
| 1333 |
+
"step": 189
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.7855297157622739,
|
| 1337 |
+
"grad_norm": 0.6546937823295593,
|
| 1338 |
+
"learning_rate": 3.437540595315423e-05,
|
| 1339 |
+
"loss": 1.9181,
|
| 1340 |
+
"step": 190
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.7896640826873385,
|
| 1344 |
+
"grad_norm": 0.8132810592651367,
|
| 1345 |
+
"learning_rate": 3.4221598113100195e-05,
|
| 1346 |
+
"loss": 1.9343,
|
| 1347 |
+
"step": 191
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.7937984496124031,
|
| 1351 |
+
"grad_norm": 0.7545456290245056,
|
| 1352 |
+
"learning_rate": 3.406738518664552e-05,
|
| 1353 |
+
"loss": 1.9097,
|
| 1354 |
+
"step": 192
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.7979328165374677,
|
| 1358 |
+
"grad_norm": 0.6333910822868347,
|
| 1359 |
+
"learning_rate": 3.3912773948056274e-05,
|
| 1360 |
+
"loss": 1.8665,
|
| 1361 |
+
"step": 193
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.8020671834625323,
|
| 1365 |
+
"grad_norm": 0.772945761680603,
|
| 1366 |
+
"learning_rate": 3.375777118909561e-05,
|
| 1367 |
+
"loss": 1.9451,
|
| 1368 |
+
"step": 194
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.8062015503875969,
|
| 1372 |
+
"grad_norm": 0.6684311032295227,
|
| 1373 |
+
"learning_rate": 3.360238371872536e-05,
|
| 1374 |
+
"loss": 1.944,
|
| 1375 |
+
"step": 195
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.8103359173126615,
|
| 1379 |
+
"grad_norm": 0.7220767736434937,
|
| 1380 |
+
"learning_rate": 3.344661836280699e-05,
|
| 1381 |
+
"loss": 1.9652,
|
| 1382 |
+
"step": 196
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.814470284237726,
|
| 1386 |
+
"grad_norm": 0.6830906867980957,
|
| 1387 |
+
"learning_rate": 3.32904819638017e-05,
|
| 1388 |
+
"loss": 1.9728,
|
| 1389 |
+
"step": 197
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.8186046511627907,
|
| 1393 |
+
"grad_norm": 0.6878849864006042,
|
| 1394 |
+
"learning_rate": 3.313398138046987e-05,
|
| 1395 |
+
"loss": 1.9231,
|
| 1396 |
+
"step": 198
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.8227390180878553,
|
| 1400 |
+
"grad_norm": 0.7480675578117371,
|
| 1401 |
+
"learning_rate": 3.297712348756982e-05,
|
| 1402 |
+
"loss": 1.9545,
|
| 1403 |
+
"step": 199
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.8268733850129198,
|
| 1407 |
+
"grad_norm": 0.6948933601379395,
|
| 1408 |
+
"learning_rate": 3.2819915175555684e-05,
|
| 1409 |
+
"loss": 1.9332,
|
| 1410 |
+
"step": 200
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.8310077519379845,
|
| 1414 |
+
"grad_norm": 0.7534158825874329,
|
| 1415 |
+
"learning_rate": 3.266236335027487e-05,
|
| 1416 |
+
"loss": 1.9518,
|
| 1417 |
+
"step": 201
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.8351421188630491,
|
| 1421 |
+
"grad_norm": 0.7088623046875,
|
| 1422 |
+
"learning_rate": 3.250447493266463e-05,
|
| 1423 |
+
"loss": 1.9011,
|
| 1424 |
+
"step": 202
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.8392764857881136,
|
| 1428 |
+
"grad_norm": 0.6807135343551636,
|
| 1429 |
+
"learning_rate": 3.234625685844803e-05,
|
| 1430 |
+
"loss": 1.9257,
|
| 1431 |
+
"step": 203
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.8434108527131783,
|
| 1435 |
+
"grad_norm": 0.7912558317184448,
|
| 1436 |
+
"learning_rate": 3.218771607782929e-05,
|
| 1437 |
+
"loss": 1.9172,
|
| 1438 |
+
"step": 204
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.8475452196382429,
|
| 1442 |
+
"grad_norm": 0.6469288468360901,
|
| 1443 |
+
"learning_rate": 3.202885955518849e-05,
|
| 1444 |
+
"loss": 1.9632,
|
| 1445 |
+
"step": 205
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.8516795865633074,
|
| 1449 |
+
"grad_norm": 0.6447204947471619,
|
| 1450 |
+
"learning_rate": 3.186969426877563e-05,
|
| 1451 |
+
"loss": 1.9568,
|
| 1452 |
+
"step": 206
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 0.8558139534883721,
|
| 1456 |
+
"grad_norm": 0.658008337020874,
|
| 1457 |
+
"learning_rate": 3.171022721040409e-05,
|
| 1458 |
+
"loss": 1.9168,
|
| 1459 |
+
"step": 207
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.8599483204134367,
|
| 1463 |
+
"grad_norm": 0.6640242338180542,
|
| 1464 |
+
"learning_rate": 3.1550465385143455e-05,
|
| 1465 |
+
"loss": 1.9243,
|
| 1466 |
+
"step": 208
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.8640826873385012,
|
| 1470 |
+
"grad_norm": 0.6505051851272583,
|
| 1471 |
+
"learning_rate": 3.139041581101187e-05,
|
| 1472 |
+
"loss": 1.8235,
|
| 1473 |
+
"step": 209
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.8682170542635659,
|
| 1477 |
+
"grad_norm": 0.6725614070892334,
|
| 1478 |
+
"learning_rate": 3.12300855186677e-05,
|
| 1479 |
+
"loss": 1.9092,
|
| 1480 |
+
"step": 210
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 0.8723514211886305,
|
| 1484 |
+
"grad_norm": 0.668488085269928,
|
| 1485 |
+
"learning_rate": 3.1069481551100695e-05,
|
| 1486 |
+
"loss": 1.9501,
|
| 1487 |
+
"step": 211
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 0.876485788113695,
|
| 1491 |
+
"grad_norm": 0.6829690933227539,
|
| 1492 |
+
"learning_rate": 3.090861096332263e-05,
|
| 1493 |
+
"loss": 1.9308,
|
| 1494 |
+
"step": 212
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.8806201550387597,
|
| 1498 |
+
"grad_norm": 0.6898390054702759,
|
| 1499 |
+
"learning_rate": 3.074748082205734e-05,
|
| 1500 |
+
"loss": 1.9279,
|
| 1501 |
+
"step": 213
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.8847545219638243,
|
| 1505 |
+
"grad_norm": 0.6641663312911987,
|
| 1506 |
+
"learning_rate": 3.0586098205430355e-05,
|
| 1507 |
+
"loss": 1.9227,
|
| 1508 |
+
"step": 214
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 0.8888888888888888,
|
| 1512 |
+
"grad_norm": 0.676388144493103,
|
| 1513 |
+
"learning_rate": 3.042447020265795e-05,
|
| 1514 |
+
"loss": 1.9263,
|
| 1515 |
+
"step": 215
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 0.8930232558139535,
|
| 1519 |
+
"grad_norm": 0.7283117175102234,
|
| 1520 |
+
"learning_rate": 3.02626039137357e-05,
|
| 1521 |
+
"loss": 1.9113,
|
| 1522 |
+
"step": 216
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 0.8971576227390181,
|
| 1526 |
+
"grad_norm": 0.693657636642456,
|
| 1527 |
+
"learning_rate": 3.010050644912662e-05,
|
| 1528 |
+
"loss": 1.9546,
|
| 1529 |
+
"step": 217
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 0.9012919896640826,
|
| 1533 |
+
"grad_norm": 0.656113862991333,
|
| 1534 |
+
"learning_rate": 2.993818492944882e-05,
|
| 1535 |
+
"loss": 1.8975,
|
| 1536 |
+
"step": 218
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 0.9054263565891473,
|
| 1540 |
+
"grad_norm": 0.6648372411727905,
|
| 1541 |
+
"learning_rate": 2.9775646485162694e-05,
|
| 1542 |
+
"loss": 1.9315,
|
| 1543 |
+
"step": 219
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 0.9095607235142119,
|
| 1547 |
+
"grad_norm": 0.6712179183959961,
|
| 1548 |
+
"learning_rate": 2.9612898256257716e-05,
|
| 1549 |
+
"loss": 1.9024,
|
| 1550 |
+
"step": 220
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 0.9136950904392764,
|
| 1554 |
+
"grad_norm": 0.6894586086273193,
|
| 1555 |
+
"learning_rate": 2.9449947391938766e-05,
|
| 1556 |
+
"loss": 1.9726,
|
| 1557 |
+
"step": 221
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.9178294573643411,
|
| 1561 |
+
"grad_norm": 0.6747611165046692,
|
| 1562 |
+
"learning_rate": 2.9286801050312078e-05,
|
| 1563 |
+
"loss": 1.9322,
|
| 1564 |
+
"step": 222
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 0.9219638242894057,
|
| 1568 |
+
"grad_norm": 2.8370180130004883,
|
| 1569 |
+
"learning_rate": 2.9123466398070852e-05,
|
| 1570 |
+
"loss": 1.9033,
|
| 1571 |
+
"step": 223
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 0.9260981912144702,
|
| 1575 |
+
"grad_norm": 0.824735164642334,
|
| 1576 |
+
"learning_rate": 2.8959950610180374e-05,
|
| 1577 |
+
"loss": 1.9108,
|
| 1578 |
+
"step": 224
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 0.9302325581395349,
|
| 1582 |
+
"grad_norm": 0.7000449895858765,
|
| 1583 |
+
"learning_rate": 2.8796260869562863e-05,
|
| 1584 |
+
"loss": 1.9964,
|
| 1585 |
+
"step": 225
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 0.9343669250645995,
|
| 1589 |
+
"grad_norm": 0.6916747093200684,
|
| 1590 |
+
"learning_rate": 2.8632404366781924e-05,
|
| 1591 |
+
"loss": 1.934,
|
| 1592 |
+
"step": 226
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 0.938501291989664,
|
| 1596 |
+
"grad_norm": 0.7057512402534485,
|
| 1597 |
+
"learning_rate": 2.8468388299726712e-05,
|
| 1598 |
+
"loss": 1.9087,
|
| 1599 |
+
"step": 227
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 0.9426356589147287,
|
| 1603 |
+
"grad_norm": 0.6310217380523682,
|
| 1604 |
+
"learning_rate": 2.830421987329569e-05,
|
| 1605 |
+
"loss": 1.9168,
|
| 1606 |
+
"step": 228
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 0.9467700258397933,
|
| 1610 |
+
"grad_norm": 0.7014176249504089,
|
| 1611 |
+
"learning_rate": 2.8139906299080203e-05,
|
| 1612 |
+
"loss": 1.9262,
|
| 1613 |
+
"step": 229
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 0.9509043927648578,
|
| 1617 |
+
"grad_norm": 0.6566993594169617,
|
| 1618 |
+
"learning_rate": 2.7975454795047622e-05,
|
| 1619 |
+
"loss": 1.9458,
|
| 1620 |
+
"step": 230
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 0.9550387596899225,
|
| 1624 |
+
"grad_norm": 0.6818047761917114,
|
| 1625 |
+
"learning_rate": 2.7810872585224308e-05,
|
| 1626 |
+
"loss": 1.8954,
|
| 1627 |
+
"step": 231
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 0.9591731266149871,
|
| 1631 |
+
"grad_norm": 0.6725473403930664,
|
| 1632 |
+
"learning_rate": 2.7646166899378255e-05,
|
| 1633 |
+
"loss": 1.8969,
|
| 1634 |
+
"step": 232
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 0.9633074935400516,
|
| 1638 |
+
"grad_norm": 0.671540379524231,
|
| 1639 |
+
"learning_rate": 2.7481344972701545e-05,
|
| 1640 |
+
"loss": 1.8251,
|
| 1641 |
+
"step": 233
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 0.9674418604651163,
|
| 1645 |
+
"grad_norm": 0.6857994794845581,
|
| 1646 |
+
"learning_rate": 2.7316414045492445e-05,
|
| 1647 |
+
"loss": 1.8961,
|
| 1648 |
+
"step": 234
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 0.9715762273901809,
|
| 1652 |
+
"grad_norm": 0.7223935723304749,
|
| 1653 |
+
"learning_rate": 2.7151381362837426e-05,
|
| 1654 |
+
"loss": 1.8999,
|
| 1655 |
+
"step": 235
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 0.9757105943152454,
|
| 1659 |
+
"grad_norm": 0.7103882431983948,
|
| 1660 |
+
"learning_rate": 2.6986254174292862e-05,
|
| 1661 |
+
"loss": 1.9217,
|
| 1662 |
+
"step": 236
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 0.9798449612403101,
|
| 1666 |
+
"grad_norm": 0.6932228803634644,
|
| 1667 |
+
"learning_rate": 2.682103973356659e-05,
|
| 1668 |
+
"loss": 1.9375,
|
| 1669 |
+
"step": 237
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 0.9839793281653747,
|
| 1673 |
+
"grad_norm": 0.7335678935050964,
|
| 1674 |
+
"learning_rate": 2.6655745298199253e-05,
|
| 1675 |
+
"loss": 1.8848,
|
| 1676 |
+
"step": 238
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 0.9881136950904392,
|
| 1680 |
+
"grad_norm": 0.7323726415634155,
|
| 1681 |
+
"learning_rate": 2.6490378129245498e-05,
|
| 1682 |
+
"loss": 1.9268,
|
| 1683 |
+
"step": 239
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 0.9922480620155039,
|
| 1687 |
+
"grad_norm": 0.6597888469696045,
|
| 1688 |
+
"learning_rate": 2.6324945490955027e-05,
|
| 1689 |
+
"loss": 1.9187,
|
| 1690 |
+
"step": 240
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 0.9963824289405685,
|
| 1694 |
+
"grad_norm": 0.6718257665634155,
|
| 1695 |
+
"learning_rate": 2.6159454650453463e-05,
|
| 1696 |
+
"loss": 1.9676,
|
| 1697 |
+
"step": 241
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 1.0,
|
| 1701 |
+
"grad_norm": 0.6718257665634155,
|
| 1702 |
+
"learning_rate": 2.599391287742315e-05,
|
| 1703 |
+
"loss": 1.8618,
|
| 1704 |
+
"step": 242
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 1.0041343669250646,
|
| 1708 |
+
"grad_norm": 0.16083045303821564,
|
| 1709 |
+
"learning_rate": 2.582832744378377e-05,
|
| 1710 |
+
"loss": 1.8551,
|
| 1711 |
+
"step": 243
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 1.0082687338501293,
|
| 1715 |
+
"grad_norm": 0.20273317396640778,
|
| 1716 |
+
"learning_rate": 2.5662705623372967e-05,
|
| 1717 |
+
"loss": 1.8274,
|
| 1718 |
+
"step": 244
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 1.012403100775194,
|
| 1722 |
+
"grad_norm": 0.20020867884159088,
|
| 1723 |
+
"learning_rate": 2.5497054691626753e-05,
|
| 1724 |
+
"loss": 1.9035,
|
| 1725 |
+
"step": 245
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 1.0165374677002583,
|
| 1729 |
+
"grad_norm": 0.20411372184753418,
|
| 1730 |
+
"learning_rate": 2.5331381925259968e-05,
|
| 1731 |
+
"loss": 1.8652,
|
| 1732 |
+
"step": 246
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 1.020671834625323,
|
| 1736 |
+
"grad_norm": 0.23273414373397827,
|
| 1737 |
+
"learning_rate": 2.5165694601946565e-05,
|
| 1738 |
+
"loss": 1.8787,
|
| 1739 |
+
"step": 247
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 1.0248062015503876,
|
| 1743 |
+
"grad_norm": 0.21661241352558136,
|
| 1744 |
+
"learning_rate": 2.5e-05,
|
| 1745 |
+
"loss": 1.8937,
|
| 1746 |
+
"step": 248
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 1.0289405684754522,
|
| 1750 |
+
"grad_norm": 0.17972636222839355,
|
| 1751 |
+
"learning_rate": 2.483430539805344e-05,
|
| 1752 |
+
"loss": 1.8592,
|
| 1753 |
+
"step": 249
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 1.0330749354005169,
|
| 1757 |
+
"grad_norm": 0.18342098593711853,
|
| 1758 |
+
"learning_rate": 2.4668618074740045e-05,
|
| 1759 |
+
"loss": 1.8266,
|
| 1760 |
+
"step": 250
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 1.0372093023255813,
|
| 1764 |
+
"grad_norm": 0.19723518192768097,
|
| 1765 |
+
"learning_rate": 2.4502945308373246e-05,
|
| 1766 |
+
"loss": 1.8778,
|
| 1767 |
+
"step": 251
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 1.041343669250646,
|
| 1771 |
+
"grad_norm": 0.19353650510311127,
|
| 1772 |
+
"learning_rate": 2.433729437662704e-05,
|
| 1773 |
+
"loss": 1.8661,
|
| 1774 |
+
"step": 252
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 1.0454780361757106,
|
| 1778 |
+
"grad_norm": 0.17848767340183258,
|
| 1779 |
+
"learning_rate": 2.4171672556216234e-05,
|
| 1780 |
+
"loss": 1.8583,
|
| 1781 |
+
"step": 253
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 1.0496124031007752,
|
| 1785 |
+
"grad_norm": 0.19387133419513702,
|
| 1786 |
+
"learning_rate": 2.4006087122576863e-05,
|
| 1787 |
+
"loss": 1.8805,
|
| 1788 |
+
"step": 254
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 1.0537467700258398,
|
| 1792 |
+
"grad_norm": 0.19400081038475037,
|
| 1793 |
+
"learning_rate": 2.3840545349546536e-05,
|
| 1794 |
+
"loss": 1.8467,
|
| 1795 |
+
"step": 255
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 1.0578811369509045,
|
| 1799 |
+
"grad_norm": 0.19158639013767242,
|
| 1800 |
+
"learning_rate": 2.3675054509044976e-05,
|
| 1801 |
+
"loss": 1.886,
|
| 1802 |
+
"step": 256
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 1.062015503875969,
|
| 1806 |
+
"grad_norm": 0.20993342995643616,
|
| 1807 |
+
"learning_rate": 2.3509621870754505e-05,
|
| 1808 |
+
"loss": 1.8698,
|
| 1809 |
+
"step": 257
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 1.0661498708010335,
|
| 1813 |
+
"grad_norm": 0.1917114406824112,
|
| 1814 |
+
"learning_rate": 2.3344254701800756e-05,
|
| 1815 |
+
"loss": 1.8819,
|
| 1816 |
+
"step": 258
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 1.0702842377260982,
|
| 1820 |
+
"grad_norm": 0.18254557251930237,
|
| 1821 |
+
"learning_rate": 2.317896026643341e-05,
|
| 1822 |
+
"loss": 1.9108,
|
| 1823 |
+
"step": 259
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 1.0744186046511628,
|
| 1827 |
+
"grad_norm": 0.19759495556354523,
|
| 1828 |
+
"learning_rate": 2.301374582570714e-05,
|
| 1829 |
+
"loss": 1.8473,
|
| 1830 |
+
"step": 260
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 1.0785529715762274,
|
| 1834 |
+
"grad_norm": 0.48980703949928284,
|
| 1835 |
+
"learning_rate": 2.2848618637162584e-05,
|
| 1836 |
+
"loss": 1.8351,
|
| 1837 |
+
"step": 261
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 1.082687338501292,
|
| 1841 |
+
"grad_norm": 0.21729247272014618,
|
| 1842 |
+
"learning_rate": 2.268358595450756e-05,
|
| 1843 |
+
"loss": 1.8416,
|
| 1844 |
+
"step": 262
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 1.0868217054263565,
|
| 1848 |
+
"grad_norm": 0.2281586080789566,
|
| 1849 |
+
"learning_rate": 2.2518655027298464e-05,
|
| 1850 |
+
"loss": 1.9227,
|
| 1851 |
+
"step": 263
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 1.0909560723514211,
|
| 1855 |
+
"grad_norm": 0.22362685203552246,
|
| 1856 |
+
"learning_rate": 2.2353833100621747e-05,
|
| 1857 |
+
"loss": 1.8309,
|
| 1858 |
+
"step": 264
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 1.0950904392764857,
|
| 1862 |
+
"grad_norm": 0.1918443739414215,
|
| 1863 |
+
"learning_rate": 2.2189127414775698e-05,
|
| 1864 |
+
"loss": 1.8799,
|
| 1865 |
+
"step": 265
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 1.0992248062015504,
|
| 1869 |
+
"grad_norm": 0.2082519829273224,
|
| 1870 |
+
"learning_rate": 2.2024545204952383e-05,
|
| 1871 |
+
"loss": 1.8673,
|
| 1872 |
+
"step": 266
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 1.103359173126615,
|
| 1876 |
+
"grad_norm": 0.18724186718463898,
|
| 1877 |
+
"learning_rate": 2.1860093700919803e-05,
|
| 1878 |
+
"loss": 1.8612,
|
| 1879 |
+
"step": 267
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 1.1074935400516797,
|
| 1883 |
+
"grad_norm": 0.19637227058410645,
|
| 1884 |
+
"learning_rate": 2.169578012670431e-05,
|
| 1885 |
+
"loss": 1.8742,
|
| 1886 |
+
"step": 268
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 1.1116279069767443,
|
| 1890 |
+
"grad_norm": 0.19105981290340424,
|
| 1891 |
+
"learning_rate": 2.1531611700273297e-05,
|
| 1892 |
+
"loss": 1.8515,
|
| 1893 |
+
"step": 269
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 1.1157622739018087,
|
| 1897 |
+
"grad_norm": 0.22116196155548096,
|
| 1898 |
+
"learning_rate": 2.1367595633218082e-05,
|
| 1899 |
+
"loss": 1.8439,
|
| 1900 |
+
"step": 270
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 1.1198966408268733,
|
| 1904 |
+
"grad_norm": 0.2203124612569809,
|
| 1905 |
+
"learning_rate": 2.1203739130437146e-05,
|
| 1906 |
+
"loss": 1.8407,
|
| 1907 |
+
"step": 271
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 1.124031007751938,
|
| 1911 |
+
"grad_norm": 0.20042136311531067,
|
| 1912 |
+
"learning_rate": 2.104004938981963e-05,
|
| 1913 |
+
"loss": 1.862,
|
| 1914 |
+
"step": 272
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 1.1281653746770026,
|
| 1918 |
+
"grad_norm": 0.2041844129562378,
|
| 1919 |
+
"learning_rate": 2.087653360192915e-05,
|
| 1920 |
+
"loss": 1.852,
|
| 1921 |
+
"step": 273
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 1.1322997416020673,
|
| 1925 |
+
"grad_norm": 0.2171774059534073,
|
| 1926 |
+
"learning_rate": 2.0713198949687924e-05,
|
| 1927 |
+
"loss": 1.8953,
|
| 1928 |
+
"step": 274
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 1.1364341085271317,
|
| 1932 |
+
"grad_norm": 0.18267354369163513,
|
| 1933 |
+
"learning_rate": 2.055005260806125e-05,
|
| 1934 |
+
"loss": 1.8498,
|
| 1935 |
+
"step": 275
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 1.1405684754521963,
|
| 1939 |
+
"grad_norm": 0.1831262856721878,
|
| 1940 |
+
"learning_rate": 2.0387101743742293e-05,
|
| 1941 |
+
"loss": 1.8367,
|
| 1942 |
+
"step": 276
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 1.144702842377261,
|
| 1946 |
+
"grad_norm": 0.16366001963615417,
|
| 1947 |
+
"learning_rate": 2.0224353514837305e-05,
|
| 1948 |
+
"loss": 1.8657,
|
| 1949 |
+
"step": 277
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 1.1488372093023256,
|
| 1953 |
+
"grad_norm": 0.24233390390872955,
|
| 1954 |
+
"learning_rate": 2.0061815070551186e-05,
|
| 1955 |
+
"loss": 1.878,
|
| 1956 |
+
"step": 278
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 1.1529715762273902,
|
| 1960 |
+
"grad_norm": 0.19091325998306274,
|
| 1961 |
+
"learning_rate": 1.989949355087339e-05,
|
| 1962 |
+
"loss": 1.9105,
|
| 1963 |
+
"step": 279
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 1.1571059431524549,
|
| 1967 |
+
"grad_norm": 0.22736191749572754,
|
| 1968 |
+
"learning_rate": 1.9737396086264313e-05,
|
| 1969 |
+
"loss": 1.8895,
|
| 1970 |
+
"step": 280
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 1.1612403100775195,
|
| 1974 |
+
"grad_norm": 0.19838637113571167,
|
| 1975 |
+
"learning_rate": 1.957552979734205e-05,
|
| 1976 |
+
"loss": 1.839,
|
| 1977 |
+
"step": 281
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 1.165374677002584,
|
| 1981 |
+
"grad_norm": 0.190949484705925,
|
| 1982 |
+
"learning_rate": 1.9413901794569644e-05,
|
| 1983 |
+
"loss": 1.9009,
|
| 1984 |
+
"step": 282
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 1.1695090439276485,
|
| 1988 |
+
"grad_norm": 0.17007027566432953,
|
| 1989 |
+
"learning_rate": 1.9252519177942667e-05,
|
| 1990 |
+
"loss": 1.8245,
|
| 1991 |
+
"step": 283
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 1.1736434108527132,
|
| 1995 |
+
"grad_norm": 0.44774138927459717,
|
| 1996 |
+
"learning_rate": 1.9091389036677382e-05,
|
| 1997 |
+
"loss": 1.8063,
|
| 1998 |
+
"step": 284
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 1.1777777777777778,
|
| 2002 |
+
"grad_norm": 0.19281768798828125,
|
| 2003 |
+
"learning_rate": 1.8930518448899304e-05,
|
| 2004 |
+
"loss": 1.8572,
|
| 2005 |
+
"step": 285
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 1.1819121447028424,
|
| 2009 |
+
"grad_norm": 0.17704680562019348,
|
| 2010 |
+
"learning_rate": 1.8769914481332303e-05,
|
| 2011 |
+
"loss": 1.7977,
|
| 2012 |
+
"step": 286
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 1.1860465116279069,
|
| 2016 |
+
"grad_norm": 0.1867540329694748,
|
| 2017 |
+
"learning_rate": 1.8609584188988136e-05,
|
| 2018 |
+
"loss": 1.8664,
|
| 2019 |
+
"step": 287
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 1.1901808785529715,
|
| 2023 |
+
"grad_norm": 0.19700385630130768,
|
| 2024 |
+
"learning_rate": 1.8449534614856558e-05,
|
| 2025 |
+
"loss": 1.8977,
|
| 2026 |
+
"step": 288
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 1.1943152454780361,
|
| 2030 |
+
"grad_norm": 0.18649935722351074,
|
| 2031 |
+
"learning_rate": 1.8289772789595917e-05,
|
| 2032 |
+
"loss": 1.8771,
|
| 2033 |
+
"step": 289
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 1.1984496124031008,
|
| 2037 |
+
"grad_norm": 0.19296646118164062,
|
| 2038 |
+
"learning_rate": 1.813030573122437e-05,
|
| 2039 |
+
"loss": 1.8976,
|
| 2040 |
+
"step": 290
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 1.2025839793281654,
|
| 2044 |
+
"grad_norm": 0.23263390362262726,
|
| 2045 |
+
"learning_rate": 1.7971140444811513e-05,
|
| 2046 |
+
"loss": 1.7874,
|
| 2047 |
+
"step": 291
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 1.20671834625323,
|
| 2051 |
+
"grad_norm": 0.19923025369644165,
|
| 2052 |
+
"learning_rate": 1.7812283922170718e-05,
|
| 2053 |
+
"loss": 1.8486,
|
| 2054 |
+
"step": 292
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 1.2108527131782947,
|
| 2058 |
+
"grad_norm": 0.1837182492017746,
|
| 2059 |
+
"learning_rate": 1.7653743141551983e-05,
|
| 2060 |
+
"loss": 1.8403,
|
| 2061 |
+
"step": 293
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 1.214987080103359,
|
| 2065 |
+
"grad_norm": 0.19565509259700775,
|
| 2066 |
+
"learning_rate": 1.749552506733537e-05,
|
| 2067 |
+
"loss": 1.8939,
|
| 2068 |
+
"step": 294
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 1.2191214470284237,
|
| 2072 |
+
"grad_norm": 0.1639636754989624,
|
| 2073 |
+
"learning_rate": 1.733763664972513e-05,
|
| 2074 |
+
"loss": 1.8646,
|
| 2075 |
+
"step": 295
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 1.2232558139534884,
|
| 2079 |
+
"grad_norm": 0.19631829857826233,
|
| 2080 |
+
"learning_rate": 1.7180084824444325e-05,
|
| 2081 |
+
"loss": 1.8722,
|
| 2082 |
+
"step": 296
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 1.227390180878553,
|
| 2086 |
+
"grad_norm": 0.19864365458488464,
|
| 2087 |
+
"learning_rate": 1.7022876512430197e-05,
|
| 2088 |
+
"loss": 1.8458,
|
| 2089 |
+
"step": 297
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 1.2315245478036176,
|
| 2093 |
+
"grad_norm": 0.20099179446697235,
|
| 2094 |
+
"learning_rate": 1.6866018619530123e-05,
|
| 2095 |
+
"loss": 1.8117,
|
| 2096 |
+
"step": 298
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 1.235658914728682,
|
| 2100 |
+
"grad_norm": 0.2023850828409195,
|
| 2101 |
+
"learning_rate": 1.6709518036198308e-05,
|
| 2102 |
+
"loss": 1.8317,
|
| 2103 |
+
"step": 299
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 1.2397932816537467,
|
| 2107 |
+
"grad_norm": 0.17931176722049713,
|
| 2108 |
+
"learning_rate": 1.6553381637193018e-05,
|
| 2109 |
+
"loss": 1.8655,
|
| 2110 |
+
"step": 300
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"epoch": 1.2439276485788113,
|
| 2114 |
+
"grad_norm": 0.1773586869239807,
|
| 2115 |
+
"learning_rate": 1.639761628127465e-05,
|
| 2116 |
+
"loss": 1.8391,
|
| 2117 |
+
"step": 301
|
| 2118 |
+
},
|
| 2119 |
+
{
|
| 2120 |
+
"epoch": 1.248062015503876,
|
| 2121 |
+
"grad_norm": 0.1897374838590622,
|
| 2122 |
+
"learning_rate": 1.6242228810904392e-05,
|
| 2123 |
+
"loss": 1.8665,
|
| 2124 |
+
"step": 302
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 1.2521963824289406,
|
| 2128 |
+
"grad_norm": 0.21313223242759705,
|
| 2129 |
+
"learning_rate": 1.6087226051943728e-05,
|
| 2130 |
+
"loss": 1.8349,
|
| 2131 |
+
"step": 303
|
| 2132 |
+
},
|
| 2133 |
+
{
|
| 2134 |
+
"epoch": 1.2563307493540052,
|
| 2135 |
+
"grad_norm": 0.16654111444950104,
|
| 2136 |
+
"learning_rate": 1.5932614813354486e-05,
|
| 2137 |
+
"loss": 1.8874,
|
| 2138 |
+
"step": 304
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 1.2604651162790699,
|
| 2142 |
+
"grad_norm": 0.19993992149829865,
|
| 2143 |
+
"learning_rate": 1.5778401886899807e-05,
|
| 2144 |
+
"loss": 1.8545,
|
| 2145 |
+
"step": 305
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 1.2645994832041343,
|
| 2149 |
+
"grad_norm": 0.2002255618572235,
|
| 2150 |
+
"learning_rate": 1.5624594046845777e-05,
|
| 2151 |
+
"loss": 1.8512,
|
| 2152 |
+
"step": 306
|
| 2153 |
+
},
|
| 2154 |
+
{
|
| 2155 |
+
"epoch": 1.268733850129199,
|
| 2156 |
+
"grad_norm": 0.1965976059436798,
|
| 2157 |
+
"learning_rate": 1.547119804966382e-05,
|
| 2158 |
+
"loss": 1.8466,
|
| 2159 |
+
"step": 307
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 1.2728682170542636,
|
| 2163 |
+
"grad_norm": 0.24566581845283508,
|
| 2164 |
+
"learning_rate": 1.5318220633733978e-05,
|
| 2165 |
+
"loss": 1.8543,
|
| 2166 |
+
"step": 308
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 1.2770025839793282,
|
| 2170 |
+
"grad_norm": 0.17836935818195343,
|
| 2171 |
+
"learning_rate": 1.5165668519048799e-05,
|
| 2172 |
+
"loss": 1.863,
|
| 2173 |
+
"step": 309
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 1.2811369509043928,
|
| 2177 |
+
"grad_norm": 0.1995442658662796,
|
| 2178 |
+
"learning_rate": 1.5013548406918215e-05,
|
| 2179 |
+
"loss": 1.8448,
|
| 2180 |
+
"step": 310
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 1.2852713178294572,
|
| 2184 |
+
"grad_norm": 0.19902704656124115,
|
| 2185 |
+
"learning_rate": 1.4861866979675154e-05,
|
| 2186 |
+
"loss": 1.801,
|
| 2187 |
+
"step": 311
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 1.2894056847545219,
|
| 2191 |
+
"grad_norm": 0.17136715352535248,
|
| 2192 |
+
"learning_rate": 1.4710630900382e-05,
|
| 2193 |
+
"loss": 1.847,
|
| 2194 |
+
"step": 312
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 1.2935400516795865,
|
| 2198 |
+
"grad_norm": 0.18989123404026031,
|
| 2199 |
+
"learning_rate": 1.455984681253787e-05,
|
| 2200 |
+
"loss": 1.8623,
|
| 2201 |
+
"step": 313
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 1.2976744186046512,
|
| 2205 |
+
"grad_norm": 0.18016654253005981,
|
| 2206 |
+
"learning_rate": 1.4409521339786808e-05,
|
| 2207 |
+
"loss": 1.8888,
|
| 2208 |
+
"step": 314
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 1.3018087855297158,
|
| 2212 |
+
"grad_norm": 0.26387009024620056,
|
| 2213 |
+
"learning_rate": 1.4259661085626801e-05,
|
| 2214 |
+
"loss": 1.8331,
|
| 2215 |
+
"step": 315
|
| 2216 |
+
},
|
| 2217 |
+
{
|
| 2218 |
+
"epoch": 1.3059431524547804,
|
| 2219 |
+
"grad_norm": 0.18496732413768768,
|
| 2220 |
+
"learning_rate": 1.4110272633119753e-05,
|
| 2221 |
+
"loss": 1.8092,
|
| 2222 |
+
"step": 316
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 1.310077519379845,
|
| 2226 |
+
"grad_norm": 0.20513956248760223,
|
| 2227 |
+
"learning_rate": 1.3961362544602213e-05,
|
| 2228 |
+
"loss": 1.8703,
|
| 2229 |
+
"step": 317
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 1.3142118863049095,
|
| 2233 |
+
"grad_norm": 0.20781855285167694,
|
| 2234 |
+
"learning_rate": 1.3812937361397165e-05,
|
| 2235 |
+
"loss": 1.872,
|
| 2236 |
+
"step": 318
|
| 2237 |
+
},
|
| 2238 |
+
{
|
| 2239 |
+
"epoch": 1.3183462532299741,
|
| 2240 |
+
"grad_norm": 0.20270758867263794,
|
| 2241 |
+
"learning_rate": 1.3665003603526705e-05,
|
| 2242 |
+
"loss": 1.8474,
|
| 2243 |
+
"step": 319
|
| 2244 |
+
},
|
| 2245 |
+
{
|
| 2246 |
+
"epoch": 1.3224806201550388,
|
| 2247 |
+
"grad_norm": 0.18668363988399506,
|
| 2248 |
+
"learning_rate": 1.3517567769425548e-05,
|
| 2249 |
+
"loss": 1.8529,
|
| 2250 |
+
"step": 320
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"epoch": 1.3266149870801034,
|
| 2254 |
+
"grad_norm": 0.1695103645324707,
|
| 2255 |
+
"learning_rate": 1.3370636335655656e-05,
|
| 2256 |
+
"loss": 1.8471,
|
| 2257 |
+
"step": 321
|
| 2258 |
+
},
|
| 2259 |
+
{
|
| 2260 |
+
"epoch": 1.330749354005168,
|
| 2261 |
+
"grad_norm": 0.2262444943189621,
|
| 2262 |
+
"learning_rate": 1.3224215756621652e-05,
|
| 2263 |
+
"loss": 1.8375,
|
| 2264 |
+
"step": 322
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 1.3348837209302324,
|
| 2268 |
+
"grad_norm": 0.18921975791454315,
|
| 2269 |
+
"learning_rate": 1.3078312464287353e-05,
|
| 2270 |
+
"loss": 1.8213,
|
| 2271 |
+
"step": 323
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 1.339018087855297,
|
| 2275 |
+
"grad_norm": 0.19748994708061218,
|
| 2276 |
+
"learning_rate": 1.2932932867893189e-05,
|
| 2277 |
+
"loss": 1.8426,
|
| 2278 |
+
"step": 324
|
| 2279 |
+
},
|
| 2280 |
+
{
|
| 2281 |
+
"epoch": 1.3431524547803617,
|
| 2282 |
+
"grad_norm": 0.1982879638671875,
|
| 2283 |
+
"learning_rate": 1.2788083353674693e-05,
|
| 2284 |
+
"loss": 1.8597,
|
| 2285 |
+
"step": 325
|
| 2286 |
+
},
|
| 2287 |
+
{
|
| 2288 |
+
"epoch": 1.3472868217054264,
|
| 2289 |
+
"grad_norm": 0.1821087747812271,
|
| 2290 |
+
"learning_rate": 1.2643770284581929e-05,
|
| 2291 |
+
"loss": 1.8445,
|
| 2292 |
+
"step": 326
|
| 2293 |
+
},
|
| 2294 |
+
{
|
| 2295 |
+
"epoch": 1.351421188630491,
|
| 2296 |
+
"grad_norm": 0.19799095392227173,
|
| 2297 |
+
"learning_rate": 1.2500000000000006e-05,
|
| 2298 |
+
"loss": 1.8973,
|
| 2299 |
+
"step": 327
|
| 2300 |
+
},
|
| 2301 |
+
{
|
| 2302 |
+
"epoch": 1.3555555555555556,
|
| 2303 |
+
"grad_norm": 0.18797126412391663,
|
| 2304 |
+
"learning_rate": 1.2356778815470573e-05,
|
| 2305 |
+
"loss": 1.8589,
|
| 2306 |
+
"step": 328
|
| 2307 |
+
},
|
| 2308 |
+
{
|
| 2309 |
+
"epoch": 1.3596899224806203,
|
| 2310 |
+
"grad_norm": 0.18349631130695343,
|
| 2311 |
+
"learning_rate": 1.2214113022414448e-05,
|
| 2312 |
+
"loss": 1.8268,
|
| 2313 |
+
"step": 329
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 1.3638242894056847,
|
| 2317 |
+
"grad_norm": 0.21064315736293793,
|
| 2318 |
+
"learning_rate": 1.2072008887855174e-05,
|
| 2319 |
+
"loss": 1.864,
|
| 2320 |
+
"step": 330
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 1.3679586563307493,
|
| 2324 |
+
"grad_norm": 0.1751461923122406,
|
| 2325 |
+
"learning_rate": 1.1930472654143776e-05,
|
| 2326 |
+
"loss": 1.8236,
|
| 2327 |
+
"step": 331
|
| 2328 |
+
},
|
| 2329 |
+
{
|
| 2330 |
+
"epoch": 1.372093023255814,
|
| 2331 |
+
"grad_norm": 0.18579532206058502,
|
| 2332 |
+
"learning_rate": 1.1789510538684523e-05,
|
| 2333 |
+
"loss": 1.8804,
|
| 2334 |
+
"step": 332
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 1.3762273901808786,
|
| 2338 |
+
"grad_norm": 0.19961760938167572,
|
| 2339 |
+
"learning_rate": 1.1649128733661802e-05,
|
| 2340 |
+
"loss": 1.8574,
|
| 2341 |
+
"step": 333
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"epoch": 1.3803617571059432,
|
| 2345 |
+
"grad_norm": 0.2009255290031433,
|
| 2346 |
+
"learning_rate": 1.1509333405768152e-05,
|
| 2347 |
+
"loss": 1.9211,
|
| 2348 |
+
"step": 334
|
| 2349 |
+
},
|
| 2350 |
+
{
|
| 2351 |
+
"epoch": 1.3844961240310076,
|
| 2352 |
+
"grad_norm": 0.2043604701757431,
|
| 2353 |
+
"learning_rate": 1.1370130695933318e-05,
|
| 2354 |
+
"loss": 1.8639,
|
| 2355 |
+
"step": 335
|
| 2356 |
+
},
|
| 2357 |
+
{
|
| 2358 |
+
"epoch": 1.3886304909560723,
|
| 2359 |
+
"grad_norm": 0.18864208459854126,
|
| 2360 |
+
"learning_rate": 1.123152671905451e-05,
|
| 2361 |
+
"loss": 1.8409,
|
| 2362 |
+
"step": 336
|
| 2363 |
+
},
|
| 2364 |
+
{
|
| 2365 |
+
"epoch": 1.392764857881137,
|
| 2366 |
+
"grad_norm": 0.20896248519420624,
|
| 2367 |
+
"learning_rate": 1.1093527563727827e-05,
|
| 2368 |
+
"loss": 1.8612,
|
| 2369 |
+
"step": 337
|
| 2370 |
+
},
|
| 2371 |
+
{
|
| 2372 |
+
"epoch": 1.3968992248062015,
|
| 2373 |
+
"grad_norm": 0.20292700827121735,
|
| 2374 |
+
"learning_rate": 1.0956139291980727e-05,
|
| 2375 |
+
"loss": 1.8504,
|
| 2376 |
+
"step": 338
|
| 2377 |
+
},
|
| 2378 |
+
{
|
| 2379 |
+
"epoch": 1.4010335917312662,
|
| 2380 |
+
"grad_norm": 0.1956772804260254,
|
| 2381 |
+
"learning_rate": 1.08193679390058e-05,
|
| 2382 |
+
"loss": 1.8497,
|
| 2383 |
+
"step": 339
|
| 2384 |
+
},
|
| 2385 |
+
{
|
| 2386 |
+
"epoch": 1.4051679586563308,
|
| 2387 |
+
"grad_norm": 0.16064977645874023,
|
| 2388 |
+
"learning_rate": 1.0683219512895612e-05,
|
| 2389 |
+
"loss": 1.8579,
|
| 2390 |
+
"step": 340
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"epoch": 1.4093023255813955,
|
| 2394 |
+
"grad_norm": 0.2131696343421936,
|
| 2395 |
+
"learning_rate": 1.0547699994378787e-05,
|
| 2396 |
+
"loss": 1.8193,
|
| 2397 |
+
"step": 341
|
| 2398 |
+
},
|
| 2399 |
+
{
|
| 2400 |
+
"epoch": 1.4134366925064599,
|
| 2401 |
+
"grad_norm": 0.2008764147758484,
|
| 2402 |
+
"learning_rate": 1.0412815336557316e-05,
|
| 2403 |
+
"loss": 1.8528,
|
| 2404 |
+
"step": 342
|
| 2405 |
+
},
|
| 2406 |
+
{
|
| 2407 |
+
"epoch": 1.4175710594315245,
|
| 2408 |
+
"grad_norm": 0.18327774107456207,
|
| 2409 |
+
"learning_rate": 1.0278571464645011e-05,
|
| 2410 |
+
"loss": 1.8185,
|
| 2411 |
+
"step": 343
|
| 2412 |
+
},
|
| 2413 |
+
{
|
| 2414 |
+
"epoch": 1.4217054263565891,
|
| 2415 |
+
"grad_norm": 0.1845582276582718,
|
| 2416 |
+
"learning_rate": 1.0144974275707241e-05,
|
| 2417 |
+
"loss": 1.8597,
|
| 2418 |
+
"step": 344
|
| 2419 |
+
},
|
| 2420 |
+
{
|
| 2421 |
+
"epoch": 1.4258397932816538,
|
| 2422 |
+
"grad_norm": 0.1995762288570404,
|
| 2423 |
+
"learning_rate": 1.001202963840187e-05,
|
| 2424 |
+
"loss": 1.8352,
|
| 2425 |
+
"step": 345
|
| 2426 |
+
},
|
| 2427 |
+
{
|
| 2428 |
+
"epoch": 1.4299741602067184,
|
| 2429 |
+
"grad_norm": 0.19521230459213257,
|
| 2430 |
+
"learning_rate": 9.879743392721506e-06,
|
| 2431 |
+
"loss": 1.8801,
|
| 2432 |
+
"step": 346
|
| 2433 |
+
},
|
| 2434 |
+
{
|
| 2435 |
+
"epoch": 1.4341085271317828,
|
| 2436 |
+
"grad_norm": 0.21650588512420654,
|
| 2437 |
+
"learning_rate": 9.748121349736892e-06,
|
| 2438 |
+
"loss": 1.8583,
|
| 2439 |
+
"step": 347
|
| 2440 |
+
},
|
| 2441 |
+
{
|
| 2442 |
+
"epoch": 1.4382428940568475,
|
| 2443 |
+
"grad_norm": 0.17347323894500732,
|
| 2444 |
+
"learning_rate": 9.617169291341689e-06,
|
| 2445 |
+
"loss": 1.875,
|
| 2446 |
+
"step": 348
|
| 2447 |
+
},
|
| 2448 |
+
{
|
| 2449 |
+
"epoch": 1.442377260981912,
|
| 2450 |
+
"grad_norm": 0.18423159420490265,
|
| 2451 |
+
"learning_rate": 9.486892969998465e-06,
|
| 2452 |
+
"loss": 1.8851,
|
| 2453 |
+
"step": 349
|
| 2454 |
+
},
|
| 2455 |
+
{
|
| 2456 |
+
"epoch": 1.4465116279069767,
|
| 2457 |
+
"grad_norm": 0.25296011567115784,
|
| 2458 |
+
"learning_rate": 9.357298108486003e-06,
|
| 2459 |
+
"loss": 1.8454,
|
| 2460 |
+
"step": 350
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 1.4506459948320414,
|
| 2464 |
+
"grad_norm": 0.2038068175315857,
|
| 2465 |
+
"learning_rate": 9.228390399647943e-06,
|
| 2466 |
+
"loss": 1.8602,
|
| 2467 |
+
"step": 351
|
| 2468 |
+
},
|
| 2469 |
+
{
|
| 2470 |
+
"epoch": 1.454780361757106,
|
| 2471 |
+
"grad_norm": 0.18208502233028412,
|
| 2472 |
+
"learning_rate": 9.10017550614265e-06,
|
| 2473 |
+
"loss": 1.8836,
|
| 2474 |
+
"step": 352
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 1.4589147286821706,
|
| 2478 |
+
"grad_norm": 0.24106204509735107,
|
| 2479 |
+
"learning_rate": 8.972659060194506e-06,
|
| 2480 |
+
"loss": 1.8628,
|
| 2481 |
+
"step": 353
|
| 2482 |
+
},
|
| 2483 |
+
{
|
| 2484 |
+
"epoch": 1.463049095607235,
|
| 2485 |
+
"grad_norm": 0.216403067111969,
|
| 2486 |
+
"learning_rate": 8.845846663346472e-06,
|
| 2487 |
+
"loss": 1.8457,
|
| 2488 |
+
"step": 354
|
| 2489 |
+
},
|
| 2490 |
+
{
|
| 2491 |
+
"epoch": 1.4671834625322997,
|
| 2492 |
+
"grad_norm": 0.18808472156524658,
|
| 2493 |
+
"learning_rate": 8.71974388621407e-06,
|
| 2494 |
+
"loss": 1.8254,
|
| 2495 |
+
"step": 355
|
| 2496 |
+
},
|
| 2497 |
+
{
|
| 2498 |
+
"epoch": 1.4713178294573643,
|
| 2499 |
+
"grad_norm": 0.17452962696552277,
|
| 2500 |
+
"learning_rate": 8.594356268240616e-06,
|
| 2501 |
+
"loss": 1.8711,
|
| 2502 |
+
"step": 356
|
| 2503 |
+
},
|
| 2504 |
+
{
|
| 2505 |
+
"epoch": 1.475452196382429,
|
| 2506 |
+
"grad_norm": 0.1923353523015976,
|
| 2507 |
+
"learning_rate": 8.469689317453908e-06,
|
| 2508 |
+
"loss": 1.8553,
|
| 2509 |
+
"step": 357
|
| 2510 |
+
},
|
| 2511 |
+
{
|
| 2512 |
+
"epoch": 1.4795865633074936,
|
| 2513 |
+
"grad_norm": 0.20313896238803864,
|
| 2514 |
+
"learning_rate": 8.345748510224299e-06,
|
| 2515 |
+
"loss": 1.8525,
|
| 2516 |
+
"step": 358
|
| 2517 |
+
},
|
| 2518 |
+
{
|
| 2519 |
+
"epoch": 1.483720930232558,
|
| 2520 |
+
"grad_norm": 0.20086300373077393,
|
| 2521 |
+
"learning_rate": 8.222539291024078e-06,
|
| 2522 |
+
"loss": 1.9113,
|
| 2523 |
+
"step": 359
|
| 2524 |
+
},
|
| 2525 |
+
{
|
| 2526 |
+
"epoch": 1.4878552971576227,
|
| 2527 |
+
"grad_norm": 0.19821697473526,
|
| 2528 |
+
"learning_rate": 8.100067072188356e-06,
|
| 2529 |
+
"loss": 1.8571,
|
| 2530 |
+
"step": 360
|
| 2531 |
+
},
|
| 2532 |
+
{
|
| 2533 |
+
"epoch": 1.4919896640826873,
|
| 2534 |
+
"grad_norm": 0.18931037187576294,
|
| 2535 |
+
"learning_rate": 7.978337233677268e-06,
|
| 2536 |
+
"loss": 1.8458,
|
| 2537 |
+
"step": 361
|
| 2538 |
+
},
|
| 2539 |
+
{
|
| 2540 |
+
"epoch": 1.496124031007752,
|
| 2541 |
+
"grad_norm": 0.23735098540782928,
|
| 2542 |
+
"learning_rate": 7.857355122839675e-06,
|
| 2543 |
+
"loss": 1.8726,
|
| 2544 |
+
"step": 362
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 1.5002583979328166,
|
| 2548 |
+
"grad_norm": 0.1827445924282074,
|
| 2549 |
+
"learning_rate": 7.737126054178237e-06,
|
| 2550 |
+
"loss": 1.8668,
|
| 2551 |
+
"step": 363
|
| 2552 |
+
},
|
| 2553 |
+
{
|
| 2554 |
+
"epoch": 1.5043927648578812,
|
| 2555 |
+
"grad_norm": 0.17717576026916504,
|
| 2556 |
+
"learning_rate": 7.617655309116009e-06,
|
| 2557 |
+
"loss": 1.8788,
|
| 2558 |
+
"step": 364
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 1.5085271317829458,
|
| 2562 |
+
"grad_norm": 0.19759993255138397,
|
| 2563 |
+
"learning_rate": 7.4989481357643694e-06,
|
| 2564 |
+
"loss": 1.8416,
|
| 2565 |
+
"step": 365
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"epoch": 1.5126614987080105,
|
| 2569 |
+
"grad_norm": 0.19131886959075928,
|
| 2570 |
+
"learning_rate": 7.381009748692527e-06,
|
| 2571 |
+
"loss": 1.8633,
|
| 2572 |
+
"step": 366
|
| 2573 |
+
},
|
| 2574 |
+
{
|
| 2575 |
+
"epoch": 1.516795865633075,
|
| 2576 |
+
"grad_norm": 0.18006229400634766,
|
| 2577 |
+
"learning_rate": 7.26384532869844e-06,
|
| 2578 |
+
"loss": 1.8743,
|
| 2579 |
+
"step": 367
|
| 2580 |
+
},
|
| 2581 |
+
{
|
| 2582 |
+
"epoch": 1.5209302325581395,
|
| 2583 |
+
"grad_norm": 0.17648297548294067,
|
| 2584 |
+
"learning_rate": 7.147460022581257e-06,
|
| 2585 |
+
"loss": 1.8014,
|
| 2586 |
+
"step": 368
|
| 2587 |
+
},
|
| 2588 |
+
{
|
| 2589 |
+
"epoch": 1.5250645994832042,
|
| 2590 |
+
"grad_norm": 0.1885407716035843,
|
| 2591 |
+
"learning_rate": 7.031858942915187e-06,
|
| 2592 |
+
"loss": 1.8386,
|
| 2593 |
+
"step": 369
|
| 2594 |
+
},
|
| 2595 |
+
{
|
| 2596 |
+
"epoch": 1.5291989664082686,
|
| 2597 |
+
"grad_norm": 0.2143668383359909,
|
| 2598 |
+
"learning_rate": 6.917047167824939e-06,
|
| 2599 |
+
"loss": 1.8405,
|
| 2600 |
+
"step": 370
|
| 2601 |
+
},
|
| 2602 |
+
{
|
| 2603 |
+
"epoch": 1.5333333333333332,
|
| 2604 |
+
"grad_norm": 0.1826908141374588,
|
| 2605 |
+
"learning_rate": 6.803029740762648e-06,
|
| 2606 |
+
"loss": 1.83,
|
| 2607 |
+
"step": 371
|
| 2608 |
+
},
|
| 2609 |
+
{
|
| 2610 |
+
"epoch": 1.5374677002583979,
|
| 2611 |
+
"grad_norm": 0.21032436192035675,
|
| 2612 |
+
"learning_rate": 6.689811670286342e-06,
|
| 2613 |
+
"loss": 1.8482,
|
| 2614 |
+
"step": 372
|
| 2615 |
+
},
|
| 2616 |
+
{
|
| 2617 |
+
"epoch": 1.5416020671834625,
|
| 2618 |
+
"grad_norm": 0.18171337246894836,
|
| 2619 |
+
"learning_rate": 6.57739792983989e-06,
|
| 2620 |
+
"loss": 1.8653,
|
| 2621 |
+
"step": 373
|
| 2622 |
+
},
|
| 2623 |
+
{
|
| 2624 |
+
"epoch": 1.5457364341085271,
|
| 2625 |
+
"grad_norm": 0.20828919112682343,
|
| 2626 |
+
"learning_rate": 6.465793457534553e-06,
|
| 2627 |
+
"loss": 1.8693,
|
| 2628 |
+
"step": 374
|
| 2629 |
+
},
|
| 2630 |
+
{
|
| 2631 |
+
"epoch": 1.5498708010335918,
|
| 2632 |
+
"grad_norm": 0.1902620643377304,
|
| 2633 |
+
"learning_rate": 6.355003155932052e-06,
|
| 2634 |
+
"loss": 1.8395,
|
| 2635 |
+
"step": 375
|
| 2636 |
+
},
|
| 2637 |
+
{
|
| 2638 |
+
"epoch": 1.5540051679586564,
|
| 2639 |
+
"grad_norm": 0.22342999279499054,
|
| 2640 |
+
"learning_rate": 6.245031891829237e-06,
|
| 2641 |
+
"loss": 1.8553,
|
| 2642 |
+
"step": 376
|
| 2643 |
+
},
|
| 2644 |
+
{
|
| 2645 |
+
"epoch": 1.558139534883721,
|
| 2646 |
+
"grad_norm": 0.15861107409000397,
|
| 2647 |
+
"learning_rate": 6.135884496044244e-06,
|
| 2648 |
+
"loss": 1.8392,
|
| 2649 |
+
"step": 377
|
| 2650 |
+
},
|
| 2651 |
+
{
|
| 2652 |
+
"epoch": 1.5622739018087857,
|
| 2653 |
+
"grad_norm": 0.19485320150852203,
|
| 2654 |
+
"learning_rate": 6.0275657632043485e-06,
|
| 2655 |
+
"loss": 1.8382,
|
| 2656 |
+
"step": 378
|
| 2657 |
+
},
|
| 2658 |
+
{
|
| 2659 |
+
"epoch": 1.56640826873385,
|
| 2660 |
+
"grad_norm": 0.20382657647132874,
|
| 2661 |
+
"learning_rate": 5.920080451535295e-06,
|
| 2662 |
+
"loss": 1.8157,
|
| 2663 |
+
"step": 379
|
| 2664 |
+
},
|
| 2665 |
+
{
|
| 2666 |
+
"epoch": 1.5705426356589147,
|
| 2667 |
+
"grad_norm": 0.1930224895477295,
|
| 2668 |
+
"learning_rate": 5.813433282652298e-06,
|
| 2669 |
+
"loss": 1.8271,
|
| 2670 |
+
"step": 380
|
| 2671 |
+
},
|
| 2672 |
+
{
|
| 2673 |
+
"epoch": 1.5746770025839794,
|
| 2674 |
+
"grad_norm": 0.1832059770822525,
|
| 2675 |
+
"learning_rate": 5.7076289413526554e-06,
|
| 2676 |
+
"loss": 1.8964,
|
| 2677 |
+
"step": 381
|
| 2678 |
+
},
|
| 2679 |
+
{
|
| 2680 |
+
"epoch": 1.5788113695090438,
|
| 2681 |
+
"grad_norm": 0.19555340707302094,
|
| 2682 |
+
"learning_rate": 5.602672075409904e-06,
|
| 2683 |
+
"loss": 1.83,
|
| 2684 |
+
"step": 382
|
| 2685 |
+
},
|
| 2686 |
+
{
|
| 2687 |
+
"epoch": 1.5829457364341084,
|
| 2688 |
+
"grad_norm": 0.1941136121749878,
|
| 2689 |
+
"learning_rate": 5.4985672953697e-06,
|
| 2690 |
+
"loss": 1.8695,
|
| 2691 |
+
"step": 383
|
| 2692 |
+
},
|
| 2693 |
+
{
|
| 2694 |
+
"epoch": 1.587080103359173,
|
| 2695 |
+
"grad_norm": 0.1988084316253662,
|
| 2696 |
+
"learning_rate": 5.395319174347244e-06,
|
| 2697 |
+
"loss": 1.8578,
|
| 2698 |
+
"step": 384
|
| 2699 |
+
},
|
| 2700 |
+
{
|
| 2701 |
+
"epoch": 1.5912144702842377,
|
| 2702 |
+
"grad_norm": 0.17628000676631927,
|
| 2703 |
+
"learning_rate": 5.292932247826449e-06,
|
| 2704 |
+
"loss": 1.8401,
|
| 2705 |
+
"step": 385
|
| 2706 |
+
},
|
| 2707 |
+
{
|
| 2708 |
+
"epoch": 1.5953488372093023,
|
| 2709 |
+
"grad_norm": 0.19002149999141693,
|
| 2710 |
+
"learning_rate": 5.191411013460645e-06,
|
| 2711 |
+
"loss": 1.8087,
|
| 2712 |
+
"step": 386
|
| 2713 |
+
},
|
| 2714 |
+
{
|
| 2715 |
+
"epoch": 1.599483204134367,
|
| 2716 |
+
"grad_norm": 0.22312882542610168,
|
| 2717 |
+
"learning_rate": 5.090759930875039e-06,
|
| 2718 |
+
"loss": 1.8407,
|
| 2719 |
+
"step": 387
|
| 2720 |
+
},
|
| 2721 |
+
{
|
| 2722 |
+
"epoch": 1.6036175710594316,
|
| 2723 |
+
"grad_norm": 0.20014852285385132,
|
| 2724 |
+
"learning_rate": 4.990983421470813e-06,
|
| 2725 |
+
"loss": 1.8525,
|
| 2726 |
+
"step": 388
|
| 2727 |
+
},
|
| 2728 |
+
{
|
| 2729 |
+
"epoch": 1.6077519379844962,
|
| 2730 |
+
"grad_norm": 0.19950371980667114,
|
| 2731 |
+
"learning_rate": 4.892085868230881e-06,
|
| 2732 |
+
"loss": 1.9135,
|
| 2733 |
+
"step": 389
|
| 2734 |
+
},
|
| 2735 |
+
{
|
| 2736 |
+
"epoch": 1.6118863049095609,
|
| 2737 |
+
"grad_norm": 0.1741892695426941,
|
| 2738 |
+
"learning_rate": 4.794071615527393e-06,
|
| 2739 |
+
"loss": 1.8808,
|
| 2740 |
+
"step": 390
|
| 2741 |
+
},
|
| 2742 |
+
{
|
| 2743 |
+
"epoch": 1.6160206718346253,
|
| 2744 |
+
"grad_norm": 0.1951276808977127,
|
| 2745 |
+
"learning_rate": 4.696944968930847e-06,
|
| 2746 |
+
"loss": 1.822,
|
| 2747 |
+
"step": 391
|
| 2748 |
+
},
|
| 2749 |
+
{
|
| 2750 |
+
"epoch": 1.62015503875969,
|
| 2751 |
+
"grad_norm": 0.17192859947681427,
|
| 2752 |
+
"learning_rate": 4.600710195020982e-06,
|
| 2753 |
+
"loss": 1.8732,
|
| 2754 |
+
"step": 392
|
| 2755 |
+
},
|
| 2756 |
+
{
|
| 2757 |
+
"epoch": 1.6242894056847546,
|
| 2758 |
+
"grad_norm": 0.19662202894687653,
|
| 2759 |
+
"learning_rate": 4.505371521199342e-06,
|
| 2760 |
+
"loss": 1.8418,
|
| 2761 |
+
"step": 393
|
| 2762 |
+
},
|
| 2763 |
+
{
|
| 2764 |
+
"epoch": 1.628423772609819,
|
| 2765 |
+
"grad_norm": 0.18868209421634674,
|
| 2766 |
+
"learning_rate": 4.4109331355036085e-06,
|
| 2767 |
+
"loss": 1.815,
|
| 2768 |
+
"step": 394
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 1.6325581395348836,
|
| 2772 |
+
"grad_norm": 0.1861567199230194,
|
| 2773 |
+
"learning_rate": 4.317399186423574e-06,
|
| 2774 |
+
"loss": 1.8274,
|
| 2775 |
+
"step": 395
|
| 2776 |
+
},
|
| 2777 |
+
{
|
| 2778 |
+
"epoch": 1.6366925064599482,
|
| 2779 |
+
"grad_norm": 0.21903838217258453,
|
| 2780 |
+
"learning_rate": 4.2247737827189435e-06,
|
| 2781 |
+
"loss": 1.7943,
|
| 2782 |
+
"step": 396
|
| 2783 |
+
},
|
| 2784 |
+
{
|
| 2785 |
+
"epoch": 1.6408268733850129,
|
| 2786 |
+
"grad_norm": 0.17177477478981018,
|
| 2787 |
+
"learning_rate": 4.1330609932388495e-06,
|
| 2788 |
+
"loss": 1.8355,
|
| 2789 |
+
"step": 397
|
| 2790 |
+
},
|
| 2791 |
+
{
|
| 2792 |
+
"epoch": 1.6449612403100775,
|
| 2793 |
+
"grad_norm": 0.1812441051006317,
|
| 2794 |
+
"learning_rate": 4.042264846743085e-06,
|
| 2795 |
+
"loss": 1.8786,
|
| 2796 |
+
"step": 398
|
| 2797 |
+
},
|
| 2798 |
+
{
|
| 2799 |
+
"epoch": 1.6490956072351421,
|
| 2800 |
+
"grad_norm": 0.18601560592651367,
|
| 2801 |
+
"learning_rate": 3.952389331725162e-06,
|
| 2802 |
+
"loss": 1.8485,
|
| 2803 |
+
"step": 399
|
| 2804 |
+
},
|
| 2805 |
+
{
|
| 2806 |
+
"epoch": 1.6532299741602068,
|
| 2807 |
+
"grad_norm": 0.1996539682149887,
|
| 2808 |
+
"learning_rate": 3.863438396237082e-06,
|
| 2809 |
+
"loss": 1.8068,
|
| 2810 |
+
"step": 400
|
| 2811 |
+
},
|
| 2812 |
+
{
|
| 2813 |
+
"epoch": 1.6573643410852714,
|
| 2814 |
+
"grad_norm": 0.28882601857185364,
|
| 2815 |
+
"learning_rate": 3.775415947715899e-06,
|
| 2816 |
+
"loss": 1.7877,
|
| 2817 |
+
"step": 401
|
| 2818 |
+
},
|
| 2819 |
+
{
|
| 2820 |
+
"epoch": 1.661498708010336,
|
| 2821 |
+
"grad_norm": 0.19347411394119263,
|
| 2822 |
+
"learning_rate": 3.6883258528121188e-06,
|
| 2823 |
+
"loss": 1.8659,
|
| 2824 |
+
"step": 402
|
| 2825 |
+
},
|
| 2826 |
+
{
|
| 2827 |
+
"epoch": 1.6656330749354005,
|
| 2828 |
+
"grad_norm": 0.18368688225746155,
|
| 2829 |
+
"learning_rate": 3.602171937219789e-06,
|
| 2830 |
+
"loss": 1.8661,
|
| 2831 |
+
"step": 403
|
| 2832 |
+
},
|
| 2833 |
+
{
|
| 2834 |
+
"epoch": 1.669767441860465,
|
| 2835 |
+
"grad_norm": 0.18610616028308868,
|
| 2836 |
+
"learning_rate": 3.516957985508476e-06,
|
| 2837 |
+
"loss": 1.8701,
|
| 2838 |
+
"step": 404
|
| 2839 |
+
},
|
| 2840 |
+
{
|
| 2841 |
+
"epoch": 1.6739018087855297,
|
| 2842 |
+
"grad_norm": 0.2384355664253235,
|
| 2843 |
+
"learning_rate": 3.432687740957008e-06,
|
| 2844 |
+
"loss": 1.8656,
|
| 2845 |
+
"step": 405
|
| 2846 |
+
},
|
| 2847 |
+
{
|
| 2848 |
+
"epoch": 1.6780361757105942,
|
| 2849 |
+
"grad_norm": 0.18446283042430878,
|
| 2850 |
+
"learning_rate": 3.3493649053890326e-06,
|
| 2851 |
+
"loss": 1.8797,
|
| 2852 |
+
"step": 406
|
| 2853 |
+
},
|
| 2854 |
+
{
|
| 2855 |
+
"epoch": 1.6821705426356588,
|
| 2856 |
+
"grad_norm": 0.16974373161792755,
|
| 2857 |
+
"learning_rate": 3.266993139010438e-06,
|
| 2858 |
+
"loss": 1.8763,
|
| 2859 |
+
"step": 407
|
| 2860 |
+
},
|
| 2861 |
+
{
|
| 2862 |
+
"epoch": 1.6863049095607234,
|
| 2863 |
+
"grad_norm": 0.19293127954006195,
|
| 2864 |
+
"learning_rate": 3.185576060248513e-06,
|
| 2865 |
+
"loss": 1.8886,
|
| 2866 |
+
"step": 408
|
| 2867 |
+
},
|
| 2868 |
+
{
|
| 2869 |
+
"epoch": 1.690439276485788,
|
| 2870 |
+
"grad_norm": 0.16171284019947052,
|
| 2871 |
+
"learning_rate": 3.1051172455930394e-06,
|
| 2872 |
+
"loss": 1.827,
|
| 2873 |
+
"step": 409
|
| 2874 |
+
},
|
| 2875 |
+
{
|
| 2876 |
+
"epoch": 1.6945736434108527,
|
| 2877 |
+
"grad_norm": 0.20056560635566711,
|
| 2878 |
+
"learning_rate": 3.0256202294391577e-06,
|
| 2879 |
+
"loss": 1.83,
|
| 2880 |
+
"step": 410
|
| 2881 |
+
},
|
| 2882 |
+
{
|
| 2883 |
+
"epoch": 1.6987080103359173,
|
| 2884 |
+
"grad_norm": 0.20635955035686493,
|
| 2885 |
+
"learning_rate": 2.9470885039321356e-06,
|
| 2886 |
+
"loss": 1.9031,
|
| 2887 |
+
"step": 411
|
| 2888 |
+
},
|
| 2889 |
+
{
|
| 2890 |
+
"epoch": 1.702842377260982,
|
| 2891 |
+
"grad_norm": 0.19662411510944366,
|
| 2892 |
+
"learning_rate": 2.8695255188139426e-06,
|
| 2893 |
+
"loss": 1.8421,
|
| 2894 |
+
"step": 412
|
| 2895 |
+
},
|
| 2896 |
+
{
|
| 2897 |
+
"epoch": 1.7069767441860466,
|
| 2898 |
+
"grad_norm": 0.20924516022205353,
|
| 2899 |
+
"learning_rate": 2.792934681271708e-06,
|
| 2900 |
+
"loss": 1.799,
|
| 2901 |
+
"step": 413
|
| 2902 |
+
},
|
| 2903 |
+
{
|
| 2904 |
+
"epoch": 1.7111111111111112,
|
| 2905 |
+
"grad_norm": 0.19942612946033478,
|
| 2906 |
+
"learning_rate": 2.7173193557880615e-06,
|
| 2907 |
+
"loss": 1.8414,
|
| 2908 |
+
"step": 414
|
| 2909 |
+
},
|
| 2910 |
+
{
|
| 2911 |
+
"epoch": 1.7152454780361757,
|
| 2912 |
+
"grad_norm": 0.19586698710918427,
|
| 2913 |
+
"learning_rate": 2.6426828639933536e-06,
|
| 2914 |
+
"loss": 1.8484,
|
| 2915 |
+
"step": 415
|
| 2916 |
+
},
|
| 2917 |
+
{
|
| 2918 |
+
"epoch": 1.7193798449612403,
|
| 2919 |
+
"grad_norm": 0.21101996302604675,
|
| 2920 |
+
"learning_rate": 2.5690284845196923e-06,
|
| 2921 |
+
"loss": 1.8877,
|
| 2922 |
+
"step": 416
|
| 2923 |
+
},
|
| 2924 |
+
{
|
| 2925 |
+
"epoch": 1.723514211886305,
|
| 2926 |
+
"grad_norm": 0.20327693223953247,
|
| 2927 |
+
"learning_rate": 2.4963594528569833e-06,
|
| 2928 |
+
"loss": 1.8535,
|
| 2929 |
+
"step": 417
|
| 2930 |
+
},
|
| 2931 |
+
{
|
| 2932 |
+
"epoch": 1.7276485788113694,
|
| 2933 |
+
"grad_norm": 0.17479753494262695,
|
| 2934 |
+
"learning_rate": 2.424678961210747e-06,
|
| 2935 |
+
"loss": 1.8502,
|
| 2936 |
+
"step": 418
|
| 2937 |
+
},
|
| 2938 |
+
{
|
| 2939 |
+
"epoch": 1.731782945736434,
|
| 2940 |
+
"grad_norm": 0.2092328816652298,
|
| 2941 |
+
"learning_rate": 2.3539901583619185e-06,
|
| 2942 |
+
"loss": 1.8292,
|
| 2943 |
+
"step": 419
|
| 2944 |
+
},
|
| 2945 |
+
{
|
| 2946 |
+
"epoch": 1.7359173126614986,
|
| 2947 |
+
"grad_norm": 0.18599312007427216,
|
| 2948 |
+
"learning_rate": 2.2842961495285335e-06,
|
| 2949 |
+
"loss": 1.8694,
|
| 2950 |
+
"step": 420
|
| 2951 |
+
},
|
| 2952 |
+
{
|
| 2953 |
+
"epoch": 1.7400516795865633,
|
| 2954 |
+
"grad_norm": 0.2305494248867035,
|
| 2955 |
+
"learning_rate": 2.2155999962293033e-06,
|
| 2956 |
+
"loss": 1.7625,
|
| 2957 |
+
"step": 421
|
| 2958 |
+
},
|
| 2959 |
+
{
|
| 2960 |
+
"epoch": 1.744186046511628,
|
| 2961 |
+
"grad_norm": 0.19540861248970032,
|
| 2962 |
+
"learning_rate": 2.147904716149135e-06,
|
| 2963 |
+
"loss": 1.8017,
|
| 2964 |
+
"step": 422
|
| 2965 |
+
},
|
| 2966 |
+
{
|
| 2967 |
+
"epoch": 1.7483204134366925,
|
| 2968 |
+
"grad_norm": 0.20109935104846954,
|
| 2969 |
+
"learning_rate": 2.081213283006575e-06,
|
| 2970 |
+
"loss": 1.8337,
|
| 2971 |
+
"step": 423
|
| 2972 |
+
},
|
| 2973 |
+
{
|
| 2974 |
+
"epoch": 1.7524547803617572,
|
| 2975 |
+
"grad_norm": 0.20418094098567963,
|
| 2976 |
+
"learning_rate": 2.0155286264231856e-06,
|
| 2977 |
+
"loss": 1.8175,
|
| 2978 |
+
"step": 424
|
| 2979 |
+
},
|
| 2980 |
+
{
|
| 2981 |
+
"epoch": 1.7565891472868218,
|
| 2982 |
+
"grad_norm": 0.2459726333618164,
|
| 2983 |
+
"learning_rate": 1.9508536317948357e-06,
|
| 2984 |
+
"loss": 1.8493,
|
| 2985 |
+
"step": 425
|
| 2986 |
+
},
|
| 2987 |
+
{
|
| 2988 |
+
"epoch": 1.7607235142118864,
|
| 2989 |
+
"grad_norm": 0.19009703397750854,
|
| 2990 |
+
"learning_rate": 1.887191140164954e-06,
|
| 2991 |
+
"loss": 1.8613,
|
| 2992 |
+
"step": 426
|
| 2993 |
+
},
|
| 2994 |
+
{
|
| 2995 |
+
"epoch": 1.7648578811369509,
|
| 2996 |
+
"grad_norm": 0.19595322012901306,
|
| 2997 |
+
"learning_rate": 1.8245439480997439e-06,
|
| 2998 |
+
"loss": 1.8511,
|
| 2999 |
+
"step": 427
|
| 3000 |
+
},
|
| 3001 |
+
{
|
| 3002 |
+
"epoch": 1.7689922480620155,
|
| 3003 |
+
"grad_norm": 0.21671347320079803,
|
| 3004 |
+
"learning_rate": 1.7629148075653245e-06,
|
| 3005 |
+
"loss": 1.8711,
|
| 3006 |
+
"step": 428
|
| 3007 |
+
},
|
| 3008 |
+
{
|
| 3009 |
+
"epoch": 1.7731266149870801,
|
| 3010 |
+
"grad_norm": 0.19006803631782532,
|
| 3011 |
+
"learning_rate": 1.7023064258068377e-06,
|
| 3012 |
+
"loss": 1.8665,
|
| 3013 |
+
"step": 429
|
| 3014 |
+
},
|
| 3015 |
+
{
|
| 3016 |
+
"epoch": 1.7772609819121445,
|
| 3017 |
+
"grad_norm": 0.1733352094888687,
|
| 3018 |
+
"learning_rate": 1.6427214652295326e-06,
|
| 3019 |
+
"loss": 1.8085,
|
| 3020 |
+
"step": 430
|
| 3021 |
+
},
|
| 3022 |
+
{
|
| 3023 |
+
"epoch": 1.7813953488372092,
|
| 3024 |
+
"grad_norm": 0.2013574093580246,
|
| 3025 |
+
"learning_rate": 1.5841625432818057e-06,
|
| 3026 |
+
"loss": 1.8855,
|
| 3027 |
+
"step": 431
|
| 3028 |
+
},
|
| 3029 |
+
{
|
| 3030 |
+
"epoch": 1.7855297157622738,
|
| 3031 |
+
"grad_norm": 0.19347961246967316,
|
| 3032 |
+
"learning_rate": 1.5266322323402277e-06,
|
| 3033 |
+
"loss": 1.9024,
|
| 3034 |
+
"step": 432
|
| 3035 |
+
},
|
| 3036 |
+
{
|
| 3037 |
+
"epoch": 1.7896640826873385,
|
| 3038 |
+
"grad_norm": 0.22144848108291626,
|
| 3039 |
+
"learning_rate": 1.4701330595965402e-06,
|
| 3040 |
+
"loss": 1.864,
|
| 3041 |
+
"step": 433
|
| 3042 |
+
},
|
| 3043 |
+
{
|
| 3044 |
+
"epoch": 1.793798449612403,
|
| 3045 |
+
"grad_norm": 0.21104314923286438,
|
| 3046 |
+
"learning_rate": 1.4146675069466403e-06,
|
| 3047 |
+
"loss": 1.8587,
|
| 3048 |
+
"step": 434
|
| 3049 |
+
},
|
| 3050 |
+
{
|
| 3051 |
+
"epoch": 1.7979328165374677,
|
| 3052 |
+
"grad_norm": 0.2236236184835434,
|
| 3053 |
+
"learning_rate": 1.3602380108815537e-06,
|
| 3054 |
+
"loss": 1.8191,
|
| 3055 |
+
"step": 435
|
| 3056 |
+
},
|
| 3057 |
+
{
|
| 3058 |
+
"epoch": 1.8020671834625324,
|
| 3059 |
+
"grad_norm": 0.19607210159301758,
|
| 3060 |
+
"learning_rate": 1.3068469623804176e-06,
|
| 3061 |
+
"loss": 1.8353,
|
| 3062 |
+
"step": 436
|
| 3063 |
+
},
|
| 3064 |
+
{
|
| 3065 |
+
"epoch": 1.806201550387597,
|
| 3066 |
+
"grad_norm": 0.16851356625556946,
|
| 3067 |
+
"learning_rate": 1.2544967068054332e-06,
|
| 3068 |
+
"loss": 1.824,
|
| 3069 |
+
"step": 437
|
| 3070 |
+
},
|
| 3071 |
+
{
|
| 3072 |
+
"epoch": 1.8103359173126616,
|
| 3073 |
+
"grad_norm": 0.1863081455230713,
|
| 3074 |
+
"learning_rate": 1.2031895437988493e-06,
|
| 3075 |
+
"loss": 1.8875,
|
| 3076 |
+
"step": 438
|
| 3077 |
+
},
|
| 3078 |
+
{
|
| 3079 |
+
"epoch": 1.814470284237726,
|
| 3080 |
+
"grad_norm": 0.20593047142028809,
|
| 3081 |
+
"learning_rate": 1.152927727181935e-06,
|
| 3082 |
+
"loss": 1.8507,
|
| 3083 |
+
"step": 439
|
| 3084 |
+
},
|
| 3085 |
+
{
|
| 3086 |
+
"epoch": 1.8186046511627907,
|
| 3087 |
+
"grad_norm": 0.15861834585666656,
|
| 3088 |
+
"learning_rate": 1.1037134648559794e-06,
|
| 3089 |
+
"loss": 1.867,
|
| 3090 |
+
"step": 440
|
| 3091 |
+
},
|
| 3092 |
+
{
|
| 3093 |
+
"epoch": 1.8227390180878553,
|
| 3094 |
+
"grad_norm": 0.20093533396720886,
|
| 3095 |
+
"learning_rate": 1.0555489187053096e-06,
|
| 3096 |
+
"loss": 1.8777,
|
| 3097 |
+
"step": 441
|
| 3098 |
+
},
|
| 3099 |
+
{
|
| 3100 |
+
"epoch": 1.8268733850129197,
|
| 3101 |
+
"grad_norm": 0.18830344080924988,
|
| 3102 |
+
"learning_rate": 1.008436204502311e-06,
|
| 3103 |
+
"loss": 1.8892,
|
| 3104 |
+
"step": 442
|
| 3105 |
+
},
|
| 3106 |
+
{
|
| 3107 |
+
"epoch": 1.8310077519379844,
|
| 3108 |
+
"grad_norm": 0.21135635673999786,
|
| 3109 |
+
"learning_rate": 9.623773918144897e-07,
|
| 3110 |
+
"loss": 1.7744,
|
| 3111 |
+
"step": 443
|
| 3112 |
+
},
|
| 3113 |
+
{
|
| 3114 |
+
"epoch": 1.835142118863049,
|
| 3115 |
+
"grad_norm": 0.1934061348438263,
|
| 3116 |
+
"learning_rate": 9.173745039135622e-07,
|
| 3117 |
+
"loss": 1.8433,
|
| 3118 |
+
"step": 444
|
| 3119 |
+
},
|
| 3120 |
+
{
|
| 3121 |
+
"epoch": 1.8392764857881136,
|
| 3122 |
+
"grad_norm": 0.23742595314979553,
|
| 3123 |
+
"learning_rate": 8.734295176865747e-07,
|
| 3124 |
+
"loss": 1.8294,
|
| 3125 |
+
"step": 445
|
| 3126 |
+
},
|
| 3127 |
+
{
|
| 3128 |
+
"epoch": 1.8434108527131783,
|
| 3129 |
+
"grad_norm": 0.19050028920173645,
|
| 3130 |
+
"learning_rate": 8.305443635490711e-07,
|
| 3131 |
+
"loss": 1.8404,
|
| 3132 |
+
"step": 446
|
| 3133 |
+
},
|
| 3134 |
+
{
|
| 3135 |
+
"epoch": 1.847545219638243,
|
| 3136 |
+
"grad_norm": 0.1853562742471695,
|
| 3137 |
+
"learning_rate": 7.887209253602839e-07,
|
| 3138 |
+
"loss": 1.8432,
|
| 3139 |
+
"step": 447
|
| 3140 |
+
},
|
| 3141 |
+
{
|
| 3142 |
+
"epoch": 1.8516795865633076,
|
| 3143 |
+
"grad_norm": 0.21074078977108002,
|
| 3144 |
+
"learning_rate": 7.479610403403781e-07,
|
| 3145 |
+
"loss": 1.8492,
|
| 3146 |
+
"step": 448
|
| 3147 |
+
},
|
| 3148 |
+
{
|
| 3149 |
+
"epoch": 1.8558139534883722,
|
| 3150 |
+
"grad_norm": 0.19240273535251617,
|
| 3151 |
+
"learning_rate": 7.082664989897487e-07,
|
| 3152 |
+
"loss": 1.8722,
|
| 3153 |
+
"step": 449
|
| 3154 |
+
},
|
| 3155 |
+
{
|
| 3156 |
+
"epoch": 1.8599483204134368,
|
| 3157 |
+
"grad_norm": 0.2002202868461609,
|
| 3158 |
+
"learning_rate": 6.696390450103867e-07,
|
| 3159 |
+
"loss": 1.8855,
|
| 3160 |
+
"step": 450
|
| 3161 |
+
},
|
| 3162 |
+
{
|
| 3163 |
+
"epoch": 1.8640826873385012,
|
| 3164 |
+
"grad_norm": 0.1758432686328888,
|
| 3165 |
+
"learning_rate": 6.320803752292464e-07,
|
| 3166 |
+
"loss": 1.8698,
|
| 3167 |
+
"step": 451
|
| 3168 |
+
},
|
| 3169 |
+
{
|
| 3170 |
+
"epoch": 1.8682170542635659,
|
| 3171 |
+
"grad_norm": 0.20342381298542023,
|
| 3172 |
+
"learning_rate": 5.955921395237318e-07,
|
| 3173 |
+
"loss": 1.8963,
|
| 3174 |
+
"step": 452
|
| 3175 |
+
},
|
| 3176 |
+
{
|
| 3177 |
+
"epoch": 1.8723514211886305,
|
| 3178 |
+
"grad_norm": 0.17242282629013062,
|
| 3179 |
+
"learning_rate": 5.601759407492107e-07,
|
| 3180 |
+
"loss": 1.8047,
|
| 3181 |
+
"step": 453
|
| 3182 |
+
},
|
| 3183 |
+
{
|
| 3184 |
+
"epoch": 1.876485788113695,
|
| 3185 |
+
"grad_norm": 0.30234503746032715,
|
| 3186 |
+
"learning_rate": 5.258333346686211e-07,
|
| 3187 |
+
"loss": 1.7953,
|
| 3188 |
+
"step": 454
|
| 3189 |
+
},
|
| 3190 |
+
{
|
| 3191 |
+
"epoch": 1.8806201550387596,
|
| 3192 |
+
"grad_norm": 0.19324825704097748,
|
| 3193 |
+
"learning_rate": 4.925658298840979e-07,
|
| 3194 |
+
"loss": 1.8466,
|
| 3195 |
+
"step": 455
|
| 3196 |
+
},
|
| 3197 |
+
{
|
| 3198 |
+
"epoch": 1.8847545219638242,
|
| 3199 |
+
"grad_norm": 0.1731712520122528,
|
| 3200 |
+
"learning_rate": 4.603748877707342e-07,
|
| 3201 |
+
"loss": 1.8405,
|
| 3202 |
+
"step": 456
|
| 3203 |
+
},
|
| 3204 |
+
{
|
| 3205 |
+
"epoch": 1.8888888888888888,
|
| 3206 |
+
"grad_norm": 0.2270544171333313,
|
| 3207 |
+
"learning_rate": 4.2926192241237175e-07,
|
| 3208 |
+
"loss": 1.875,
|
| 3209 |
+
"step": 457
|
| 3210 |
+
},
|
| 3211 |
+
{
|
| 3212 |
+
"epoch": 1.8930232558139535,
|
| 3213 |
+
"grad_norm": 0.20387256145477295,
|
| 3214 |
+
"learning_rate": 3.992283005394837e-07,
|
| 3215 |
+
"loss": 1.8635,
|
| 3216 |
+
"step": 458
|
| 3217 |
+
},
|
| 3218 |
+
{
|
| 3219 |
+
"epoch": 1.8971576227390181,
|
| 3220 |
+
"grad_norm": 0.1744472235441208,
|
| 3221 |
+
"learning_rate": 3.7027534146913676e-07,
|
| 3222 |
+
"loss": 1.8324,
|
| 3223 |
+
"step": 459
|
| 3224 |
+
},
|
| 3225 |
+
{
|
| 3226 |
+
"epoch": 1.9012919896640827,
|
| 3227 |
+
"grad_norm": 0.19538050889968872,
|
| 3228 |
+
"learning_rate": 3.424043170470376e-07,
|
| 3229 |
+
"loss": 1.8829,
|
| 3230 |
+
"step": 460
|
| 3231 |
+
},
|
| 3232 |
+
{
|
| 3233 |
+
"epoch": 1.9054263565891474,
|
| 3234 |
+
"grad_norm": 0.18182292580604553,
|
| 3235 |
+
"learning_rate": 3.1561645159166597e-07,
|
| 3236 |
+
"loss": 1.8715,
|
| 3237 |
+
"step": 461
|
| 3238 |
+
},
|
| 3239 |
+
{
|
| 3240 |
+
"epoch": 1.909560723514212,
|
| 3241 |
+
"grad_norm": 0.2156144231557846,
|
| 3242 |
+
"learning_rate": 2.89912921840485e-07,
|
| 3243 |
+
"loss": 1.8551,
|
| 3244 |
+
"step": 462
|
| 3245 |
+
},
|
| 3246 |
+
{
|
| 3247 |
+
"epoch": 1.9136950904392764,
|
| 3248 |
+
"grad_norm": 0.19815553724765778,
|
| 3249 |
+
"learning_rate": 2.6529485689825997e-07,
|
| 3250 |
+
"loss": 1.8608,
|
| 3251 |
+
"step": 463
|
| 3252 |
+
},
|
| 3253 |
+
{
|
| 3254 |
+
"epoch": 1.917829457364341,
|
| 3255 |
+
"grad_norm": 0.190420463681221,
|
| 3256 |
+
"learning_rate": 2.417633381874534e-07,
|
| 3257 |
+
"loss": 1.8855,
|
| 3258 |
+
"step": 464
|
| 3259 |
+
},
|
| 3260 |
+
{
|
| 3261 |
+
"epoch": 1.9219638242894057,
|
| 3262 |
+
"grad_norm": 0.25073426961898804,
|
| 3263 |
+
"learning_rate": 2.1931939940071366e-07,
|
| 3264 |
+
"loss": 1.8424,
|
| 3265 |
+
"step": 465
|
| 3266 |
+
},
|
| 3267 |
+
{
|
| 3268 |
+
"epoch": 1.9260981912144701,
|
| 3269 |
+
"grad_norm": 0.19041046500205994,
|
| 3270 |
+
"learning_rate": 1.9796402645547995e-07,
|
| 3271 |
+
"loss": 1.8745,
|
| 3272 |
+
"step": 466
|
| 3273 |
+
},
|
| 3274 |
+
{
|
| 3275 |
+
"epoch": 1.9302325581395348,
|
| 3276 |
+
"grad_norm": 0.20114633440971375,
|
| 3277 |
+
"learning_rate": 1.7769815745066475e-07,
|
| 3278 |
+
"loss": 1.8746,
|
| 3279 |
+
"step": 467
|
| 3280 |
+
},
|
| 3281 |
+
{
|
| 3282 |
+
"epoch": 1.9343669250645994,
|
| 3283 |
+
"grad_norm": 0.1998317837715149,
|
| 3284 |
+
"learning_rate": 1.5852268262544768e-07,
|
| 3285 |
+
"loss": 1.8308,
|
| 3286 |
+
"step": 468
|
| 3287 |
+
},
|
| 3288 |
+
{
|
| 3289 |
+
"epoch": 1.938501291989664,
|
| 3290 |
+
"grad_norm": 0.19528813660144806,
|
| 3291 |
+
"learning_rate": 1.4043844432016506e-07,
|
| 3292 |
+
"loss": 1.8205,
|
| 3293 |
+
"step": 469
|
| 3294 |
+
},
|
| 3295 |
+
{
|
| 3296 |
+
"epoch": 1.9426356589147287,
|
| 3297 |
+
"grad_norm": 0.19325582683086395,
|
| 3298 |
+
"learning_rate": 1.234462369393147e-07,
|
| 3299 |
+
"loss": 1.8457,
|
| 3300 |
+
"step": 470
|
| 3301 |
+
},
|
| 3302 |
+
{
|
| 3303 |
+
"epoch": 1.9467700258397933,
|
| 3304 |
+
"grad_norm": 0.1830948442220688,
|
| 3305 |
+
"learning_rate": 1.0754680691665298e-07,
|
| 3306 |
+
"loss": 1.8358,
|
| 3307 |
+
"step": 471
|
| 3308 |
+
},
|
| 3309 |
+
{
|
| 3310 |
+
"epoch": 1.950904392764858,
|
| 3311 |
+
"grad_norm": 0.1968577653169632,
|
| 3312 |
+
"learning_rate": 9.274085268241028e-08,
|
| 3313 |
+
"loss": 1.8508,
|
| 3314 |
+
"step": 472
|
| 3315 |
+
},
|
| 3316 |
+
{
|
| 3317 |
+
"epoch": 1.9550387596899226,
|
| 3318 |
+
"grad_norm": 0.20363371074199677,
|
| 3319 |
+
"learning_rate": 7.90290246326042e-08,
|
| 3320 |
+
"loss": 1.7873,
|
| 3321 |
+
"step": 473
|
| 3322 |
+
},
|
| 3323 |
+
{
|
| 3324 |
+
"epoch": 1.9591731266149872,
|
| 3325 |
+
"grad_norm": 0.1976526975631714,
|
| 3326 |
+
"learning_rate": 6.641192510047634e-08,
|
| 3327 |
+
"loss": 1.8693,
|
| 3328 |
+
"step": 474
|
| 3329 |
+
},
|
| 3330 |
+
{
|
| 3331 |
+
"epoch": 1.9633074935400516,
|
| 3332 |
+
"grad_norm": 0.20463722944259644,
|
| 3333 |
+
"learning_rate": 5.489010833002739e-08,
|
| 3334 |
+
"loss": 1.7866,
|
| 3335 |
+
"step": 475
|
| 3336 |
+
},
|
| 3337 |
+
{
|
| 3338 |
+
"epoch": 1.9674418604651163,
|
| 3339 |
+
"grad_norm": 0.18927815556526184,
|
| 3340 |
+
"learning_rate": 4.4464080451675494e-08,
|
| 3341 |
+
"loss": 1.8249,
|
| 3342 |
+
"step": 476
|
| 3343 |
+
},
|
| 3344 |
+
{
|
| 3345 |
+
"epoch": 1.971576227390181,
|
| 3346 |
+
"grad_norm": 0.1959766000509262,
|
| 3347 |
+
"learning_rate": 3.51342994600129e-08,
|
| 3348 |
+
"loss": 1.8257,
|
| 3349 |
+
"step": 477
|
| 3350 |
+
},
|
| 3351 |
+
{
|
| 3352 |
+
"epoch": 1.9757105943152453,
|
| 3353 |
+
"grad_norm": 0.16031917929649353,
|
| 3354 |
+
"learning_rate": 2.6901175193699835e-08,
|
| 3355 |
+
"loss": 1.7818,
|
| 3356 |
+
"step": 478
|
| 3357 |
+
},
|
| 3358 |
+
{
|
| 3359 |
+
"epoch": 1.97984496124031,
|
| 3360 |
+
"grad_norm": 0.1876872181892395,
|
| 3361 |
+
"learning_rate": 1.976506931745392e-08,
|
| 3362 |
+
"loss": 1.8652,
|
| 3363 |
+
"step": 479
|
| 3364 |
+
},
|
| 3365 |
+
{
|
| 3366 |
+
"epoch": 1.9839793281653746,
|
| 3367 |
+
"grad_norm": 0.17847619950771332,
|
| 3368 |
+
"learning_rate": 1.3726295306162873e-08,
|
| 3369 |
+
"loss": 1.8704,
|
| 3370 |
+
"step": 480
|
| 3371 |
+
},
|
| 3372 |
+
{
|
| 3373 |
+
"epoch": 1.9881136950904392,
|
| 3374 |
+
"grad_norm": 0.21231304109096527,
|
| 3375 |
+
"learning_rate": 8.785118431120509e-09,
|
| 3376 |
+
"loss": 1.8785,
|
| 3377 |
+
"step": 481
|
| 3378 |
+
},
|
| 3379 |
+
{
|
| 3380 |
+
"epoch": 1.9922480620155039,
|
| 3381 |
+
"grad_norm": 0.18760918080806732,
|
| 3382 |
+
"learning_rate": 4.941755748361088e-09,
|
| 3383 |
+
"loss": 1.8445,
|
| 3384 |
+
"step": 482
|
| 3385 |
+
},
|
| 3386 |
+
{
|
| 3387 |
+
"epoch": 1.9963824289405685,
|
| 3388 |
+
"grad_norm": 0.19136686623096466,
|
| 3389 |
+
"learning_rate": 2.1963760891391407e-09,
|
| 3390 |
+
"loss": 1.8895,
|
| 3391 |
+
"step": 483
|
| 3392 |
+
},
|
| 3393 |
+
{
|
| 3394 |
+
"epoch": 2.0,
|
| 3395 |
+
"grad_norm": 0.19582392275333405,
|
| 3396 |
+
"learning_rate": 5.491000525020828e-10,
|
| 3397 |
+
"loss": 1.813,
|
| 3398 |
+
"step": 484
|
| 3399 |
+
},
|
| 3400 |
+
{
|
| 3401 |
+
"epoch": 2.0,
|
| 3402 |
+
"step": 484,
|
| 3403 |
+
"total_flos": 3.051681632621691e+17,
|
| 3404 |
+
"train_loss": 1.9266295598065557,
|
| 3405 |
+
"train_runtime": 872.3743,
|
| 3406 |
+
"train_samples_per_second": 283.775,
|
| 3407 |
+
"train_steps_per_second": 0.555
|
| 3408 |
+
}
|
| 3409 |
+
],
|
| 3410 |
+
"logging_steps": 1.0,
|
| 3411 |
+
"max_steps": 484,
|
| 3412 |
+
"num_input_tokens_seen": 0,
|
| 3413 |
+
"num_train_epochs": 2,
|
| 3414 |
+
"save_steps": 500,
|
| 3415 |
+
"stateful_callbacks": {
|
| 3416 |
+
"TrainerControl": {
|
| 3417 |
+
"args": {
|
| 3418 |
+
"should_epoch_stop": false,
|
| 3419 |
+
"should_evaluate": false,
|
| 3420 |
+
"should_log": false,
|
| 3421 |
+
"should_save": true,
|
| 3422 |
+
"should_training_stop": true
|
| 3423 |
+
},
|
| 3424 |
+
"attributes": {}
|
| 3425 |
+
}
|
| 3426 |
+
},
|
| 3427 |
+
"total_flos": 3.051681632621691e+17,
|
| 3428 |
+
"train_batch_size": 8,
|
| 3429 |
+
"trial_name": null,
|
| 3430 |
+
"trial_params": null
|
| 3431 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:547ec7445ef0b2999265880b0f40bc28187fac494574bab36730d94075513f39
|
| 3 |
+
size 7825
|