Hugging Face's logo

Jesteban247
/
medgemma-brats-experiments

Visual Question Answering
Transformers
Safetensors
English
sft
medical-imaging
brats
textbrats
unsloth
Model card Files
xet
Community
Jesteban247 commited on
Commit
600f2a5
·
verified ·
1 Parent(s): ff5d3fc

Upload brats_medgemma_r1_alpha4_20251014_001744

Browse files
Files changed (43) hide show
  1. .gitattributes +3 -0
  2. brats_medgemma_r1_alpha4_20251014_001744/checkpoint-124/adapter_config.json +38 -0
  3. brats_medgemma_r1_alpha4_20251014_001744/checkpoint-124/adapter_model.safetensors +3 -0
  4. brats_medgemma_r1_alpha4_20251014_001744/checkpoint-124/added_tokens.json +3 -0
  5. brats_medgemma_r1_alpha4_20251014_001744/checkpoint-124/chat_template.jinja +47 -0
  6. brats_medgemma_r1_alpha4_20251014_001744/checkpoint-124/optimizer.pt +3 -0
  7. brats_medgemma_r1_alpha4_20251014_001744/checkpoint-124/rng_state.pth +3 -0
  8. brats_medgemma_r1_alpha4_20251014_001744/checkpoint-124/scheduler.pt +3 -0
  9. brats_medgemma_r1_alpha4_20251014_001744/checkpoint-124/special_tokens_map.json +33 -0
  10. brats_medgemma_r1_alpha4_20251014_001744/checkpoint-124/tokenizer.json +3 -0
  11. brats_medgemma_r1_alpha4_20251014_001744/checkpoint-124/tokenizer.model +3 -0
  12. brats_medgemma_r1_alpha4_20251014_001744/checkpoint-124/tokenizer_config.json +0 -0
  13. brats_medgemma_r1_alpha4_20251014_001744/checkpoint-124/trainer_state.json +902 -0
  14. brats_medgemma_r1_alpha4_20251014_001744/checkpoint-124/training_args.bin +3 -0
  15. brats_medgemma_r1_alpha4_20251014_001744/lora_adapters/adapter_config.json +38 -0
  16. brats_medgemma_r1_alpha4_20251014_001744/lora_adapters/adapter_model.safetensors +3 -0
  17. brats_medgemma_r1_alpha4_20251014_001744/lora_adapters/added_tokens.json +3 -0
  18. brats_medgemma_r1_alpha4_20251014_001744/lora_adapters/chat_template.jinja +47 -0
  19. brats_medgemma_r1_alpha4_20251014_001744/lora_adapters/preprocessor_config.json +29 -0
  20. brats_medgemma_r1_alpha4_20251014_001744/lora_adapters/processor_config.json +4 -0
  21. brats_medgemma_r1_alpha4_20251014_001744/lora_adapters/special_tokens_map.json +33 -0
  22. brats_medgemma_r1_alpha4_20251014_001744/lora_adapters/tokenizer.json +3 -0
  23. brats_medgemma_r1_alpha4_20251014_001744/lora_adapters/tokenizer.model +3 -0
  24. brats_medgemma_r1_alpha4_20251014_001744/lora_adapters/tokenizer_config.json +0 -0
  25. brats_medgemma_r1_alpha4_20251014_001744/merged_model/added_tokens.json +3 -0
  26. brats_medgemma_r1_alpha4_20251014_001744/merged_model/chat_template.jinja +47 -0
  27. brats_medgemma_r1_alpha4_20251014_001744/merged_model/config.json +99 -0
  28. brats_medgemma_r1_alpha4_20251014_001744/merged_model/model-00001-of-00002.safetensors +3 -0
  29. brats_medgemma_r1_alpha4_20251014_001744/merged_model/model-00002-of-00002.safetensors +3 -0
  30. brats_medgemma_r1_alpha4_20251014_001744/merged_model/model.safetensors.index.json +891 -0
  31. brats_medgemma_r1_alpha4_20251014_001744/merged_model/preprocessor_config.json +29 -0
  32. brats_medgemma_r1_alpha4_20251014_001744/merged_model/processor_config.json +4 -0
  33. brats_medgemma_r1_alpha4_20251014_001744/merged_model/special_tokens_map.json +33 -0
  34. brats_medgemma_r1_alpha4_20251014_001744/merged_model/tokenizer.json +3 -0
  35. brats_medgemma_r1_alpha4_20251014_001744/merged_model/tokenizer.model +3 -0
  36. brats_medgemma_r1_alpha4_20251014_001744/merged_model/tokenizer_config.json +0 -0
  37. brats_medgemma_r1_alpha4_20251014_001744/metrics/complete_data_distribution_20251014_001744.json +29 -0
  38. brats_medgemma_r1_alpha4_20251014_001744/metrics/test_detailed_20251014_001744.csv +0 -0
  39. brats_medgemma_r1_alpha4_20251014_001744/metrics/test_summary_20251014_001744.csv +4 -0
  40. brats_medgemma_r1_alpha4_20251014_001744/metrics/training_log_20251014_001744.csv +125 -0
  41. brats_medgemma_r1_alpha4_20251014_001744/metrics/training_summary_20251014_001744.csv +16 -0
  42. brats_medgemma_r1_alpha4_20251014_001744/metrics/validation_during_training_20251014_001744.json +470 -0
  43. brats_medgemma_r1_alpha4_20251014_001744/metrics/validation_log_20251014_001744.csv +37 -0
.gitattributes CHANGED
@@ -36,3 +36,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
36
  brats_medgemma_r1_alpha2_20251013_235648/checkpoint-124/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
  brats_medgemma_r1_alpha2_20251013_235648/lora_adapters/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
  brats_medgemma_r1_alpha2_20251013_235648/merged_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
36
  brats_medgemma_r1_alpha2_20251013_235648/checkpoint-124/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
  brats_medgemma_r1_alpha2_20251013_235648/lora_adapters/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
  brats_medgemma_r1_alpha2_20251013_235648/merged_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
+ brats_medgemma_r1_alpha4_20251014_001744/checkpoint-124/tokenizer.json filter=lfs diff=lfs merge=lfs -text
40
+ brats_medgemma_r1_alpha4_20251014_001744/lora_adapters/tokenizer.json filter=lfs diff=lfs merge=lfs -text
41
+ brats_medgemma_r1_alpha4_20251014_001744/merged_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
brats_medgemma_r1_alpha4_20251014_001744/checkpoint-124/adapter_config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": {
4
+ "base_model_class": "Gemma3ForConditionalGeneration",
5
+ "parent_library": "transformers.models.gemma3.modeling_gemma3",
6
+ "unsloth_fixed": true
7
+ },
8
+ "base_model_name_or_path": "unsloth/medgemma-4b-it-unsloth-bnb-4bit",
9
+ "bias": "none",
10
+ "corda_config": null,
11
+ "eva_config": null,
12
+ "exclude_modules": null,
13
+ "fan_in_fan_out": false,
14
+ "inference_mode": true,
15
+ "init_lora_weights": true,
16
+ "layer_replication": null,
17
+ "layers_pattern": null,
18
+ "layers_to_transform": null,
19
+ "loftq_config": {},
20
+ "lora_alpha": 4,
21
+ "lora_bias": false,
22
+ "lora_dropout": 0,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "peft_type": "LORA",
27
+ "qalora_group_size": 16,
28
+ "r": 1,
29
+ "rank_pattern": {},
30
+ "revision": null,
31
+ "target_modules": "(?:.*?(?:vision|image|visual|patch|language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:k_proj|v_proj|q_proj|out_proj|fc1|fc2|o_proj|gate_proj|up_proj|down_proj).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:k_proj|v_proj|q_proj|out_proj|fc1|fc2|o_proj|gate_proj|up_proj|down_proj)))",
32
+ "target_parameters": null,
33
+ "task_type": "CAUSAL_LM",
34
+ "trainable_token_indices": null,
35
+ "use_dora": false,
36
+ "use_qalora": false,
37
+ "use_rslora": false
38
+ }
brats_medgemma_r1_alpha4_20251014_001744/checkpoint-124/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d15df29b626401034ed224a223eb77fb34e4620cf5a5f5c222d99ab660f5fd8b
3
+ size 9746344
brats_medgemma_r1_alpha4_20251014_001744/checkpoint-124/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<image_soft_token>": 262144
3
+ }
brats_medgemma_r1_alpha4_20251014_001744/checkpoint-124/chat_template.jinja ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{ bos_token }}
2
+ {%- if messages[0]['role'] == 'system' -%}
3
+ {%- if messages[0]['content'] is string -%}
4
+ {%- set first_user_prefix = messages[0]['content'] + '
5
+
6
+ ' -%}
7
+ {%- else -%}
8
+ {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
9
+
10
+ ' -%}
11
+ {%- endif -%}
12
+ {%- set loop_messages = messages[1:] -%}
13
+ {%- else -%}
14
+ {%- set first_user_prefix = "" -%}
15
+ {%- set loop_messages = messages -%}
16
+ {%- endif -%}
17
+ {%- for message in loop_messages -%}
18
+ {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
19
+ {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
20
+ {%- endif -%}
21
+ {%- if (message['role'] == 'assistant') -%}
22
+ {%- set role = "model" -%}
23
+ {%- else -%}
24
+ {%- set role = message['role'] -%}
25
+ {%- endif -%}
26
+ {{ '<start_of_turn>' + role + '
27
+ ' + (first_user_prefix if loop.first else "") }}
28
+ {%- if message['content'] is string -%}
29
+ {{ message['content'] | trim }}
30
+ {%- elif message['content'] is iterable -%}
31
+ {%- for item in message['content'] -%}
32
+ {%- if item['type'] == 'image' -%}
33
+ {{ '<start_of_image>' }}
34
+ {%- elif item['type'] == 'text' -%}
35
+ {{ item['text'] | trim }}
36
+ {%- endif -%}
37
+ {%- endfor -%}
38
+ {%- else -%}
39
+ {{ raise_exception("Invalid content type") }}
40
+ {%- endif -%}
41
+ {{ '<end_of_turn>
42
+ ' }}
43
+ {%- endfor -%}
44
+ {%- if add_generation_prompt -%}
45
+ {{'<start_of_turn>model
46
+ '}}
47
+ {%- endif -%}
brats_medgemma_r1_alpha4_20251014_001744/checkpoint-124/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02422c75083c1b539f211749f50b33071ccba32e1ee65e082bd7cd55cf0064bf
3
+ size 19934531
brats_medgemma_r1_alpha4_20251014_001744/checkpoint-124/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86ea1e6afe1d2d10dfe54b3294328a819995e8acd1cc665ce9b073d869ce0d05
3
+ size 14645
brats_medgemma_r1_alpha4_20251014_001744/checkpoint-124/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fefd18b384108436f245902e685f9b279b0fcb33eb50300309680ecaa95057c6
3
+ size 1465
brats_medgemma_r1_alpha4_20251014_001744/checkpoint-124/special_tokens_map.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "boi_token": "<start_of_image>",
3
+ "bos_token": {
4
+ "content": "<bos>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "eoi_token": "<end_of_image>",
11
+ "eos_token": {
12
+ "content": "<end_of_turn>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "image_token": "<image_soft_token>",
19
+ "pad_token": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "unk_token": {
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
brats_medgemma_r1_alpha4_20251014_001744/checkpoint-124/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7666402c0617d170e6b0a985b3130c3fb0795393aa0970600994a5d9aae12351
3
+ size 33384822
brats_medgemma_r1_alpha4_20251014_001744/checkpoint-124/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
3
+ size 4689074
brats_medgemma_r1_alpha4_20251014_001744/checkpoint-124/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
brats_medgemma_r1_alpha4_20251014_001744/checkpoint-124/trainer_state.json ADDED
@@ -0,0 +1,902 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.9959839357429718,
6
+ "eval_steps": 500,
7
+ "global_step": 124,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.008032128514056224,
14
+ "grad_norm": 2.019815683364868,
15
+ "learning_rate": 0.0,
16
+ "loss": 3.661,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.01606425702811245,
21
+ "grad_norm": 1.2853758335113525,
22
+ "learning_rate": 5e-05,
23
+ "loss": 3.5315,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.024096385542168676,
28
+ "grad_norm": 1.1758249998092651,
29
+ "learning_rate": 0.0001,
30
+ "loss": 3.4565,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.0321285140562249,
35
+ "grad_norm": 1.3129501342773438,
36
+ "learning_rate": 0.00015000000000000001,
37
+ "loss": 3.5396,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.040160642570281124,
42
+ "grad_norm": 1.672165036201477,
43
+ "learning_rate": 0.0002,
44
+ "loss": 3.5246,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.04819277108433735,
49
+ "grad_norm": 1.5011506080627441,
50
+ "learning_rate": 0.00019996573249755572,
51
+ "loss": 3.3024,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.05622489959839357,
56
+ "grad_norm": 1.659716248512268,
57
+ "learning_rate": 0.0001998629534754574,
58
+ "loss": 3.2627,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.0642570281124498,
63
+ "grad_norm": 1.6134133338928223,
64
+ "learning_rate": 0.0001996917333733128,
65
+ "loss": 3.0717,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.07228915662650602,
70
+ "grad_norm": 1.6855814456939697,
71
+ "learning_rate": 0.00019945218953682734,
72
+ "loss": 2.9298,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.08032128514056225,
77
+ "grad_norm": 1.6935063600540161,
78
+ "learning_rate": 0.00019914448613738106,
79
+ "loss": 2.7155,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.08835341365461848,
84
+ "grad_norm": 1.7328497171401978,
85
+ "learning_rate": 0.00019876883405951377,
86
+ "loss": 2.64,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.0963855421686747,
91
+ "grad_norm": 1.8865529298782349,
92
+ "learning_rate": 0.0001983254907563955,
93
+ "loss": 2.6265,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.10441767068273092,
98
+ "grad_norm": 2.0051887035369873,
99
+ "learning_rate": 0.00019781476007338058,
100
+ "loss": 2.3969,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.11244979919678715,
105
+ "grad_norm": 2.0362915992736816,
106
+ "learning_rate": 0.00019723699203976766,
107
+ "loss": 2.2397,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.12048192771084337,
112
+ "grad_norm": 2.2752039432525635,
113
+ "learning_rate": 0.00019659258262890683,
114
+ "loss": 2.1839,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.1285140562248996,
119
+ "grad_norm": 2.1745102405548096,
120
+ "learning_rate": 0.0001958819734868193,
121
+ "loss": 2.0868,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.13654618473895583,
126
+ "grad_norm": 2.3117716312408447,
127
+ "learning_rate": 0.00019510565162951537,
128
+ "loss": 1.9497,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.14457831325301204,
133
+ "grad_norm": 2.1332054138183594,
134
+ "learning_rate": 0.00019426414910921787,
135
+ "loss": 1.9352,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.15261044176706828,
140
+ "grad_norm": 1.9905061721801758,
141
+ "learning_rate": 0.00019335804264972018,
142
+ "loss": 1.7922,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.1606425702811245,
147
+ "grad_norm": 1.719763159751892,
148
+ "learning_rate": 0.0001923879532511287,
149
+ "loss": 1.7261,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.1686746987951807,
154
+ "grad_norm": 1.8796164989471436,
155
+ "learning_rate": 0.0001913545457642601,
156
+ "loss": 1.7057,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.17670682730923695,
161
+ "grad_norm": 1.8936994075775146,
162
+ "learning_rate": 0.00019025852843498607,
163
+ "loss": 1.5605,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.18473895582329317,
168
+ "grad_norm": 1.9554697275161743,
169
+ "learning_rate": 0.0001891006524188368,
170
+ "loss": 1.604,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.1927710843373494,
175
+ "grad_norm": 1.7591966390609741,
176
+ "learning_rate": 0.00018788171126619653,
177
+ "loss": 1.5353,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.20080321285140562,
182
+ "grad_norm": 1.8183223009109497,
183
+ "learning_rate": 0.00018660254037844388,
184
+ "loss": 1.4564,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.20883534136546184,
189
+ "grad_norm": 1.7630478143692017,
190
+ "learning_rate": 0.00018526401643540922,
191
+ "loss": 1.4414,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.21686746987951808,
196
+ "grad_norm": 1.680556297302246,
197
+ "learning_rate": 0.00018386705679454242,
198
+ "loss": 1.3715,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 0.2248995983935743,
203
+ "grad_norm": 1.6417803764343262,
204
+ "learning_rate": 0.00018241261886220154,
205
+ "loss": 1.2303,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 0.23293172690763053,
210
+ "grad_norm": 1.52765691280365,
211
+ "learning_rate": 0.00018090169943749476,
212
+ "loss": 1.2292,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 0.24096385542168675,
217
+ "grad_norm": 1.7861028909683228,
218
+ "learning_rate": 0.00017933533402912354,
219
+ "loss": 1.3359,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 0.24899598393574296,
224
+ "grad_norm": 1.636149287223816,
225
+ "learning_rate": 0.0001777145961456971,
226
+ "loss": 1.1348,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 0.2570281124497992,
231
+ "grad_norm": 1.5470186471939087,
232
+ "learning_rate": 0.0001760405965600031,
233
+ "loss": 1.2926,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 0.26506024096385544,
238
+ "grad_norm": 1.408089518547058,
239
+ "learning_rate": 0.00017431448254773944,
240
+ "loss": 1.1804,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 0.27309236947791166,
245
+ "grad_norm": 1.4028633832931519,
246
+ "learning_rate": 0.00017253743710122875,
247
+ "loss": 1.0454,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 0.28112449799196787,
252
+ "grad_norm": 1.455613613128662,
253
+ "learning_rate": 0.00017071067811865476,
254
+ "loss": 1.078,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 0.2891566265060241,
259
+ "grad_norm": 1.3026847839355469,
260
+ "learning_rate": 0.0001688354575693754,
261
+ "loss": 1.1061,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 0.2971887550200803,
266
+ "grad_norm": 1.1518399715423584,
267
+ "learning_rate": 0.00016691306063588583,
268
+ "loss": 0.9997,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 0.30522088353413657,
273
+ "grad_norm": 1.3398936986923218,
274
+ "learning_rate": 0.00016494480483301836,
275
+ "loss": 1.0365,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 0.3132530120481928,
280
+ "grad_norm": 1.308660864830017,
281
+ "learning_rate": 0.00016293203910498376,
282
+ "loss": 0.9457,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 0.321285140562249,
287
+ "grad_norm": 1.3927632570266724,
288
+ "learning_rate": 0.00016087614290087208,
289
+ "loss": 1.0802,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 0.3293172690763052,
294
+ "grad_norm": 1.243821382522583,
295
+ "learning_rate": 0.00015877852522924732,
296
+ "loss": 0.9294,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 0.3373493975903614,
301
+ "grad_norm": 1.2406731843948364,
302
+ "learning_rate": 0.00015664062369248328,
303
+ "loss": 0.9674,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 0.3453815261044177,
308
+ "grad_norm": 1.2783746719360352,
309
+ "learning_rate": 0.00015446390350150273,
310
+ "loss": 0.9965,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 0.3534136546184739,
315
+ "grad_norm": 1.2946393489837646,
316
+ "learning_rate": 0.0001522498564715949,
317
+ "loss": 0.9856,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 0.3614457831325301,
322
+ "grad_norm": 1.4061180353164673,
323
+ "learning_rate": 0.00015000000000000001,
324
+ "loss": 0.868,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 0.36947791164658633,
329
+ "grad_norm": 1.2646836042404175,
330
+ "learning_rate": 0.00014771587602596084,
331
+ "loss": 0.9247,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 0.37751004016064255,
336
+ "grad_norm": 1.1976709365844727,
337
+ "learning_rate": 0.00014539904997395468,
338
+ "loss": 0.9048,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 0.3855421686746988,
343
+ "grad_norm": 1.2490942478179932,
344
+ "learning_rate": 0.00014305110968082952,
345
+ "loss": 0.8922,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 0.39357429718875503,
350
+ "grad_norm": 1.3626363277435303,
351
+ "learning_rate": 0.00014067366430758004,
352
+ "loss": 0.917,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 0.40160642570281124,
357
+ "grad_norm": 1.2563056945800781,
358
+ "learning_rate": 0.000138268343236509,
359
+ "loss": 0.8949,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 0.40963855421686746,
364
+ "grad_norm": 1.295912504196167,
365
+ "learning_rate": 0.00013583679495453,
366
+ "loss": 0.9594,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 0.41767068273092367,
371
+ "grad_norm": 1.1771835088729858,
372
+ "learning_rate": 0.0001333806859233771,
373
+ "loss": 0.8689,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 0.42570281124497994,
378
+ "grad_norm": 1.2049306631088257,
379
+ "learning_rate": 0.00013090169943749476,
380
+ "loss": 0.733,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 0.43373493975903615,
385
+ "grad_norm": 1.2039227485656738,
386
+ "learning_rate": 0.00012840153447039228,
387
+ "loss": 0.8277,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 0.44176706827309237,
392
+ "grad_norm": 1.2359619140625,
393
+ "learning_rate": 0.00012588190451025207,
394
+ "loss": 0.8141,
395
+ "step": 55
396
+ },
397
+ {
398
+ "epoch": 0.4497991967871486,
399
+ "grad_norm": 1.3563880920410156,
400
+ "learning_rate": 0.00012334453638559057,
401
+ "loss": 0.788,
402
+ "step": 56
403
+ },
404
+ {
405
+ "epoch": 0.4578313253012048,
406
+ "grad_norm": 1.356992483139038,
407
+ "learning_rate": 0.00012079116908177593,
408
+ "loss": 0.8572,
409
+ "step": 57
410
+ },
411
+ {
412
+ "epoch": 0.46586345381526106,
413
+ "grad_norm": 1.3412925004959106,
414
+ "learning_rate": 0.00011822355254921478,
415
+ "loss": 0.7479,
416
+ "step": 58
417
+ },
418
+ {
419
+ "epoch": 0.4738955823293173,
420
+ "grad_norm": 2.170516014099121,
421
+ "learning_rate": 0.0001156434465040231,
422
+ "loss": 0.8603,
423
+ "step": 59
424
+ },
425
+ {
426
+ "epoch": 0.4819277108433735,
427
+ "grad_norm": 1.6985067129135132,
428
+ "learning_rate": 0.00011305261922200519,
429
+ "loss": 0.9334,
430
+ "step": 60
431
+ },
432
+ {
433
+ "epoch": 0.4899598393574297,
434
+ "grad_norm": 1.7688255310058594,
435
+ "learning_rate": 0.00011045284632676536,
436
+ "loss": 0.7675,
437
+ "step": 61
438
+ },
439
+ {
440
+ "epoch": 0.4979919678714859,
441
+ "grad_norm": 1.2064976692199707,
442
+ "learning_rate": 0.0001078459095727845,
443
+ "loss": 0.7948,
444
+ "step": 62
445
+ },
446
+ {
447
+ "epoch": 0.5060240963855421,
448
+ "grad_norm": 1.2789366245269775,
449
+ "learning_rate": 0.0001052335956242944,
450
+ "loss": 0.7756,
451
+ "step": 63
452
+ },
453
+ {
454
+ "epoch": 0.5140562248995983,
455
+ "grad_norm": 1.365412950515747,
456
+ "learning_rate": 0.00010261769483078733,
457
+ "loss": 0.7969,
458
+ "step": 64
459
+ },
460
+ {
461
+ "epoch": 0.5220883534136547,
462
+ "grad_norm": 1.2265170812606812,
463
+ "learning_rate": 0.0001,
464
+ "loss": 0.7497,
465
+ "step": 65
466
+ },
467
+ {
468
+ "epoch": 0.5301204819277109,
469
+ "grad_norm": 1.1440318822860718,
470
+ "learning_rate": 9.73823051692127e-05,
471
+ "loss": 0.8249,
472
+ "step": 66
473
+ },
474
+ {
475
+ "epoch": 0.5381526104417671,
476
+ "grad_norm": 1.1888175010681152,
477
+ "learning_rate": 9.476640437570562e-05,
478
+ "loss": 0.799,
479
+ "step": 67
480
+ },
481
+ {
482
+ "epoch": 0.5461847389558233,
483
+ "grad_norm": 1.2540967464447021,
484
+ "learning_rate": 9.215409042721552e-05,
485
+ "loss": 0.7884,
486
+ "step": 68
487
+ },
488
+ {
489
+ "epoch": 0.5542168674698795,
490
+ "grad_norm": 1.5006526708602905,
491
+ "learning_rate": 8.954715367323468e-05,
492
+ "loss": 0.7512,
493
+ "step": 69
494
+ },
495
+ {
496
+ "epoch": 0.5622489959839357,
497
+ "grad_norm": 1.3374214172363281,
498
+ "learning_rate": 8.694738077799488e-05,
499
+ "loss": 0.7946,
500
+ "step": 70
501
+ },
502
+ {
503
+ "epoch": 0.570281124497992,
504
+ "grad_norm": 1.0757158994674683,
505
+ "learning_rate": 8.435655349597689e-05,
506
+ "loss": 0.7236,
507
+ "step": 71
508
+ },
509
+ {
510
+ "epoch": 0.5783132530120482,
511
+ "grad_norm": 1.544098973274231,
512
+ "learning_rate": 8.177644745078526e-05,
513
+ "loss": 0.7618,
514
+ "step": 72
515
+ },
516
+ {
517
+ "epoch": 0.5863453815261044,
518
+ "grad_norm": 1.1211774349212646,
519
+ "learning_rate": 7.920883091822408e-05,
520
+ "loss": 0.6957,
521
+ "step": 73
522
+ },
523
+ {
524
+ "epoch": 0.5943775100401606,
525
+ "grad_norm": 1.2740777730941772,
526
+ "learning_rate": 7.66554636144095e-05,
527
+ "loss": 0.8462,
528
+ "step": 74
529
+ },
530
+ {
531
+ "epoch": 0.6024096385542169,
532
+ "grad_norm": 1.0581215620040894,
533
+ "learning_rate": 7.411809548974792e-05,
534
+ "loss": 0.6713,
535
+ "step": 75
536
+ },
537
+ {
538
+ "epoch": 0.6104417670682731,
539
+ "grad_norm": 1.3543978929519653,
540
+ "learning_rate": 7.159846552960774e-05,
541
+ "loss": 0.8175,
542
+ "step": 76
543
+ },
544
+ {
545
+ "epoch": 0.6184738955823293,
546
+ "grad_norm": 1.1732665300369263,
547
+ "learning_rate": 6.909830056250527e-05,
548
+ "loss": 0.6849,
549
+ "step": 77
550
+ },
551
+ {
552
+ "epoch": 0.6265060240963856,
553
+ "grad_norm": 1.1747123003005981,
554
+ "learning_rate": 6.661931407662292e-05,
555
+ "loss": 0.7137,
556
+ "step": 78
557
+ },
558
+ {
559
+ "epoch": 0.6345381526104418,
560
+ "grad_norm": 1.3373887538909912,
561
+ "learning_rate": 6.416320504546997e-05,
562
+ "loss": 0.7106,
563
+ "step": 79
564
+ },
565
+ {
566
+ "epoch": 0.642570281124498,
567
+ "grad_norm": 1.1053829193115234,
568
+ "learning_rate": 6.173165676349103e-05,
569
+ "loss": 0.7363,
570
+ "step": 80
571
+ },
572
+ {
573
+ "epoch": 0.6506024096385542,
574
+ "grad_norm": 1.1043962240219116,
575
+ "learning_rate": 5.9326335692419995e-05,
576
+ "loss": 0.7063,
577
+ "step": 81
578
+ },
579
+ {
580
+ "epoch": 0.6586345381526104,
581
+ "grad_norm": 1.0286561250686646,
582
+ "learning_rate": 5.694889031917047e-05,
583
+ "loss": 0.7034,
584
+ "step": 82
585
+ },
586
+ {
587
+ "epoch": 0.6666666666666666,
588
+ "grad_norm": 1.0178589820861816,
589
+ "learning_rate": 5.4600950026045326e-05,
590
+ "loss": 0.6894,
591
+ "step": 83
592
+ },
593
+ {
594
+ "epoch": 0.6746987951807228,
595
+ "grad_norm": 1.086310863494873,
596
+ "learning_rate": 5.2284123974039154e-05,
597
+ "loss": 0.6692,
598
+ "step": 84
599
+ },
600
+ {
601
+ "epoch": 0.6827309236947792,
602
+ "grad_norm": 1.25288724899292,
603
+ "learning_rate": 5.000000000000002e-05,
604
+ "loss": 0.7244,
605
+ "step": 85
606
+ },
607
+ {
608
+ "epoch": 0.6907630522088354,
609
+ "grad_norm": 0.9437931180000305,
610
+ "learning_rate": 4.7750143528405126e-05,
611
+ "loss": 0.7015,
612
+ "step": 86
613
+ },
614
+ {
615
+ "epoch": 0.6987951807228916,
616
+ "grad_norm": 0.945963978767395,
617
+ "learning_rate": 4.5536096498497295e-05,
618
+ "loss": 0.6888,
619
+ "step": 87
620
+ },
621
+ {
622
+ "epoch": 0.7068273092369478,
623
+ "grad_norm": 0.9686598181724548,
624
+ "learning_rate": 4.335937630751674e-05,
625
+ "loss": 0.5903,
626
+ "step": 88
627
+ },
628
+ {
629
+ "epoch": 0.714859437751004,
630
+ "grad_norm": 1.095584750175476,
631
+ "learning_rate": 4.12214747707527e-05,
632
+ "loss": 0.7598,
633
+ "step": 89
634
+ },
635
+ {
636
+ "epoch": 0.7228915662650602,
637
+ "grad_norm": 1.0428060293197632,
638
+ "learning_rate": 3.9123857099127936e-05,
639
+ "loss": 0.7166,
640
+ "step": 90
641
+ },
642
+ {
643
+ "epoch": 0.7309236947791165,
644
+ "grad_norm": 1.0729337930679321,
645
+ "learning_rate": 3.7067960895016275e-05,
646
+ "loss": 0.7613,
647
+ "step": 91
648
+ },
649
+ {
650
+ "epoch": 0.7389558232931727,
651
+ "grad_norm": 1.0446807146072388,
652
+ "learning_rate": 3.5055195166981645e-05,
653
+ "loss": 0.6746,
654
+ "step": 92
655
+ },
656
+ {
657
+ "epoch": 0.7469879518072289,
658
+ "grad_norm": 1.2135626077651978,
659
+ "learning_rate": 3.308693936411421e-05,
660
+ "loss": 0.7373,
661
+ "step": 93
662
+ },
663
+ {
664
+ "epoch": 0.7550200803212851,
665
+ "grad_norm": 1.4108779430389404,
666
+ "learning_rate": 3.116454243062459e-05,
667
+ "loss": 0.7076,
668
+ "step": 94
669
+ },
670
+ {
671
+ "epoch": 0.7630522088353414,
672
+ "grad_norm": 1.0012396574020386,
673
+ "learning_rate": 2.9289321881345254e-05,
674
+ "loss": 0.6448,
675
+ "step": 95
676
+ },
677
+ {
678
+ "epoch": 0.7710843373493976,
679
+ "grad_norm": 1.197523832321167,
680
+ "learning_rate": 2.746256289877126e-05,
681
+ "loss": 0.8074,
682
+ "step": 96
683
+ },
684
+ {
685
+ "epoch": 0.7791164658634538,
686
+ "grad_norm": 1.1583105325698853,
687
+ "learning_rate": 2.5685517452260567e-05,
688
+ "loss": 0.6817,
689
+ "step": 97
690
+ },
691
+ {
692
+ "epoch": 0.7871485943775101,
693
+ "grad_norm": 1.046449899673462,
694
+ "learning_rate": 2.3959403439996907e-05,
695
+ "loss": 0.6974,
696
+ "step": 98
697
+ },
698
+ {
699
+ "epoch": 0.7951807228915663,
700
+ "grad_norm": 1.101068139076233,
701
+ "learning_rate": 2.2285403854302912e-05,
702
+ "loss": 0.6708,
703
+ "step": 99
704
+ },
705
+ {
706
+ "epoch": 0.8032128514056225,
707
+ "grad_norm": 1.1206387281417847,
708
+ "learning_rate": 2.0664665970876496e-05,
709
+ "loss": 0.7836,
710
+ "step": 100
711
+ },
712
+ {
713
+ "epoch": 0.8112449799196787,
714
+ "grad_norm": 1.0255687236785889,
715
+ "learning_rate": 1.9098300562505266e-05,
716
+ "loss": 0.6972,
717
+ "step": 101
718
+ },
719
+ {
720
+ "epoch": 0.8192771084337349,
721
+ "grad_norm": 0.903447151184082,
722
+ "learning_rate": 1.7587381137798432e-05,
723
+ "loss": 0.6719,
724
+ "step": 102
725
+ },
726
+ {
727
+ "epoch": 0.8273092369477911,
728
+ "grad_norm": 1.0198670625686646,
729
+ "learning_rate": 1.6132943205457606e-05,
730
+ "loss": 0.7369,
731
+ "step": 103
732
+ },
733
+ {
734
+ "epoch": 0.8353413654618473,
735
+ "grad_norm": 1.0521577596664429,
736
+ "learning_rate": 1.4735983564590783e-05,
737
+ "loss": 0.7706,
738
+ "step": 104
739
+ },
740
+ {
741
+ "epoch": 0.8433734939759037,
742
+ "grad_norm": 1.0232212543487549,
743
+ "learning_rate": 1.339745962155613e-05,
744
+ "loss": 0.7128,
745
+ "step": 105
746
+ },
747
+ {
748
+ "epoch": 0.8514056224899599,
749
+ "grad_norm": 1.000497579574585,
750
+ "learning_rate": 1.2118288733803473e-05,
751
+ "loss": 0.7666,
752
+ "step": 106
753
+ },
754
+ {
755
+ "epoch": 0.8594377510040161,
756
+ "grad_norm": 1.0526843070983887,
757
+ "learning_rate": 1.0899347581163221e-05,
758
+ "loss": 0.6957,
759
+ "step": 107
760
+ },
761
+ {
762
+ "epoch": 0.8674698795180723,
763
+ "grad_norm": 1.0339035987854004,
764
+ "learning_rate": 9.74147156501396e-06,
765
+ "loss": 0.7518,
766
+ "step": 108
767
+ },
768
+ {
769
+ "epoch": 0.8755020080321285,
770
+ "grad_norm": 1.0229682922363281,
771
+ "learning_rate": 8.645454235739903e-06,
772
+ "loss": 0.734,
773
+ "step": 109
774
+ },
775
+ {
776
+ "epoch": 0.8835341365461847,
777
+ "grad_norm": 0.9889814257621765,
778
+ "learning_rate": 7.612046748871327e-06,
779
+ "loss": 0.6662,
780
+ "step": 110
781
+ },
782
+ {
783
+ "epoch": 0.891566265060241,
784
+ "grad_norm": 0.9586426019668579,
785
+ "learning_rate": 6.6419573502798374e-06,
786
+ "loss": 0.6482,
787
+ "step": 111
788
+ },
789
+ {
790
+ "epoch": 0.8995983935742972,
791
+ "grad_norm": 1.1700459718704224,
792
+ "learning_rate": 5.735850890782157e-06,
793
+ "loss": 0.7095,
794
+ "step": 112
795
+ },
796
+ {
797
+ "epoch": 0.9076305220883534,
798
+ "grad_norm": 1.0031837224960327,
799
+ "learning_rate": 4.8943483704846475e-06,
800
+ "loss": 0.7488,
801
+ "step": 113
802
+ },
803
+ {
804
+ "epoch": 0.9156626506024096,
805
+ "grad_norm": 1.0449550151824951,
806
+ "learning_rate": 4.118026513180695e-06,
807
+ "loss": 0.7344,
808
+ "step": 114
809
+ },
810
+ {
811
+ "epoch": 0.9236947791164659,
812
+ "grad_norm": 1.0832496881484985,
813
+ "learning_rate": 3.40741737109318e-06,
814
+ "loss": 0.7495,
815
+ "step": 115
816
+ },
817
+ {
818
+ "epoch": 0.9317269076305221,
819
+ "grad_norm": 0.9887351989746094,
820
+ "learning_rate": 2.7630079602323442e-06,
821
+ "loss": 0.6892,
822
+ "step": 116
823
+ },
824
+ {
825
+ "epoch": 0.9397590361445783,
826
+ "grad_norm": 0.9139643311500549,
827
+ "learning_rate": 2.1852399266194314e-06,
828
+ "loss": 0.7611,
829
+ "step": 117
830
+ },
831
+ {
832
+ "epoch": 0.9477911646586346,
833
+ "grad_norm": 0.9678295254707336,
834
+ "learning_rate": 1.6745092436045494e-06,
835
+ "loss": 0.7479,
836
+ "step": 118
837
+ },
838
+ {
839
+ "epoch": 0.9558232931726908,
840
+ "grad_norm": 0.9584624171257019,
841
+ "learning_rate": 1.231165940486234e-06,
842
+ "loss": 0.7046,
843
+ "step": 119
844
+ },
845
+ {
846
+ "epoch": 0.963855421686747,
847
+ "grad_norm": 0.9923776388168335,
848
+ "learning_rate": 8.555138626189618e-07,
849
+ "loss": 0.6822,
850
+ "step": 120
851
+ },
852
+ {
853
+ "epoch": 0.9718875502008032,
854
+ "grad_norm": 1.2370564937591553,
855
+ "learning_rate": 5.478104631726711e-07,
856
+ "loss": 0.8131,
857
+ "step": 121
858
+ },
859
+ {
860
+ "epoch": 0.9799196787148594,
861
+ "grad_norm": 1.0564265251159668,
862
+ "learning_rate": 3.0826662668720364e-07,
863
+ "loss": 0.7308,
864
+ "step": 122
865
+ },
866
+ {
867
+ "epoch": 0.9879518072289156,
868
+ "grad_norm": 1.0349600315093994,
869
+ "learning_rate": 1.3704652454261668e-07,
870
+ "loss": 0.8534,
871
+ "step": 123
872
+ },
873
+ {
874
+ "epoch": 0.9959839357429718,
875
+ "grad_norm": 1.053878664970398,
876
+ "learning_rate": 3.4267502444274015e-08,
877
+ "loss": 0.73,
878
+ "step": 124
879
+ }
880
+ ],
881
+ "logging_steps": 1,
882
+ "max_steps": 124,
883
+ "num_input_tokens_seen": 0,
884
+ "num_train_epochs": 1,
885
+ "save_steps": 124,
886
+ "stateful_callbacks": {
887
+ "TrainerControl": {
888
+ "args": {
889
+ "should_epoch_stop": false,
890
+ "should_evaluate": false,
891
+ "should_log": false,
892
+ "should_save": true,
893
+ "should_training_stop": true
894
+ },
895
+ "attributes": {}
896
+ }
897
+ },
898
+ "total_flos": 1.038039007856832e+16,
899
+ "train_batch_size": 2,
900
+ "trial_name": null,
901
+ "trial_params": null
902
+ }
brats_medgemma_r1_alpha4_20251014_001744/checkpoint-124/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2bec9c7ec03f9ca5f8e1a476a7b82ea5262e70ba6a42a3370b3dedb489dc34c
3
+ size 6353
brats_medgemma_r1_alpha4_20251014_001744/lora_adapters/adapter_config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": {
4
+ "base_model_class": "Gemma3ForConditionalGeneration",
5
+ "parent_library": "transformers.models.gemma3.modeling_gemma3",
6
+ "unsloth_fixed": true
7
+ },
8
+ "base_model_name_or_path": "unsloth/medgemma-4b-it-unsloth-bnb-4bit",
9
+ "bias": "none",
10
+ "corda_config": null,
11
+ "eva_config": null,
12
+ "exclude_modules": null,
13
+ "fan_in_fan_out": false,
14
+ "inference_mode": true,
15
+ "init_lora_weights": true,
16
+ "layer_replication": null,
17
+ "layers_pattern": null,
18
+ "layers_to_transform": null,
19
+ "loftq_config": {},
20
+ "lora_alpha": 4,
21
+ "lora_bias": false,
22
+ "lora_dropout": 0,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "peft_type": "LORA",
27
+ "qalora_group_size": 16,
28
+ "r": 1,
29
+ "rank_pattern": {},
30
+ "revision": null,
31
+ "target_modules": "(?:.*?(?:vision|image|visual|patch|language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:k_proj|v_proj|q_proj|out_proj|fc1|fc2|o_proj|gate_proj|up_proj|down_proj).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:k_proj|v_proj|q_proj|out_proj|fc1|fc2|o_proj|gate_proj|up_proj|down_proj)))",
32
+ "target_parameters": null,
33
+ "task_type": "CAUSAL_LM",
34
+ "trainable_token_indices": null,
35
+ "use_dora": false,
36
+ "use_qalora": false,
37
+ "use_rslora": false
38
+ }
brats_medgemma_r1_alpha4_20251014_001744/lora_adapters/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d15df29b626401034ed224a223eb77fb34e4620cf5a5f5c222d99ab660f5fd8b
3
+ size 9746344
brats_medgemma_r1_alpha4_20251014_001744/lora_adapters/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<image_soft_token>": 262144
3
+ }
brats_medgemma_r1_alpha4_20251014_001744/lora_adapters/chat_template.jinja ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{ bos_token }}
2
+ {%- if messages[0]['role'] == 'system' -%}
3
+ {%- if messages[0]['content'] is string -%}
4
+ {%- set first_user_prefix = messages[0]['content'] + '
5
+
6
+ ' -%}
7
+ {%- else -%}
8
+ {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
9
+
10
+ ' -%}
11
+ {%- endif -%}
12
+ {%- set loop_messages = messages[1:] -%}
13
+ {%- else -%}
14
+ {%- set first_user_prefix = "" -%}
15
+ {%- set loop_messages = messages -%}
16
+ {%- endif -%}
17
+ {%- for message in loop_messages -%}
18
+ {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
19
+ {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
20
+ {%- endif -%}
21
+ {%- if (message['role'] == 'assistant') -%}
22
+ {%- set role = "model" -%}
23
+ {%- else -%}
24
+ {%- set role = message['role'] -%}
25
+ {%- endif -%}
26
+ {{ '<start_of_turn>' + role + '
27
+ ' + (first_user_prefix if loop.first else "") }}
28
+ {%- if message['content'] is string -%}
29
+ {{ message['content'] | trim }}
30
+ {%- elif message['content'] is iterable -%}
31
+ {%- for item in message['content'] -%}
32
+ {%- if item['type'] == 'image' -%}
33
+ {{ '<start_of_image>' }}
34
+ {%- elif item['type'] == 'text' -%}
35
+ {{ item['text'] | trim }}
36
+ {%- endif -%}
37
+ {%- endfor -%}
38
+ {%- else -%}
39
+ {{ raise_exception("Invalid content type") }}
40
+ {%- endif -%}
41
+ {{ '<end_of_turn>
42
+ ' }}
43
+ {%- endfor -%}
44
+ {%- if add_generation_prompt -%}
45
+ {{ '<start_of_turn>model
46
+ ' }}
47
+ {%- endif -%}
brats_medgemma_r1_alpha4_20251014_001744/lora_adapters/preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": null,
3
+ "do_normalize": true,
4
+ "do_pan_and_scan": null,
5
+ "do_rescale": true,
6
+ "do_resize": true,
7
+ "image_mean": [
8
+ 0.5,
9
+ 0.5,
10
+ 0.5
11
+ ],
12
+ "image_processor_type": "Gemma3ImageProcessor",
13
+ "image_seq_length": 256,
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "pan_and_scan_max_num_crops": null,
20
+ "pan_and_scan_min_crop_size": null,
21
+ "pan_and_scan_min_ratio_to_activate": null,
22
+ "processor_class": "Gemma3Processor",
23
+ "resample": 2,
24
+ "rescale_factor": 0.00392156862745098,
25
+ "size": {
26
+ "height": 896,
27
+ "width": 896
28
+ }
29
+ }
brats_medgemma_r1_alpha4_20251014_001744/lora_adapters/processor_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "image_seq_length": 256,
3
+ "processor_class": "Gemma3Processor"
4
+ }
brats_medgemma_r1_alpha4_20251014_001744/lora_adapters/special_tokens_map.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "boi_token": "<start_of_image>",
3
+ "bos_token": {
4
+ "content": "<bos>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "eoi_token": "<end_of_image>",
11
+ "eos_token": {
12
+ "content": "<end_of_turn>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "image_token": "<image_soft_token>",
19
+ "pad_token": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "unk_token": {
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
brats_medgemma_r1_alpha4_20251014_001744/lora_adapters/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
3
+ size 33384568
brats_medgemma_r1_alpha4_20251014_001744/lora_adapters/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
3
+ size 4689074
brats_medgemma_r1_alpha4_20251014_001744/lora_adapters/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
brats_medgemma_r1_alpha4_20251014_001744/merged_model/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<image_soft_token>": 262144
3
+ }
brats_medgemma_r1_alpha4_20251014_001744/merged_model/chat_template.jinja ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{ bos_token }}
2
+ {%- if messages[0]['role'] == 'system' -%}
3
+ {%- if messages[0]['content'] is string -%}
4
+ {%- set first_user_prefix = messages[0]['content'] + '
5
+
6
+ ' -%}
7
+ {%- else -%}
8
+ {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
9
+
10
+ ' -%}
11
+ {%- endif -%}
12
+ {%- set loop_messages = messages[1:] -%}
13
+ {%- else -%}
14
+ {%- set first_user_prefix = "" -%}
15
+ {%- set loop_messages = messages -%}
16
+ {%- endif -%}
17
+ {%- for message in loop_messages -%}
18
+ {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
19
+ {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
20
+ {%- endif -%}
21
+ {%- if (message['role'] == 'assistant') -%}
22
+ {%- set role = "model" -%}
23
+ {%- else -%}
24
+ {%- set role = message['role'] -%}
25
+ {%- endif -%}
26
+ {{ '<start_of_turn>' + role + '
27
+ ' + (first_user_prefix if loop.first else "") }}
28
+ {%- if message['content'] is string -%}
29
+ {{ message['content'] | trim }}
30
+ {%- elif message['content'] is iterable -%}
31
+ {%- for item in message['content'] -%}
32
+ {%- if item['type'] == 'image' -%}
33
+ {{ '<start_of_image>' }}
34
+ {%- elif item['type'] == 'text' -%}
35
+ {{ item['text'] | trim }}
36
+ {%- endif -%}
37
+ {%- endfor -%}
38
+ {%- else -%}
39
+ {{ raise_exception("Invalid content type") }}
40
+ {%- endif -%}
41
+ {{ '<end_of_turn>
42
+ ' }}
43
+ {%- endfor -%}
44
+ {%- if add_generation_prompt -%}
45
+ {{ '<start_of_turn>model
46
+ ' }}
47
+ {%- endif -%}
brats_medgemma_r1_alpha4_20251014_001744/merged_model/config.json ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Gemma3ForConditionalGeneration"
4
+ ],
5
+ "boi_token_index": 255999,
6
+ "bos_token_id": 2,
7
+ "torch_dtype": "bfloat16",
8
+ "eoi_token_index": 256000,
9
+ "eos_token_id": 106,
10
+ "image_token_index": 262144,
11
+ "initializer_range": 0.02,
12
+ "mm_tokens_per_image": 256,
13
+ "model_type": "gemma3",
14
+ "pad_token_id": 0,
15
+ "text_config": {
16
+ "_sliding_window_pattern": 6,
17
+ "attention_bias": false,
18
+ "attention_dropout": 0.0,
19
+ "attn_logit_softcapping": null,
20
+ "cache_implementation": "hybrid",
21
+ "torch_dtype": "bfloat16",
22
+ "final_logit_softcapping": null,
23
+ "head_dim": 256,
24
+ "hidden_activation": "gelu_pytorch_tanh",
25
+ "hidden_size": 2560,
26
+ "initializer_range": 0.02,
27
+ "intermediate_size": 10240,
28
+ "layer_types": [
29
+ "sliding_attention",
30
+ "sliding_attention",
31
+ "sliding_attention",
32
+ "sliding_attention",
33
+ "sliding_attention",
34
+ "full_attention",
35
+ "sliding_attention",
36
+ "sliding_attention",
37
+ "sliding_attention",
38
+ "sliding_attention",
39
+ "sliding_attention",
40
+ "full_attention",
41
+ "sliding_attention",
42
+ "sliding_attention",
43
+ "sliding_attention",
44
+ "sliding_attention",
45
+ "sliding_attention",
46
+ "full_attention",
47
+ "sliding_attention",
48
+ "sliding_attention",
49
+ "sliding_attention",
50
+ "sliding_attention",
51
+ "sliding_attention",
52
+ "full_attention",
53
+ "sliding_attention",
54
+ "sliding_attention",
55
+ "sliding_attention",
56
+ "sliding_attention",
57
+ "sliding_attention",
58
+ "full_attention",
59
+ "sliding_attention",
60
+ "sliding_attention",
61
+ "sliding_attention",
62
+ "sliding_attention"
63
+ ],
64
+ "max_position_embeddings": 131072,
65
+ "model_type": "gemma3_text",
66
+ "num_attention_heads": 8,
67
+ "num_hidden_layers": 34,
68
+ "num_key_value_heads": 4,
69
+ "query_pre_attn_scalar": 256,
70
+ "rms_norm_eps": 1e-06,
71
+ "rope_local_base_freq": 10000,
72
+ "rope_scaling": {
73
+ "factor": 8.0,
74
+ "rope_type": "linear"
75
+ },
76
+ "rope_theta": 1000000,
77
+ "sliding_window": 1024,
78
+ "use_cache": true,
79
+ "vocab_size": 262208
80
+ },
81
+ "transformers_version": "4.56.2",
82
+ "unsloth_fixed": true,
83
+ "unsloth_version": "2025.10.1",
84
+ "vision_config": {
85
+ "attention_dropout": 0.0,
86
+ "torch_dtype": "bfloat16",
87
+ "hidden_act": "gelu_pytorch_tanh",
88
+ "hidden_size": 1152,
89
+ "image_size": 896,
90
+ "intermediate_size": 4304,
91
+ "layer_norm_eps": 1e-06,
92
+ "model_type": "siglip_vision_model",
93
+ "num_attention_heads": 16,
94
+ "num_channels": 3,
95
+ "num_hidden_layers": 27,
96
+ "patch_size": 14,
97
+ "vision_use_head": false
98
+ }
99
+ }
brats_medgemma_r1_alpha4_20251014_001744/merged_model/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acbdfbacb836378223af927d80fdae2c5876efca87987f2137c677e2f19203d1
3
+ size 4961251752
brats_medgemma_r1_alpha4_20251014_001744/merged_model/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2153f61cfda4606fd51ffe81acb5f81fada3cb9791ad8f21ccd0b194b1d67a15
3
+ size 3639026128
brats_medgemma_r1_alpha4_20251014_001744/merged_model/model.safetensors.index.json ADDED
@@ -0,0 +1,891 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 4971331952,
4
+ "total_size": 8600158944
5
+ },
6
+ "weight_map": {
7
+ "language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
+ "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
9
+ "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
10
+ "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
11
+ "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
12
+ "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
13
+ "language_model.model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
14
+ "language_model.model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
15
+ "language_model.model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
16
+ "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
17
+ "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
18
+ "language_model.model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
19
+ "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
20
+ "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
21
+ "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
22
+ "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
23
+ "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
24
+ "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
25
+ "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
26
+ "language_model.model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
27
+ "language_model.model.layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
28
+ "language_model.model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
29
+ "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
30
+ "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
31
+ "language_model.model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
32
+ "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
33
+ "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
34
+ "language_model.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
35
+ "language_model.model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
36
+ "language_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
37
+ "language_model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
38
+ "language_model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
39
+ "language_model.model.layers.10.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
40
+ "language_model.model.layers.10.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
41
+ "language_model.model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
42
+ "language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
43
+ "language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
44
+ "language_model.model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
45
+ "language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
46
+ "language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
47
+ "language_model.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
48
+ "language_model.model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
49
+ "language_model.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
50
+ "language_model.model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
51
+ "language_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
52
+ "language_model.model.layers.11.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
53
+ "language_model.model.layers.11.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
54
+ "language_model.model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
55
+ "language_model.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
56
+ "language_model.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
57
+ "language_model.model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
58
+ "language_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
59
+ "language_model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
60
+ "language_model.model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
61
+ "language_model.model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
62
+ "language_model.model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
63
+ "language_model.model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
64
+ "language_model.model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
65
+ "language_model.model.layers.12.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
66
+ "language_model.model.layers.12.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
67
+ "language_model.model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
68
+ "language_model.model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
69
+ "language_model.model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
70
+ "language_model.model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
71
+ "language_model.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
72
+ "language_model.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
73
+ "language_model.model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
74
+ "language_model.model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
75
+ "language_model.model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
76
+ "language_model.model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
77
+ "language_model.model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
78
+ "language_model.model.layers.13.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
79
+ "language_model.model.layers.13.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
80
+ "language_model.model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
81
+ "language_model.model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
82
+ "language_model.model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
83
+ "language_model.model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
84
+ "language_model.model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
85
+ "language_model.model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
86
+ "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
87
+ "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
88
+ "language_model.model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
89
+ "language_model.model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
90
+ "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
91
+ "language_model.model.layers.14.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
92
+ "language_model.model.layers.14.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
93
+ "language_model.model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
94
+ "language_model.model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
95
+ "language_model.model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
96
+ "language_model.model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
97
+ "language_model.model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
98
+ "language_model.model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
99
+ "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
100
+ "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
101
+ "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
102
+ "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
103
+ "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
104
+ "language_model.model.layers.15.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
105
+ "language_model.model.layers.15.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
106
+ "language_model.model.layers.15.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
107
+ "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
108
+ "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
109
+ "language_model.model.layers.15.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
110
+ "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
111
+ "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
112
+ "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
113
+ "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
114
+ "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
115
+ "language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
116
+ "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
117
+ "language_model.model.layers.16.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
118
+ "language_model.model.layers.16.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
119
+ "language_model.model.layers.16.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
120
+ "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
121
+ "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
122
+ "language_model.model.layers.16.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
123
+ "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
124
+ "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
125
+ "language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
126
+ "language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
127
+ "language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
128
+ "language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
129
+ "language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
130
+ "language_model.model.layers.17.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
131
+ "language_model.model.layers.17.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
132
+ "language_model.model.layers.17.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
133
+ "language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
134
+ "language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
135
+ "language_model.model.layers.17.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
136
+ "language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
137
+ "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
138
+ "language_model.model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
139
+ "language_model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
140
+ "language_model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
141
+ "language_model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
142
+ "language_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
143
+ "language_model.model.layers.18.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
144
+ "language_model.model.layers.18.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
145
+ "language_model.model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
146
+ "language_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
147
+ "language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
148
+ "language_model.model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
149
+ "language_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
150
+ "language_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
151
+ "language_model.model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
152
+ "language_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
153
+ "language_model.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
154
+ "language_model.model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
155
+ "language_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
156
+ "language_model.model.layers.19.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
157
+ "language_model.model.layers.19.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
158
+ "language_model.model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
159
+ "language_model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
160
+ "language_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
161
+ "language_model.model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
162
+ "language_model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
163
+ "language_model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
164
+ "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
165
+ "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
166
+ "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
167
+ "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
168
+ "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
169
+ "language_model.model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
170
+ "language_model.model.layers.2.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
171
+ "language_model.model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
172
+ "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
173
+ "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
174
+ "language_model.model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
175
+ "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
176
+ "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
177
+ "language_model.model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
178
+ "language_model.model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
179
+ "language_model.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
180
+ "language_model.model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
181
+ "language_model.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
182
+ "language_model.model.layers.20.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
183
+ "language_model.model.layers.20.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
184
+ "language_model.model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
185
+ "language_model.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
186
+ "language_model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
187
+ "language_model.model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
188
+ "language_model.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
189
+ "language_model.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
190
+ "language_model.model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
191
+ "language_model.model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
192
+ "language_model.model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
193
+ "language_model.model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
194
+ "language_model.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
195
+ "language_model.model.layers.21.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
196
+ "language_model.model.layers.21.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
197
+ "language_model.model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
198
+ "language_model.model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
199
+ "language_model.model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
200
+ "language_model.model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
201
+ "language_model.model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
202
+ "language_model.model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
203
+ "language_model.model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
204
+ "language_model.model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
205
+ "language_model.model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
206
+ "language_model.model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
207
+ "language_model.model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
208
+ "language_model.model.layers.22.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
209
+ "language_model.model.layers.22.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
210
+ "language_model.model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
211
+ "language_model.model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
212
+ "language_model.model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
213
+ "language_model.model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
214
+ "language_model.model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
215
+ "language_model.model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
216
+ "language_model.model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
217
+ "language_model.model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
218
+ "language_model.model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
219
+ "language_model.model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
220
+ "language_model.model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
221
+ "language_model.model.layers.23.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
222
+ "language_model.model.layers.23.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
223
+ "language_model.model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
224
+ "language_model.model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
225
+ "language_model.model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
226
+ "language_model.model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
227
+ "language_model.model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
228
+ "language_model.model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
229
+ "language_model.model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
230
+ "language_model.model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
231
+ "language_model.model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
232
+ "language_model.model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
233
+ "language_model.model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
234
+ "language_model.model.layers.24.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
235
+ "language_model.model.layers.24.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
236
+ "language_model.model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
237
+ "language_model.model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
238
+ "language_model.model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
239
+ "language_model.model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
240
+ "language_model.model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
241
+ "language_model.model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
242
+ "language_model.model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
243
+ "language_model.model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
244
+ "language_model.model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
245
+ "language_model.model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
246
+ "language_model.model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
247
+ "language_model.model.layers.25.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
248
+ "language_model.model.layers.25.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
249
+ "language_model.model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
250
+ "language_model.model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
251
+ "language_model.model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
252
+ "language_model.model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
253
+ "language_model.model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
254
+ "language_model.model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
255
+ "language_model.model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
256
+ "language_model.model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
257
+ "language_model.model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
258
+ "language_model.model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
259
+ "language_model.model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
260
+ "language_model.model.layers.26.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
261
+ "language_model.model.layers.26.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
262
+ "language_model.model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
263
+ "language_model.model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
264
+ "language_model.model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
265
+ "language_model.model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
266
+ "language_model.model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
267
+ "language_model.model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
268
+ "language_model.model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
269
+ "language_model.model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
270
+ "language_model.model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
271
+ "language_model.model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
272
+ "language_model.model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
273
+ "language_model.model.layers.27.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
274
+ "language_model.model.layers.27.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
275
+ "language_model.model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
276
+ "language_model.model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
277
+ "language_model.model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
278
+ "language_model.model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
279
+ "language_model.model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
280
+ "language_model.model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
281
+ "language_model.model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
282
+ "language_model.model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
283
+ "language_model.model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
284
+ "language_model.model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
285
+ "language_model.model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
286
+ "language_model.model.layers.28.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
287
+ "language_model.model.layers.28.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
288
+ "language_model.model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
289
+ "language_model.model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
290
+ "language_model.model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
291
+ "language_model.model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
292
+ "language_model.model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
293
+ "language_model.model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
294
+ "language_model.model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
295
+ "language_model.model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
296
+ "language_model.model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
297
+ "language_model.model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
298
+ "language_model.model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
299
+ "language_model.model.layers.29.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
300
+ "language_model.model.layers.29.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
301
+ "language_model.model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
302
+ "language_model.model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
303
+ "language_model.model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
304
+ "language_model.model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
305
+ "language_model.model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
306
+ "language_model.model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
307
+ "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
308
+ "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
309
+ "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
310
+ "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
311
+ "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
312
+ "language_model.model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
313
+ "language_model.model.layers.3.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
314
+ "language_model.model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
315
+ "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
316
+ "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
317
+ "language_model.model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
318
+ "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
319
+ "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
320
+ "language_model.model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
321
+ "language_model.model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
322
+ "language_model.model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
323
+ "language_model.model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
324
+ "language_model.model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
325
+ "language_model.model.layers.30.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
326
+ "language_model.model.layers.30.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
327
+ "language_model.model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
328
+ "language_model.model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
329
+ "language_model.model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
330
+ "language_model.model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
331
+ "language_model.model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
332
+ "language_model.model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
333
+ "language_model.model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
334
+ "language_model.model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
335
+ "language_model.model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
336
+ "language_model.model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
337
+ "language_model.model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
338
+ "language_model.model.layers.31.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
339
+ "language_model.model.layers.31.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
340
+ "language_model.model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
341
+ "language_model.model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
342
+ "language_model.model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
343
+ "language_model.model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
344
+ "language_model.model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
345
+ "language_model.model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
346
+ "language_model.model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
347
+ "language_model.model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
348
+ "language_model.model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
349
+ "language_model.model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
350
+ "language_model.model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
351
+ "language_model.model.layers.32.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
352
+ "language_model.model.layers.32.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
353
+ "language_model.model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
354
+ "language_model.model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
355
+ "language_model.model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
356
+ "language_model.model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
357
+ "language_model.model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
358
+ "language_model.model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
359
+ "language_model.model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
360
+ "language_model.model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
361
+ "language_model.model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
362
+ "language_model.model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
363
+ "language_model.model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
364
+ "language_model.model.layers.33.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
365
+ "language_model.model.layers.33.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
366
+ "language_model.model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
367
+ "language_model.model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
368
+ "language_model.model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
369
+ "language_model.model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
370
+ "language_model.model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
371
+ "language_model.model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
372
+ "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
373
+ "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
374
+ "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
375
+ "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
376
+ "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
377
+ "language_model.model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
378
+ "language_model.model.layers.4.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
379
+ "language_model.model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
380
+ "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
381
+ "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
382
+ "language_model.model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
383
+ "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
384
+ "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
385
+ "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
386
+ "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
387
+ "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
388
+ "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
389
+ "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
390
+ "language_model.model.layers.5.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
391
+ "language_model.model.layers.5.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
392
+ "language_model.model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
393
+ "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
394
+ "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
395
+ "language_model.model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
396
+ "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
397
+ "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
398
+ "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
399
+ "language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
400
+ "language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
401
+ "language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
402
+ "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
403
+ "language_model.model.layers.6.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
404
+ "language_model.model.layers.6.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
405
+ "language_model.model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
406
+ "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
407
+ "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
408
+ "language_model.model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
409
+ "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
410
+ "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
411
+ "language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
412
+ "language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
413
+ "language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
414
+ "language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
415
+ "language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
416
+ "language_model.model.layers.7.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
417
+ "language_model.model.layers.7.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
418
+ "language_model.model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
419
+ "language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
420
+ "language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
421
+ "language_model.model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
422
+ "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
423
+ "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
424
+ "language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
425
+ "language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
426
+ "language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
427
+ "language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
428
+ "language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
429
+ "language_model.model.layers.8.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
430
+ "language_model.model.layers.8.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
431
+ "language_model.model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
432
+ "language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
433
+ "language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
434
+ "language_model.model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
435
+ "language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
436
+ "language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
437
+ "language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
438
+ "language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
439
+ "language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
440
+ "language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
441
+ "language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
442
+ "language_model.model.layers.9.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
443
+ "language_model.model.layers.9.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
444
+ "language_model.model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
445
+ "language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
446
+ "language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
447
+ "language_model.model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
448
+ "language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
449
+ "language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
450
+ "language_model.model.norm.weight": "model-00002-of-00002.safetensors",
451
+ "multi_modal_projector.mm_input_projection_weight": "model-00001-of-00002.safetensors",
452
+ "multi_modal_projector.mm_soft_emb_norm.weight": "model-00001-of-00002.safetensors",
453
+ "vision_tower.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00002.safetensors",
454
+ "vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00002.safetensors",
455
+ "vision_tower.vision_model.embeddings.position_embedding.weight": "model-00001-of-00002.safetensors",
456
+ "vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00002.safetensors",
457
+ "vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00002.safetensors",
458
+ "vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00002.safetensors",
459
+ "vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00002.safetensors",
460
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
461
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
462
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
463
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
464
+ "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
465
+ "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
466
+ "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
467
+ "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
468
+ "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
469
+ "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
470
+ "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
471
+ "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
472
+ "vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00002.safetensors",
473
+ "vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00002.safetensors",
474
+ "vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00002.safetensors",
475
+ "vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00002.safetensors",
476
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
477
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
478
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
479
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
480
+ "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
481
+ "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
482
+ "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
483
+ "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
484
+ "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
485
+ "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
486
+ "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
487
+ "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
488
+ "vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00002.safetensors",
489
+ "vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00002.safetensors",
490
+ "vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00002.safetensors",
491
+ "vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00002.safetensors",
492
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
493
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
494
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
495
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
496
+ "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
497
+ "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
498
+ "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
499
+ "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
500
+ "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
501
+ "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
502
+ "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
503
+ "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
504
+ "vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00002.safetensors",
505
+ "vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00002.safetensors",
506
+ "vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00002.safetensors",
507
+ "vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00002.safetensors",
508
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
509
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
510
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
511
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
512
+ "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
513
+ "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
514
+ "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
515
+ "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
516
+ "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
517
+ "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
518
+ "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
519
+ "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
520
+ "vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00002.safetensors",
521
+ "vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00002.safetensors",
522
+ "vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00002.safetensors",
523
+ "vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00002.safetensors",
524
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
525
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
526
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
527
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
528
+ "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
529
+ "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
530
+ "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
531
+ "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
532
+ "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
533
+ "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
534
+ "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
535
+ "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
536
+ "vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00002.safetensors",
537
+ "vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00002.safetensors",
538
+ "vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00002.safetensors",
539
+ "vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00002.safetensors",
540
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
541
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
542
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
543
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
544
+ "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
545
+ "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
546
+ "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
547
+ "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
548
+ "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
549
+ "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
550
+ "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
551
+ "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
552
+ "vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00002.safetensors",
553
+ "vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00002.safetensors",
554
+ "vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00002.safetensors",
555
+ "vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00002.safetensors",
556
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
557
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
558
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
559
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
560
+ "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
561
+ "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
562
+ "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
563
+ "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
564
+ "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
565
+ "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
566
+ "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
567
+ "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
568
+ "vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00002.safetensors",
569
+ "vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00002.safetensors",
570
+ "vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00002.safetensors",
571
+ "vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00002.safetensors",
572
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
573
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
574
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
575
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
576
+ "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
577
+ "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
578
+ "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
579
+ "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
580
+ "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
581
+ "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
582
+ "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
583
+ "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
584
+ "vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00002.safetensors",
585
+ "vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00002.safetensors",
586
+ "vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00002.safetensors",
587
+ "vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00002.safetensors",
588
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
589
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
590
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
591
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
592
+ "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
593
+ "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
594
+ "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
595
+ "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
596
+ "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
597
+ "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
598
+ "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
599
+ "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
600
+ "vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00002.safetensors",
601
+ "vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00002.safetensors",
602
+ "vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00002.safetensors",
603
+ "vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00002.safetensors",
604
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
605
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
606
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
607
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
608
+ "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
609
+ "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
610
+ "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
611
+ "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
612
+ "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
613
+ "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
614
+ "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
615
+ "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
616
+ "vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00002.safetensors",
617
+ "vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00002.safetensors",
618
+ "vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00002.safetensors",
619
+ "vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00002.safetensors",
620
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
621
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
622
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
623
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
624
+ "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
625
+ "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
626
+ "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
627
+ "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
628
+ "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
629
+ "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
630
+ "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
631
+ "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
632
+ "vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00002.safetensors",
633
+ "vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00002.safetensors",
634
+ "vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00002.safetensors",
635
+ "vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00002.safetensors",
636
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
637
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
638
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
639
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
640
+ "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
641
+ "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
642
+ "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
643
+ "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
644
+ "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
645
+ "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
646
+ "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
647
+ "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
648
+ "vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00002.safetensors",
649
+ "vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00002.safetensors",
650
+ "vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00002.safetensors",
651
+ "vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00002.safetensors",
652
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
653
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
654
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
655
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
656
+ "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
657
+ "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
658
+ "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
659
+ "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
660
+ "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
661
+ "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
662
+ "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
663
+ "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
664
+ "vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00002.safetensors",
665
+ "vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00002.safetensors",
666
+ "vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00002.safetensors",
667
+ "vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00002.safetensors",
668
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
669
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
670
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
671
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
672
+ "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
673
+ "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
674
+ "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
675
+ "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
676
+ "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
677
+ "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
678
+ "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
679
+ "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
680
+ "vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00002.safetensors",
681
+ "vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00002.safetensors",
682
+ "vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00002.safetensors",
683
+ "vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00002.safetensors",
684
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
685
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
686
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
687
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
688
+ "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
689
+ "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
690
+ "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
691
+ "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
692
+ "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
693
+ "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
694
+ "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
695
+ "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
696
+ "vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00002.safetensors",
697
+ "vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00002.safetensors",
698
+ "vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00002.safetensors",
699
+ "vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00002.safetensors",
700
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
701
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
702
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
703
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
704
+ "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
705
+ "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
706
+ "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
707
+ "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
708
+ "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
709
+ "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
710
+ "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
711
+ "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
712
+ "vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00002.safetensors",
713
+ "vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00002.safetensors",
714
+ "vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00002.safetensors",
715
+ "vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00002.safetensors",
716
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
717
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
718
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
719
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
720
+ "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
721
+ "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
722
+ "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
723
+ "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
724
+ "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
725
+ "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
726
+ "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
727
+ "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
728
+ "vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00002.safetensors",
729
+ "vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00002.safetensors",
730
+ "vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00002.safetensors",
731
+ "vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00002.safetensors",
732
+ "vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
733
+ "vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
734
+ "vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
735
+ "vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
736
+ "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
737
+ "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
738
+ "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
739
+ "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
740
+ "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
741
+ "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
742
+ "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
743
+ "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
744
+ "vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00002.safetensors",
745
+ "vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00002.safetensors",
746
+ "vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00002.safetensors",
747
+ "vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00002.safetensors",
748
+ "vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
749
+ "vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
750
+ "vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
751
+ "vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
752
+ "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
753
+ "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
754
+ "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
755
+ "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
756
+ "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
757
+ "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
758
+ "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
759
+ "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
760
+ "vision_tower.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00002.safetensors",
761
+ "vision_tower.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00002.safetensors",
762
+ "vision_tower.vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00002.safetensors",
763
+ "vision_tower.vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00002.safetensors",
764
+ "vision_tower.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
765
+ "vision_tower.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
766
+ "vision_tower.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
767
+ "vision_tower.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
768
+ "vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
769
+ "vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
770
+ "vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
771
+ "vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
772
+ "vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
773
+ "vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
774
+ "vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
775
+ "vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
776
+ "vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00002.safetensors",
777
+ "vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00002.safetensors",
778
+ "vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00002.safetensors",
779
+ "vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00002.safetensors",
780
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
781
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
782
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
783
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
784
+ "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
785
+ "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
786
+ "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
787
+ "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
788
+ "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
789
+ "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
790
+ "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
791
+ "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
792
+ "vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00002.safetensors",
793
+ "vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00002.safetensors",
794
+ "vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00002.safetensors",
795
+ "vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00002.safetensors",
796
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
797
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
798
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
799
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
800
+ "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
801
+ "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
802
+ "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
803
+ "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
804
+ "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
805
+ "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
806
+ "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
807
+ "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
808
+ "vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00002.safetensors",
809
+ "vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00002.safetensors",
810
+ "vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00002.safetensors",
811
+ "vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00002.safetensors",
812
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
813
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
814
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
815
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
816
+ "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
817
+ "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
818
+ "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
819
+ "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
820
+ "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
821
+ "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
822
+ "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
823
+ "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
824
+ "vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00002.safetensors",
825
+ "vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00002.safetensors",
826
+ "vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00002.safetensors",
827
+ "vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00002.safetensors",
828
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
829
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
830
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
831
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
832
+ "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
833
+ "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
834
+ "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
835
+ "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
836
+ "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
837
+ "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
838
+ "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
839
+ "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
840
+ "vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00002.safetensors",
841
+ "vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00002.safetensors",
842
+ "vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00002.safetensors",
843
+ "vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00002.safetensors",
844
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
845
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
846
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
847
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
848
+ "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
849
+ "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
850
+ "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
851
+ "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
852
+ "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
853
+ "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
854
+ "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
855
+ "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
856
+ "vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00002.safetensors",
857
+ "vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00002.safetensors",
858
+ "vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00002.safetensors",
859
+ "vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00002.safetensors",
860
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
861
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
862
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
863
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
864
+ "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
865
+ "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
866
+ "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
867
+ "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
868
+ "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
869
+ "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
870
+ "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
871
+ "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
872
+ "vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00002.safetensors",
873
+ "vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00002.safetensors",
874
+ "vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00002.safetensors",
875
+ "vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00002.safetensors",
876
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
877
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
878
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
879
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
880
+ "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
881
+ "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
882
+ "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
883
+ "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
884
+ "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
885
+ "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
886
+ "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
887
+ "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
888
+ "vision_tower.vision_model.post_layernorm.bias": "model-00001-of-00002.safetensors",
889
+ "vision_tower.vision_model.post_layernorm.weight": "model-00001-of-00002.safetensors"
890
+ }
891
+ }
brats_medgemma_r1_alpha4_20251014_001744/merged_model/preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": null,
3
+ "do_normalize": true,
4
+ "do_pan_and_scan": null,
5
+ "do_rescale": true,
6
+ "do_resize": true,
7
+ "image_mean": [
8
+ 0.5,
9
+ 0.5,
10
+ 0.5
11
+ ],
12
+ "image_processor_type": "Gemma3ImageProcessor",
13
+ "image_seq_length": 256,
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "pan_and_scan_max_num_crops": null,
20
+ "pan_and_scan_min_crop_size": null,
21
+ "pan_and_scan_min_ratio_to_activate": null,
22
+ "processor_class": "Gemma3Processor",
23
+ "resample": 2,
24
+ "rescale_factor": 0.00392156862745098,
25
+ "size": {
26
+ "height": 896,
27
+ "width": 896
28
+ }
29
+ }
brats_medgemma_r1_alpha4_20251014_001744/merged_model/processor_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "image_seq_length": 256,
3
+ "processor_class": "Gemma3Processor"
4
+ }
brats_medgemma_r1_alpha4_20251014_001744/merged_model/special_tokens_map.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "boi_token": "<start_of_image>",
3
+ "bos_token": {
4
+ "content": "<bos>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "eoi_token": "<end_of_image>",
11
+ "eos_token": {
12
+ "content": "<end_of_turn>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "image_token": "<image_soft_token>",
19
+ "pad_token": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "unk_token": {
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
brats_medgemma_r1_alpha4_20251014_001744/merged_model/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
3
+ size 33384568
brats_medgemma_r1_alpha4_20251014_001744/merged_model/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
3
+ size 4689074
brats_medgemma_r1_alpha4_20251014_001744/merged_model/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
brats_medgemma_r1_alpha4_20251014_001744/metrics/complete_data_distribution_20251014_001744.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "experiment_metadata": {
3
+ "timestamp": "20251014_001744",
4
+ "random_seed": 3407,
5
+ "source_dataset": "Jupitern52/TextBraTS"
6
+ },
7
+ "data_summary": {
8
+ "original_textbrats_samples": 369,
9
+ "available_patients": 369,
10
+ "patients_used": 369,
11
+ "total_created_samples": 1107,
12
+ "train_samples": 996,
13
+ "test_samples": 111
14
+ },
15
+ "train_split": {
16
+ "image_type_distribution": {
17
+ "single_slice": 336,
18
+ "three_slices": 326,
19
+ "five_slices": 334
20
+ }
21
+ },
22
+ "test_split": {
23
+ "image_type_distribution": {
24
+ "three_slices": 43,
25
+ "five_slices": 35,
26
+ "single_slice": 33
27
+ }
28
+ }
29
+ }
brats_medgemma_r1_alpha4_20251014_001744/metrics/test_detailed_20251014_001744.csv ADDED
The diff for this file is too large to render. See raw diff
 
brats_medgemma_r1_alpha4_20251014_001744/metrics/test_summary_20251014_001744.csv ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ Metric,Score
2
+ ROUGE1,0.617902
3
+ ROUGE2,0.334360
4
+ ROUGEL,0.455338
brats_medgemma_r1_alpha4_20251014_001744/metrics/training_log_20251014_001744.csv ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ step,epoch,loss,learning_rate,grad_norm,elapsed_time_s,timestamp
2
+ 1,0.0080,3.661000,0.00e+00,2.0198,4.46,2025-10-14 00:19:53
3
+ 2,0.0161,3.531500,5.00e-05,1.2854,7.24,2025-10-14 00:19:56
4
+ 3,0.0241,3.456500,1.00e-04,1.1758,10.23,2025-10-14 00:19:59
5
+ 4,0.0321,3.539600,1.50e-04,1.3130,12.95,2025-10-14 00:20:02
6
+ 5,0.0402,3.524600,2.00e-04,1.6722,15.74,2025-10-14 00:20:04
7
+ 6,0.0482,3.302400,2.00e-04,1.5012,18.72,2025-10-14 00:20:07
8
+ 7,0.0562,3.262700,2.00e-04,1.6597,21.35,2025-10-14 00:20:10
9
+ 8,0.0643,3.071700,2.00e-04,1.6134,24.17,2025-10-14 00:20:13
10
+ 9,0.0723,2.929800,1.99e-04,1.6856,27.04,2025-10-14 00:20:16
11
+ 10,0.0803,2.715500,1.99e-04,1.6935,52.14,2025-10-14 00:20:41
12
+ 11,0.0884,2.640000,1.99e-04,1.7328,54.82,2025-10-14 00:20:43
13
+ 12,0.0964,2.626500,1.98e-04,1.8866,57.80,2025-10-14 00:20:46
14
+ 13,0.1044,2.396900,1.98e-04,2.0052,60.51,2025-10-14 00:20:49
15
+ 14,0.1124,2.239700,1.97e-04,2.0363,63.20,2025-10-14 00:20:52
16
+ 15,0.1205,2.183900,1.97e-04,2.2752,66.14,2025-10-14 00:20:55
17
+ 16,0.1285,2.086800,1.96e-04,2.1745,68.87,2025-10-14 00:20:57
18
+ 17,0.1365,1.949700,1.95e-04,2.3118,71.48,2025-10-14 00:21:00
19
+ 18,0.1446,1.935200,1.94e-04,2.1332,74.36,2025-10-14 00:21:03
20
+ 19,0.1526,1.792200,1.93e-04,1.9905,77.08,2025-10-14 00:21:06
21
+ 20,0.1606,1.726100,1.92e-04,1.7198,103.39,2025-10-14 00:21:32
22
+ 21,0.1687,1.705700,1.91e-04,1.8796,106.33,2025-10-14 00:21:35
23
+ 22,0.1767,1.560500,1.90e-04,1.8937,109.06,2025-10-14 00:21:38
24
+ 23,0.1847,1.604000,1.89e-04,1.9555,111.70,2025-10-14 00:21:40
25
+ 24,0.1928,1.535300,1.88e-04,1.7592,114.71,2025-10-14 00:21:43
26
+ 25,0.2008,1.456400,1.87e-04,1.8183,117.42,2025-10-14 00:21:46
27
+ 26,0.2088,1.441400,1.85e-04,1.7630,120.08,2025-10-14 00:21:49
28
+ 27,0.2169,1.371500,1.84e-04,1.6806,123.01,2025-10-14 00:21:52
29
+ 28,0.2249,1.230300,1.82e-04,1.6418,125.73,2025-10-14 00:21:54
30
+ 29,0.2329,1.229200,1.81e-04,1.5277,128.45,2025-10-14 00:21:57
31
+ 30,0.2410,1.335900,1.79e-04,1.7861,155.03,2025-10-14 00:22:24
32
+ 31,0.2490,1.134800,1.78e-04,1.6361,157.72,2025-10-14 00:22:26
33
+ 32,0.2570,1.292600,1.76e-04,1.5470,160.35,2025-10-14 00:22:29
34
+ 33,0.2651,1.180400,1.74e-04,1.4081,163.25,2025-10-14 00:22:32
35
+ 34,0.2731,1.045400,1.73e-04,1.4029,165.92,2025-10-14 00:22:34
36
+ 35,0.2811,1.078000,1.71e-04,1.4556,168.55,2025-10-14 00:22:37
37
+ 36,0.2892,1.106100,1.69e-04,1.3027,171.47,2025-10-14 00:22:40
38
+ 37,0.2972,0.999700,1.67e-04,1.1518,174.19,2025-10-14 00:22:43
39
+ 38,0.3052,1.036500,1.65e-04,1.3399,176.93,2025-10-14 00:22:45
40
+ 39,0.3133,0.945700,1.63e-04,1.3087,179.86,2025-10-14 00:22:48
41
+ 40,0.3213,1.080200,1.61e-04,1.3928,206.68,2025-10-14 00:23:15
42
+ 41,0.3293,0.929400,1.59e-04,1.2438,209.35,2025-10-14 00:23:18
43
+ 42,0.3373,0.967400,1.57e-04,1.2407,212.33,2025-10-14 00:23:21
44
+ 43,0.3454,0.996500,1.54e-04,1.2784,215.07,2025-10-14 00:23:24
45
+ 44,0.3534,0.985600,1.52e-04,1.2946,217.79,2025-10-14 00:23:26
46
+ 45,0.3614,0.868000,1.50e-04,1.4061,220.63,2025-10-14 00:23:29
47
+ 46,0.3695,0.924700,1.48e-04,1.2647,223.29,2025-10-14 00:23:32
48
+ 47,0.3775,0.904800,1.45e-04,1.1977,225.97,2025-10-14 00:23:35
49
+ 48,0.3855,0.892200,1.43e-04,1.2491,228.89,2025-10-14 00:23:37
50
+ 49,0.3936,0.917000,1.41e-04,1.3626,231.53,2025-10-14 00:23:40
51
+ 50,0.4016,0.894900,1.38e-04,1.2563,260.13,2025-10-14 00:24:09
52
+ 51,0.4096,0.959400,1.36e-04,1.2959,263.03,2025-10-14 00:24:12
53
+ 52,0.4177,0.868900,1.33e-04,1.1772,265.76,2025-10-14 00:24:14
54
+ 53,0.4257,0.733000,1.31e-04,1.2049,268.46,2025-10-14 00:24:17
55
+ 54,0.4337,0.827700,1.28e-04,1.2039,271.34,2025-10-14 00:24:20
56
+ 55,0.4418,0.814100,1.26e-04,1.2360,274.04,2025-10-14 00:24:23
57
+ 56,0.4498,0.788000,1.23e-04,1.3564,276.71,2025-10-14 00:24:25
58
+ 57,0.4578,0.857200,1.21e-04,1.3570,279.62,2025-10-14 00:24:28
59
+ 58,0.4659,0.747900,1.18e-04,1.3413,282.30,2025-10-14 00:24:31
60
+ 59,0.4739,0.860300,1.16e-04,2.1705,285.06,2025-10-14 00:24:34
61
+ 60,0.4819,0.933400,1.13e-04,1.6985,312.60,2025-10-14 00:25:01
62
+ 61,0.4900,0.767500,1.10e-04,1.7688,315.26,2025-10-14 00:25:04
63
+ 62,0.4980,0.794800,1.08e-04,1.2065,317.95,2025-10-14 00:25:06
64
+ 63,0.5060,0.775600,1.05e-04,1.2789,320.88,2025-10-14 00:25:09
65
+ 64,0.5141,0.796900,1.03e-04,1.3654,323.56,2025-10-14 00:25:12
66
+ 65,0.5221,0.749700,1.00e-04,1.2265,326.29,2025-10-14 00:25:15
67
+ 66,0.5301,0.824900,9.74e-05,1.1440,329.14,2025-10-14 00:25:18
68
+ 67,0.5382,0.799000,9.48e-05,1.1888,331.82,2025-10-14 00:25:20
69
+ 68,0.5462,0.788400,9.22e-05,1.2541,334.57,2025-10-14 00:25:23
70
+ 69,0.5542,0.751200,8.95e-05,1.5007,337.45,2025-10-14 00:25:26
71
+ 70,0.5622,0.794600,8.69e-05,1.3374,367.03,2025-10-14 00:25:56
72
+ 71,0.5703,0.723600,8.44e-05,1.0757,370.04,2025-10-14 00:25:59
73
+ 72,0.5783,0.761800,8.18e-05,1.5441,372.70,2025-10-14 00:26:01
74
+ 73,0.5863,0.695700,7.92e-05,1.1212,375.41,2025-10-14 00:26:04
75
+ 74,0.5944,0.846200,7.67e-05,1.2741,378.10,2025-10-14 00:26:07
76
+ 75,0.6024,0.671300,7.41e-05,1.0581,381.03,2025-10-14 00:26:10
77
+ 76,0.6104,0.817500,7.16e-05,1.3544,383.65,2025-10-14 00:26:12
78
+ 77,0.6185,0.684900,6.91e-05,1.1733,386.32,2025-10-14 00:26:15
79
+ 78,0.6265,0.713700,6.66e-05,1.1747,389.25,2025-10-14 00:26:18
80
+ 79,0.6345,0.710600,6.42e-05,1.3374,391.99,2025-10-14 00:26:21
81
+ 80,0.6426,0.736300,6.17e-05,1.1054,421.14,2025-10-14 00:26:50
82
+ 81,0.6506,0.706300,5.93e-05,1.1044,424.04,2025-10-14 00:26:53
83
+ 82,0.6586,0.703400,5.69e-05,1.0287,426.77,2025-10-14 00:26:55
84
+ 83,0.6667,0.689400,5.46e-05,1.0179,429.51,2025-10-14 00:26:58
85
+ 84,0.6747,0.669200,5.23e-05,1.0863,432.41,2025-10-14 00:27:01
86
+ 85,0.6827,0.724400,5.00e-05,1.2529,435.07,2025-10-14 00:27:04
87
+ 86,0.6908,0.701500,4.78e-05,0.9438,437.78,2025-10-14 00:27:06
88
+ 87,0.6988,0.688800,4.55e-05,0.9460,440.70,2025-10-14 00:27:09
89
+ 88,0.7068,0.590300,4.34e-05,0.9687,443.41,2025-10-14 00:27:12
90
+ 89,0.7149,0.759800,4.12e-05,1.0956,446.17,2025-10-14 00:27:15
91
+ 90,0.7229,0.716600,3.91e-05,1.0428,475.86,2025-10-14 00:27:44
92
+ 91,0.7309,0.761300,3.71e-05,1.0729,478.59,2025-10-14 00:27:47
93
+ 92,0.7390,0.674600,3.51e-05,1.0447,481.31,2025-10-14 00:27:50
94
+ 93,0.7470,0.737300,3.31e-05,1.2136,484.24,2025-10-14 00:27:53
95
+ 94,0.7550,0.707600,3.12e-05,1.4109,486.94,2025-10-14 00:27:55
96
+ 95,0.7631,0.644800,2.93e-05,1.0012,489.63,2025-10-14 00:27:58
97
+ 96,0.7711,0.807400,2.75e-05,1.1975,492.57,2025-10-14 00:28:01
98
+ 97,0.7791,0.681700,2.57e-05,1.1583,495.31,2025-10-14 00:28:04
99
+ 98,0.7871,0.697400,2.40e-05,1.0464,497.99,2025-10-14 00:28:07
100
+ 99,0.7952,0.670800,2.23e-05,1.1011,500.93,2025-10-14 00:28:09
101
+ 100,0.8032,0.783600,2.07e-05,1.1206,526.27,2025-10-14 00:28:35
102
+ 101,0.8112,0.697200,1.91e-05,1.0256,528.92,2025-10-14 00:28:37
103
+ 102,0.8193,0.671900,1.76e-05,0.9034,531.90,2025-10-14 00:28:40
104
+ 103,0.8273,0.736900,1.61e-05,1.0199,534.63,2025-10-14 00:28:43
105
+ 104,0.8353,0.770600,1.47e-05,1.0522,537.31,2025-10-14 00:28:46
106
+ 105,0.8434,0.712800,1.34e-05,1.0232,540.26,2025-10-14 00:28:49
107
+ 106,0.8514,0.766600,1.21e-05,1.0005,542.89,2025-10-14 00:28:51
108
+ 107,0.8594,0.695700,1.09e-05,1.0527,545.62,2025-10-14 00:28:54
109
+ 108,0.8675,0.751800,9.74e-06,1.0339,548.47,2025-10-14 00:28:57
110
+ 109,0.8755,0.734000,8.65e-06,1.0230,551.09,2025-10-14 00:29:00
111
+ 110,0.8835,0.666200,7.61e-06,0.9890,578.04,2025-10-14 00:29:27
112
+ 111,0.8916,0.648200,6.64e-06,0.9586,580.94,2025-10-14 00:29:29
113
+ 112,0.8996,0.709500,5.74e-06,1.1700,583.64,2025-10-14 00:29:32
114
+ 113,0.9076,0.748800,4.89e-06,1.0032,586.33,2025-10-14 00:29:35
115
+ 114,0.9157,0.734400,4.12e-06,1.0450,589.24,2025-10-14 00:29:38
116
+ 115,0.9237,0.749500,3.41e-06,1.0832,591.93,2025-10-14 00:29:40
117
+ 116,0.9317,0.689200,2.76e-06,0.9887,594.59,2025-10-14 00:29:43
118
+ 117,0.9398,0.761100,2.19e-06,0.9140,597.61,2025-10-14 00:29:46
119
+ 118,0.9478,0.747900,1.67e-06,0.9678,600.24,2025-10-14 00:29:49
120
+ 119,0.9558,0.704600,1.23e-06,0.9585,602.92,2025-10-14 00:29:51
121
+ 120,0.9639,0.682200,8.56e-07,0.9924,630.67,2025-10-14 00:30:19
122
+ 121,0.9719,0.813100,5.48e-07,1.2371,633.38,2025-10-14 00:30:22
123
+ 122,0.9799,0.730800,3.08e-07,1.0564,636.11,2025-10-14 00:30:25
124
+ 123,0.9880,0.853400,1.37e-07,1.0350,639.03,2025-10-14 00:30:28
125
+ 124,0.9960,0.730000,3.43e-08,1.0539,641.70,2025-10-14 00:30:30
brats_medgemma_r1_alpha4_20251014_001744/metrics/training_summary_20251014_001744.csv ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Metric,Value
2
+ Timestamp,20251014_001744
3
+ Training Time (s),642.73
4
+ Training Time (min),10.71
5
+ Final Loss,1.164830807235933
6
+ Epochs,1
7
+ Steps,Full epochs
8
+ Train Samples,996
9
+ Test Samples,111
10
+ Train Split,0.9
11
+ Learning Rate,0.0002
12
+ LoRA Rank,1
13
+ LoRA Alpha,4
14
+ Batch Size,2
15
+ Gradient Accumulation,4
16
+ Validation Every N Steps,10
brats_medgemma_r1_alpha4_20251014_001744/metrics/validation_during_training_20251014_001744.json ADDED
@@ -0,0 +1,470 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "step": 10,
4
+ "epoch": 0.08032128514056225,
5
+ "sample_id": 7,
6
+ "patient_id": "BraTS20_Training_005",
7
+ "image_type": "three_slices",
8
+ "instruction": "Describe tumor progression across these 3 consecutive brain MRI slices (10-slice intervals). \nSegmentation colors indicate:\n- RED: Non-Enhancing Tumor Core (NCR/NET) - necrotic tumor tissue\n- GREEN: Peritumoral Edema (ED) - swelling around the tumor\n- BLUE: Enhancing Tumor (ET) - actively growing tumor tissue",
9
+ "ground_truth": "Across these 3 consecutive slices (10-slice intervals), the tumor shows: The lesion area is in the left parietal lobe region with a mix of heterogeneous high and low signals with patchy high signal areas. Edema is significant, mainly located in the left parietal lobe with intense and extensive signal, indicating considerable swelling of the surrounding tissue. Necrosis is a potentially necrotic area located in the right parietal lobe, manifesting as a mixed high signal region and exhibiting a patchy signal, concentrated at the center of the main lesion. Ventricular compression is minor deformation of some ventricles, suggesting a certain degree of compression is present.",
10
+ "generated": "Based on the provided image, here's a description of the tumor progression between the three slices:\n\n* **Slice 85:** The lesion is visible in the right frontal region. The lesion shows an area with necrosis, edema, and active growth.\n\n* **Slice 95:** The lesion is still visible in the right frontal region, but there are signs of increased edema and some areas of necrosis.\n\n* **Slice 105:** The lesion is still visible in the right frontal region, with more pronounced edema and necrosis. The lesion appears to be larger than it was at Slice 85",
11
+ "rouge1": 0.38383838383838387,
12
+ "rouge2": 0.08163265306122448,
13
+ "rougeL": 0.24242424242424246
14
+ },
15
+ {
16
+ "step": 10,
17
+ "epoch": 0.08032128514056225,
18
+ "sample_id": 53,
19
+ "patient_id": "BraTS20_Training_048",
20
+ "image_type": "five_slices",
21
+ "instruction": "Examine these 5 axial slices and characterize tumor extent, necrosis, edema, and enhancing regions. \nSegmentation colors indicate:\n- RED: Non-Enhancing Tumor Core (NCR/NET) - necrotic tumor tissue\n- GREEN: Peritumoral Edema (ED) - swelling around the tumor\n- BLUE: Enhancing Tumor (ET) - actively growing tumor tissue",
22
+ "ground_truth": "Examining these 5 axial slices with 5-slice spacing: The lesion area is in the left temporal lobe of the brain with heterogeneous mixed signals characterized by alternating high and low signal intensities. Edema is significant, mainly concentrated in the left temporal lobe area and extending to the surrounding brain tissue of the lesions. Necrosis is present in the lesion region of the left temporal lobe, suggested by high signal areas with a mixture of high and low signal characteristics, primarily at the center of the lesion. Ventricular compression is present as the right ventricle is deformed and compressed due to the lesion and edema, but no significant ventricular obstruction is observed.",
23
+ "generated": "Based on the provided axial slices, here's a characterization of the tumor extent, necrosis, edema, and enhancing regions:\n\n* **Tumor Extent:** The tumor appears to be located in the right temporal lobe. It shows irregular borders with some areas of increased signal intensity within the tumor mass.\n* **Necrosis (NCR/NET):** There is significant non-enhancing tumor core (NCR/NET) present at the location of the tumor. This indicates necrosis or death of cells within the tumor.\n* **Edema (ED):** Peritumoral edema is visible surrounding the tumor. This",
24
+ "rouge1": 0.3737373737373737,
25
+ "rouge2": 0.10204081632653061,
26
+ "rougeL": 0.22222222222222224
27
+ },
28
+ {
29
+ "step": 10,
30
+ "epoch": 0.08032128514056225,
31
+ "sample_id": 16,
32
+ "patient_id": "BraTS20_Training_199",
33
+ "image_type": "three_slices",
34
+ "instruction": "Examine these 3 MRI slices and describe how the lesion evolves through brain volume. \nSegmentation colors indicate:\n- RED: Non-Enhancing Tumor Core (NCR/NET) - necrotic tumor tissue\n- GREEN: Peritumoral Edema (ED) - swelling around the tumor\n- BLUE: Enhancing Tumor (ET) - actively growing tumor tissue",
35
+ "ground_truth": "The tumor progression through these 3 slices demonstrates: The lesion area is in the right frontal lobe of the brain with mixed signals of varying intensities and patchy high-signal areas, suggesting multiple lesions. Edema is significant, occupying a large portion of the right hemisphere with higher signal intensity, indicating swelling of the tissues around the lesion. Necrosis is potentially present in the deep regions of the right frontal lobe, showing markedly low signal intensity intermingled with regions of high signal lesions. Ventricular compression is observed with the right lateral ventricle notably compressed and deformed, while the left lateral ventricle also shows slight compression, suggesting the lesion has a significant impact on the ventricular system.",
36
+ "generated": "I am unable to view or analyze images, so I cannot provide a description of the evolution of the lesion through brain volume based on the provided MRI slices. If you can describe what is happening in each slice it would be helpful for me to understand your situation better.",
37
+ "rouge1": 0.15757575757575756,
38
+ "rouge2": 0.049079754601226995,
39
+ "rougeL": 0.09696969696969697
40
+ },
41
+ {
42
+ "step": 20,
43
+ "epoch": 0.1606425702811245,
44
+ "sample_id": 42,
45
+ "patient_id": "BraTS20_Training_165",
46
+ "image_type": "three_slices",
47
+ "instruction": "Describe tumor progression across these 3 consecutive brain MRI slices (10-slice intervals). \nSegmentation colors indicate:\n- RED: Non-Enhancing Tumor Core (NCR/NET) - necrotic tumor tissue\n- GREEN: Peritumoral Edema (ED) - swelling around the tumor\n- BLUE: Enhancing Tumor (ET) - actively growing tumor tissue",
48
+ "ground_truth": "Across these 3 consecutive slices (10-slice intervals), the tumor shows: The lesion area is in the left parietal and temporal lobes with a mix of heterogeneous high and low signals along with speckled high signal areas. Edema is detected surrounding the lesion, with a larger area of edema observed on the left side, mainly in the parietal and temporal lobes, indicating significant swelling of the tissue around the lesion. Necrosis is characterized by mixed low and high signals mainly concentrated in the left parietal lobe and is relatively centralized. Ventricular compression is evident in the left ventricle, showing compression and deformation.",
49
+ "generated": "These 3 consecutive slices show a significant area of mixed signal intensity in the left temporal and parietal lobes, with high signals indicating edema regions, patchy low signals indicative of necrosis areas. Ventricular compression is also evident in the right ventricle, which indicates that the lesion volume occupies a large part of the brain parenchyma, leading to compression and deformation of normal brain structures.",
50
+ "rouge1": 0.5180722891566265,
51
+ "rouge2": 0.21951219512195122,
52
+ "rougeL": 0.3373493975903615
53
+ },
54
+ {
55
+ "step": 20,
56
+ "epoch": 0.1606425702811245,
57
+ "sample_id": 27,
58
+ "patient_id": "BraTS20_Training_128",
59
+ "image_type": "three_slices",
60
+ "instruction": "Provide comprehensive analysis of tumor across these 3 sequential slices at 10-slice intervals. \nSegmentation colors indicate:\n- RED: Non-Enhancing Tumor Core (NCR/NET) - necrotic tumor tissue\n- GREEN: Peritumoral Edema (ED) - swelling around the tumor\n- BLUE: Enhancing Tumor (ET) - actively growing tumor tissue",
61
+ "ground_truth": "Examining these 3 axial slices with 10-slice spacing: The lesion area is in the left frontal lobe with a significant high-signal region, left temporal lobe with high-signal regions, and left parietal lobe with several spotty high-signal regions. Edema is pronounced in the left frontal lobe and a large area in the left parietal lobe, suggesting significant swelling of surrounding tissues. Necrosis is suggested by mixed low-signal areas in the left frontal lobe and dispersed low-signal regions in the left parietal lobe. Ventricular compression is mild, primarily observed near the left frontal and parietal lobes.",
62
+ "generated": "Analysis of the three consecutive slices shows the following key features. The lesion area is mainly concentrated in the left frontal and parietal lobes, with partial involvement of the right frontotemporal region, showing significant non-enhancement areas and uneven high signal intensity regions. Ventricular compression is visible on both sides, indicating that the edema has caused expansion and deformation of the ventricles. Necrosis indicates a large mixed zone with high signal intensity, demonstrating heterogeneous lesions with low signal intensity zones surrounded by high signal intensity, reflecting various tumor degeneration patterns. Ventricular compression is evident on both sides, suggesting substantial ventricular deformation due to extensive swelling. Edema is widespread,",
63
+ "rouge1": 0.4711538461538462,
64
+ "rouge2": 0.1844660194174757,
65
+ "rougeL": 0.2692307692307692
66
+ },
67
+ {
68
+ "step": 20,
69
+ "epoch": 0.1606425702811245,
70
+ "sample_id": 51,
71
+ "patient_id": "BraTS20_Training_146",
72
+ "image_type": "single_slice",
73
+ "instruction": "Analyze this axial T1CE brain scan. \nSegmentation colors indicate:\n- RED: Non-Enhancing Tumor Core (NCR/NET) - necrotic tumor tissue\n- GREEN: Peritumoral Edema (ED) - swelling around the tumor\n- BLUE: Enhancing Tumor (ET) - actively growing tumor tissue Identify all tumor components present.",
74
+ "ground_truth": "Analysis of this brain scan reveals: The lesion area is in the right frontal, temporal, and parietal lobes with a mix of heterogeneous high and low signals along with speckled high signal regions, suggesting multiple lesions. Edema is significant, observed in the right frontal and parietal lobes, presenting as large areas with high signal intensity. Necrosis is concentrated in the right temporal lobe and part of the parietal lobe, showing extremely low signal intensity as clear low signal areas. Ventricular compression is noticeable, with the right lateral ventricle deformed under pressure and the left third ventricle also experiencing some degree of compression, indicating significant pressure exerted by the lesions on the ventricular system.",
75
+ "generated": "This single slice shows high mixed signals in the right frontal and parietal regions, with heterogeneous mixed signals in the left frontal and parietal regions, indicating a large lesion area with scattered high signal areas and low signal areas, representing necrosis, edema, hemorrhage, and other pathological changes. Mixed signals were observed in the left frontal and parietal lobes, with high signal areas mainly concentrated in the posterior part of the left frontal lobe and the anterior part of the left parietal lobe. Ventricular compression was evident in both ventricles, especially in the left ventricle, with significant compression of the left horn and body, indicating substantial pressure exerted by the mass effect caused by the",
76
+ "rouge1": 0.6079295154185022,
77
+ "rouge2": 0.26666666666666666,
78
+ "rougeL": 0.41409691629955947
79
+ },
80
+ {
81
+ "step": 30,
82
+ "epoch": 0.24096385542168675,
83
+ "sample_id": 39,
84
+ "patient_id": "BraTS20_Training_107",
85
+ "image_type": "single_slice",
86
+ "instruction": "Provide a detailed medical description of this brain scan. \nSegmentation colors indicate:\n- RED: Non-Enhancing Tumor Core (NCR/NET) - necrotic tumor tissue\n- GREEN: Peritumoral Edema (ED) - swelling around the tumor\n- BLUE: Enhancing Tumor (ET) - actively growing tumor tissue Note lesions and abnormalities.",
87
+ "ground_truth": "The MRI slice demonstrates: The lesion area is in multiple regions of the left cerebral hemisphere, primarily in the left parietal lobe and part of the frontal lobe, with mixed high and low heterogeneous signals with speckled high signal areas, indicating the presence of multiple lesions. Edema is significant in the perilesional areas of the left parietal and frontal lobes, presenting as high signal, indicating severe swelling of the surrounding tissues. Necrosis is observed with distinct low signal areas mainly concentrated in the deep regions of the left parietal lobe, presenting as irregularly shaped low signal areas. Ventricular compression is mild compression of the left ventricle, suggesting that while the lesion exerts compressive effects on the brain tissue and ventricles, it is not severe.",
88
+ "generated": "Examined axial T1CE MRI slice shows heterogeneous signals with high signal areas in the left frontal lobe, moderate signal intensity changes in the right parietal lobe, and low signal intensity in the central region of the brain. Edema is observed in these regions, characterized by uneven high signal intensity throughout these lobes. Necrosis is marked by low signal intensity patches scattered across the lesion area. Ventricular compression is noted, indicating that the tumor has significantly affected the ventricles of both hemispheres.",
89
+ "rouge1": 0.49756097560975615,
90
+ "rouge2": 0.26600985221674883,
91
+ "rougeL": 0.3219512195121951
92
+ },
93
+ {
94
+ "step": 30,
95
+ "epoch": 0.24096385542168675,
96
+ "sample_id": 75,
97
+ "patient_id": "BraTS20_Training_347",
98
+ "image_type": "five_slices",
99
+ "instruction": "Provide detailed analysis of lesion distribution visible in these 5 slices. \nSegmentation colors indicate:\n- RED: Non-Enhancing Tumor Core (NCR/NET) - necrotic tumor tissue\n- GREEN: Peritumoral Edema (ED) - swelling around the tumor\n- BLUE: Enhancing Tumor (ET) - actively growing tumor tissue",
100
+ "ground_truth": "The comprehensive tumor distribution through these 5 slices demonstrates: The lesion area is in the right cerebral region, particularly in the right parietal and frontal lobes, with a mix of uneven high and low signals and speckled high-signal areas, suggesting multiple lesions. Edema is significant around the right frontal and parietal lobes, represented by high signals, covering a large area. Necrosis is indicated by high signal areas in the central part of the lesion, displaying disorganized signals with unclear boundaries. Ventricular compression is present, with the right ventricle showing varying degrees of compression and deformation.",
101
+ "generated": "Analysis across these 5 sequential brain scans reveals the following: The lesion area is mainly located in the right parietal and temporal lobes, with some areas showing high signal intensity and significant edema, indicating a substantial amount of tissue damage. Necrosis is present in the central part of the right parietal lobe as indicated by low signal intensity, suggesting that some tumor cells have died, but the extent of necrosis is limited to these few spots within the lesions. Ventricular compression is observed on the left side due to compression caused by the tumor.",
102
+ "rouge1": 0.5473684210526316,
103
+ "rouge2": 0.2553191489361702,
104
+ "rougeL": 0.35789473684210527
105
+ },
106
+ {
107
+ "step": 30,
108
+ "epoch": 0.24096385542168675,
109
+ "sample_id": 108,
110
+ "patient_id": "BraTS20_Training_279",
111
+ "image_type": "three_slices",
112
+ "instruction": "Examine these 3 MRI slices and describe how the lesion evolves through brain volume. \nSegmentation colors indicate:\n- RED: Non-Enhancing Tumor Core (NCR/NET) - necrotic tumor tissue\n- GREEN: Peritumoral Edema (ED) - swelling around the tumor\n- BLUE: Enhancing Tumor (ET) - actively growing tumor tissue",
113
+ "ground_truth": "The tumor progression through these 3 slices demonstrates: The lesion area is in the right parietal and occipital lobes with mixed signals of varying intensity, including patchy high signal areas. Edema is mainly located around the lesions in the right parietal and occipital lobes, with high signals and a large extent, widely distributed around the lesion area. Necrosis is potentially necrotic areas mainly concentrated in the right parietal lobe, appearing as mixed signal regions with lower signal intensity and uneven mixed signals. Ventricular compression is the right ventricle is compressed and deformed, while the left ventricle appears slightly expanded.",
114
+ "generated": "Analysis of these three axial T1-weighted MRI slices spanning a 10-slice interval reveals: The lesion area is in the right frontal lobe with mixed signal characteristics, including areas of high intensity (bright spots), low intensity (dark spots), and heterogeneous signals within the lesions, indicating varying degrees of tissue damage such as edema and necrosis. Ventricular compression is observed, suggesting significant pressure on adjacent ventricles due to tumor mass effect. Edema is present in surrounding regions, particularly extending from the right frontal lobe to parts of the temporal lobes. Necrosis appears patchy throughout the tumor core region, with some high-signal patches that suggest",
115
+ "rouge1": 0.4705882352941177,
116
+ "rouge2": 0.1683168316831683,
117
+ "rougeL": 0.28431372549019607
118
+ },
119
+ {
120
+ "step": 40,
121
+ "epoch": 0.321285140562249,
122
+ "sample_id": 45,
123
+ "patient_id": "BraTS20_Training_364",
124
+ "image_type": "single_slice",
125
+ "instruction": "Examine this MRI slice and describe tumor characteristics. \nSegmentation colors indicate:\n- RED: Non-Enhancing Tumor Core (NCR/NET) - necrotic tumor tissue\n- GREEN: Peritumoral Edema (ED) - swelling around the tumor\n- BLUE: Enhancing Tumor (ET) - actively growing tumor tissue Include necrosis and edema assessment.",
126
+ "ground_truth": "Examining this single slice, I observe: The lesion area is in the right frontal lobe and parts of the right parietal lobe with mixed high and low signal intensities. Edema is mainly located around the right frontal lobe, extending to parts of the right parietal lobe, suggesting significant cerebral edema. Necrosis is primarily concentrated in the core region of the lesions, characterized by low signal areas with a concentrated distribution. Ventricular compression is observed with the right ventricle being compressed and deformed, suggesting notable pressure on the brain tissue.",
127
+ "generated": "The lesion area is in the right frontal lobe with mixed high and low signals, showing a mixture of heterogeneous high and low signal areas within the frontal lobes. Edema is significant, concentrated in the right frontal and temporal regions surrounding the lesions, indicating extensive cerebral edema. Necrosis is present as low signal areas within these tumors, mainly located in the central part of the right frontal lobe, with patchy distribution and limited extent, suggesting partial necrosis. Ventricular compression is observed, primarily affecting the lateral ventricles on the right side with slight deformation compared to normal ventricular shape.",
128
+ "rouge1": 0.6737967914438502,
129
+ "rouge2": 0.37837837837837834,
130
+ "rougeL": 0.4171122994652406
131
+ },
132
+ {
133
+ "step": 40,
134
+ "epoch": 0.321285140562249,
135
+ "sample_id": 31,
136
+ "patient_id": "BraTS20_Training_080",
137
+ "image_type": "single_slice",
138
+ "instruction": "Examine this MRI slice and describe tumor characteristics. \nSegmentation colors indicate:\n- RED: Non-Enhancing Tumor Core (NCR/NET) - necrotic tumor tissue\n- GREEN: Peritumoral Edema (ED) - swelling around the tumor\n- BLUE: Enhancing Tumor (ET) - actively growing tumor tissue Include necrosis and edema assessment.",
139
+ "ground_truth": "Examining this single slice, I observe: The lesion area is in the right frontal and occipital lobes with mixed signals of varying intensities and speckled high-signal areas. Edema is significant high signals suggesting prominent edema mainly concentrated in the right occipital lobe, extending widely, encompassing most of the surrounding tissue of the lesion areas. Necrosis is low-signal areas observed in the right frontal and occipital lobes, with necrotic areas scattered among the high-signal lesion regions and relatively concentrated in the core of the lesions. Ventricular compression is some ventricles are compressed, and their shapes are slightly deformed, although no significant ventricular obstruction was observed.",
140
+ "generated": "The lesion area is in the left frontal lobe with mixed signals, including patchy high-signal regions and low-signal regions, suggesting a mix of different tissue components within the lesions. Edema is significant, particularly concentrated in the surrounding tissues of the lesion areas, especially noticeable near the left frontal lobe region and extending to parts of the adjacent temporal lobe, indicating substantial swelling of brain tissue. Necrosis appears as low signal intensity with scattered spots, mainly observed in the deep part of the lesions, particularly in the right frontal lobe, and exhibiting uneven distribution throughout the lesions, showing heterogeneity. Ventricular compression is present, with both lateral ventricles appearing",
141
+ "rouge1": 0.5555555555555556,
142
+ "rouge2": 0.2897196261682243,
143
+ "rougeL": 0.37962962962962965
144
+ },
145
+ {
146
+ "step": 40,
147
+ "epoch": 0.321285140562249,
148
+ "sample_id": 99,
149
+ "patient_id": "BraTS20_Training_329",
150
+ "image_type": "five_slices",
151
+ "instruction": "Analyze these 5 consecutive MRI slices (5-slice intervals) and describe complete tumor profile. \nSegmentation colors indicate:\n- RED: Non-Enhancing Tumor Core (NCR/NET) - necrotic tumor tissue\n- GREEN: Peritumoral Edema (ED) - swelling around the tumor\n- BLUE: Enhancing Tumor (ET) - actively growing tumor tissue",
152
+ "ground_truth": "Across these 5 consecutive slices (5-slice intervals), the complete tumor profile shows: The lesion area is in the frontal lobe region, particularly in the right frontal lobe, with heterogeneous mixed signals. Edema is significant around the aforementioned lesions, with pronounced surrounding tissue edema indicating a relatively high degree of tissue swelling, and relatively mild edema signal in the parietal lobe suggesting the lesion's effect on surrounding tissues. Necrosis is present in some lesion areas, with low signals in the center of the lesion on the right frontal lobe suggesting possible necrotic regions, and localized low signals in the parietal lobe suggesting possible localized necrotic areas. Ventricular compression is observed with the right lateral ventricle compressed and deformed, with a slight shift in the right lateral ventricle.",
153
+ "generated": "Analysis of these 5 consecutive MRI slices reveals: The lesion area is in the left frontal lobe with a mix of high and low signals, suggesting necrosis and edema. Edema is concentrated around the lesions, primarily affecting the surrounding tissues of the brain. Necrosis appears as heterogeneous areas within the lesions, characterized by speckled high signal intensities. Ventricular compression is mild, observed at the ventricular system, which has been slightly compressed but does not show significant deformation or distortion.",
154
+ "rouge1": 0.47342995169082125,
155
+ "rouge2": 0.1853658536585366,
156
+ "rougeL": 0.34782608695652173
157
+ },
158
+ {
159
+ "step": 50,
160
+ "epoch": 0.40160642570281124,
161
+ "sample_id": 108,
162
+ "patient_id": "BraTS20_Training_279",
163
+ "image_type": "three_slices",
164
+ "instruction": "Examine these 3 MRI slices and describe how the lesion evolves through brain volume. \nSegmentation colors indicate:\n- RED: Non-Enhancing Tumor Core (NCR/NET) - necrotic tumor tissue\n- GREEN: Peritumoral Edema (ED) - swelling around the tumor\n- BLUE: Enhancing Tumor (ET) - actively growing tumor tissue",
165
+ "ground_truth": "The tumor progression through these 3 slices demonstrates: The lesion area is in the right parietal and occipital lobes with mixed signals of varying intensity, including patchy high signal areas. Edema is mainly located around the lesions in the right parietal and occipital lobes, with high signals and a large extent, widely distributed around the lesion area. Necrosis is potentially necrotic areas mainly concentrated in the right parietal lobe, appearing as mixed signal regions with lower signal intensity and uneven mixed signals. Ventricular compression is the right ventricle is compressed and deformed, while the left ventricle appears slightly expanded.",
166
+ "generated": "Across these 3 axial slices, the lesion shows: The lesion area is in the left temporal lobe with a mixed signal of heterogeneous high and low signals with speckled high-signal areas. Edema is significant surrounding the lesion, mainly concentrated in the left temporal region, showing a strong degree of edema. Necrosis is suspected within the left temporal lobe, appearing as uneven regions with speckled high signal intensity, possibly indicating necrosis. Ventricular compression occurs due to lesions in the left temporal region, demonstrating that the lesions are compressing the ventricles on the left side of the brain.",
167
+ "rouge1": 0.5408163265306122,
168
+ "rouge2": 0.288659793814433,
169
+ "rougeL": 0.4081632653061224
170
+ },
171
+ {
172
+ "step": 50,
173
+ "epoch": 0.40160642570281124,
174
+ "sample_id": 60,
175
+ "patient_id": "BraTS20_Training_366",
176
+ "image_type": "single_slice",
177
+ "instruction": "Analyze this axial T1CE brain scan. \nSegmentation colors indicate:\n- RED: Non-Enhancing Tumor Core (NCR/NET) - necrotic tumor tissue\n- GREEN: Peritumoral Edema (ED) - swelling around the tumor\n- BLUE: Enhancing Tumor (ET) - actively growing tumor tissue Identify all tumor components present.",
178
+ "ground_truth": "Analysis of this brain scan reveals: The lesion area is in the left temporal and parietal lobes with multiple heterogeneous mixed signals and spotty high-signal areas, suggesting the presence of multiple lesions. Edema is significant, concentrated in the left parietal and temporal regions, with extensive high-signal areas, suggesting noticeable swelling in the tissue surrounding the lesions. Necrosis is located mainly in the left temporal lobe, appearing as low signals with blurred boundaries mixed with the high-signal edema areas, indicating severe tissue damage. Ventricular compression is observed with the left ventricle compressed and deformed, showing slight compression and deformation due to the mass effect of the lesion.",
179
+ "generated": "Analysis of this brain scan reveals: The lesion area is in the right frontal lobe and part of the right temporal lobe with a mixture of heterogeneous high and low signals, suggesting multiple lesions, especially in the right temporal lobe. Edema is significant, mainly observed as high signal areas surrounding the right temporal lobe, indicating significant swelling of the tissues near the lesions, indicating edema extending to surrounding tissues. Necrosis is suspected, visible as some uneven regions with low signal intensity within the lesion areas, particularly in the right temporal lobe region. Ventricular compression is mild, the right lateral ventricle appears compressed by the mass effect of the lesion.",
180
+ "rouge1": 0.6605504587155964,
181
+ "rouge2": 0.3055555555555556,
182
+ "rougeL": 0.46788990825688076
183
+ },
184
+ {
185
+ "step": 50,
186
+ "epoch": 0.40160642570281124,
187
+ "sample_id": 90,
188
+ "patient_id": "BraTS20_Training_248",
189
+ "image_type": "five_slices",
190
+ "instruction": "Examine these 5 axial slices and characterize tumor extent, necrosis, edema, and enhancing regions. \nSegmentation colors indicate:\n- RED: Non-Enhancing Tumor Core (NCR/NET) - necrotic tumor tissue\n- GREEN: Peritumoral Edema (ED) - swelling around the tumor\n- BLUE: Enhancing Tumor (ET) - actively growing tumor tissue",
191
+ "ground_truth": "Examining these 5 axial slices with 5-slice spacing: The lesion area is in the left parietal lobe with a mix of heterogeneous high and low signals with spotted areas of high signal. Edema is significant, visible surrounding the lesions, primarily observed in the left brain tissue, extending over a large area, spreading to parts of the left parietal lobe and adjacent regions. Necrosis is in the deeper regions of the left parietal lobe, exhibiting a high level of mixed signal intensity, with scattered small high signal areas. Ventricular compression is observed with the left ventricle compressed and deformed.",
192
+ "generated": "Examining this 5-slice series with CE brain scans: The lesion area is in the frontal lobe of the right cerebral hemisphere with a mixture of heterogeneous high and low signals. Edema is significant, appearing as a large region of high signal intensity surrounding the lesions, particularly concentrated in the right temporal and parietal lobes, indicating significant swelling of the tissues. Necrosis is suggested by uneven high and low signal areas within the lesion zone, suggesting possible necrosis and mixed signals. Ventricular compression is not obvious, but the shape of the ventricles shows signs of being compressed, especially on the right side.",
193
+ "rouge1": 0.5870646766169154,
194
+ "rouge2": 0.3115577889447236,
195
+ "rougeL": 0.3980099502487562
196
+ },
197
+ {
198
+ "step": 60,
199
+ "epoch": 0.4819277108433735,
200
+ "sample_id": 65,
201
+ "patient_id": "BraTS20_Training_368",
202
+ "image_type": "five_slices",
203
+ "instruction": "Examine these 5 axial slices and characterize tumor extent, necrosis, edema, and enhancing regions. \nSegmentation colors indicate:\n- RED: Non-Enhancing Tumor Core (NCR/NET) - necrotic tumor tissue\n- GREEN: Peritumoral Edema (ED) - swelling around the tumor\n- BLUE: Enhancing Tumor (ET) - actively growing tumor tissue",
204
+ "ground_truth": "Examining these 5 axial slices with 5-slice spacing: The lesion area is in the left parietal region with a mixture of high and low signals. Edema is a significant high-signal area surrounding the lesion, extending across most of the left parietal region and spreading to adjacent areas. Necrosis is present with mixed signals within the left parietal region, exhibiting alternating distributions of high and low signals, suggesting varying degrees of necrotic lesions. Ventricular compression is not observed.",
205
+ "generated": "Examining these 5 sequential brain scans with CE-MRI slice spacing of 10 mm: The lesion area is in the left frontal lobe and part of the parietal lobe with mixed signals including spotty high signal areas. Edema is primarily concentrated in the left parietal lobe and extends into some parts of the left frontal lobe. Necrosis is mainly observed in the central region of the left parietal lobe with low signal intensity, suggesting potential necrosis or possibly edema. Ventricular compression is mild but noticeable, with slight deformation of the left ventricle.",
206
+ "rouge1": 0.5497076023391814,
207
+ "rouge2": 0.272189349112426,
208
+ "rougeL": 0.4093567251461988
209
+ },
210
+ {
211
+ "step": 60,
212
+ "epoch": 0.4819277108433735,
213
+ "sample_id": 52,
214
+ "patient_id": "BraTS20_Training_239",
215
+ "image_type": "five_slices",
216
+ "instruction": "Provide detailed analysis of lesion distribution visible in these 5 slices. \nSegmentation colors indicate:\n- RED: Non-Enhancing Tumor Core (NCR/NET) - necrotic tumor tissue\n- GREEN: Peritumoral Edema (ED) - swelling around the tumor\n- BLUE: Enhancing Tumor (ET) - actively growing tumor tissue",
217
+ "ground_truth": "The comprehensive tumor distribution through these 5 slices demonstrates: The lesion area is in the frontal and parietal lobes of the right hemisphere with heterogeneous signal intensities and patchy high signals. Edema is marked and extensive, affecting parts of the frontal and parietal lobes of the right hemisphere, displaying high signals and a diffusive pattern. Necrosis is evident with mixed signal characteristics; some regions display high signals while others show low signals, spatially scattered within the lesions. Ventricular compression is noted, with lesions exerting a compressive effect on the ventricular structures.",
218
+ "generated": "The MRI slice series demonstrates: The lesion area is in the right frontal, parietal and occipital lobes with a mixture of heterogeneous high and low signals along with spotted high signal areas. Edema is significant edema mainly concentrated in the right parietal lobe and part of the occipital lobe, extending to adjacent regions. Necrosis is observed as low signal areas within the lesions, primarily located in the central region of the right frontal and parietal lobes. Ventricular compression is notable with the left ventricle compressed by the lesion in the right side of the brain.",
219
+ "rouge1": 0.5698924731182795,
220
+ "rouge2": 0.26086956521739124,
221
+ "rougeL": 0.39784946236559143
222
+ },
223
+ {
224
+ "step": 60,
225
+ "epoch": 0.4819277108433735,
226
+ "sample_id": 86,
227
+ "patient_id": "BraTS20_Training_121",
228
+ "image_type": "single_slice",
229
+ "instruction": "Describe this brain MRI slice in detail. \nSegmentation colors indicate:\n- RED: Non-Enhancing Tumor Core (NCR/NET) - necrotic tumor tissue\n- GREEN: Peritumoral Edema (ED) - swelling around the tumor\n- BLUE: Enhancing Tumor (ET) - actively growing tumor tissue Focus on tumor regions and their characteristics.",
230
+ "ground_truth": "This single axial T1CE MRI slice shows: The lesion area is in the frontal and parietal lobes of the left hemisphere of the brain with a mixture of heterogeneous high and low signals along with speckled high signal areas. Edema is a prominent high signal area surrounding the lesions in the left frontal and parietal lobes, appearing as a large patch of high signal, with markedly increased signal intensity compared to the surrounding normal brain tissue. Necrosis is a low signal area observed within the left parietal region, appearing as irregular low signals that are unevenly distributed with blurred boundaries. Ventricular compression is the left lateral ventricle is narrowed and slightly altered in shape.",
231
+ "generated": "This single axial T1CE MRI slice shows: The lesion area is in the right frontal, temporal, and parietal lobes with a heterogeneous mix of high and low signals along with spotty high signal areas. Edema is significant, mainly located in the right frontal, temporal, and parietal lobes, covering a large region with considerable intensity. Necrosis is visible as irregular low-signal regions within the edema area, mostly concentrated in the central part of the lesions with patchy distribution. Ventricular compression is observed near the lesions, particularly in the ventricular system of the right side, suggesting some degree of pressure from the lesions.",
232
+ "rouge1": 0.6296296296296297,
233
+ "rouge2": 0.36448598130841126,
234
+ "rougeL": 0.49074074074074076
235
+ },
236
+ {
237
+ "step": 70,
238
+ "epoch": 0.5622489959839357,
239
+ "sample_id": 33,
240
+ "patient_id": "BraTS20_Training_214",
241
+ "image_type": "five_slices",
242
+ "instruction": "Describe tumor characteristics across these 5 sequential brain scans with 5-slice spacing. \nSegmentation colors indicate:\n- RED: Non-Enhancing Tumor Core (NCR/NET) - necrotic tumor tissue\n- GREEN: Peritumoral Edema (ED) - swelling around the tumor\n- BLUE: Enhancing Tumor (ET) - actively growing tumor tissue",
243
+ "ground_truth": "Analysis of these 5 sequential MRI scans reveals: The lesion area is in the right frontal lobe, temporal lobe, and part of the parietal lobe with a mixture of high and low signal intensity and multiple patchy high-signal regions. Edema is significant in the peripheral regions of the right frontal and temporal lobes with pronounced signals, suggesting notable swelling affecting surrounding neural tissue. Necrosis is primarily concentrated in the deep region of the right temporal lobe, characterized by uneven signal intensity with a mixture of signals, indicating varying degrees, with severe necrosis in some areas. Ventricular compression is observed with significant compression and morphological changes in the right lateral ventricle, which is slightly widened.",
244
+ "generated": "Analysis of these 5 axial MRI scans reveals: The lesion area is in the right frontal lobe, parietal lobe and occipital lobe with a mixture of heterogeneous high and low signals along with patchy high signal areas. Edema is prominent around the lesions in the right frontal lobe and parietal lobes, indicating significant edema affecting surrounding tissues. Necrosis is suspected within the core region of the lesions, mainly appearing as low-signal regions but are scattered and difficult to identify clearly. Ventricular compression is observed due to pressure from the lesions on the ventricles, particularly noticeable in the lateral ventricle.",
245
+ "rouge1": 0.6139534883720932,
246
+ "rouge2": 0.3755868544600939,
247
+ "rougeL": 0.5209302325581395
248
+ },
249
+ {
250
+ "step": 70,
251
+ "epoch": 0.5622489959839357,
252
+ "sample_id": 109,
253
+ "patient_id": "BraTS20_Training_178",
254
+ "image_type": "three_slices",
255
+ "instruction": "Analyze spatial distribution of tumor components in these 3 axial slices with 10-slice spacing. \nSegmentation colors indicate:\n- RED: Non-Enhancing Tumor Core (NCR/NET) - necrotic tumor tissue\n- GREEN: Peritumoral Edema (ED) - swelling around the tumor\n- BLUE: Enhancing Tumor (ET) - actively growing tumor tissue",
256
+ "ground_truth": "Analysis of these 3 sequential brain scans reveals: The lesion area is in the right frontal and parietal lobes with heterogeneous signal, including high signal intensity and spot-like high signal intensities indicating multiple lesions. Edema is significant, mainly concentrated in the right frontal and parietal lobes, extending over a large area including the tissues surrounding the lesion, suggesting notable swelling of the surrounding tissue. Necrosis is located at the center of the lesion, characterized by lower signal intensity and highly heterogeneous, displaying uneven signals and is relatively concentrated. Ventricular compression is evident, particularly on the right side, as the ventricles appear deformed due to the pressure from surrounding edema and necrotic regions.",
257
+ "generated": "Analysis of these 3 sequential brain scans reveals: The lesion area is in the right frontal lobe and parietal lobe with mixed signals, including high-signal regions and spotty low-signal areas, indicating multiple lesions. Edema is mainly observed in the frontal and parietal lobes of the right hemisphere, with extensive edema affecting a large area around the lesions, suggesting significant swelling of surrounding tissues due to edema. Necrosis is observed at the junction between the right frontal and parietal lobes, characterized by low signal intensity and irregular borders, potentially indicating possible necrotic zones within the main lesion region. Ventricular compression is observed as the left ventricle is compressed and deformed",
258
+ "rouge1": 0.7142857142857142,
259
+ "rouge2": 0.44144144144144143,
260
+ "rougeL": 0.5803571428571428
261
+ },
262
+ {
263
+ "step": 70,
264
+ "epoch": 0.5622489959839357,
265
+ "sample_id": 34,
266
+ "patient_id": "BraTS20_Training_116",
267
+ "image_type": "three_slices",
268
+ "instruction": "Provide comprehensive analysis of tumor across these 3 sequential slices at 10-slice intervals. \nSegmentation colors indicate:\n- RED: Non-Enhancing Tumor Core (NCR/NET) - necrotic tumor tissue\n- GREEN: Peritumoral Edema (ED) - swelling around the tumor\n- BLUE: Enhancing Tumor (ET) - actively growing tumor tissue",
269
+ "ground_truth": "Examining these 3 axial slices with 10-slice spacing: The lesion area is in the right frontal and temporal lobes with mixed signals of varying intensity and spotty high-signal areas. Edema is noticeable, predominantly in the right frontal and temporal lobes, exhibiting higher signals and a larger range, suggesting significant swelling in the surrounding tissue of the lesions. Necrosis is possible in the right frontal and temporal lobes, characterized by lower, mixed signal intensity, and more concentrated in the central part of the lesions. Ventricular compression is exerted by the lesion areas on the surrounding normal brain tissue and ventricles, with mild compression of the right lateral ventricle.",
270
+ "generated": "Across these 3 axial slices with 10-slice spacing, I observe: The lesion area is in the right parietal and occipital lobes of the brain with a mix of heterogeneous high and low signals along with patchy high signal areas. Edema is significant, mainly concentrated near the lesions but also extending into surrounding regions, notably affecting tissues adjacent to the lesions particularly in the parietal lobe, indicating edema extent covering a substantial portion of the right parietal and occipital lobes. Necrosis is suggested by multiple low signal regions, primarily observed within the main lesion areas, appearing as irregularly shaped low-signal zones suggesting necrosis spread throughout some parts of the",
271
+ "rouge1": 0.547945205479452,
272
+ "rouge2": 0.2488479262672811,
273
+ "rougeL": 0.4018264840182648
274
+ },
275
+ {
276
+ "step": 80,
277
+ "epoch": 0.642570281124498,
278
+ "sample_id": 28,
279
+ "patient_id": "BraTS20_Training_271",
280
+ "image_type": "three_slices",
281
+ "instruction": "Examine these 3 MRI slices and describe how the lesion evolves through brain volume. \nSegmentation colors indicate:\n- RED: Non-Enhancing Tumor Core (NCR/NET) - necrotic tumor tissue\n- GREEN: Peritumoral Edema (ED) - swelling around the tumor\n- BLUE: Enhancing Tumor (ET) - actively growing tumor tissue",
282
+ "ground_truth": "The tumor progression through these 3 slices demonstrates: The lesion area is in the right hemisphere of the brain, near the frontal and parietal lobes, with a heterogeneous mix of high and low signals, and patchy high signal areas. Edema is significant, mainly around the lesion sites, particularly in the posterior part of the right frontal lobe and the medial part of the right parietal lobe. Necrosis is observed as low signal images, with heterogeneous signals concentrated at the junction of the parietal and frontal lobes in the right hemisphere. Ventricular compression is not observed, as the ventricular morphology is normal, showing no clear signs of deformation or compression.",
283
+ "generated": "The tumor progression through these 3 slices demonstrates: The lesion area is in the right parietal lobe with a mixture of heterogeneous high and low signals, accompanied by multiple spotty high signal areas. Edema is significant, extending from the right parietal lobe to cover parts of the frontal and occipital lobes on the left side of the brain. Necrosis is mainly located in the central part of the right parietal lobe, where it shows a mixed pattern of high and low signals with some concentrated areas of very high signal intensity. Ventricular compression is observed as the right lateral ventricle is compressed and deformed.",
284
+ "rouge1": 0.7230046948356808,
285
+ "rouge2": 0.4454976303317536,
286
+ "rougeL": 0.5258215962441315
287
+ },
288
+ {
289
+ "step": 80,
290
+ "epoch": 0.642570281124498,
291
+ "sample_id": 13,
292
+ "patient_id": "BraTS20_Training_132",
293
+ "image_type": "three_slices",
294
+ "instruction": "Provide comprehensive analysis of tumor across these 3 sequential slices at 10-slice intervals. \nSegmentation colors indicate:\n- RED: Non-Enhancing Tumor Core (NCR/NET) - necrotic tumor tissue\n- GREEN: Peritumoral Edema (ED) - swelling around the tumor\n- BLUE: Enhancing Tumor (ET) - actively growing tumor tissue",
295
+ "ground_truth": "Examining these 3 axial slices with 10-slice spacing: The lesion area is in the right frontal lobe, partially extending into the temporal and parietal regions, with heterogeneous signals characterized by a mix of high and low signals, as well as speckled high signal areas. Edema is surrounding the lesion area, predominantly in the right cerebrum, mainly concentrated in the right frontal and temporal lobes, with some extension into the parietal region. Necrosis is in the lesion area with a low-signal region, exhibiting heterogeneous signals with a mix of both high and low signal regions, primarily located in the core region of the lesion. Ventricular compression is significant compression of the right lateral ventricle, presenting as asymmetrical changes.",
296
+ "generated": "Examining these 3 axial slices with 10-slice spacing, I observe: The lesion area is in the right frontal lobe and part of the parietal lobe with heterogeneous high signals and spotty areas showing high signal intensity. Edema is significant, mainly concentrated in the surrounding tissues of the lesions, particularly in the right frontal lobe region, which shows a large extent indicating edema. Necrosis may be present as low-signal regions within the lesions, exhibiting mixed patterns but primarily located near the edges of the lesions. Ventricular compression is observed with noticeable deformation of the right ventricle, suggesting pressure exerted by the lesion on the ventricles.",
297
+ "rouge1": 0.6577777777777777,
298
+ "rouge2": 0.36771300448430494,
299
+ "rougeL": 0.49777777777777776
300
+ },
301
+ {
302
+ "step": 80,
303
+ "epoch": 0.642570281124498,
304
+ "sample_id": 38,
305
+ "patient_id": "BraTS20_Training_040",
306
+ "image_type": "single_slice",
307
+ "instruction": "Examine this MRI slice and describe tumor characteristics. \nSegmentation colors indicate:\n- RED: Non-Enhancing Tumor Core (NCR/NET) - necrotic tumor tissue\n- GREEN: Peritumoral Edema (ED) - swelling around the tumor\n- BLUE: Enhancing Tumor (ET) - actively growing tumor tissue Include necrosis and edema assessment.",
308
+ "ground_truth": "Examining this single slice, I observe: The lesion area is in the bilateral frontal and temporal lobes with a mixed signal of uneven high and low intensity with patchy high signal areas. Edema is pronounced, chiefly observed in the bilateral lateral frontal lobes, with significant swelling of surrounding tissues, extensive and extending into the temporal lobes. Necrosis is located at the center of the bilateral lateral frontal lobes, characterized by high signal areas interspersed with low signals, primarily in the aforementioned areas. Ventricular compression is notably present as the right ventricle is compressed and deformed, whereas the left ventricle maintains a normal shape.",
309
+ "generated": "Examining this single slice, I observe: The lesion area is in the right hemisphere of the brain with a mix of heterogeneous high and low signals along with speckled high signal areas, indicating multiple lesions. Edema is significant surrounding the lesions on the right side of the brain, particularly at the left parietal and occipital lobes, exhibiting extensive swelling of the brain tissue. Necrosis is present within the lesions primarily concentrated near the center of the right hemisphere but shows a more patchy distribution, scattered through the lesion regions. Ventricular compression is observed with the right ventricle showing deformation due to pressure from the lesions.",
310
+ "rouge1": 0.5673076923076923,
311
+ "rouge2": 0.2912621359223301,
312
+ "rougeL": 0.43269230769230765
313
+ },
314
+ {
315
+ "step": 90,
316
+ "epoch": 0.7228915662650602,
317
+ "sample_id": 108,
318
+ "patient_id": "BraTS20_Training_279",
319
+ "image_type": "three_slices",
320
+ "instruction": "Examine these 3 MRI slices and describe how the lesion evolves through brain volume. \nSegmentation colors indicate:\n- RED: Non-Enhancing Tumor Core (NCR/NET) - necrotic tumor tissue\n- GREEN: Peritumoral Edema (ED) - swelling around the tumor\n- BLUE: Enhancing Tumor (ET) - actively growing tumor tissue",
321
+ "ground_truth": "The tumor progression through these 3 slices demonstrates: The lesion area is in the right parietal and occipital lobes with mixed signals of varying intensity, including patchy high signal areas. Edema is mainly located around the lesions in the right parietal and occipital lobes, with high signals and a large extent, widely distributed around the lesion area. Necrosis is potentially necrotic areas mainly concentrated in the right parietal lobe, appearing as mixed signal regions with lower signal intensity and uneven mixed signals. Ventricular compression is the right ventricle is compressed and deformed, while the left ventricle appears slightly expanded.",
322
+ "generated": "The tumor progression through these 3 sequential slices demonstrates: The lesion area is in the left temporal, parietal, and frontal lobes with mixed signal intensities of varying degrees, including spotty high signals and low signals with a heterogeneous distribution. Edema is significant, mainly concentrated in the left temporal lobe region, indicating that edema is extensive and affects most areas surrounding the lesions. Necrosis is present as uneven signal intensity within the left temporal lobe, suggesting necrosis is localized but scattered throughout the tissues. Ventricular compression is mild due to increased pressure from the lesion regions on the ventricles.",
323
+ "rouge1": 0.6192893401015229,
324
+ "rouge2": 0.3076923076923077,
325
+ "rougeL": 0.45685279187817257
326
+ },
327
+ {
328
+ "step": 90,
329
+ "epoch": 0.7228915662650602,
330
+ "sample_id": 24,
331
+ "patient_id": "BraTS20_Training_139",
332
+ "image_type": "five_slices",
333
+ "instruction": "Provide detailed analysis of lesion distribution visible in these 5 slices. \nSegmentation colors indicate:\n- RED: Non-Enhancing Tumor Core (NCR/NET) - necrotic tumor tissue\n- GREEN: Peritumoral Edema (ED) - swelling around the tumor\n- BLUE: Enhancing Tumor (ET) - actively growing tumor tissue",
334
+ "ground_truth": "The comprehensive tumor distribution through these 5 slices demonstrates: The lesion area is in the left frontal and temporal lobes with a mixture of heterogeneous high and low signals, accompanied by spotted high signal areas. Edema is significant around the lesions, particularly in the central part of the left frontal lobe and the lateral side of the temporal lobe, indicating significant tissue swelling in these regions. Necrosis is indicated by high signal intensity, primarily concentrated within the left frontal and temporal lobes, showing a high degree of heterogeneity but generally a localized distribution. Ventricular compression is observed, especially in areas adjacent to the lesions.",
335
+ "generated": "The comprehensive tumor distribution through these 5 slices demonstrates: The lesion area is in the right parietal and occipital lobes with a mix of heterogeneous high and low signals along with spotted high signal areas, indicating multiple lesions. Edema is significant, mainly concentrated around the lesion regions in the right parietal and occipital lobes, suggesting that the surrounding tissues are significantly swollen due to edema. Necrosis is observed as low-signal regions scattered within the lesion areas, particularly prominent near the center of the lesion in the right parietal lobe. Ventricular compression is evident as the ventricles show signs of being compressed by the pressure exerted by the lesions, particularly noticeable",
336
+ "rouge1": 0.6232558139534884,
337
+ "rouge2": 0.3474178403755869,
338
+ "rougeL": 0.47441860465116276
339
+ },
340
+ {
341
+ "step": 90,
342
+ "epoch": 0.7228915662650602,
343
+ "sample_id": 40,
344
+ "patient_id": "BraTS20_Training_192",
345
+ "image_type": "three_slices",
346
+ "instruction": "Provide comprehensive analysis of tumor across these 3 sequential slices at 10-slice intervals. \nSegmentation colors indicate:\n- RED: Non-Enhancing Tumor Core (NCR/NET) - necrotic tumor tissue\n- GREEN: Peritumoral Edema (ED) - swelling around the tumor\n- BLUE: Enhancing Tumor (ET) - actively growing tumor tissue",
347
+ "ground_truth": "Examining these 3 axial slices with 10-slice spacing: The lesion area is in the frontal and parietal lobes with high signal intensity in the left parietal lobe and mixed signal intensities with patchy high-signal regions in certain areas. Edema is significant, primarily noted around the left parietal lobe lesion with high signal intensity, extensive, and affecting the adjacent normal brain tissue. Necrosis is primarily located in the core region of the left parietal lobe lesion with uneven low signal intensity, characterized by a central low-signal area surrounded by high signal, indicating widespread distribution but predominantly concentrated in the parietal lobe area. Ventricular compression is observed in the right ventricle, which is compressed and deformed, with no significant ventricular expansion.",
348
+ "generated": "Examining these 3 axial slices with 10-slice spacing: The lesion area is in the left parietal and occipital lobes, characterized by heterogeneous high and low signals along with spotted high signal areas. Edema is significant, mainly observed in the left parietal and occipital lobes, indicating substantial swelling within the brain tissue surrounding the lesions, especially prominent near the lesion regions on the left side of the brain. Necrosis is suggested by mixed signals of uneven intensity, primarily located in the center of the lesions, with some necrotic zones appearing as low signals. Ventricular compression is notable, where ventricular deformation is observed with partial compression of the",
349
+ "rouge1": 0.6550218340611353,
350
+ "rouge2": 0.3524229074889868,
351
+ "rougeL": 0.445414847161572
352
+ },
353
+ {
354
+ "step": 100,
355
+ "epoch": 0.8032128514056225,
356
+ "sample_id": 73,
357
+ "patient_id": "BraTS20_Training_111",
358
+ "image_type": "single_slice",
359
+ "instruction": "Provide a detailed medical description of this brain scan. \nSegmentation colors indicate:\n- RED: Non-Enhancing Tumor Core (NCR/NET) - necrotic tumor tissue\n- GREEN: Peritumoral Edema (ED) - swelling around the tumor\n- BLUE: Enhancing Tumor (ET) - actively growing tumor tissue Note lesions and abnormalities.",
360
+ "ground_truth": "The MRI slice demonstrates: The lesion area is in the right frontal lobe with heterogeneous high and low signals along with speckled high-signal areas. Edema is significant, as signal areas are mainly observed in the right frontal lobe, with a large scope of edema. Necrosis is possibly indicated by some low-signal areas within the right frontal lobe, characterized by mixed signals and scattered throughout the lesions. Ventricular compression is mild compression of the right lateral ventricle.",
361
+ "generated": "The MRI slice demonstrates: The lesion area is in the left parietal lobe with mixed heterogeneous signals, including spotty high signal areas. Edema is significant surrounding the left parietal lesion area, observed as distinct high-signal zones, indicating that the edema area is relatively extensive and covers parts of the adjacent brain tissue. Necrosis is possible within the lesion region on the left side of the parietal lobe, characterized by low signal intensity spots scattered throughout the lesion. Ventricular compression is not observed at present.",
362
+ "rouge1": 0.6257668711656442,
363
+ "rouge2": 0.34782608695652173,
364
+ "rougeL": 0.49079754601226994
365
+ },
366
+ {
367
+ "step": 100,
368
+ "epoch": 0.8032128514056225,
369
+ "sample_id": 95,
370
+ "patient_id": "BraTS20_Training_039",
371
+ "image_type": "single_slice",
372
+ "instruction": "Provide a detailed medical description of this brain scan. \nSegmentation colors indicate:\n- RED: Non-Enhancing Tumor Core (NCR/NET) - necrotic tumor tissue\n- GREEN: Peritumoral Edema (ED) - swelling around the tumor\n- BLUE: Enhancing Tumor (ET) - actively growing tumor tissue Note lesions and abnormalities.",
373
+ "ground_truth": "The MRI slice demonstrates: The lesion area is in the left frontal and parietal lobes with mixed high and low signals with blotchy high-signal regions. Edema is significant, most notably in the left parietal lobe region, with considerable extent, indicating a severe degree of edema. Necrosis is a prominent high-signal area in the left parietal lobe, showing high signal intensity with mixed, blotchy signals. Ventricular compression is the lesion on the left side exerts some pressure on the ventricles, resulting in deformation of the left ventricle.",
374
+ "generated": "The MRI slice demonstrates: The lesion area is in the right frontal lobe with mixed high and low signals, along with spotty high signal regions. Edema is significant, particularly observed in the right frontal lobe surrounding the lesion, with extensive swelling. Necrosis is suggested by areas of low signal intensity within the right frontal lobe, appearing as mixed or speckled low signals. Ventricular compression is not evident due to the ventricular system being relatively intact without notable deformation.",
375
+ "rouge1": 0.5662650602409638,
376
+ "rouge2": 0.32926829268292684,
377
+ "rougeL": 0.49397590361445776
378
+ },
379
+ {
380
+ "step": 100,
381
+ "epoch": 0.8032128514056225,
382
+ "sample_id": 14,
383
+ "patient_id": "BraTS20_Training_259",
384
+ "image_type": "five_slices",
385
+ "instruction": "Provide detailed analysis of lesion distribution visible in these 5 slices. \nSegmentation colors indicate:\n- RED: Non-Enhancing Tumor Core (NCR/NET) - necrotic tumor tissue\n- GREEN: Peritumoral Edema (ED) - swelling around the tumor\n- BLUE: Enhancing Tumor (ET) - actively growing tumor tissue",
386
+ "ground_truth": "The comprehensive tumor distribution through these 5 slices demonstrates: The lesion area is in the right cerebral region, including the frontal lobe and part of the parietal lobe, with mixed high and low signals and patchy high signal areas. Edema is significant, observed in the right frontal lobe area and parts of the parietal lobe with relatively high intensity, extending over a considerable area. Necrosis is potential, identified in the high-intensity signal region of the right frontal lobe with highly uneven signal intensity, suggesting necrotic tissue more concentrated in the mid to posterior part of the right cerebrum. Ventricular compression is present, with the right ventricle compressed and deformed, indicating pressure exertion by the lesion.",
387
+ "generated": "The comprehensive tumor distribution through these 5 slices demonstrates: The lesion area is in the left temporal and parietal lobes with a mix of heterogeneous high and low signals, interspersed with spotty high signal regions. Edema is significant, primarily concentrated in the left frontal lobe with extensive edema, indicating substantial swelling within the tissue surrounding the lesions. Necrosis is possible, represented by low-signal areas deep inside the lesion region on the left side of the brain, showing mixed characteristics with both high and low signals scattered throughout the lesion. Ventricular compression is mild, but some signs suggest pressure on the ventricles.",
388
+ "rouge1": 0.6055045871559633,
389
+ "rouge2": 0.30555555555555564,
390
+ "rougeL": 0.4403669724770642
391
+ },
392
+ {
393
+ "step": 110,
394
+ "epoch": 0.8835341365461847,
395
+ "sample_id": 15,
396
+ "patient_id": "BraTS20_Training_343",
397
+ "image_type": "five_slices",
398
+ "instruction": "Provide detailed analysis of lesion distribution visible in these 5 slices. \nSegmentation colors indicate:\n- RED: Non-Enhancing Tumor Core (NCR/NET) - necrotic tumor tissue\n- GREEN: Peritumoral Edema (ED) - swelling around the tumor\n- BLUE: Enhancing Tumor (ET) - actively growing tumor tissue",
399
+ "ground_truth": "The comprehensive tumor distribution through these 5 slices demonstrates: The lesion area is in the frontal and parietal regions of the right cerebral hemisphere with a mixture of heterogeneous high and low signals, accompanied by speckled high-signal areas, suggesting the presence of multiple lesions. Edema is significant around the right frontal and parietal lobes, with notable swelling indicating a significant edema response that is extensive and impacts the surrounding tissue structures. Necrosis is observed within the high-signal areas in the right frontal and parietal lobes, as some low-signal regions suggest possible necrotic regions that are clustered in blocks and have indications of scattered distribution. Ventricular compression is exerted on the right lateral ventricle, showing mild deformation in its shape.",
400
+ "generated": "The comprehensive tumor distribution through these 5 slices demonstrates: The lesion area is in the left temporal lobe with a mixture of heterogeneous high and low signals, as well as speckled high signal areas. Edema is observed surrounding the lesions in the left temporal lobe, extending to parts of the adjacent parietal lobe, indicating significant swelling of tissues near the lesions. Necrosis is indicated by some low signal regions within the central part of the lesion in the left temporal lobe. Ventricular compression is not obvious from this slice range.",
401
+ "rouge1": 0.6132075471698113,
402
+ "rouge2": 0.36190476190476195,
403
+ "rougeL": 0.43396226415094336
404
+ },
405
+ {
406
+ "step": 110,
407
+ "epoch": 0.8835341365461847,
408
+ "sample_id": 75,
409
+ "patient_id": "BraTS20_Training_347",
410
+ "image_type": "five_slices",
411
+ "instruction": "Provide detailed analysis of lesion distribution visible in these 5 slices. \nSegmentation colors indicate:\n- RED: Non-Enhancing Tumor Core (NCR/NET) - necrotic tumor tissue\n- GREEN: Peritumoral Edema (ED) - swelling around the tumor\n- BLUE: Enhancing Tumor (ET) - actively growing tumor tissue",
412
+ "ground_truth": "The comprehensive tumor distribution through these 5 slices demonstrates: The lesion area is in the right cerebral region, particularly in the right parietal and frontal lobes, with a mix of uneven high and low signals and speckled high-signal areas, suggesting multiple lesions. Edema is significant around the right frontal and parietal lobes, represented by high signals, covering a large area. Necrosis is indicated by high signal areas in the central part of the lesion, displaying disorganized signals with unclear boundaries. Ventricular compression is present, with the right ventricle showing varying degrees of compression and deformation.",
413
+ "generated": "The comprehensive tumor distribution through these 5 slices demonstrates: The lesion area is in the left temporal and parietal regions with a mix of heterogeneous high and low signals, along with speckled high signal areas. Edema is significant, primarily located in the left temporal and parietal lobes, suggesting extensive swelling of surrounding tissues. Necrosis is present in the core of the lesions with mixed high and low signals but appears to be scattered and irregularly distributed. Ventricular compression is observed as slight deformation on the ventricles caused by increased pressure from the lesions.",
414
+ "rouge1": 0.6666666666666667,
415
+ "rouge2": 0.37433155080213903,
416
+ "rougeL": 0.5079365079365079
417
+ },
418
+ {
419
+ "step": 110,
420
+ "epoch": 0.8835341365461847,
421
+ "sample_id": 82,
422
+ "patient_id": "BraTS20_Training_301",
423
+ "image_type": "five_slices",
424
+ "instruction": "Analyze these 5 consecutive MRI slices (5-slice intervals) and describe complete tumor profile. \nSegmentation colors indicate:\n- RED: Non-Enhancing Tumor Core (NCR/NET) - necrotic tumor tissue\n- GREEN: Peritumoral Edema (ED) - swelling around the tumor\n- BLUE: Enhancing Tumor (ET) - actively growing tumor tissue",
425
+ "ground_truth": "Across these 5 consecutive slices (5-slice intervals), the complete tumor profile shows: The lesion area is in the left frontal, parietal, and temporal lobes with a mix of irregular high and low signals along with spotty high signal areas. Edema is significant, primarily located in the left parietal and frontal lobes, indicating considerable swelling of the surrounding tissues near the lesions. Necrosis is suggested by regions with abnormal signal intensity, exhibiting a mix of high and low signals, focusing on the left parietal and frontal lobes. Ventricular compression is observed as the ventricles are deformed and compressed, particularly near the parietal lobe lesion area, showing a notable impact of the lesion on the ventricles.",
426
+ "generated": "Across these 5 consecutive slices, the complete tumor distribution shows: The lesion area is in the left frontal lobe with a mixture of heterogeneous high and low signals along with speckled high signal areas, indicating multiple lesions. Edema is mainly observed in the left frontal and parietal lobes surrounding the lesion, with significant swelling that has spread to nearby brain tissues but is not severe. Necrosis is within the left frontal and parietal lobes, characterized by uneven mixed signal intensity of both low and high signals, suggesting a mix of necrosis and edema patterns. Ventricular compression is seen with the left lateral ventricle showing mild compression while the right lateral ventricle remains largely normal.",
427
+ "rouge1": 0.6986899563318777,
428
+ "rouge2": 0.31718061674008813,
429
+ "rougeL": 0.4978165938864629
430
+ },
431
+ {
432
+ "step": 120,
433
+ "epoch": 0.963855421686747,
434
+ "sample_id": 28,
435
+ "patient_id": "BraTS20_Training_271",
436
+ "image_type": "three_slices",
437
+ "instruction": "Examine these 3 MRI slices and describe how the lesion evolves through brain volume. \nSegmentation colors indicate:\n- RED: Non-Enhancing Tumor Core (NCR/NET) - necrotic tumor tissue\n- GREEN: Peritumoral Edema (ED) - swelling around the tumor\n- BLUE: Enhancing Tumor (ET) - actively growing tumor tissue",
438
+ "ground_truth": "The tumor progression through these 3 slices demonstrates: The lesion area is in the right hemisphere of the brain, near the frontal and parietal lobes, with a heterogeneous mix of high and low signals, and patchy high signal areas. Edema is significant, mainly around the lesion sites, particularly in the posterior part of the right frontal lobe and the medial part of the right parietal lobe. Necrosis is observed as low signal images, with heterogeneous signals concentrated at the junction of the parietal and frontal lobes in the right hemisphere. Ventricular compression is not observed, as the ventricular morphology is normal, showing no clear signs of deformation or compression.",
439
+ "generated": "The tumor progression through these 3 sequential slices demonstrates: The lesion area is in the right frontal lobe with a mix of heterogeneous signals, including high signal regions and spotty high signal areas. Edema is observed surrounding the lesions on both sides of the right frontal lobe, indicating significant swelling of the tissues near the lesions, especially concentrated at the right parietal lobe region. Necrosis is indicated by low signal intensity within some parts of the right frontal lobe, suggesting possible necrosis occurring at the core of the lesions. Ventricular compression is noted as the ventricular system shows deformation but no clear signs of blockage or obstruction.",
440
+ "rouge1": 0.7037037037037038,
441
+ "rouge2": 0.4485981308411215,
442
+ "rougeL": 0.5740740740740741
443
+ },
444
+ {
445
+ "step": 120,
446
+ "epoch": 0.963855421686747,
447
+ "sample_id": 42,
448
+ "patient_id": "BraTS20_Training_165",
449
+ "image_type": "three_slices",
450
+ "instruction": "Describe tumor progression across these 3 consecutive brain MRI slices (10-slice intervals). \nSegmentation colors indicate:\n- RED: Non-Enhancing Tumor Core (NCR/NET) - necrotic tumor tissue\n- GREEN: Peritumoral Edema (ED) - swelling around the tumor\n- BLUE: Enhancing Tumor (ET) - actively growing tumor tissue",
451
+ "ground_truth": "Across these 3 consecutive slices (10-slice intervals), the tumor shows: The lesion area is in the left parietal and temporal lobes with a mix of heterogeneous high and low signals along with speckled high signal areas. Edema is detected surrounding the lesion, with a larger area of edema observed on the left side, mainly in the parietal and temporal lobes, indicating significant swelling of the tissue around the lesion. Necrosis is characterized by mixed low and high signals mainly concentrated in the left parietal lobe and is relatively centralized. Ventricular compression is evident in the left ventricle, showing compression and deformation.",
452
+ "generated": "Across these 3 consecutive slices (10-slice intervals), the tumor shows: The lesion area is in the frontal lobe region with a mixed signal of uneven high and low, accompanied by speckled high signal regions. Edema is significant surrounding the lesions, notably observed in areas near the frontal lobe, indicating pronounced swelling of the tissues nearby the lesions, extending into adjacent normal brain tissue. Necrosis is present as some lower signals within the lesion area, suggesting possible necrosis but scattered, with uneven distribution. Ventricular compression is not prominent, but there are signs of compression on the ventricles, particularly noticeable in the left lateral ventricle which appears slightly",
453
+ "rouge1": 0.6220095693779903,
454
+ "rouge2": 0.34782608695652173,
455
+ "rougeL": 0.5263157894736842
456
+ },
457
+ {
458
+ "step": 120,
459
+ "epoch": 0.963855421686747,
460
+ "sample_id": 3,
461
+ "patient_id": "BraTS20_Training_355",
462
+ "image_type": "single_slice",
463
+ "instruction": "Provide a detailed medical description of this brain scan. \nSegmentation colors indicate:\n- RED: Non-Enhancing Tumor Core (NCR/NET) - necrotic tumor tissue\n- GREEN: Peritumoral Edema (ED) - swelling around the tumor\n- BLUE: Enhancing Tumor (ET) - actively growing tumor tissue Note lesions and abnormalities.",
464
+ "ground_truth": "The MRI slice demonstrates: The lesion area is in the right parietal and temporal lobes, with a mixture of multiple uneven high and low signals along with speckled high signal areas. Edema is significant, with a large area of swelling occurring around the lesion, notably widespread and clearly spread to surrounding areas. Necrosis is primarily concentrated in the lesion sites, characterized by low signals, with mixed signals focused in the core region. Ventricular compression is with compression and deformation of the right ventricle.",
465
+ "generated": "The MRI slice demonstrates: The lesion area is in the left frontal lobe with mixed signals, including both high and low intensities, along with spotty high signal regions. Edema is extensive, particularly observed on the left side with significant swelling extending into adjacent tissues. Necrosis is possible as some areas are characterized by lower intensity signals, suggesting potential necrosis but not definitively confirmed due to their small size. Ventricular compression is noticeable as the right ventricle shows slight deformation.",
466
+ "rouge1": 0.5185185185185185,
467
+ "rouge2": 0.2875,
468
+ "rougeL": 0.41975308641975306
469
+ }
470
+ ]
brats_medgemma_r1_alpha4_20251014_001744/metrics/validation_log_20251014_001744.csv ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ step,epoch,sample_id,patient_id,image_type,rouge1,rouge2,rougeL,avg_rouge
2
+ 10,0.0803,7,BraTS20_Training_005,three_slices,0.3838,0.0816,0.2424,0.2360
3
+ 10,0.0803,53,BraTS20_Training_048,five_slices,0.3737,0.1020,0.2222,0.2327
4
+ 10,0.0803,16,BraTS20_Training_199,three_slices,0.1576,0.0491,0.0970,0.1012
5
+ 20,0.1606,42,BraTS20_Training_165,three_slices,0.5181,0.2195,0.3373,0.3583
6
+ 20,0.1606,27,BraTS20_Training_128,three_slices,0.4712,0.1845,0.2692,0.3083
7
+ 20,0.1606,51,BraTS20_Training_146,single_slice,0.6079,0.2667,0.4141,0.4296
8
+ 30,0.2410,39,BraTS20_Training_107,single_slice,0.4976,0.2660,0.3220,0.3618
9
+ 30,0.2410,75,BraTS20_Training_347,five_slices,0.5474,0.2553,0.3579,0.3869
10
+ 30,0.2410,108,BraTS20_Training_279,three_slices,0.4706,0.1683,0.2843,0.3077
11
+ 40,0.3213,45,BraTS20_Training_364,single_slice,0.6738,0.3784,0.4171,0.4898
12
+ 40,0.3213,31,BraTS20_Training_080,single_slice,0.5556,0.2897,0.3796,0.4083
13
+ 40,0.3213,99,BraTS20_Training_329,five_slices,0.4734,0.1854,0.3478,0.3355
14
+ 50,0.4016,108,BraTS20_Training_279,three_slices,0.5408,0.2887,0.4082,0.4125
15
+ 50,0.4016,60,BraTS20_Training_366,single_slice,0.6606,0.3056,0.4679,0.4780
16
+ 50,0.4016,90,BraTS20_Training_248,five_slices,0.5871,0.3116,0.3980,0.4322
17
+ 60,0.4819,65,BraTS20_Training_368,five_slices,0.5497,0.2722,0.4094,0.4104
18
+ 60,0.4819,52,BraTS20_Training_239,five_slices,0.5699,0.2609,0.3978,0.4095
19
+ 60,0.4819,86,BraTS20_Training_121,single_slice,0.6296,0.3645,0.4907,0.4950
20
+ 70,0.5622,33,BraTS20_Training_214,five_slices,0.6140,0.3756,0.5209,0.5035
21
+ 70,0.5622,109,BraTS20_Training_178,three_slices,0.7143,0.4414,0.5804,0.5787
22
+ 70,0.5622,34,BraTS20_Training_116,three_slices,0.5479,0.2488,0.4018,0.3995
23
+ 80,0.6426,28,BraTS20_Training_271,three_slices,0.7230,0.4455,0.5258,0.5648
24
+ 80,0.6426,13,BraTS20_Training_132,three_slices,0.6578,0.3677,0.4978,0.5078
25
+ 80,0.6426,38,BraTS20_Training_040,single_slice,0.5673,0.2913,0.4327,0.4304
26
+ 90,0.7229,108,BraTS20_Training_279,three_slices,0.6193,0.3077,0.4569,0.4613
27
+ 90,0.7229,24,BraTS20_Training_139,five_slices,0.6233,0.3474,0.4744,0.4817
28
+ 90,0.7229,40,BraTS20_Training_192,three_slices,0.6550,0.3524,0.4454,0.4843
29
+ 100,0.8032,73,BraTS20_Training_111,single_slice,0.6258,0.3478,0.4908,0.4881
30
+ 100,0.8032,95,BraTS20_Training_039,single_slice,0.5663,0.3293,0.4940,0.4632
31
+ 100,0.8032,14,BraTS20_Training_259,five_slices,0.6055,0.3056,0.4404,0.4505
32
+ 110,0.8835,15,BraTS20_Training_343,five_slices,0.6132,0.3619,0.4340,0.4697
33
+ 110,0.8835,75,BraTS20_Training_347,five_slices,0.6667,0.3743,0.5079,0.5163
34
+ 110,0.8835,82,BraTS20_Training_301,five_slices,0.6987,0.3172,0.4978,0.5046
35
+ 120,0.9639,28,BraTS20_Training_271,three_slices,0.7037,0.4486,0.5741,0.5755
36
+ 120,0.9639,42,BraTS20_Training_165,three_slices,0.6220,0.3478,0.5263,0.4987
37
+ 120,0.9639,3,BraTS20_Training_355,single_slice,0.5185,0.2875,0.4198,0.4086