Upload 9 files

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:589f092724206cdcff9df9c709f552ab03a6bce7a3af87738df3364f8205eb31
+oid sha256:fe7fd1764c7c90f6d43cdd67295e5233d46cdc1193418c56bd9a019183019dc7
 size 2490594117

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87cfc3d39029c9690dd86b4f0275f4111954d33b4e1c685fd7f36825e00a3eae
+oid sha256:7438d7620c8202515f2afa81498da17b53ec1debae3c4f7fa871d57a678ca488
 size 1262168365

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d78fbb1a5438682b3e56cdcbcd670790d52471dfc41d3e1df54743de1874ab2
+oid sha256:0cdaf50a0753d3a6e101916319bd71a8a4deca5c897164903ee046122c35005a
 size 14575

scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc40a4be6a52cee4d7658df4041e660ffa02b0d8b5bd143bb8bb397f7b71b1a5
+oid sha256:c4e827e327ff1e038aa2027dda2c3ed3be5c6a6d7a0f9578e32510d4dcaf26a3
 size 557

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cd51f54c3c9ede3156fe9d077aa80e3c39fad9c7aefb825e83dd16225db78dd
+oid sha256:387faccb2a2f1652b597f93e0dfe377728691d7dafb8a403a4470c4646c76cd5
 size 627

trainer_state.json

@@ -1,37 +1,130 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.379540400296516,
-  "global_step": 400,
+  "epoch": 13.791738382099828,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.89,
-      "learning_rate": 9.999702363235908e-06,
-      "loss": 0.0354,
+      "epoch": 1.03,
+      "learning_rate": 9.99965514863094e-07,
+      "loss": 0.0333,
       "step": 150
     },
     {
-      "epoch": 1.78,
-      "learning_rate": 9.99880945294363e-06,
-      "loss": 0.0336,
+      "epoch": 2.07,
+      "learning_rate": 9.99862059452376e-07,
+      "loss": 0.0332,
       "step": 300
     },
     {
-      "epoch": 2.38,
-      "eval_loss": 0.19874997437000275,
-      "eval_runtime": 421.2238,
-      "eval_samples_per_second": 11.438,
-      "eval_steps_per_second": 1.432,
-      "eval_wer": 0.15169214199908868,
-      "step": 400
+      "epoch": 3.1,
+      "learning_rate": 9.99758604041658e-07,
+      "loss": 0.0336,
+      "step": 450
+    },
+    {
+      "epoch": 3.45,
+      "eval_loss": 0.21229705214500427,
+      "eval_runtime": 487.1939,
+      "eval_samples_per_second": 10.649,
+      "eval_steps_per_second": 1.332,
+      "eval_wer": 0.1448122092799754,
+      "step": 500
+    },
+    {
+      "epoch": 4.14,
+      "learning_rate": 9.9965514863094e-07,
+      "loss": 0.0329,
+      "step": 600
+    },
+    {
+      "epoch": 5.17,
+      "learning_rate": 9.995516932202221e-07,
+      "loss": 0.0323,
+      "step": 750
+    },
+    {
+      "epoch": 6.21,
+      "learning_rate": 9.99448237809504e-07,
+      "loss": 0.0317,
+      "step": 900
+    },
+    {
+      "epoch": 6.9,
+      "eval_loss": 0.20801204442977905,
+      "eval_runtime": 282.77,
+      "eval_samples_per_second": 18.347,
+      "eval_steps_per_second": 2.295,
+      "eval_wer": 0.14550417099142737,
+      "step": 1000
+    },
+    {
+      "epoch": 7.24,
+      "learning_rate": 9.993454721015242e-07,
+      "loss": 0.0323,
+      "step": 1050
+    },
+    {
+      "epoch": 8.28,
+      "learning_rate": 9.992420166908062e-07,
+      "loss": 0.031,
+      "step": 1200
+    },
+    {
+      "epoch": 9.31,
+      "learning_rate": 9.991385612800883e-07,
+      "loss": 0.0314,
+      "step": 1350
+    },
+    {
+      "epoch": 10.34,
+      "learning_rate": 9.990351058693703e-07,
+      "loss": 0.0317,
+      "step": 1500
+    },
+    {
+      "epoch": 10.34,
+      "eval_loss": 0.2071654200553894,
+      "eval_runtime": 303.1157,
+      "eval_samples_per_second": 17.116,
+      "eval_steps_per_second": 2.141,
+      "eval_wer": 0.14465844001076386,
+      "step": 1500
+    },
+    {
+      "epoch": 11.38,
+      "learning_rate": 9.989316504586522e-07,
+      "loss": 0.031,
+      "step": 1650
+    },
+    {
+      "epoch": 12.41,
+      "learning_rate": 9.988281950479342e-07,
+      "loss": 0.0318,
+      "step": 1800
+    },
+    {
+      "epoch": 13.45,
+      "learning_rate": 9.987247396372162e-07,
+      "loss": 0.0314,
+      "step": 1950
+    },
+    {
+      "epoch": 13.79,
+      "eval_loss": 0.20706616342067719,
+      "eval_runtime": 287.3918,
+      "eval_samples_per_second": 18.052,
+      "eval_steps_per_second": 2.258,
+      "eval_wer": 0.1442355745204321,
+      "step": 2000
     }
   ],
-  "max_steps": 1680000,
+  "max_steps": 1450000,
   "num_train_epochs": 10000,
-  "total_flos": 9.154271872958712e+18,
+  "total_flos": 5.652539665735567e+19,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:baa3cfd4e4131e4651786c3cda673f577d5bd99579c07be55652efaf86dc1600
+oid sha256:c61dd66333a3a0d68eedaaf6d552d4521e71274edd381e8de2a88579575bba8c
 size 3323