Training in progress, step 4300

{checkpoint-3800 → checkpoint-4200}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3916c502476103f3ffc7a1308222895c30676a37dc692fc61cb70066e716d9ac
+oid sha256:6ddef0f5049947aa8210403bee49ef1fd880b41459272b4c05c3eb32308f2f44
 size 2490337809

{checkpoint-3900 → checkpoint-4200}/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b689bc4f48a4fe8515030b196fb5bd4de5819b77555cbfd8e1979aa0d04c367
+oid sha256:588e62e516d26a20bbfce337c36c9f1a83451a67d19e583d1cdceb96aff5859f
 size 1262063089

{checkpoint-3900 → checkpoint-4200}/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:266a5b6d767d7cc2ccd3807fca6c4cfb051cc7d3796a6836ef75e2cf3c6b3218
+oid sha256:4e03d76f10a67412455e92aefe077a6da7230abf78e55d42dec22dfbaea90dbd
 size 14567

{checkpoint-3900 → checkpoint-4200}/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26f1e0a22621c69063b9f7d6715acac2896bf4745746722f322c93153a0c85b5
+oid sha256:7018904ee53324745014ee00f0192d0f3344069918f4c8dd54467134a03ae355
 size 559

{checkpoint-3800 → checkpoint-4200}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:108cf3add24d85591d96de728715165debaf66f2fb85e7a11bb55ca6e478dd61
+oid sha256:7fb4edd93c6eef5711ff572cfd2e93da18eb0ae8a7738f853f88ca1ecfb5e8b9
 size 623

{checkpoint-3900 → checkpoint-4200}/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 42.85245901639344,
-  "global_step": 3900,
+  "epoch": 46.15300546448088,
+  "global_step": 4200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1527,11 +1527,128 @@
       "eval_steps_per_second": 0.798,
       "eval_wer": 0.12883905762134545,
       "step": 3900
+    },
+    {
+      "epoch": 43.08,
+      "learning_rate": 6.205882352941176e-05,
+      "loss": 0.7691,
+      "step": 3920
+    },
+    {
+      "epoch": 43.3,
+      "learning_rate": 6.0098039215686274e-05,
+      "loss": 0.728,
+      "step": 3940
+    },
+    {
+      "epoch": 43.51,
+      "learning_rate": 5.813725490196078e-05,
+      "loss": 0.7585,
+      "step": 3960
+    },
+    {
+      "epoch": 43.73,
+      "learning_rate": 5.6176470588235296e-05,
+      "loss": 0.7564,
+      "step": 3980
+    },
+    {
+      "epoch": 43.95,
+      "learning_rate": 5.4215686274509804e-05,
+      "loss": 0.7383,
+      "step": 4000
+    },
+    {
+      "epoch": 43.95,
+      "eval_loss": 0.15269021689891815,
+      "eval_runtime": 188.5816,
+      "eval_samples_per_second": 25.681,
+      "eval_steps_per_second": 0.806,
+      "eval_wer": 0.13003122338915696,
+      "step": 4000
+    },
+    {
+      "epoch": 44.17,
+      "learning_rate": 5.225490196078431e-05,
+      "loss": 0.7693,
+      "step": 4020
+    },
+    {
+      "epoch": 44.39,
+      "learning_rate": 5.0294117647058826e-05,
+      "loss": 0.7347,
+      "step": 4040
+    },
+    {
+      "epoch": 44.61,
+      "learning_rate": 4.8333333333333334e-05,
+      "loss": 0.7185,
+      "step": 4060
+    },
+    {
+      "epoch": 44.83,
+      "learning_rate": 4.637254901960784e-05,
+      "loss": 0.7394,
+      "step": 4080
+    },
+    {
+      "epoch": 45.05,
+      "learning_rate": 4.4411764705882356e-05,
+      "loss": 0.7565,
+      "step": 4100
+    },
+    {
+      "epoch": 45.05,
+      "eval_loss": 0.14823457598686218,
+      "eval_runtime": 191.1254,
+      "eval_samples_per_second": 25.339,
+      "eval_steps_per_second": 0.795,
+      "eval_wer": 0.12886744252057905,
+      "step": 4100
+    },
+    {
+      "epoch": 45.27,
+      "learning_rate": 4.2450980392156864e-05,
+      "loss": 0.7535,
+      "step": 4120
+    },
+    {
+      "epoch": 45.49,
+      "learning_rate": 4.049019607843137e-05,
+      "loss": 0.737,
+      "step": 4140
+    },
+    {
+      "epoch": 45.71,
+      "learning_rate": 3.852941176470588e-05,
+      "loss": 0.7501,
+      "step": 4160
+    },
+    {
+      "epoch": 45.93,
+      "learning_rate": 3.6568627450980393e-05,
+      "loss": 0.7285,
+      "step": 4180
+    },
+    {
+      "epoch": 46.15,
+      "learning_rate": 3.46078431372549e-05,
+      "loss": 0.7697,
+      "step": 4200
+    },
+    {
+      "epoch": 46.15,
+      "eval_loss": 0.1494804471731186,
+      "eval_runtime": 190.3868,
+      "eval_samples_per_second": 25.438,
+      "eval_steps_per_second": 0.798,
+      "eval_wer": 0.1271927334657962,
+      "step": 4200
     }
   ],
   "max_steps": 4550,
   "num_train_epochs": 50,
-  "total_flos": 6.032084123274907e+19,
+  "total_flos": 6.496086001622114e+19,
   "trial_name": null,
   "trial_params": null
 }

{checkpoint-3900 → checkpoint-4300}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:168e59323a9bf241005906b1870612b1b524768b8a27757437012f8cdf781fc3
+oid sha256:58cce60fe69424e2a89d307caa661955fd8777a8855b339f2af2ad4573bb989c
 size 2490337809

{checkpoint-3800 → checkpoint-4300}/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0b145b6b59bd869ef8bc9342a6f9c151b7c459935f0fd7b3877c9afe90a49de
+oid sha256:ca11c993941e9cd903a98a8d6a851a925b5bc173fcb10c435092a4ff2bbe4c56
 size 1262063089

{checkpoint-3800 → checkpoint-4300}/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd0c1e59d01355dc7800f78e2a8c707b3bf501a6ea7d92076b4d2400614623cf
-size 14567
+oid sha256:412f958acca27a8108970c9e2ebea1c88954db1eb284dd8fe51687e899621b23
+size 14503

{checkpoint-3800 → checkpoint-4300}/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29eb923c97bb88614ccb0255ae678634f872dd8aa03ae16319e241eb7a1e8c90
+oid sha256:6924042b31741a307a9c2d3e5d4148105227679127f306862679a760336ca11c
 size 559

{checkpoint-3900 → checkpoint-4300}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1bc34f9b39344288eae3f0b593523acd1748174f4d473bee33a329e62da9e8a
+oid sha256:d9bfd4ddf4228b39539babfcc9c868a929c00cb0946eb4b8ecfaa5fa12431293
 size 623

{checkpoint-3800 → checkpoint-4300}/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 41.75409836065574,
-  "global_step": 3800,
+  "epoch": 47.25136612021858,
+  "global_step": 4300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1488,11 +1488,206 @@
       "eval_steps_per_second": 0.815,
       "eval_wer": 0.13170593244393983,
       "step": 3800
+    },
+    {
+      "epoch": 41.97,
+      "learning_rate": 7.186274509803923e-05,
+      "loss": 0.7765,
+      "step": 3820
+    },
+    {
+      "epoch": 42.2,
+      "learning_rate": 6.990196078431373e-05,
+      "loss": 0.7599,
+      "step": 3840
+    },
+    {
+      "epoch": 42.42,
+      "learning_rate": 6.794117647058824e-05,
+      "loss": 0.7782,
+      "step": 3860
+    },
+    {
+      "epoch": 42.63,
+      "learning_rate": 6.598039215686274e-05,
+      "loss": 0.7395,
+      "step": 3880
+    },
+    {
+      "epoch": 42.85,
+      "learning_rate": 6.401960784313726e-05,
+      "loss": 0.7594,
+      "step": 3900
+    },
+    {
+      "epoch": 42.85,
+      "eval_loss": 0.14983513951301575,
+      "eval_runtime": 190.4439,
+      "eval_samples_per_second": 25.43,
+      "eval_steps_per_second": 0.798,
+      "eval_wer": 0.12883905762134545,
+      "step": 3900
+    },
+    {
+      "epoch": 43.08,
+      "learning_rate": 6.205882352941176e-05,
+      "loss": 0.7691,
+      "step": 3920
+    },
+    {
+      "epoch": 43.3,
+      "learning_rate": 6.0098039215686274e-05,
+      "loss": 0.728,
+      "step": 3940
+    },
+    {
+      "epoch": 43.51,
+      "learning_rate": 5.813725490196078e-05,
+      "loss": 0.7585,
+      "step": 3960
+    },
+    {
+      "epoch": 43.73,
+      "learning_rate": 5.6176470588235296e-05,
+      "loss": 0.7564,
+      "step": 3980
+    },
+    {
+      "epoch": 43.95,
+      "learning_rate": 5.4215686274509804e-05,
+      "loss": 0.7383,
+      "step": 4000
+    },
+    {
+      "epoch": 43.95,
+      "eval_loss": 0.15269021689891815,
+      "eval_runtime": 188.5816,
+      "eval_samples_per_second": 25.681,
+      "eval_steps_per_second": 0.806,
+      "eval_wer": 0.13003122338915696,
+      "step": 4000
+    },
+    {
+      "epoch": 44.17,
+      "learning_rate": 5.225490196078431e-05,
+      "loss": 0.7693,
+      "step": 4020
+    },
+    {
+      "epoch": 44.39,
+      "learning_rate": 5.0294117647058826e-05,
+      "loss": 0.7347,
+      "step": 4040
+    },
+    {
+      "epoch": 44.61,
+      "learning_rate": 4.8333333333333334e-05,
+      "loss": 0.7185,
+      "step": 4060
+    },
+    {
+      "epoch": 44.83,
+      "learning_rate": 4.637254901960784e-05,
+      "loss": 0.7394,
+      "step": 4080
+    },
+    {
+      "epoch": 45.05,
+      "learning_rate": 4.4411764705882356e-05,
+      "loss": 0.7565,
+      "step": 4100
+    },
+    {
+      "epoch": 45.05,
+      "eval_loss": 0.14823457598686218,
+      "eval_runtime": 191.1254,
+      "eval_samples_per_second": 25.339,
+      "eval_steps_per_second": 0.795,
+      "eval_wer": 0.12886744252057905,
+      "step": 4100
+    },
+    {
+      "epoch": 45.27,
+      "learning_rate": 4.2450980392156864e-05,
+      "loss": 0.7535,
+      "step": 4120
+    },
+    {
+      "epoch": 45.49,
+      "learning_rate": 4.049019607843137e-05,
+      "loss": 0.737,
+      "step": 4140
+    },
+    {
+      "epoch": 45.71,
+      "learning_rate": 3.852941176470588e-05,
+      "loss": 0.7501,
+      "step": 4160
+    },
+    {
+      "epoch": 45.93,
+      "learning_rate": 3.6568627450980393e-05,
+      "loss": 0.7285,
+      "step": 4180
+    },
+    {
+      "epoch": 46.15,
+      "learning_rate": 3.46078431372549e-05,
+      "loss": 0.7697,
+      "step": 4200
+    },
+    {
+      "epoch": 46.15,
+      "eval_loss": 0.1494804471731186,
+      "eval_runtime": 190.3868,
+      "eval_samples_per_second": 25.438,
+      "eval_steps_per_second": 0.798,
+      "eval_wer": 0.1271927334657962,
+      "step": 4200
+    },
+    {
+      "epoch": 46.37,
+      "learning_rate": 3.264705882352941e-05,
+      "loss": 0.7283,
+      "step": 4220
+    },
+    {
+      "epoch": 46.59,
+      "learning_rate": 3.0686274509803923e-05,
+      "loss": 0.7218,
+      "step": 4240
+    },
+    {
+      "epoch": 46.81,
+      "learning_rate": 2.872549019607843e-05,
+      "loss": 0.7341,
+      "step": 4260
+    },
+    {
+      "epoch": 47.03,
+      "learning_rate": 2.6764705882352942e-05,
+      "loss": 0.7293,
+      "step": 4280
+    },
+    {
+      "epoch": 47.25,
+      "learning_rate": 2.480392156862745e-05,
+      "loss": 0.7194,
+      "step": 4300
+    },
+    {
+      "epoch": 47.25,
+      "eval_loss": 0.14928147196769714,
+      "eval_runtime": 189.625,
+      "eval_samples_per_second": 25.54,
+      "eval_steps_per_second": 0.802,
+      "eval_wer": 0.12693726937269373,
+      "step": 4300
     }
   ],
   "max_steps": 4550,
   "num_train_epochs": 50,
-  "total_flos": 5.876357873041098e+19,
+  "total_flos": 6.648181588185401e+19,
   "trial_name": null,
   "trial_params": null
 }