Training in progress, epoch 1

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4eb118859ccd2b17b7c4ddc77d35f3fe0ef85393a1eeeb72c87b218498a749f7
+oid sha256:15e0b09d6517be8dfbfa192a629bf8c8ebbd7a36b42f6874dc9469ccb08abf3d
 size 721655813

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abc34843e0965196a4479f17cf08bf8a88225eec6c573845d80ec4df06d5bcf4
+oid sha256:433004263a1040799e6bfe1d5d5cb128be82e2f0212a989bd17392c683139c99
 size 377643361

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:769917d52eee0e3ec39baab8d23748c7392a020826ef8ddf1250670f1fa7a2d1
+oid sha256:706cb5515dfb83acf46311e8872450c873a190e15c985bac9f03ac1601afb4ca
 size 14575

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d06a48b6590730359e992b5a9274a6f0aa5a3415a51fce3457d99a6fd60c656
+oid sha256:d130c113354872d1ca46ad7aa6c522fdfca3010ff0ae55e7777fc12049fdca1d
 size 557

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bb234e8aff204ba837868e8af06d316f481bb10dedb985a07200d97b524462f
+oid sha256:00e56ff1f9aeef202866d18c52f49cf630af4e847aa9aca70191fe768f73377a
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.0,
-  "global_step": 2576,
+  "epoch": 1.0,
+  "global_step": 322,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -10,143 +10,24 @@
     {
       "epoch": 1.0,
       "learning_rate": 9.83874482458052e-05,
-      "loss": 22.6211,
+      "loss": 22.5987,
       "step": 322
     },
     {
       "epoch": 1.0,
       "eval_cer": 1.0,
-      "eval_loss": 3.3536856174468994,
+      "eval_loss": 3.259235143661499,
       "eval_new_wer": 1.0,
       "eval_old_wer": 1.0,
-      "eval_runtime": 7.7387,
-      "eval_samples_per_second": 27.136,
-      "eval_steps_per_second": 3.489,
+      "eval_runtime": 8.6332,
+      "eval_samples_per_second": 24.325,
+      "eval_steps_per_second": 3.127,
       "step": 322
-    },
-    {
-      "epoch": 2.0,
-      "learning_rate": 9.13706689910656e-05,
-      "loss": 3.4051,
-      "step": 644
-    },
-    {
-      "epoch": 2.0,
-      "eval_cer": 1.0,
-      "eval_loss": 3.384406328201294,
-      "eval_new_wer": 1.0,
-      "eval_old_wer": 1.0,
-      "eval_runtime": 7.5183,
-      "eval_samples_per_second": 27.932,
-      "eval_steps_per_second": 3.591,
-      "step": 644
-    },
-    {
-      "epoch": 3.0,
-      "learning_rate": 8.4353889736326e-05,
-      "loss": 3.4379,
-      "step": 966
-    },
-    {
-      "epoch": 3.0,
-      "eval_cer": 1.0,
-      "eval_loss": 3.2850329875946045,
-      "eval_new_wer": 1.0,
-      "eval_old_wer": 1.0,
-      "eval_runtime": 7.8755,
-      "eval_samples_per_second": 26.665,
-      "eval_steps_per_second": 3.428,
-      "step": 966
-    },
-    {
-      "epoch": 4.0,
-      "learning_rate": 7.73371104815864e-05,
-      "loss": 3.4255,
-      "step": 1288
-    },
-    {
-      "epoch": 4.0,
-      "eval_cer": 1.0,
-      "eval_loss": 3.3971991539001465,
-      "eval_new_wer": 1.0,
-      "eval_old_wer": 1.0,
-      "eval_runtime": 7.5517,
-      "eval_samples_per_second": 27.808,
-      "eval_steps_per_second": 3.575,
-      "step": 1288
-    },
-    {
-      "epoch": 5.0,
-      "learning_rate": 7.032033122684682e-05,
-      "loss": 3.4102,
-      "step": 1610
-    },
-    {
-      "epoch": 5.0,
-      "eval_cer": 1.0,
-      "eval_loss": 3.3659400939941406,
-      "eval_new_wer": 1.0,
-      "eval_old_wer": 1.0,
-      "eval_runtime": 7.5128,
-      "eval_samples_per_second": 27.952,
-      "eval_steps_per_second": 3.594,
-      "step": 1610
-    },
-    {
-      "epoch": 6.0,
-      "learning_rate": 6.330355197210721e-05,
-      "loss": 3.4039,
-      "step": 1932
-    },
-    {
-      "epoch": 6.0,
-      "eval_cer": 1.0,
-      "eval_loss": 3.3250296115875244,
-      "eval_new_wer": 1.0,
-      "eval_old_wer": 1.0,
-      "eval_runtime": 7.4768,
-      "eval_samples_per_second": 28.087,
-      "eval_steps_per_second": 3.611,
-      "step": 1932
-    },
-    {
-      "epoch": 7.0,
-      "learning_rate": 5.628677271736762e-05,
-      "loss": 3.4033,
-      "step": 2254
-    },
-    {
-      "epoch": 7.0,
-      "eval_cer": 1.0,
-      "eval_loss": 3.3770763874053955,
-      "eval_new_wer": 1.0,
-      "eval_old_wer": 1.0,
-      "eval_runtime": 7.4897,
-      "eval_samples_per_second": 28.038,
-      "eval_steps_per_second": 3.605,
-      "step": 2254
-    },
-    {
-      "epoch": 8.0,
-      "learning_rate": 4.9269993462628025e-05,
-      "loss": 3.3976,
-      "step": 2576
-    },
-    {
-      "epoch": 8.0,
-      "eval_cer": 1.0,
-      "eval_loss": 3.305764675140381,
-      "eval_new_wer": 1.0,
-      "eval_old_wer": 1.0,
-      "eval_runtime": 7.4908,
-      "eval_samples_per_second": 28.034,
-      "eval_steps_per_second": 3.604,
-      "step": 2576
     }
   ],
   "max_steps": 4830,
   "num_train_epochs": 15,
-  "total_flos": 1.912160410310016e+18,
+  "total_flos": 2.38632755188128e+17,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:728f47a3aa9aa6097ab096de7ed2d1e438a0a05309a80b28f01c0f3f6e7eaa44
+oid sha256:950b7a3f32c6bae99f90ac51b590f1a0cedbba08cabd0e9d7ec6feb261e68f5e
 size 3387

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abc34843e0965196a4479f17cf08bf8a88225eec6c573845d80ec4df06d5bcf4
+oid sha256:433004263a1040799e6bfe1d5d5cb128be82e2f0212a989bd17392c683139c99
 size 377643361

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:728f47a3aa9aa6097ab096de7ed2d1e438a0a05309a80b28f01c0f3f6e7eaa44
+oid sha256:950b7a3f32c6bae99f90ac51b590f1a0cedbba08cabd0e9d7ec6feb261e68f5e
 size 3387