Training in progress, step 28800, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6232fc3031019ccf927066ee428a2de682063c59bfbfa36005b4a59f91d614b6
+oid sha256:2685df91b0212c3d771f740af7d493329819e9ece934c6572ec91f4ac11a64ea
 size 1262135480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93a781d7be1174e0a1fb9282b76358acefa16e55f3114a4a9c7954793376fd63
+oid sha256:f33961fae286f63a4d7d03dcc99f6908f11c6a773bd2e93e0e7d4d192962b30a
 size 2490815798

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df573c8ebef5630b90590bf8e61369a0825dfe9a42993039ba55510b3bb81d53
-size 14244
+oid sha256:dd07cca9b4e51cb881f8cba86aaed9cb56420ad7f452f9d07931ab907d7921d1
+size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:467385a064422d8119ef7edb78ee1eb671b8d69173aea975b423c4489c0404fe
+oid sha256:eb762c3231bb27770a54b360094bd1e9cd8e02cdf5dec63794e81b5cd90258bf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 19.26729986431479,
+  "epoch": 19.53867028493894,
   "eval_steps": 400,
-  "global_step": 28400,
+  "global_step": 28800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1143,6 +1143,22 @@
       "eval_steps_per_second": 0.835,
       "eval_wer": 0.04121090741026036,
       "step": 28400
+    },
+    {
+      "epoch": 19.54,
+      "grad_norm": 0.8942829966545105,
+      "learning_rate": 0.00010580969807868251,
+      "loss": 0.0498,
+      "step": 28800
+    },
+    {
+      "epoch": 19.54,
+      "eval_loss": 0.02821315824985504,
+      "eval_runtime": 210.0298,
+      "eval_samples_per_second": 6.661,
+      "eval_steps_per_second": 0.833,
+      "eval_wer": 0.04190417501155446,
+      "step": 28800
     }
   ],
   "logging_steps": 400,
@@ -1150,7 +1166,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 400,
-  "total_flos": 8.66018018334763e+19,
+  "total_flos": 8.781106063335208e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null