Training in progress, step 29200, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2685df91b0212c3d771f740af7d493329819e9ece934c6572ec91f4ac11a64ea
+oid sha256:9fe283633a388ba2d022ff9f5bd22a4410a9ce61cf5ab36a933f8316c404dc0d
 size 1262135480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f33961fae286f63a4d7d03dcc99f6908f11c6a773bd2e93e0e7d4d192962b30a
+oid sha256:4ffc119225525035a7f335e5b8efd08e194472d357b13852524d4f4eb0578b80
 size 2490815798

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd07cca9b4e51cb881f8cba86aaed9cb56420ad7f452f9d07931ab907d7921d1
-size 14308
+oid sha256:1d853691023356ee049c7f9520a152041301e582ba9494903ecaa091cb4963f6
+size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb762c3231bb27770a54b360094bd1e9cd8e02cdf5dec63794e81b5cd90258bf
+oid sha256:76c2f43626453dc6c68d43c01f88ecb4cc62eda02fd56285615f23696dcf1415
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 19.53867028493894,
+  "epoch": 19.810040705563093,
   "eval_steps": 400,
-  "global_step": 28800,
+  "global_step": 29200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1159,6 +1159,22 @@
       "eval_steps_per_second": 0.833,
       "eval_wer": 0.04190417501155446,
       "step": 28800
+    },
+    {
+      "epoch": 19.81,
+      "grad_norm": 0.6549252271652222,
+      "learning_rate": 0.00010306495882891125,
+      "loss": 0.0454,
+      "step": 29200
+    },
+    {
+      "epoch": 19.81,
+      "eval_loss": 0.027856331318616867,
+      "eval_runtime": 210.3168,
+      "eval_samples_per_second": 6.652,
+      "eval_steps_per_second": 0.832,
+      "eval_wer": 0.04167308581112309,
+      "step": 29200
     }
   ],
   "logging_steps": 400,
@@ -1166,7 +1182,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 400,
-  "total_flos": 8.781106063335208e+19,
+  "total_flos": 8.903221408478038e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null