Training in progress, step 21200, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2ccbaa3366fc91a9caa865d514bdc5bc7272bb243e4623552358daf6c381842
+oid sha256:16dbb1a04572952218422ea39cf7570a42446d5f087786783ad33828643993bc
 size 1262135480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd4cc3504193d269c1271fcbb4b8624ac22d68154afdcd94625f3fb1b458ee8d
+oid sha256:a216eb1303cd5b71afad6f5a91b0b5e3768ab04fd074af690869ca5bedb8926f
 size 2490815798

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f7bbcf5ff7ad61af1c3ef61aa10d73d1160259d8b5010c2a4340676fa439df1
-size 14308
+oid sha256:7ad8ec50c3c1c91dac2f5655527d8594f2033e004db09ad65dd9a85d7afb91a4
+size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af549fa9698688de4d4da8eafe34f4994b7fb3147b788357d90bc61bb8d36a8a
+oid sha256:a3f2e6e05de398f17a37f5b322d92a7ed3bd1f1f712be1a3b88b12b3511e8906
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 14.111261872455902,
+  "epoch": 14.382632293080054,
   "eval_steps": 400,
-  "global_step": 20800,
+  "global_step": 21200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -839,6 +839,22 @@
       "eval_steps_per_second": 0.834,
       "eval_wer": 0.060314281312586655,
       "step": 20800
+    },
+    {
+      "epoch": 14.38,
+      "grad_norm": 1.34682297706604,
+      "learning_rate": 0.00015795974382433665,
+      "loss": 0.075,
+      "step": 21200
+    },
+    {
+      "epoch": 14.38,
+      "eval_loss": 0.03607061505317688,
+      "eval_runtime": 209.844,
+      "eval_samples_per_second": 6.667,
+      "eval_steps_per_second": 0.834,
+      "eval_wer": 0.06262517331690032,
+      "step": 21200
     }
   ],
   "logging_steps": 400,
@@ -846,7 +862,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 400,
-  "total_flos": 6.345721739092566e+19,
+  "total_flos": 6.467377957667312e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null