Training in progress, step 30000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e63f877c4506681a490774017678ec3ddaf77e75d1e84f86025ada6590efbd8
+oid sha256:5fb424cac1e2d010e183cc28e2544eed732f3969bc3fc7d6f63c5a15303ff7db
 size 1262135480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ff96e9d8d8bd2f41f071244c4ff2909a15f3a277d70d0f48e2c1231181b87b5
+oid sha256:6d8c2fd4a199f40a3b1bb2ef0ae17cf264dc50c866fc146af84019e4704a9ae0
 size 2490815798

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32ab7f10ca6b13468e41de24a05121a51b38477fe4c9a87064b918ea752578ac
-size 14244
+oid sha256:8991d33c7c265f2af3e04a4a749dcab837ff877724ff423aa010bda81cf2a85f
+size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:940d3836b6775a577a1a3b78f4ff4621e538b7a2a81b57676d7aecf40e93b414
+oid sha256:5a4b23347cc382ce56eb15ec7757e239673e6865119a2d36680cb384e26cd2a3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 20.081411126187245,
+  "epoch": 20.352781546811396,
   "eval_steps": 400,
-  "global_step": 29600,
+  "global_step": 30000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1191,6 +1191,22 @@
       "eval_steps_per_second": 0.831,
       "eval_wer": 0.0395932830072408,
       "step": 29600
+    },
+    {
+      "epoch": 20.35,
+      "grad_norm": 0.2715985178947449,
+      "learning_rate": 9.75754803293687e-05,
+      "loss": 0.0447,
+      "step": 30000
+    },
+    {
+      "epoch": 20.35,
+      "eval_loss": 0.026736732572317123,
+      "eval_runtime": 209.4915,
+      "eval_samples_per_second": 6.678,
+      "eval_steps_per_second": 0.835,
+      "eval_wer": 0.041750115544600216,
+      "step": 30000
     }
   ],
   "logging_steps": 400,
@@ -1198,7 +1214,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 400,
-  "total_flos": 9.027987196010655e+19,
+  "total_flos": 9.150437899797026e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null