Training in progress, step 26400, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bd0ac7089d948316b22e064332f81e5eba36434c93021981c84174777b9efe8
+oid sha256:21142536b7429d36ebfde44d13c2b325374448c902fcc9e839cba576d4af0a5d
 size 1262135480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2991d8ef389401f570f8ed55b49db28740a400b6a211d3788e121b65bdb4db48
+oid sha256:eb6ffa4a4ac815d752cb56575bdd6ff326deddd4f4faf61327414b0ac96d10f5
 size 2490815798

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c70eba2c3e87d25a42f72d3fc1ec41bcf6b13d68fba50d03aed6177406ffc07a
-size 14244
+oid sha256:236d55043b3599d5a469ae056de5086947317f985ab12d123e125917adb2b500
+size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7293ef8edd3806cfd0e0c0ac31cfd79b423b33c4d713efd38abefda759e5e240
+oid sha256:928c9f403c58021dae7447c256dc2a1215c54e4c2d233c0751f8c3952708770e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 17.639077340569877,
+  "epoch": 17.91044776119403,
   "eval_steps": 400,
-  "global_step": 26000,
+  "global_step": 26400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1047,6 +1047,22 @@
       "eval_steps_per_second": 0.841,
       "eval_wer": 0.045216453551070714,
       "step": 26000
+    },
+    {
+      "epoch": 17.91,
+      "grad_norm": 0.33733347058296204,
+      "learning_rate": 0.00012227813357731015,
+      "loss": 0.056,
+      "step": 26400
+    },
+    {
+      "epoch": 17.91,
+      "eval_loss": 0.02792263962328434,
+      "eval_runtime": 208.746,
+      "eval_samples_per_second": 6.702,
+      "eval_steps_per_second": 0.838,
+      "eval_wer": 0.04513942381759359,
+      "step": 26400
     }
   ],
   "logging_steps": 400,
@@ -1054,7 +1070,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 400,
-  "total_flos": 7.929872623542338e+19,
+  "total_flos": 8.050306741013055e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null