Training in progress, step 26000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1309fe10b172bb260fb88a1ef512f0133cab403545e2e410e012ee77c1b61079
+oid sha256:1bd0ac7089d948316b22e064332f81e5eba36434c93021981c84174777b9efe8
 size 1262135480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0a3553dc821d23806cfaa4fae7f776de5dc8546d1865096234c8afdc141d396
+oid sha256:2991d8ef389401f570f8ed55b49db28740a400b6a211d3788e121b65bdb4db48
 size 2490815798

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5262439c917fd4e99ff014fbcd1abfcb88c18e776e072e32cebb9351832a6a75
+oid sha256:c70eba2c3e87d25a42f72d3fc1ec41bcf6b13d68fba50d03aed6177406ffc07a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59e4db644290cc0b4cb99efa12e07fb0da05480d4cd19963f6986ed6d2705369
+oid sha256:7293ef8edd3806cfd0e0c0ac31cfd79b423b33c4d713efd38abefda759e5e240
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 17.367706919945725,
+  "epoch": 17.639077340569877,
   "eval_steps": 400,
-  "global_step": 25600,
+  "global_step": 26000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1031,6 +1031,22 @@
       "eval_steps_per_second": 0.839,
       "eval_wer": 0.04922199969188107,
       "step": 25600
+    },
+    {
+      "epoch": 17.64,
+      "grad_norm": 1.3281415700912476,
+      "learning_rate": 0.0001250228728270814,
+      "loss": 0.0547,
+      "step": 26000
+    },
+    {
+      "epoch": 17.64,
+      "eval_loss": 0.028093835338950157,
+      "eval_runtime": 208.0055,
+      "eval_samples_per_second": 6.726,
+      "eval_steps_per_second": 0.841,
+      "eval_wer": 0.045216453551070714,
+      "step": 26000
     }
   ],
   "logging_steps": 400,
@@ -1038,7 +1054,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 400,
-  "total_flos": 7.807330775664206e+19,
+  "total_flos": 7.929872623542338e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null