Training in progress, step 24000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f27f5b61c1f90948dd0010ae8fe09b2ee05d65814c1485c88a416751b2977ce6
+oid sha256:39204bd8c2effd818050f284c17a150073ae020ee23cd64f286987976e50533b
 size 1262135480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8c7327b4481ffedc3f87866a5c81e8bef2081ee0e7564ef993f87477b497ca6
+oid sha256:24afea734dd4236bf84afdf310768accb6affaddd0956339a57c60d2fea96b82
 size 2490815798

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa7e40ee09d6a17e6a9f525685c6dd28582a8bf9dd51f9ac2e205828da6e88ad
+oid sha256:dafea8a7d8992903186fb33a4a431ffac98c6764650c46ce6f4f3880d2734c1a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f92ad734640125620ead43ba6f565701d742f7f96a1acb5b572295c79e960c56
+oid sha256:dd45939ba7a4f7f568ef5975dddbd1e6ecf925ae50169882721525fdfd0f9abc
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 16.010854816824967,
+  "epoch": 16.28222523744912,
   "eval_steps": 400,
-  "global_step": 23600,
+  "global_step": 24000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -951,6 +951,22 @@
       "eval_steps_per_second": 0.823,
       "eval_wer": 0.054845170235710984,
       "step": 23600
+    },
+    {
+      "epoch": 16.28,
+      "grad_norm": 0.3012249767780304,
+      "learning_rate": 0.00013874656907593777,
+      "loss": 0.0616,
+      "step": 24000
+    },
+    {
+      "epoch": 16.28,
+      "eval_loss": 0.0315285250544548,
+      "eval_runtime": 208.0351,
+      "eval_samples_per_second": 6.725,
+      "eval_steps_per_second": 0.841,
+      "eval_wer": 0.052688337698351566,
+      "step": 24000
     }
   ],
   "logging_steps": 400,
@@ -958,7 +974,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 400,
-  "total_flos": 7.198809146011316e+19,
+  "total_flos": 7.3207680887953244e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null