Training in progress, step 24400, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39204bd8c2effd818050f284c17a150073ae020ee23cd64f286987976e50533b
+oid sha256:7f2397e6114960d2082bdf5be464d269b233b0aacd6184267a435fc8a6ecd222
 size 1262135480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24afea734dd4236bf84afdf310768accb6affaddd0956339a57c60d2fea96b82
+oid sha256:3061d8247c75832593a3c5d379d8136a34802911a21c1a7e98ce18e9370afc80
 size 2490815798

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dafea8a7d8992903186fb33a4a431ffac98c6764650c46ce6f4f3880d2734c1a
+oid sha256:081b36c60682558da2008c23faaa9a9c965a8e6a3032698eae1b9a1cec945b2f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd45939ba7a4f7f568ef5975dddbd1e6ecf925ae50169882721525fdfd0f9abc
+oid sha256:7385ea8fcbfe828da13abda991b7c863c98739c7403d7f8feb3c6c861ca53671
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 16.28222523744912,
+  "epoch": 16.55359565807327,
   "eval_steps": 400,
-  "global_step": 24000,
+  "global_step": 24400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -967,6 +967,22 @@
       "eval_steps_per_second": 0.841,
       "eval_wer": 0.052688337698351566,
       "step": 24000
+    },
+    {
+      "epoch": 16.55,
+      "grad_norm": 0.2116428166627884,
+      "learning_rate": 0.0001360018298261665,
+      "loss": 0.0644,
+      "step": 24400
+    },
+    {
+      "epoch": 16.55,
+      "eval_loss": 0.026890287175774574,
+      "eval_runtime": 209.0713,
+      "eval_samples_per_second": 6.691,
+      "eval_steps_per_second": 0.837,
+      "eval_wer": 0.048066553689724234,
+      "step": 24400
     }
   ],
   "logging_steps": 400,
@@ -974,7 +990,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 400,
-  "total_flos": 7.3207680887953244e+19,
+  "total_flos": 7.443488870240685e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null