Training in progress, step 28300, checkpoint

last-checkpoint/model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:591e41e3676418cd1c0210ac5103de2c047f43c3f40415a403018bd7d93769db
+oid sha256:43f58101992470ce99c1c24e2ed6ac1048281fa6539f6045c9dff060f69941d5
 size 4978139416

last-checkpoint/model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:863179f4b823aa37294186590a641d7ed7cb2231bfd420a0c652e61f745b5712
+oid sha256:6704070a643620f09ad45b4926d920d7c7503d06723489d09b8e5566b2037939
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95a10135880171da7d27bdded0b5de859e991b9d6813ef6865b69bba57646c69
+oid sha256:4548ca236f4173864dbd0ca1a1498544aaf94a4e29a4240dab5c4e4067bc8c43
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03f3a47e3fd45356df14e05e927bc513c40aadb8fa39b6a917dcbafa2c841ea6
-size 14567
+oid sha256:01741ba2843fcc38342b1b30b163edc00ac6120a04533362fb33d9ecac4ce1fe
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f156c07503fa6a6e1c8ecec02179bc06ca2b282b6a513c49c6076a8fe0c0f5f
+oid sha256:b4f04843d80970cd259c83429daf5f235586900bc4e8d66f6edb21ed7d2feb79
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 11.829088612923595,
+  "epoch": 11.913281414439066,
   "eval_steps": 100,
-  "global_step": 28100,
+  "global_step": 28300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4503,6 +4503,38 @@
       "eval_samples_per_second": 25.562,
       "eval_steps_per_second": 3.196,
       "step": 28100
+    },
+    {
+      "epoch": 11.87,
+      "grad_norm": 5.378576755523682,
+      "learning_rate": 3.0435335689045936e-05,
+      "loss": 1.125,
+      "step": 28200
+    },
+    {
+      "epoch": 11.87,
+      "eval_cer": 0.4203663329553009,
+      "eval_loss": 1.5670437812805176,
+      "eval_runtime": 388.8978,
+      "eval_samples_per_second": 24.371,
+      "eval_steps_per_second": 3.047,
+      "step": 28200
+    },
+    {
+      "epoch": 11.91,
+      "grad_norm": 4.532820701599121,
+      "learning_rate": 3.0364664310954068e-05,
+      "loss": 1.1398,
+      "step": 28300
+    },
+    {
+      "epoch": 11.91,
+      "eval_cer": 0.42046654413202456,
+      "eval_loss": 1.8523951768875122,
+      "eval_runtime": 367.1427,
+      "eval_samples_per_second": 25.816,
+      "eval_steps_per_second": 3.228,
+      "step": 28300
     }
   ],
   "logging_steps": 100,
@@ -4510,7 +4542,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 3.079345538947467e+20,
+  "total_flos": 3.101048540517328e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null