Training in progress, step 37700, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcc05bffb8c241d61a3dc3d581cb5886a3909df431621dcf4dd9ce53d1493de7
+oid sha256:020f93a158168205cca3915538c4ed9109b5ffc2b96fdeb0f1c4d79a07042c55
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e03ec0ba4df87757138b2f936b9502249cf8be8c7b02363976349bcb69c91ca3
+oid sha256:3befc5d87f20164d7ddccdca6c81786e192784cb6ebe0faa3bf6a1782ef9e1bc
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a522d20a06a7366cf25154577cd411876c1eae2ed75c78dc5cb6dbb8ab486ded
+oid sha256:9e3dc33eb709a480424a714d2444abb7f1cdabf9f95720d6a97f58d1827cb80e
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f57f2e335f6242f37d8f62964bd040064cd24494d16cadfe606f7af6e6e33ed2
-size 14503
+oid sha256:bc3db78812f5b1281be37cba1a96865a0e99afcb4f7c40d8dd207953ac5fefc5
+size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:331c71e4dbe6e06ea5ac4e13a3a74ea2edc9963430ef549063c5def06827f8ad
+oid sha256:bbc911d1c134d3a4e026e82aa7a427672312a8867cae577cfbbeccb41bd9874b
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 15.786150284150706,
+  "epoch": 15.870343085666175,
   "eval_steps": 100,
-  "global_step": 37500,
+  "global_step": 37700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6007,6 +6007,38 @@
       "eval_samples_per_second": 25.348,
       "eval_steps_per_second": 3.169,
       "step": 37500
+    },
+    {
+      "epoch": 15.83,
+      "grad_norm": 10.501407623291016,
+      "learning_rate": 2.3793639575971734e-05,
+      "loss": 0.843,
+      "step": 37600
+    },
+    {
+      "epoch": 15.83,
+      "eval_cer": 0.37860271401196666,
+      "eval_loss": 1.4808061122894287,
+      "eval_runtime": 394.8535,
+      "eval_samples_per_second": 24.004,
+      "eval_steps_per_second": 3.001,
+      "step": 37600
+    },
+    {
+      "epoch": 15.87,
+      "grad_norm": 4.368974208831787,
+      "learning_rate": 2.372296819787986e-05,
+      "loss": 0.824,
+      "step": 37700
+    },
+    {
+      "epoch": 15.87,
+      "eval_cer": 0.3751050995268077,
+      "eval_loss": 1.6123182773590088,
+      "eval_runtime": 373.2585,
+      "eval_samples_per_second": 25.393,
+      "eval_steps_per_second": 3.175,
+      "step": 37700
     }
   ],
   "logging_steps": 100,
@@ -6014,7 +6046,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 4.109762412671853e+20,
+  "total_flos": 4.1315834714403255e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null