Training in progress, step 37500, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e144bce46edf775616a4443f82caf425c0686653b94ab2fb483c2313495144e3
+oid sha256:fcc05bffb8c241d61a3dc3d581cb5886a3909df431621dcf4dd9ce53d1493de7
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eddb4901907ffccd8be8dddebdf534eb37f79032b8b4e81df81b79532d08d4d1
+oid sha256:e03ec0ba4df87757138b2f936b9502249cf8be8c7b02363976349bcb69c91ca3
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75ad29ad88eda9c787c71227c136deda6d40511f9d451c48bfb06d56d2adb55d
+oid sha256:a522d20a06a7366cf25154577cd411876c1eae2ed75c78dc5cb6dbb8ab486ded
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16adb65f6f3f6217c263cb3f3368dbfde118f82cd4ff73c393b45170a494b241
-size 14567
+oid sha256:f57f2e335f6242f37d8f62964bd040064cd24494d16cadfe606f7af6e6e33ed2
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aad7c4d73dc18622cfa786ae77c4f4bb6ce05f62b97dafb8f0c14d806f84f5f0
+oid sha256:331c71e4dbe6e06ea5ac4e13a3a74ea2edc9963430ef549063c5def06827f8ad
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 15.701957482635235,
+  "epoch": 15.786150284150706,
   "eval_steps": 100,
-  "global_step": 37300,
+  "global_step": 37500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5975,6 +5975,38 @@
       "eval_samples_per_second": 25.441,
       "eval_steps_per_second": 3.181,
       "step": 37300
+    },
+    {
+      "epoch": 15.74,
+      "grad_norm": 1.8703219890594482,
+      "learning_rate": 2.3934982332155477e-05,
+      "loss": 0.8085,
+      "step": 37400
+    },
+    {
+      "epoch": 15.74,
+      "eval_cer": 0.38297778733721793,
+      "eval_loss": 2.4081192016601562,
+      "eval_runtime": 395.9622,
+      "eval_samples_per_second": 23.937,
+      "eval_steps_per_second": 2.993,
+      "step": 37400
+    },
+    {
+      "epoch": 15.79,
+      "grad_norm": 1.6956226825714111,
+      "learning_rate": 2.3864310954063605e-05,
+      "loss": 0.8194,
+      "step": 37500
+    },
+    {
+      "epoch": 15.79,
+      "eval_cer": 0.3802305345899652,
+      "eval_loss": 2.873920202255249,
+      "eval_runtime": 373.9204,
+      "eval_samples_per_second": 25.348,
+      "eval_steps_per_second": 3.169,
+      "step": 37500
     }
   ],
   "logging_steps": 100,
@@ -5982,7 +6014,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 4.087953409101901e+20,
+  "total_flos": 4.109762412671853e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null