Training in progress, step 35900, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:977a5c69feae10b912f571de7977009febbf01a0eaa266424ca31544fa3061d4
+oid sha256:5b35f734ee856f18dc12768c16472dc4fa4a48e29bb5476207b1dd1732446ff9
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2957ac18ba2253b8c409a29674b89329d32e320d7a98ce2b81ee8d57641bc16
+oid sha256:cfa23d05a63ef98a7a08510cfe63830d8c0bfde6e697c271a310ceb8b3f71341
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b3b488252dd3d31bc05954dcc0188157b4ef2c211110990aacba94eb2fa5123
+oid sha256:a5a4e470770ebadc4146150e5c1b050c970bb70871bdd3d49120d1a71cafdf88
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1edf5ffcac2b5407479ae34e05195359730147dee5af532317f0b039b8c166f2
+oid sha256:aa8c3ee406720d81ffabaf84f9e91e08e6b6eb075e6cb1267455d95c6a23d91a
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a8b1f07cc0159a990d1350d3b8aacd4d203ba9556ec73cabc9467bc15b486a5
+oid sha256:89c666c1e074cfdb22c4aa9905324d78e551418b1a46be058b6dc5f2e31bf25c
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 15.028415070511471,
+  "epoch": 15.112607872026942,
   "eval_steps": 100,
-  "global_step": 35700,
+  "global_step": 35900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5719,6 +5719,38 @@
       "eval_samples_per_second": 25.476,
       "eval_steps_per_second": 3.185,
       "step": 35700
+    },
+    {
+      "epoch": 15.07,
+      "grad_norm": 2.7166266441345215,
+      "learning_rate": 2.5065724381625445e-05,
+      "loss": 0.8238,
+      "step": 35800
+    },
+    {
+      "epoch": 15.07,
+      "eval_cer": 0.38250361737906224,
+      "eval_loss": 2.33854079246521,
+      "eval_runtime": 394.007,
+      "eval_samples_per_second": 24.055,
+      "eval_steps_per_second": 3.008,
+      "step": 35800
+    },
+    {
+      "epoch": 15.11,
+      "grad_norm": 5.8333282470703125,
+      "learning_rate": 2.499505300353357e-05,
+      "loss": 0.8495,
+      "step": 35900
+    },
+    {
+      "epoch": 15.11,
+      "eval_cer": 0.38729908881154435,
+      "eval_loss": 1.496200680732727,
+      "eval_runtime": 379.9915,
+      "eval_samples_per_second": 24.943,
+      "eval_steps_per_second": 3.118,
+      "step": 35900
     }
   ],
   "logging_steps": 100,
@@ -5726,7 +5758,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 3.9129036959681564e+20,
+  "total_flos": 3.934653943012538e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null