Training in progress, step 43400, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0eb2a4125ad1a7315e858d1ec425c31c0225728ecd851456bd049f4b28d82684
+oid sha256:78bfa8129454072c8c32c94fa339da1e7db8837b42fa2a7620513cd425347a92
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26ed6c75b1d4dd08e6d5a69ce38d051550dd1e132eb7c5c3cc2907fcfd274f09
+oid sha256:224a09200a13bb23610224c23c9a5ad18beeb64e8e6de1d6f1a032a9cc4fc868
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:570718c1a3107f72b9835aebde8201578aa5cac012163b08f2d422add92f9b57
+oid sha256:8fde3ac13038245c91bb688a3b900a8a05d6f4090a0644b5fa0b43c251c7e804
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cabf6aa5277a418e56bd50c4b5e00c316d5d399a947ff43462e2f5b5e4ed1cb
+oid sha256:8879eb789e2a8197b665f6a79959932405d70ce0ce7f991f6e2862e40f7f8d12
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbe8fd4fd0978147c2baede31ea6ef4a0a0b17f797bdb14e649102ad1d246c5e
+oid sha256:9ad64049007b3eb10ddd15c4910a9945e35909beab5d22fbdf14483daad28d6d
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 18.185645127341612,
+  "epoch": 18.269837928857083,
   "eval_steps": 100,
-  "global_step": 43200,
+  "global_step": 43400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6919,6 +6919,38 @@
       "eval_samples_per_second": 24.766,
       "eval_steps_per_second": 3.096,
       "step": 43200
+    },
+    {
+      "epoch": 18.23,
+      "grad_norm": 2.318678140640259,
+      "learning_rate": 1.976749116607774e-05,
+      "loss": 0.7104,
+      "step": 43300
+    },
+    {
+      "epoch": 18.23,
+      "eval_cer": 0.35606253177427555,
+      "eval_loss": 3.2951183319091797,
+      "eval_runtime": 399.8798,
+      "eval_samples_per_second": 23.702,
+      "eval_steps_per_second": 2.963,
+      "step": 43300
+    },
+    {
+      "epoch": 18.27,
+      "grad_norm": 2.007765769958496,
+      "learning_rate": 1.9696819787985867e-05,
+      "loss": 0.551,
+      "step": 43400
+    },
+    {
+      "epoch": 18.27,
+      "eval_cer": 0.35518996128426733,
+      "eval_loss": 3.7015881538391113,
+      "eval_runtime": 380.644,
+      "eval_samples_per_second": 24.9,
+      "eval_steps_per_second": 3.113,
+      "step": 43400
     }
   ],
   "logging_steps": 100,
@@ -6926,7 +6958,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 4.7342574597265654e+20,
+  "total_flos": 4.7559365623395444e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null