Training in progress, step 43200, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a919983f1774a9944c46697486622fd0ab96a6cb0e5bb0ee5c0f2e12ae0b8f09
+oid sha256:0eb2a4125ad1a7315e858d1ec425c31c0225728ecd851456bd049f4b28d82684
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a81581bf4180e242fb2429b75ca88a74d80d18891749a9cf8e4f4deba4cad01d
+oid sha256:26ed6c75b1d4dd08e6d5a69ce38d051550dd1e132eb7c5c3cc2907fcfd274f09
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b98abc9ef51226b8ec3536d18259a383a922c96c0834dabdd5ac597c877815a9
+oid sha256:570718c1a3107f72b9835aebde8201578aa5cac012163b08f2d422add92f9b57
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff26a1c9e8953fc53b225ecae4b59ac3cf75bfa228df53ad0a8cf47f04790b7a
+oid sha256:2cabf6aa5277a418e56bd50c4b5e00c316d5d399a947ff43462e2f5b5e4ed1cb
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8692b2cb9f5034153fef29e02c28ec94848180acab9070361551809efd9866b6
+oid sha256:fbe8fd4fd0978147c2baede31ea6ef4a0a0b17f797bdb14e649102ad1d246c5e
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 18.10145232582614,
+  "epoch": 18.185645127341612,
   "eval_steps": 100,
-  "global_step": 43000,
+  "global_step": 43200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6887,6 +6887,38 @@
       "eval_samples_per_second": 24.887,
       "eval_steps_per_second": 3.112,
       "step": 43000
+    },
+    {
+      "epoch": 18.14,
+      "grad_norm": 2.088670015335083,
+      "learning_rate": 1.990812720848057e-05,
+      "loss": 0.5513,
+      "step": 43100
+    },
+    {
+      "epoch": 18.14,
+      "eval_cer": 0.35743126979781786,
+      "eval_loss": 3.069037914276123,
+      "eval_runtime": 401.5683,
+      "eval_samples_per_second": 23.602,
+      "eval_steps_per_second": 2.951,
+      "step": 43100
+    },
+    {
+      "epoch": 18.19,
+      "grad_norm": 13.482215881347656,
+      "learning_rate": 1.9837455830388694e-05,
+      "loss": 0.5517,
+      "step": 43200
+    },
+    {
+      "epoch": 18.19,
+      "eval_cer": 0.35501398068124046,
+      "eval_loss": 3.0275192260742188,
+      "eval_runtime": 382.7019,
+      "eval_samples_per_second": 24.766,
+      "eval_steps_per_second": 3.096,
+      "step": 43200
     }
   ],
   "logging_steps": 100,
@@ -6894,7 +6926,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 4.7124629252969575e+20,
+  "total_flos": 4.7342574597265654e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null