Training in progress, step 26300, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6256e490b0e43c626084d84a341037e37434fd9bcabcbc558b3172b0e909df6
+oid sha256:40d05fd16c8588673c1e6ccde78de203e04e081ce27b72ee44b52315e644b740
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8951c5ab590b2778d41e2dc16e2017cb3db0033da9f8d4a91ee266d3a370c3c
+oid sha256:5812acb9bb3d64b8d63f94464a796cff46b7ad7f07e8e2c4a1aa5e63c47a7c54
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d909f75ea0266c0aca1a09ff4c06a42792691131283c14fd1a26cdd5f46c7cd8
+oid sha256:0b23cd02c502517bc70ad64a5dec054c9efc4df18822ed05bd1e7e119d953775
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6db111608e60b5c73e6c2423d408c2a31f6a8c6486b5343e756b1090ce10da2e
+oid sha256:34fbd3601d535cbde5b18a032775aec5cee5099b7fbfab69d247bf1219d7534a
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78b045b8a4735f098f688aa2d4a47ca9b1dff6138fd3367077decbe825c59f79
+oid sha256:92ad90ae3571dbb88467083f26508c8007da34c4d92b38346a376256e4c52e28
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.90296779625342,
+  "epoch": 11.07135339928436,
   "eval_steps": 100,
-  "global_step": 25900,
+  "global_step": 26300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4151,6 +4151,70 @@
       "eval_samples_per_second": 25.933,
       "eval_steps_per_second": 3.242,
       "step": 25900
+    },
+    {
+      "epoch": 10.95,
+      "grad_norm": 3.8992362022399902,
+      "learning_rate": 3.198939929328622e-05,
+      "loss": 1.1808,
+      "step": 26000
+    },
+    {
+      "epoch": 10.95,
+      "eval_cer": 0.419022036682179,
+      "eval_loss": 1.6932332515716553,
+      "eval_runtime": 384.5535,
+      "eval_samples_per_second": 24.647,
+      "eval_steps_per_second": 3.081,
+      "step": 26000
+    },
+    {
+      "epoch": 10.99,
+      "grad_norm": 64.95602416992188,
+      "learning_rate": 3.191872791519435e-05,
+      "loss": 1.2023,
+      "step": 26100
+    },
+    {
+      "epoch": 10.99,
+      "eval_cer": 0.4221408040358218,
+      "eval_loss": 1.5864986181259155,
+      "eval_runtime": 363.5244,
+      "eval_samples_per_second": 26.073,
+      "eval_steps_per_second": 3.26,
+      "step": 26100
+    },
+    {
+      "epoch": 11.03,
+      "grad_norm": 1.6677500009536743,
+      "learning_rate": 3.184805653710248e-05,
+      "loss": 1.1585,
+      "step": 26200
+    },
+    {
+      "epoch": 11.03,
+      "eval_cer": 0.4356106526925032,
+      "eval_loss": 1.4082372188568115,
+      "eval_runtime": 386.3668,
+      "eval_samples_per_second": 24.531,
+      "eval_steps_per_second": 3.067,
+      "step": 26200
+    },
+    {
+      "epoch": 11.07,
+      "grad_norm": 1.4230600595474243,
+      "learning_rate": 3.1777385159010606e-05,
+      "loss": 1.2774,
+      "step": 26300
+    },
+    {
+      "epoch": 11.07,
+      "eval_cer": 0.41568573774979467,
+      "eval_loss": 1.6947673559188843,
+      "eval_runtime": 370.2625,
+      "eval_samples_per_second": 25.598,
+      "eval_steps_per_second": 3.2,
+      "step": 26300
     }
   ],
   "logging_steps": 100,
@@ -4158,7 +4222,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 2.8377007760000103e+20,
+  "total_flos": 2.8824923424902952e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null