Training in progress, step 28900, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9d7a9a80fc16ae19f3ee016e1f87ebbe28f8e5c54d2dee20067ac1375b3a699
+oid sha256:d251d0c72ed5a7685017bde159d15ce6766dc5be3bb7e7e581c05a02a62c04c5
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6412766255f9548b27afe82cfd466bfa83c0ceff5e923f6bd16707cb31228ca1
+oid sha256:b752e7177166bebeb1530b608aac17f572602cfe388058cc6e1fe0d959654324
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb1d84e520f4f8a65b7489c9592eba3324b25ef0380fb698f857e6540f071004
+oid sha256:be5846d525ecdc166b3d6f60d5b1bd254c1dd87056dcca60cac2b041ad05f37b
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54b7c6a6814674e66826f920adadd693d50e8c9564cda211cba81879f559c0af
-size 14503
+oid sha256:855244fb6d2f7e56e44886d31c5782f973bfa784c99f0334fee935eb6b3be025
+size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cf7c52a861212ad700d353d281972076097e14210eec92b789d70cbdc6a0277
+oid sha256:d8e7befc489c14232ad92a4c0e54914d7e1f33b1fa2d6656378fe60d0f3de637
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 11.997474215954536,
+  "epoch": 12.165859818985476,
   "eval_steps": 100,
-  "global_step": 28500,
+  "global_step": 28900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4567,6 +4567,70 @@
       "eval_samples_per_second": 25.906,
       "eval_steps_per_second": 3.239,
       "step": 28500
+    },
+    {
+      "epoch": 12.04,
+      "grad_norm": 7.630153656005859,
+      "learning_rate": 3.015265017667845e-05,
+      "loss": 1.0524,
+      "step": 28600
+    },
+    {
+      "epoch": 12.04,
+      "eval_cer": 0.4113008877243753,
+      "eval_loss": 1.9460973739624023,
+      "eval_runtime": 389.3684,
+      "eval_samples_per_second": 24.342,
+      "eval_steps_per_second": 3.043,
+      "step": 28600
+    },
+    {
+      "epoch": 12.08,
+      "grad_norm": 16.8402099609375,
+      "learning_rate": 3.0081978798586573e-05,
+      "loss": 1.073,
+      "step": 28700
+    },
+    {
+      "epoch": 12.08,
+      "eval_cer": 0.4151773493410504,
+      "eval_loss": 2.0268595218658447,
+      "eval_runtime": 367.5014,
+      "eval_samples_per_second": 25.79,
+      "eval_steps_per_second": 3.224,
+      "step": 28700
+    },
+    {
+      "epoch": 12.12,
+      "grad_norm": 1.9278266429901123,
+      "learning_rate": 3.0011307420494698e-05,
+      "loss": 1.0857,
+      "step": 28800
+    },
+    {
+      "epoch": 12.12,
+      "eval_cer": 0.4125180868953111,
+      "eval_loss": 1.7026644945144653,
+      "eval_runtime": 390.3027,
+      "eval_samples_per_second": 24.284,
+      "eval_steps_per_second": 3.036,
+      "step": 28800
+    },
+    {
+      "epoch": 12.17,
+      "grad_norm": 1.4629472494125366,
+      "learning_rate": 2.994063604240283e-05,
+      "loss": 1.1243,
+      "step": 28900
+    },
+    {
+      "epoch": 12.17,
+      "eval_cer": 0.411283778499081,
+      "eval_loss": 2.061549663543701,
+      "eval_runtime": 372.4148,
+      "eval_samples_per_second": 25.45,
+      "eval_steps_per_second": 3.182,
+      "step": 28900
     }
   ],
   "logging_steps": 100,
@@ -4574,7 +4638,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 3.122274035580518e+20,
+  "total_flos": 3.16704104262254e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null