Training in progress, step 51900, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6879e7a47865a2d9dbdc1dee441becb941a61f7ae9db55a4342ae07a816d700
+oid sha256:e17ce21e8ae5702d27ee13ccfe698b9519f9191b1c9caff5644e90a5bb5c25d9
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab07935c87ce3f230af1aca71f7d354f2ae99539d4922cd9ff951ce52ecc827f
+oid sha256:a17a30230270a34456dc1ba21c1ead1f7aa39a64e33c3faa6efbf4b18d99cb5f
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:691a9b667c584e2397167aa221b255d9341ff38ca1d8535cfe09f55be3c23054
+oid sha256:dde4f5875f81547bdef6920d87fd6a84a4cb8fc9273b6febfeb843f0442e8a66
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6da86477a7e38c974647d1441bec2689395584cdc4189de87cdd2736695ba37f
-size 14631
+oid sha256:a4a50bec4064f680866f4e14ae49d80472966a4af2720d1f7bf3be3feeaef2f0
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a0508acb91372d3d8167376986d8fc4095af16c3a72cecf2777e3dd527abab5
+oid sha256:5317f1b977bf0c5dd9e58209a5a3433f99d034b727592196ceb70ddd3bde3377
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 21.679646390233636,
+  "epoch": 21.848031993264577,
   "eval_steps": 100,
-  "global_step": 51500,
+  "global_step": 51900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -8247,6 +8247,70 @@
       "eval_samples_per_second": 24.206,
       "eval_steps_per_second": 3.026,
       "step": 51500
+    },
+    {
+      "epoch": 21.72,
+      "grad_norm": 5.330277919769287,
+      "learning_rate": 1.3903180212014135e-05,
+      "loss": 0.3529,
+      "step": 51600
+    },
+    {
+      "epoch": 21.72,
+      "eval_cer": 0.34077421688631654,
+      "eval_loss": 2.4329657554626465,
+      "eval_runtime": 422.4059,
+      "eval_samples_per_second": 22.438,
+      "eval_steps_per_second": 2.805,
+      "step": 51600
+    },
+    {
+      "epoch": 21.76,
+      "grad_norm": 2.12868595123291,
+      "learning_rate": 1.3833215547703182e-05,
+      "loss": 0.3733,
+      "step": 51700
+    },
+    {
+      "epoch": 21.76,
+      "eval_cer": 0.34047358335614564,
+      "eval_loss": 2.4534361362457275,
+      "eval_runtime": 382.1988,
+      "eval_samples_per_second": 24.799,
+      "eval_steps_per_second": 3.1,
+      "step": 51700
+    },
+    {
+      "epoch": 21.81,
+      "grad_norm": 1.6962841749191284,
+      "learning_rate": 1.3762544169611308e-05,
+      "loss": 0.3523,
+      "step": 51800
+    },
+    {
+      "epoch": 21.81,
+      "eval_cer": 0.3399554182472332,
+      "eval_loss": 2.549654483795166,
+      "eval_runtime": 415.7902,
+      "eval_samples_per_second": 22.795,
+      "eval_steps_per_second": 2.85,
+      "step": 51800
+    },
+    {
+      "epoch": 21.85,
+      "grad_norm": 1.762255072593689,
+      "learning_rate": 1.3691872791519436e-05,
+      "loss": 0.3523,
+      "step": 51900
+    },
+    {
+      "epoch": 21.85,
+      "eval_cer": 0.33849624574713544,
+      "eval_loss": 2.5730228424072266,
+      "eval_runtime": 391.5055,
+      "eval_samples_per_second": 24.209,
+      "eval_steps_per_second": 3.027,
+      "step": 51900
     }
   ],
   "logging_steps": 100,
@@ -8254,7 +8318,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 5.643614886293618e+20,
+  "total_flos": 5.6872995302509294e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null