Training in progress, step 40100, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7287b40e0c6de9ef270e710f16c4acc766ed561015816aba94d3ada772955ea0
+oid sha256:234d353a9c16df150a9c4d16ea704e6c85931b80cbba47b784e4547b73a51715
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55a1b4fccd53ff169ebe311d0768ce5fb6e3b059e4140a6f1734cacccd56b0e6
+oid sha256:939ab97ad49a707233e95f14ca0a1419257ae4e79296c50f05ffbdd48d9d5bca
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0260a4c3ca6ca53fa3b42cf50f7f92b4150ea244f048dbfa1ce457d84f4119fe
+oid sha256:1bbf2096820ceefbefa37220cda6972a36788b6a6894f9f4793885c92ca72069
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bfb0adc6bfe8622be753ac3a0f24b82f548e8791dfa2e559460dc20afa0313b
+oid sha256:15ed916a67962ea3d466c350187b755a76acf54704cf9a56f9ed8a19cc7f3bbd
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:758837119a231eb27945cf2b19a2b83a829f1699f442e7c9366e800eb23d0d1a
+oid sha256:ddc3dcc2dc6784f422e1a3ad05503da45d0549dd29f1492b723c27b252617267
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 16.79646390233635,
+  "epoch": 16.88065670385182,
   "eval_steps": 100,
-  "global_step": 39900,
+  "global_step": 40100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6391,6 +6391,38 @@
       "eval_samples_per_second": 25.152,
       "eval_steps_per_second": 3.145,
       "step": 39900
+    },
+    {
+      "epoch": 16.84,
+      "grad_norm": 10.867044448852539,
+      "learning_rate": 2.2097526501766784e-05,
+      "loss": 0.7286,
+      "step": 40000
+    },
+    {
+      "epoch": 16.84,
+      "eval_cer": 0.36576346251613157,
+      "eval_loss": 2.3375942707061768,
+      "eval_runtime": 391.3944,
+      "eval_samples_per_second": 24.216,
+      "eval_steps_per_second": 3.028,
+      "step": 40000
+    },
+    {
+      "epoch": 16.88,
+      "grad_norm": 2.3577775955200195,
+      "learning_rate": 2.2026855123674912e-05,
+      "loss": 0.7599,
+      "step": 40100
+    },
+    {
+      "epoch": 16.88,
+      "eval_cer": 0.36309197919518205,
+      "eval_loss": 1.8121538162231445,
+      "eval_runtime": 378.3056,
+      "eval_samples_per_second": 25.054,
+      "eval_steps_per_second": 3.132,
+      "step": 40100
     }
   ],
   "logging_steps": 100,
@@ -6398,7 +6430,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 4.3726588831730395e+20,
+  "total_flos": 4.393961093701251e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null