Training in progress, step 39900, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e5ed2da44c27bc890c8ea9f6105fd0a53f62d5d80dfd31f75d14fd115db2cdd
+oid sha256:7287b40e0c6de9ef270e710f16c4acc766ed561015816aba94d3ada772955ea0
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f057e139d906c78952ba74b4d37c6edb80db873e643241e191394c956ebbf6a
+oid sha256:55a1b4fccd53ff169ebe311d0768ce5fb6e3b059e4140a6f1734cacccd56b0e6
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1931460d5e459c7dd130a6844e5132390ce78447fc54caa1ca9965416b759b0c
+oid sha256:0260a4c3ca6ca53fa3b42cf50f7f92b4150ea244f048dbfa1ce457d84f4119fe
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccbf24f06506ce49d495c2f8b2b9de6ab0a93b2d20fbd2a2f06681444c854113
+oid sha256:5bfb0adc6bfe8622be753ac3a0f24b82f548e8791dfa2e559460dc20afa0313b
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfdaee5a60fdfdb51226c40d315ad694d9948fae35d824dce01188f3978aafe2
+oid sha256:758837119a231eb27945cf2b19a2b83a829f1699f442e7c9366e800eb23d0d1a
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 16.712271100820878,
+  "epoch": 16.79646390233635,
   "eval_steps": 100,
-  "global_step": 39700,
+  "global_step": 39900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6359,6 +6359,38 @@
       "eval_samples_per_second": 24.507,
       "eval_steps_per_second": 3.064,
       "step": 39700
+    },
+    {
+      "epoch": 16.75,
+      "grad_norm": 3.9978723526000977,
+      "learning_rate": 2.223886925795053e-05,
+      "loss": 0.7286,
+      "step": 39800
+    },
+    {
+      "epoch": 16.75,
+      "eval_cer": 0.3679216690782527,
+      "eval_loss": 1.6313321590423584,
+      "eval_runtime": 398.1769,
+      "eval_samples_per_second": 23.803,
+      "eval_steps_per_second": 2.976,
+      "step": 39800
+    },
+    {
+      "epoch": 16.8,
+      "grad_norm": 1.9248440265655518,
+      "learning_rate": 2.2168197879858656e-05,
+      "loss": 0.7211,
+      "step": 39900
+    },
+    {
+      "epoch": 16.8,
+      "eval_cer": 0.365851452817645,
+      "eval_loss": 1.687284231185913,
+      "eval_runtime": 376.8233,
+      "eval_samples_per_second": 25.152,
+      "eval_steps_per_second": 3.145,
+      "step": 39900
     }
   ],
   "logging_steps": 100,
@@ -6366,7 +6398,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 4.350920052860814e+20,
+  "total_flos": 4.3726588831730395e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null