Training in progress, step 39700, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d6825f4a17e39ca3df3effbf21d7f32ed1545ec9aec9ba20098846041083574
+oid sha256:6e5ed2da44c27bc890c8ea9f6105fd0a53f62d5d80dfd31f75d14fd115db2cdd
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0af944c7c9c469f7aebd311567f3c33ffe63ef9f70efd93e8822e7921c3f2d6f
+oid sha256:6f057e139d906c78952ba74b4d37c6edb80db873e643241e191394c956ebbf6a
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4c593e409771c80e1808ae19146aa7f37f9ced1b60ef046ea440f1301bf278a
+oid sha256:1931460d5e459c7dd130a6844e5132390ce78447fc54caa1ca9965416b759b0c
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1f11ec8ea1e825f20e5a35c769fb841763170d6306b3c0372ecf458faeb41f5
-size 14503
+oid sha256:ccbf24f06506ce49d495c2f8b2b9de6ab0a93b2d20fbd2a2f06681444c854113
+size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a189e23788ccc3257b3ab439e9ae8abe94cccbaa26260dabcde4a1d95c4991b3
+oid sha256:bfdaee5a60fdfdb51226c40d315ad694d9948fae35d824dce01188f3978aafe2
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 16.62807829930541,
+  "epoch": 16.712271100820878,
   "eval_steps": 100,
-  "global_step": 39500,
+  "global_step": 39700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6327,6 +6327,38 @@
       "eval_samples_per_second": 24.465,
       "eval_steps_per_second": 3.059,
       "step": 39500
+    },
+    {
+      "epoch": 16.67,
+      "grad_norm": 4.028792858123779,
+      "learning_rate": 2.238021201413428e-05,
+      "loss": 0.738,
+      "step": 39600
+    },
+    {
+      "epoch": 16.67,
+      "eval_cer": 0.36522085565679874,
+      "eval_loss": 1.9882181882858276,
+      "eval_runtime": 394.101,
+      "eval_samples_per_second": 24.05,
+      "eval_steps_per_second": 3.007,
+      "step": 39600
+    },
+    {
+      "epoch": 16.71,
+      "grad_norm": 2.6417016983032227,
+      "learning_rate": 2.2309540636042403e-05,
+      "loss": 0.7357,
+      "step": 39700
+    },
+    {
+      "epoch": 16.71,
+      "eval_cer": 0.3660787610965547,
+      "eval_loss": 2.067323923110962,
+      "eval_runtime": 386.7519,
+      "eval_samples_per_second": 24.507,
+      "eval_steps_per_second": 3.064,
+      "step": 39700
     }
   ],
   "logging_steps": 100,
@@ -6334,7 +6366,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 4.3287004594488685e+20,
+  "total_flos": 4.350920052860814e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null