Training in progress, step 25900, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7781a53d6b5b7512ff0ff1d38c7eaabb023d480f361f98431565fe95b327859
+oid sha256:f6256e490b0e43c626084d84a341037e37434fd9bcabcbc558b3172b0e909df6
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72d83ec1e6bf950a1d60198c789353d4e7b343be90d1474a02b4880043c647b8
+oid sha256:b8951c5ab590b2778d41e2dc16e2017cb3db0033da9f8d4a91ee266d3a370c3c
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e43534489fe9b0667499677fea38991daee7ef7e44c8bba59d24e7af296df2cf
+oid sha256:d909f75ea0266c0aca1a09ff4c06a42792691131283c14fd1a26cdd5f46c7cd8
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20fff49ae707308451e57857b198857501948a824acc26025a78021e3c4d9970
+oid sha256:6db111608e60b5c73e6c2423d408c2a31f6a8c6486b5343e756b1090ce10da2e
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b567208206c71e420de4afc268070bb8059d13be7ed02d0130d55f8213c8c995
+oid sha256:78b045b8a4735f098f688aa2d4a47ca9b1dff6138fd3367077decbe825c59f79
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.81877499473795,
+  "epoch": 10.90296779625342,
   "eval_steps": 100,
-  "global_step": 25700,
+  "global_step": 25900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4119,6 +4119,38 @@
       "eval_samples_per_second": 26.366,
       "eval_steps_per_second": 3.296,
       "step": 25700
+    },
+    {
+      "epoch": 10.86,
+      "grad_norm": 5.47965145111084,
+      "learning_rate": 3.2130035335689045e-05,
+      "loss": 1.1865,
+      "step": 25800
+    },
+    {
+      "epoch": 10.86,
+      "eval_cer": 0.4287083023737828,
+      "eval_loss": 1.6172243356704712,
+      "eval_runtime": 386.7546,
+      "eval_samples_per_second": 24.506,
+      "eval_steps_per_second": 3.064,
+      "step": 25800
+    },
+    {
+      "epoch": 10.9,
+      "grad_norm": 7.293168544769287,
+      "learning_rate": 3.2060070671378093e-05,
+      "loss": 1.3999,
+      "step": 25900
+    },
+    {
+      "epoch": 10.9,
+      "eval_cer": 0.42187194478119744,
+      "eval_loss": 1.8544808626174927,
+      "eval_runtime": 365.482,
+      "eval_samples_per_second": 25.933,
+      "eval_steps_per_second": 3.242,
+      "step": 25900
     }
   ],
   "logging_steps": 100,
@@ -4126,7 +4158,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 2.815852220682527e+20,
+  "total_flos": 2.8377007760000103e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null