Training in progress, step 25700, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ab007dd960c183c2e30e85616514e3da6c3660d56809b3a634e02652595cf69
+oid sha256:b7781a53d6b5b7512ff0ff1d38c7eaabb023d480f361f98431565fe95b327859
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6778800cc796c45ea30ad3a22874ae830638e117c355360ea6c92a3dfd474eab
+oid sha256:72d83ec1e6bf950a1d60198c789353d4e7b343be90d1474a02b4880043c647b8
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e13a3e04c3bc95af16ed8a2dd0f5ca31f7946fe6e95a84fd44ba865570960002
+oid sha256:e43534489fe9b0667499677fea38991daee7ef7e44c8bba59d24e7af296df2cf
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:846f249b88befad596e3b348fc9d3af50438f51fe4f7aa809cab2c988dc38c0e
+oid sha256:20fff49ae707308451e57857b198857501948a824acc26025a78021e3c4d9970
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e006367d18ff2557748c2cef8502481c62684745dc5fb7eb9b01c6baf1a2184
+oid sha256:b567208206c71e420de4afc268070bb8059d13be7ed02d0130d55f8213c8c995
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.73458219322248,
+  "epoch": 10.81877499473795,
   "eval_steps": 100,
-  "global_step": 25500,
+  "global_step": 25700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4087,6 +4087,38 @@
       "eval_samples_per_second": 25.6,
       "eval_steps_per_second": 3.201,
       "step": 25500
+    },
+    {
+      "epoch": 10.78,
+      "grad_norm": 3.47428035736084,
+      "learning_rate": 3.2271378091872796e-05,
+      "loss": 1.3785,
+      "step": 25600
+    },
+    {
+      "epoch": 10.78,
+      "eval_cer": 0.4252571272144226,
+      "eval_loss": 2.5334064960479736,
+      "eval_runtime": 380.018,
+      "eval_samples_per_second": 24.941,
+      "eval_steps_per_second": 3.118,
+      "step": 25600
+    },
+    {
+      "epoch": 10.82,
+      "grad_norm": 2.5327584743499756,
+      "learning_rate": 3.2200706713780924e-05,
+      "loss": 1.518,
+      "step": 25700
+    },
+    {
+      "epoch": 10.82,
+      "eval_cer": 0.42553087481913104,
+      "eval_loss": 2.6629116535186768,
+      "eval_runtime": 359.4773,
+      "eval_samples_per_second": 26.366,
+      "eval_steps_per_second": 3.296,
+      "step": 25700
     }
   ],
   "logging_steps": 100,
@@ -4094,7 +4126,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 2.7941943750609027e+20,
+  "total_flos": 2.815852220682527e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null