Training in progress, step 23500, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:885e4086287d81a6c57b433d7482c8a891e84519bd6a20d1ec115d03c74c0ce0
+oid sha256:bf49c6b82f7665a604e40742defaf43941c7586bf80b494ee902b2c620087cc4
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5486ea2d5d852edcc9c66f324045c258e41e901f713ba2047c61095d581b32e9
+oid sha256:f98af73c68edabc39c71995cd33d7c87eed9ee1a1350930152351ece5229c762
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec688ceaf93ae471f57a8056ca6dbf8c0b36abdc291ae512e6cb0dbe74e4638d
+oid sha256:e95a4e83c0629f0505bbb8d535207996a723259667e4045da0c20dd5dcda6985
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b95ac58f573cfcf6a4b348ea728bffa80f65499c1f4c3ba4d255445fd485d15b
-size 14567
+oid sha256:5113b92b4d7def74e8c7a35c67502e1a4c59c5544bae2c22551f00c5f5b8acd6
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:889ad38937ee9ef0869ccade470844b4b0a09f60a10384d27c3be448b16e4af6
+oid sha256:549665abf4f20a24c12813b0847df3413b770048a1d4544619085eecf6a394ea
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.808461376552305,
+  "epoch": 9.892654178067776,
   "eval_steps": 100,
-  "global_step": 23300,
+  "global_step": 23500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3735,6 +3735,38 @@
       "eval_samples_per_second": 25.185,
       "eval_steps_per_second": 3.149,
       "step": 23300
+    },
+    {
+      "epoch": 9.85,
+      "grad_norm": 19.793508529663086,
+      "learning_rate": 3.382614840989399e-05,
+      "loss": 1.9455,
+      "step": 23400
+    },
+    {
+      "epoch": 9.85,
+      "eval_cer": 0.45229947987955105,
+      "eval_loss": 1.607908010482788,
+      "eval_runtime": 388.4585,
+      "eval_samples_per_second": 24.399,
+      "eval_steps_per_second": 3.051,
+      "step": 23400
+    },
+    {
+      "epoch": 9.89,
+      "grad_norm": 25.258953094482422,
+      "learning_rate": 3.3755477031802126e-05,
+      "loss": 1.2352,
+      "step": 23500
+    },
+    {
+      "epoch": 9.89,
+      "eval_cer": 0.43993439834187165,
+      "eval_loss": 1.3818862438201904,
+      "eval_runtime": 363.0875,
+      "eval_samples_per_second": 26.104,
+      "eval_steps_per_second": 3.264,
+      "step": 23500
     }
   ],
   "logging_steps": 100,
@@ -3742,7 +3774,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 2.5535582493052453e+20,
+  "total_flos": 2.575180974094451e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null