Training in progress, step 26500, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40d05fd16c8588673c1e6ccde78de203e04e081ce27b72ee44b52315e644b740
+oid sha256:4a6f6f50b75e53f88f456a440ba99a4024e31f9424c3be014a002cb574db9080
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5812acb9bb3d64b8d63f94464a796cff46b7ad7f07e8e2c4a1aa5e63c47a7c54
+oid sha256:1d0d3f50750973222fb25da6c949b2a0a8537e325e53090985a92f861de32eea
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b23cd02c502517bc70ad64a5dec054c9efc4df18822ed05bd1e7e119d953775
+oid sha256:ad6c81cb83edbb3cfd00fa6e082ac509892ec328a2c87c50274cee2405cde601
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34fbd3601d535cbde5b18a032775aec5cee5099b7fbfab69d247bf1219d7534a
+oid sha256:6696be169116cd06c49001a7406234fedc653144f3b5c806d950a921ea10d5f1
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92ad90ae3571dbb88467083f26508c8007da34c4d92b38346a376256e4c52e28
+oid sha256:a30c44f6f4c7b9b608f34a4bbe0eeff7385b81ec6e639bfbef514ac626117dc6
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 11.07135339928436,
+  "epoch": 11.155546200799831,
   "eval_steps": 100,
-  "global_step": 26300,
+  "global_step": 26500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4215,6 +4215,38 @@
       "eval_samples_per_second": 25.598,
       "eval_steps_per_second": 3.2,
       "step": 26300
+    },
+    {
+      "epoch": 11.11,
+      "grad_norm": 10.38554859161377,
+      "learning_rate": 3.170671378091873e-05,
+      "loss": 1.1303,
+      "step": 26400
+    },
+    {
+      "epoch": 11.11,
+      "eval_cer": 0.42248543271674943,
+      "eval_loss": 2.5170605182647705,
+      "eval_runtime": 383.496,
+      "eval_samples_per_second": 24.715,
+      "eval_steps_per_second": 3.09,
+      "step": 26400
+    },
+    {
+      "epoch": 11.16,
+      "grad_norm": 1.8860437870025635,
+      "learning_rate": 3.1636042402826855e-05,
+      "loss": 1.1186,
+      "step": 26500
+    },
+    {
+      "epoch": 11.16,
+      "eval_cer": 0.4318832857533925,
+      "eval_loss": 1.2920070886611938,
+      "eval_runtime": 374.2965,
+      "eval_samples_per_second": 25.322,
+      "eval_steps_per_second": 3.166,
+      "step": 26500
     }
   ],
   "logging_steps": 100,
@@ -4222,7 +4254,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 2.8824923424902952e+20,
+  "total_flos": 2.9042272694513363e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null