Training in progress, step 18600, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce9799401c39c71a0cd9f1ebdf6a16f0ac4e723de7b22b57d999c5161366972b
+oid sha256:05600eb332380574b52f500b4d9acf6495af5b8f8c8a80d16d05132a35dbdde4
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a108474f50a0efca90382b4d207acc17a6d168f1ba66241707a217c75910dce
+oid sha256:6a4566bb143a9221c476166298783b072e2d5600fad5a694751515835f2329e9
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a9d6a3ff9e16aec0f67353aa981343ca07640557c27a59eca4811f64c218c41
+oid sha256:5217e8be28535efa2a4e60fd1aa4e2ad60fdba5e79e0caffb56d99a0213dd6ae
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3841b9e537739134e582030ad4b8b96b4b45677b00f72ce75fa56b4b4070d92
-size 14503
+oid sha256:96e574121cd2f48fe3779fc12e2fc48d6f0347b202db10a57a0f0ac24a750e3f
+size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c544fcd0738aab978188bc5cbfad82678c3f7d9d75b06c8c4f740f0ef0a9607
+oid sha256:848b9d4191f57596a67ed77f7f652c25002d270d8cdf8a0d9e34a780cddc39f5
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.745737739423279,
+  "epoch": 7.82993054093875,
   "eval_steps": 100,
-  "global_step": 18400,
+  "global_step": 18600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2951,6 +2951,38 @@
       "eval_samples_per_second": 24.821,
       "eval_steps_per_second": 3.103,
       "step": 18400
+    },
+    {
+      "epoch": 7.79,
+      "grad_norm": 4.755228042602539,
+      "learning_rate": 3.728763250883393e-05,
+      "loss": 1.417,
+      "step": 18500
+    },
+    {
+      "epoch": 7.79,
+      "eval_cer": 0.47154491416057254,
+      "eval_loss": 1.8104172945022583,
+      "eval_runtime": 382.6075,
+      "eval_samples_per_second": 24.772,
+      "eval_steps_per_second": 3.097,
+      "step": 18500
+    },
+    {
+      "epoch": 7.83,
+      "grad_norm": 2.874833822250366,
+      "learning_rate": 3.721696113074205e-05,
+      "loss": 1.3215,
+      "step": 18600
+    },
+    {
+      "epoch": 7.83,
+      "eval_cer": 0.45071076610222516,
+      "eval_loss": 3.382107973098755,
+      "eval_runtime": 367.7162,
+      "eval_samples_per_second": 25.775,
+      "eval_steps_per_second": 3.223,
+      "step": 18600
     }
   ],
   "logging_steps": 100,
@@ -2958,7 +2990,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 2.0158114839380017e+20,
+  "total_flos": 2.0376121366581146e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null