End of training

logs/events.out.tfevents.1702885199.f99763f5b9a6.40910.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfc2304108de57b732a5a6b519fefd1ff858ad98df8ac1ca52dcccec92c690eb
+size 4661

logs/events.out.tfevents.1702885463.f99763f5b9a6.40910.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71161617aaf09a07e106669dc827138d37a6bea47350e527a500cfe19e550f39
+size 4855

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e7dc4954663319ae553f7c8324f0be8209074fd1a7d694d36b48d737871b3fb
+oid sha256:bce1ad637c7a99828fc7e7d3601c659a5dd4de6c4967b5f8d19f044d6350570b
 size 497918592

trainer_state.json

@@ -1,28 +1,28 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.25,
+  "epoch": 0.09375,
   "eval_steps": 10,
-  "global_step": 1,
+  "global_step": 3,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.25,
-      "step": 1,
-      "total_flos": 2090336256000.0,
-      "train_loss": 1.2067252397537231,
-      "train_runtime": 2.2969,
-      "train_samples_per_second": 3.918,
-      "train_steps_per_second": 0.435
+      "epoch": 0.09,
+      "step": 3,
+      "total_flos": 6271008768000.0,
+      "train_loss": 1.1875303586324055,
+      "train_runtime": 2.2971,
+      "train_samples_per_second": 39.179,
+      "train_steps_per_second": 1.306
     }
   ],
   "logging_steps": 10,
-  "max_steps": 1,
+  "max_steps": 3,
   "num_train_epochs": 1,
   "save_steps": 10,
-  "total_flos": 2090336256000.0,
+  "total_flos": 6271008768000.0,
   "trial_name": null,
   "trial_params": null
 }