End of training

logs/events.out.tfevents.1702875920.f99763f5b9a6.723.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0853dd269ae7325919b2b75567b98dea19701459058c7b218d26c63ae568f56
+size 4867

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c4de7f5916f44599f9620dafeb5655aeda10ebec759dcf9c996dcdb8733eb74
+oid sha256:d5783b94e2123ea92a2fcb12f597daf94cce815710a6a4759832dcc278ace309
 size 497918592

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.09000653376041816,
+  "epoch": 0.09002246976143806,
   "eval_steps": 8000,
-  "global_step": 5648,
+  "global_step": 5649,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -25,13 +25,22 @@
       "train_runtime": 2474.3011,
       "train_samples_per_second": 73.04,
       "train_steps_per_second": 2.283
+    },
+    {
+      "epoch": 0.09,
+      "step": 5649,
+      "total_flos": 1.1808309510144e+16,
+      "train_loss": 0.00021651981783917697,
+      "train_runtime": 2.6879,
+      "train_samples_per_second": 67235.558,
+      "train_steps_per_second": 2101.269
     }
   ],
   "logging_steps": 8000,
   "max_steps": 5648,
   "num_train_epochs": 1,
   "save_steps": 8000,
-  "total_flos": 1.1806219173888e+16,
+  "total_flos": 1.1808309510144e+16,
   "trial_name": null,
   "trial_params": null
 }