End of training

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:853b3e25a4f56a4058e2078c5744e4f1921ae8c9ef88fca3ca29050b836218f6
+oid sha256:7796a8b8b48c8a65dd69eaa720ca767ce8793f9c21b27bee282ae5a9c1fd9103
 size 167832240

runs/Jul14_14-59-55_ml-cluster/events.out.tfevents.1720969199.ml-cluster

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f4be315bf2ecfce060091693340341a56f61b00183d03eb0162c1fa7c6c9d94
-size 5702
+oid sha256:acc2a729553151c5f4b3d68429955e6d2be2f98470663adfcc4d2397c395885b
+size 6267

trainer_state.json

@@ -10,19 +10,19 @@
   "log_history": [
     {
       "epoch": 2.9940119760479043,
-      "grad_norm": 2.417518377304077,
+      "grad_norm": 2.0207631587982178,
       "learning_rate": 9.98003992015968e-08,
-      "loss": 0.9995,
+      "loss": 0.9071,
       "step": 500
     },
     {
       "epoch": 3.0,
       "step": 501,
-      "total_flos": 2.0033559725080576e+16,
-      "train_loss": 0.9991578065944527,
-      "train_runtime": 874.8982,
-      "train_samples_per_second": 2.287,
-      "train_steps_per_second": 0.573
+      "total_flos": 2.157617842277581e+16,
+      "train_loss": 0.9067429488528512,
+      "train_runtime": 916.1317,
+      "train_samples_per_second": 2.184,
+      "train_steps_per_second": 0.547
     }
   ],
   "logging_steps": 500,
@@ -42,7 +42,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.0033559725080576e+16,
+  "total_flos": 2.157617842277581e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null