Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ab9d93a6e2424c72af74449b3d1e570242b0a06125c84201cc266a1065fccaf
+oid sha256:6425da1a1e6047c3c11c5d24fd4b4bb2be119e9445b1097f977af114b79a7f87
 size 109009752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c67acf17ac8b391da4accbd94a103bc4eb1a1d5e3177ee7f03550302ae0dbc10
+oid sha256:3aef043c80c88a2af75d872775a44e13b146fc9db1b10bd1af7ef5348552f87c
 size 56088148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfa7797c4d348b0ea862ef56cfd8150da890921bb52975fbd7503a82b9686f51
+oid sha256:549051ad39d1adbb8cf2fefa8cfb5b7ddb10daa48ddd04b59c99694ed0258087
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007894736842105263,
+  "epoch": 0.008771929824561403,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,13 @@
       "eval_samples_per_second": 17.29,
       "eval_steps_per_second": 8.663,
       "step": 9
+    },
+    {
+      "epoch": 0.008771929824561403,
+      "grad_norm": 0.999865710735321,
+      "learning_rate": 0.0002,
+      "loss": 1.5445,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -116,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2904251223244800.0,
+  "total_flos": 3115469494026240.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null