Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44e3ec27ff173bf2c063977b4c6ac6dd84345ac663bce4e937c185baf6525d0a
+oid sha256:e48536186cd2081126869cdbff740091491e88e6d9d788f261b2c11b1864655b
 size 17425352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08d525efd674acbfe5bbe053e3ad7ee03f6998f02e0963b4915916b912960fa6
+oid sha256:ab4fdd746f4334f759e9f986a6d447331644ac4e6932ab7f0fc60ba189414942
 size 10251668

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79fef229ddf80177f84717213c08caa8a37a43e854c261a1754ce4f6b16c6c60
+oid sha256:bfa25943342783a61b36c4d0bbac9c63f166b2ceef5f747acc8e288833dd451a
 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": 0.005989020129762102,
+  "epoch": 0.006654466810846781,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -94,6 +94,13 @@
       "eval_samples_per_second": 20.979,
       "eval_steps_per_second": 10.506,
       "step": 9
+    },
+    {
+      "epoch": 0.006654466810846781,
+      "grad_norm": 0.08498664200305939,
+      "learning_rate": 0.0002,
+      "loss": 1.3204,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -108,12 +115,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 109748488765440.0,
+  "total_flos": 117587666534400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null