Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1868fe543ccd1f448f4d246685ebcc5bbfa0a23558369b1442c7d6d868bf14a1
+oid sha256:2df3c1f91fb221719e9cbb8d490ad0aba9c52cc04365495e9d49df80acf852e8
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74ab38df2395ab11f570828d6c734f8214908b36112c734b5b3eb89b064878c5
+oid sha256:4e831a61934648675a9d8ebe63e871227b1400f2df77b97f641de9a5f6d7b2bb
 size 82460660

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:623fb9bddd1501e2540f9214d6610cbcc7bd89bc3e4795cd57afb5fe1a5754f3
+oid sha256:9af747332e806743c48a94d1dd2c7bd4fedb9f8155ebded9fa20de9e63b6d948
 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": 0.0020895002611875328,
+  "epoch": 0.0023216669568750362,
   "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": 4.593,
       "eval_steps_per_second": 4.593,
       "step": 9
+    },
+    {
+      "epoch": 0.0023216669568750362,
+      "grad_norm": 1.9000203609466553,
+      "learning_rate": 0.0002,
+      "loss": 0.5152,
+      "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": 6291348239941632.0,
+  "total_flos": 6990386933268480.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null