Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cde26a5d5e00a77626bb777213f7ce9d0a6465c5c4c9e36263bd48fded84356
+oid sha256:77a25462fc27e5abd83681a5ed0dbc236b83eb21e714d2f726c2e8fc971bc6cb
 size 619632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d459dc46d22c02a3baa12dc4bbd62996b67292ccb165171fd6ebd09105f64c8
+oid sha256:a9c6c52cee4b3c33a1d6b38e4da3b1b2cc99226002ed0dd0d9c6058019681a2c
 size 1324026

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60c9e35ce390deeed83aeaef6f7c1f6649ab9ed361bc0bf084a07c434458cee2
+oid sha256:6edb4c660568a65bef01d630b56e760940c5b85cc53771b6da9e3adfc2928313
 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": 0.1276595744680851,
+  "epoch": 0.14184397163120568,
   "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": 142.243,
       "eval_steps_per_second": 47.414,
       "step": 9
+    },
+    {
+      "epoch": 0.14184397163120568,
+      "grad_norm": 0.2909541130065918,
+      "learning_rate": 0.0002,
+      "loss": 11.9263,
+      "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": 6855373357056.0,
+  "total_flos": 7617081507840.0,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null