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:fb1ff2b021eaf2f3149b427eae9104f2a03a43b3c36dd2b93369ec81ae77c71f
+oid sha256:9c962e42cdd74bfb9866eba670469f6c1232049aed980599b59c925e322648de
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7228f554b2602104c615c4fcb52631457b7fe407f6bba46f99674010d1dbdae0
+oid sha256:509d5c6897b04c2ffc66e2daa736739aa905f5ebb40c95a715b9e6af8127ceae
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18947dd72744f5e15a32bf79856a222e61386e4565f4bc346034eafb1764ad11
+oid sha256:15e384a1f037b808e519059075ab1fcf8b83458cebdf061d0351090752029612
 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": 0.34951456310679613,
+  "epoch": 0.3883495145631068,
   "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": 2.192,
       "eval_steps_per_second": 1.196,
       "step": 9
+    },
+    {
+      "epoch": 0.3883495145631068,
+      "grad_norm": 31.062732696533203,
+      "learning_rate": 0.0002,
+      "loss": 2.3454,
+      "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": 1.3353971104088064e+16,
+  "total_flos": 1.483774567120896e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null