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:b963c3213fe76a49a09a0c2c3abece6f291643ca63222e8846c1124b010e6df4
+oid sha256:1acbd3db3d948f46e7f901387f6e170dd4d5d0ce03dafe2b2502c82c6bcc0462
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05d41470bc64efd2d860083f7f38b2ec0f8caba43c8daaf3ea08aeb4c2f4425f
+oid sha256:6d5ed6e6fe652579c041c8d1e25e8a1a6c8a48074d9cda393325aa885a875d4e
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17602379fd7311d0f276d1ebf45e775c93bcab84ae4bf6e66fb3d0fb451e92a1
+oid sha256:508b60f52b738b8a0523530488d1e5c72c72b0f0e1559b2f99aef9c5a89d8e56
 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": 0.032,
+  "epoch": 0.035555555555555556,
   "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": 12.974,
       "eval_steps_per_second": 6.541,
       "step": 9
+    },
+    {
+      "epoch": 0.035555555555555556,
+      "grad_norm": 7.295120716094971,
+      "learning_rate": 0.0002,
+      "loss": 14.3428,
+      "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": 1465859822321664.0,
+  "total_flos": 1628733135912960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null