Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9eab753fcca0017f33f104e2b8f09de8b52fe1a13837e52b5883c4c5e10d0192
+oid sha256:c117eef10018b5cfade34aa3ef2ed497c0bc80a4ad4547ee30e192940cb0f844
 size 15182728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e8a185cd101dab3d5102dee4d622c95c5f7122ee3ce7eb2ad1159e637c37c62
+oid sha256:01ab7a2c0a6fe30757d865dd2914da8968f7705541d59438a96ef18e21447178
 size 8075796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afdcebae8560a2d6cbef8990b206835b56f148729a2a93b18893f76e81bcddbb
+oid sha256:3391499f2be1a446bbf09cc3b20045449a55ecf9d7ef1ac34f82fb629982ab6b
 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": 0.02936378466557912,
+  "epoch": 0.03262642740619902,
   "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": 45.089,
       "eval_steps_per_second": 22.544,
       "step": 9
+    },
+    {
+      "epoch": 0.03262642740619902,
+      "grad_norm": 0.6495545506477356,
+      "learning_rate": 0.0002,
+      "loss": 1.4099,
+      "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": 97822848319488.0,
+  "total_flos": 109331418710016.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null