Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:672c605344bdf205ac6998451e8fc34fa43f5a08923dadd24aa9f407c921bea9
+oid sha256:fc284fd8457776261f76bab54e9dda3a2609cb0c2f96d43e78599feafd6fde8a
 size 390888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02ebf469ac7d65e70f0fcfec66bffeec087adac64aeb03f69282bc12cc068e0d
+oid sha256:f6542d09ba2faefb429b9d4f9f9cc1df7d1d8f081e6e325218a0470e0a3a304a
 size 819770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96a5a857ed41b50df491280680008400b63a0cea9bbaf95bf767f775a18248db
+oid sha256:580a78039b006147c49fed961f84593aff50f8571d4e98d9723902082cb2076d
 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": 0.04195804195804196,
+  "epoch": 0.046620046620046623,
   "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": 125.766,
       "eval_steps_per_second": 63.574,
       "step": 9
+    },
+    {
+      "epoch": 0.046620046620046623,
+      "grad_norm": 8.551138877868652,
+      "learning_rate": 0.0002,
+      "loss": 9.2544,
+      "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": 983378165760.0,
+  "total_flos": 1081715982336.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null