Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dc4ef51d48b75cf51f1cf7e6074888c2cadb122e526193f9fe5687fbc4b00c4
+oid sha256:d0cf1814ee622cc6c5c79ad3b7194ac01afd2d68d1a2ad164e641edbce48f732
 size 108113968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d8912d691fd67ece5eb5d2da66c5178e4c35f7863496490e0928881ef405737
+oid sha256:6cca3ab4e2e943c79015f686d24d47e909c2fa2b157a12994223966e25176206
 size 55549892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea79ba6b741361467cf4e50bbf4517697d1d1f11c3bfdd43932d2f7f51104b12
+oid sha256:942fa56788748f4bde17a6e90bdc88b86be9f963b4971c9092a1ddf8bfafad81
 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": 0.00010505918333994817,
+  "epoch": 0.00011673242593327574,
   "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": 13.562,
       "eval_steps_per_second": 6.781,
       "step": 9
+    },
+    {
+      "epoch": 0.00011673242593327574,
+      "grad_norm": 6.351680278778076,
+      "learning_rate": 0.0002,
+      "loss": 1.3756,
+      "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": 2975970745122816.0,
+  "total_flos": 3283829787721728.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null