Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:322b1adb1c2a13bbdb198735b13acdec6d29d7899af427e1e8ca47e474898505
+oid sha256:c0a4a36a0415679624763c84881c794492ae9013dad042cb07ed069b368de778
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f8c5e5180e20f329800cd9adc0dec24171fa6566abe84aa3fe102b1d0153bde
+oid sha256:ef79baa0fca45b57c21fb4654f62cee124ff1d445a845732733f76ae6727e3d1
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6a629bcc4d1cf05d0ed241ade838414811cac61f7bea2bcdb22033b753ca109
+oid sha256:11606da0bea000f6b0519f7cecd1161c20c1570b07e67029fa0e118e63654d4d
 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": 0.021712907117008445,
+  "epoch": 0.024125452352231604,
   "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": 9.143,
       "eval_steps_per_second": 4.597,
       "step": 9
+    },
+    {
+      "epoch": 0.024125452352231604,
+      "grad_norm": 21.228473663330078,
+      "learning_rate": 0.0002,
+      "loss": 16.7548,
+      "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": 2849583755427840.0,
+  "total_flos": 3166204172697600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null