Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71896af2d79388e18d107d4db5d4bfa1da34b41f6ae9443f585c66429d03477d
+oid sha256:7e15b49d12f271a6fa4ac8fdaf4bb6844254860edfa3cbbca0b44e4459c07a1a
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e3920daf2089c1d06466e68a88608754656265bd573d7dd7a845726aaca2082
+oid sha256:fedc4ef48d8a30c787fac5c907178473e41fb4d38026da00a898ff6a4826f327
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc05cd3a98949633cd0945d642fde31aa27434b462cc4feb8ff105332385519f
+oid sha256:2431fbde914d288016858b6cb5609b72dae4b3f1f99b197bd647068cb11c807f
 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": 0.0059210526315789476,
+  "epoch": 0.006578947368421052,
   "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": 17.341,
       "eval_steps_per_second": 8.67,
       "step": 9
+    },
+    {
+      "epoch": 0.006578947368421052,
+      "grad_norm": 1.086848258972168,
+      "learning_rate": 0.0002,
+      "loss": 0.7216,
+      "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": 3329215646662656.0,
+  "total_flos": 3699128496291840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null