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:fca73cb63560b99a239d4e19e993726ddb76cdf5f825663927d3deac781bc796
+oid sha256:465eb8a0bcf1d1d3c8e9fe210afe7bd64130395921481dbad1a0b6e6bac64602
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb4734109f2055ce3cc13dc56b2cc0e0eae961401967cc7b0fff7f59fdf34d56
+oid sha256:c6f178a1dbb036c8211b20f9d51b1a72517108e06832fead103ae69f0cd530f2
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20fcd20993d40639a43d37688307179c27149f3c2c0e22843985ee1afc726a1b
+oid sha256:1a2216831b32fe96593b54e3c0610340ea6af644508f9da010aed76603490251
 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": 0.0011090231354548535,
+  "epoch": 0.0012322479282831705,
   "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": 20.629,
       "eval_steps_per_second": 10.318,
       "step": 9
+    },
+    {
+      "epoch": 0.0012322479282831705,
+      "grad_norm": 6.596424102783203,
+      "learning_rate": 0.0002,
+      "loss": 6.0204,
+      "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": 2541374108860416.0,
+  "total_flos": 2891908468703232.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null