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:c31867ddd45ff84ec6be45c7289e6cafcb56b8cd469d77b8a6bafd609513277b
+oid sha256:80f502ec2d8bb2f16489d78da378793857972192485a06b422bede7eb85c0cae
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0f322d7b663ed310d3af11aca10ad2e381747ae16983f5da6de416c7c7418d3
+oid sha256:e914806792e505935a1d57847ef3c904c07b2587bfe7cca2f4c8134a3571e3de
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19394caac0370dc5eb8bb3d271a9b6d245fc10d68ceffd549459fcf4f2e70bc9
+oid sha256:8b381771eb8b42d7f741c5a919735473d66e4c89494b6a3360ab83c471ea546e
 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": 0.00018140132523745937,
+  "epoch": 0.00020155702804162154,
   "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": 24.367,
       "eval_steps_per_second": 12.183,
       "step": 9
+    },
+    {
+      "epoch": 0.00020155702804162154,
+      "grad_norm": 1.3552900552749634,
+      "learning_rate": 0.0002,
+      "loss": 1.1348,
+      "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": 2450672628793344.0,
+  "total_flos": 2728107266015232.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null