Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5555eb717158130fc3b91c907f196c1083fde68fe1d95c107af7542d0a5cea54
+oid sha256:ac5013cd0556270fdfc3a24e7f224f991b0802139803d4732e40e535659e3834
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc0787487d4791dafe0be7cfd864895b3e9c85acf269b881e53820f2a596b8a9
+oid sha256:68eddc984f92e39fcc9eb5a8fa89eebda378efc9a15696ba0e68b0e708e3a78b
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04a94b83956618c5f6ad1eb1e148eb701d120c1b0cae59d7acf6b263a4a79491
+oid sha256:7f67aff9f0cdd92218acf4442ad1be927d0f03fbd597b3574918cfb798f32cfe
 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": 8.964969382139291e-05,
+  "epoch": 9.961077091265879e-05,
   "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": 19.377,
       "eval_steps_per_second": 9.688,
       "step": 9
+    },
+    {
+      "epoch": 9.961077091265879e-05,
+      "grad_norm": 26.626014709472656,
+      "learning_rate": 0.0002,
+      "loss": 9.7356,
+      "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": 2849601874821120.0,
+  "total_flos": 3166224305356800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null