Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:894ebf3126ef1afa2ad7f0a1c28c4e7c6927d9dfd2726e92bdb3c0e719b6de79
+oid sha256:b70991faa5369d9bd503ce0d5d62ad5315e960fdbd63223c4a04b2c0fdf588e9
 size 2264640

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3dbed04c1738469a08f9db8002360bf85604704c60493a7729041f6a34721d85
+oid sha256:83895582e2d006825a6d7d30f6f76cb018157512d3355631109124a2fccdc5d8
 size 1183674

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5081bbbd97460339927b75a3b99f728398902a94fba87e277472912c152eb515
+oid sha256:3c72530c1181e385391bf43f1fdf08c8275fccd52a2134362ec0beb66af41fd8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:917587e2c0a52fd7c3d6680e02e388879c84c249a215f319208d6a9951b36ba9
+oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03858520900321544,
+  "epoch": 0.04287245444801715,
   "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": 107.473,
       "eval_steps_per_second": 107.473,
       "step": 9
+    },
+    {
+      "epoch": 0.04287245444801715,
+      "grad_norm": 17.39168930053711,
+      "learning_rate": 0.0001,
+      "loss": 15.691,
+      "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": 38945597423616.0,
+  "total_flos": 43272886026240.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null