Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27fadc57cfae1f820c2cc64483d50d56581f9e0ece76450c6427962e01b4c46f
+oid sha256:72c893c3eeff4405ef6a6641760c89d7a4c804aa9fea6bd8ad161ec97df4388a
 size 109009752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b14a261abf486663feeac25d6420bcde3d6231de477b15c1042d45b3f6f58343
+oid sha256:f4cd0cb34d8f7dc539b314a4b194251acf62ab665d5959a07857617f0c3e7f1a
 size 56088148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cff9316fc0987986e0fe3dc3c93191fefd1ec67bfc89b5d08c00fb6737409e70
+oid sha256:fef0d2d7902ec6473fa3a6fd8bbc53ac22da886e4be1152576f3220976e1ae65
 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": 0.00022787550401630577,
+  "epoch": 0.00025319500446256194,
   "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": 22.239,
       "eval_steps_per_second": 11.119,
       "step": 9
+    },
+    {
+      "epoch": 0.00025319500446256194,
+      "grad_norm": 13.027254104614258,
+      "learning_rate": 0.0002,
+      "loss": 3.55,
+      "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": 2164987275509760.0,
+  "total_flos": 2376205546291200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null