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:db24bab980bd1f33651c7134011cf8ee9d8cbb51d7aabd2986fa20cec5a8edb3
+oid sha256:655f035c17d2d784c5897fdb5fcd908c1b2bb67b7f56081b5265610ba79cb62c
 size 60010048

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53b035c874ce94ffbfffc3ba56750ead100bd438deefd946864864e5b5916756
+oid sha256:8e42f8a84aa44c5f974324ba75559900b8fbe5ab444ff619af3acc65e0df9158
 size 30839892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17112f18adb57bd8c3d3808f3312936260bf4574741894fd027bd7b76c17fa99
+oid sha256:748fcfdce901ffd0c1f1b9274561dc47c6655aac5e63e76e420301ca7cb34a3b
 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": 0.010443864229765013,
+  "epoch": 0.011604293588627792,
   "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": 5.049,
       "eval_steps_per_second": 2.532,
       "step": 9
+    },
+    {
+      "epoch": 0.011604293588627792,
+      "grad_norm": 0.22967161238193512,
+      "learning_rate": 0.0002,
+      "loss": 0.2514,
+      "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": 2291251638435840.0,
+  "total_flos": 2545835153817600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null