Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ee4d05b4c02ed66326e99fd1df18389dddac6bc1c570fba5dfbc3d09285b0cf
+oid sha256:df9c7ea6dfa34d1902c53525664dd4a1727f94c7f51855d872c64a3c57b9a899
 size 12609312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a849fa1d9941b3754ba370b3e6ee14ddb9dd082ae6fa641fd5377aa3bf63a516
+oid sha256:89adc4ae8b9fe65cd721f943fdc25e67072c33c37a700cd039db2dcf20d68546
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bafe321b9c5a1744332ee7bfba8928cea1245498308304b39f58a86543bb739e
+oid sha256:2fea276383daa6be11cb41bcf079e20917a66b8a1df06264809ff50445c989c9
 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": 0.02140309155766944,
+  "epoch": 0.023781212841854936,
   "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": 81.585,
       "eval_steps_per_second": 40.793,
       "step": 9
+    },
+    {
+      "epoch": 0.023781212841854936,
+      "grad_norm": 23.219770431518555,
+      "learning_rate": 0.0002,
+      "loss": 10.4842,
+      "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": 100887850647552.0,
+  "total_flos": 109660707225600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null