Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0328b2f069d53eddc742691dcf3eb0bd2e9cd8ccf1e058068e3f9206ed99f2b7
+oid sha256:39c1bec42b7b2bef34690476d64044c05fd19b3876ecde113fb9ebdd522a7798
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4ae13eb833f2ba132c67a9f50c538e52a5fdaf3608d9c1fc4660caa98bcdecc
+oid sha256:82ce28894959df7f570ed54eaf51e6898f6f748e138bc26298081d5fd1572c49
 size 42608388

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:975e2fef0ce023c45a0d7bbabf76a79358b37a1de8f82a4354020f8b97bfa2fa
+oid sha256:d8fb5c2de708c8564f6e7216f5673a79fe25a9c85499b64b7385f5503a9d7208
 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": 0.00014610863989090555,
+  "epoch": 0.00016234293321211728,
   "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": 7.697,
       "eval_steps_per_second": 7.697,
       "step": 9
+    },
+    {
+      "epoch": 0.00016234293321211728,
+      "grad_norm": 5.726334571838379,
+      "learning_rate": 0.0002,
+      "loss": 2.212,
+      "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": 1809536922943488.0,
+  "total_flos": 2010596581048320.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null