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:e13ba27fc13f48d86dabfedddf91fd5a2e1fe8c1fae91dfd51bb3669da0ac7a9
+oid sha256:d6017bdb7f99dbde62ecd8133deb7b1efc91717859d4aaea863bf25936146ff8
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:481d82f5050e86e5f862bca29201362d77505a0a085f5f2eaf45c5d348a5811a
+oid sha256:c38227cdef1b2d3d94b6d97ebb897ace6446df85620c4ed3dca4deed9c6ea9e0
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc28ff65b756b2bb84099df0a7e138a0c562c67de8bb4fd9c1530df43337b20e
+oid sha256:787ec9b173bd68d303b6af8c44c357d592cfac90a041f8c1ed405e446c660408
 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": 0.0001241597660278187,
+  "epoch": 0.0001379552955864652,
   "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": 24.907,
       "eval_steps_per_second": 12.454,
       "step": 9
+    },
+    {
+      "epoch": 0.0001379552955864652,
+      "grad_norm": 1.9102445840835571,
+      "learning_rate": 0.0002,
+      "loss": 12.4421,
+      "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": 1791624166244352.0,
+  "total_flos": 1995217821499392.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null