Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:458d38fb0a6aae54b2a8c29bbe75a18fbe266a586e31ec7af154eb1d0d985b12
+oid sha256:c2ea92bbc178c0c334eae54a8faeb24aef4e8577608318ca0789d807ffe764f8
 size 104902272

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93e3e91588ca755bc2d1120cf86f7e4bf41402ce28d7d70e29b3be4249f331ae
+oid sha256:a1c850d86073b7e197777e87ec915998279bf1ac3e34acb9d964c33aef6565c4
 size 53622996

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45e4abb5d8f838d7298d0da53d751603c0e159cddd8e50398726666cfef25317
+oid sha256:f06dc400444691b20cd0161805e955b193c9256e8e96477d1c3f4ece92014368
 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": 0.010321100917431193,
+  "epoch": 0.011467889908256881,
   "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": 13.768,
       "eval_steps_per_second": 6.884,
       "step": 9
+    },
+    {
+      "epoch": 0.011467889908256881,
+      "grad_norm": 0.8208650946617126,
+      "learning_rate": 0.0002,
+      "loss": 5.2877,
+      "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": 5647185236459520.0,
+  "total_flos": 6274650262732800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null