Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02e66d9e7fa31bd7db4bd299becb1a3900af3fe9575a1c5bc4f3961f0eb89fdb
+oid sha256:37c70c2a6f01e0c04faec80983ab7a9febcde2456180586c46db8075cba3010f
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e7be6cb3881b5453b3807652a5b2c2fb899301b11721562d2201aa6bd4d0eb6
+oid sha256:e22eafe5a050dbfe5da3572cd3b48f5965963717aa59f3904d13f9edb825dd78
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a57a497a8167611d7b73245c1d38436f06d54fb1850480c05c7559c4e1238b86
+oid sha256:7b5ce19cb009bbae58fb775280947371ab0ca362b5277ce916cb8a25ba73a8f7
 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": 0.006112054329371817,
+  "epoch": 0.006791171477079796,
   "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": 30.498,
       "eval_steps_per_second": 15.249,
       "step": 9
+    },
+    {
+      "epoch": 0.006791171477079796,
+      "grad_norm": 0.6021103858947754,
+      "learning_rate": 0.0002,
+      "loss": 0.6509,
+      "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": 650126529921024.0,
+  "total_flos": 725141129527296.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null