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:d77d7e74993863eadcb8b70229a840d5c0af1a5573e8c6d67ebf96e92975513b
+oid sha256:3722afd2b6487ca850695717be1c94bc51e9d0eb5b2a477a93d8e61ad64f7f78
 size 2185308208

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:032d7b898732fcaa9105d6b2fbc4fa269cf11c20257c3e772e5779f329681bd5
+oid sha256:e4bd641add1c019375dec64bea20665f9de8e0fff410778dc2361fcfd8878779
 size 168037178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b90a19943f8ef28f7f3c1abafd8de7b24ff68c3eda11dffdc748b1a1d989fcb2
+oid sha256:574c700717b33f47ad8a70b47083271e5db120d9e87ae1c83258d7702c5eeb81
 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": 0.000307831752845306,
+  "epoch": 0.0003420352809392289,
   "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": 12.559,
       "eval_steps_per_second": 12.559,
       "step": 9
+    },
+    {
+      "epoch": 0.0003420352809392289,
+      "grad_norm": 2.75307559967041,
+      "learning_rate": 0.0002,
+      "loss": 3.7808,
+      "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": 1664608729300992.0,
+  "total_flos": 1849565254778880.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null