Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5474de2fab7406c330a9092099c68132e7fc386b7f1ea1296bd6dca7c91c1747
+oid sha256:9cc3d7afdb1e6083765bb5d1d620ed8f789d8d79c63bae638692021ea84f2357
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dcacb10cb431d3274ee66b1b941a2b8e9f0862b32078045de5f448ab6f04f49
+oid sha256:ee3264fe21535f19f4871e719a367643d312208e78662a44207d184c81be05ff
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f139111d58a1bfb8978c748077ab6e58b42441cce775f3c2473388cafe954c0
+oid sha256:af0be4faa022efe244e3a43285351d87f9c47f8da1a13b511898dcf690c59e3a
 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": 0.011155872327238922,
+  "epoch": 0.012395413696932134,
   "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": 16.428,
       "eval_steps_per_second": 8.214,
       "step": 9
+    },
+    {
+      "epoch": 0.012395413696932134,
+      "grad_norm": 3.9063289165496826,
+      "learning_rate": 0.0002,
+      "loss": 1.3487,
+      "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": 3296632693063680.0,
+  "total_flos": 3678850976317440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null