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:a5b3b07b5c167e8ded7435f88a7d93ec78d631e2529ef440869e32d8883029cd
+oid sha256:1a417180d66ec530e8288ab88719bf8aca23cbadba04b29807b70e5c5a9024d0
 size 114106856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0dd8ede2b13fa7fbdbcbc48492e7382d568dd439f54216d0c10245deb980796a
+oid sha256:4a6635b3ff28a27821e3e15835497bdc7d3915e84547b755881a4dc69ee72910
 size 58562260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a59ccec7033553ae34d84603591a8663aa3252c7b3a14c2ca59ac6a3e005c0d
+oid sha256:01970748f690b31b99006aacb016cd6be7f60a4ca93784a6e1b1a8fdf9de41b7
 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": 0.0004148995021205975,
+  "epoch": 0.0004609994468006638,
   "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": 1.921,
       "eval_steps_per_second": 1.921,
       "step": 9
+    },
+    {
+      "epoch": 0.0004609994468006638,
+      "grad_norm": 80.12603759765625,
+      "learning_rate": 0.0002,
+      "loss": 2.254,
+      "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": 5133769962946560.0,
+  "total_flos": 5704188847718400.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null