Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e040314da350808ad16b7a5df1d334eddec92464e45c1ee61b68dd5cd82d8f7
+oid sha256:438c24a3b7beb6ef98000be84a24946fe268bda4b71c308207c18392c4b1e48c
 size 30322120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:023c610d7d9a89c9b50e551da44d1fedde5088b156a3bfeb824c17537862fb0f
+oid sha256:3b88606ab0bff32bd99232939e57e79228dca53d6d20c471c6d39fe7c86f8af2
 size 15768084

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d84a5cf2454179937316496e4212e2e56502a7858df2afe7855b38d36059da33
+oid sha256:3c3490f66f3193c19d960a03b365425045c9218364a7eba1fbfdba254d9a4965
 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": 0.010241820768136558,
+  "epoch": 0.011379800853485065,
   "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": 2.563,
       "eval_steps_per_second": 1.282,
       "step": 9
+    },
+    {
+      "epoch": 0.011379800853485065,
+      "grad_norm": 4.849100112915039,
+      "learning_rate": 0.0002,
+      "loss": 1.8402,
+      "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": 559108306501632.0,
+  "total_flos": 621231451668480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null