Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6163655239d603d59ecf7b2eddcf16a5b1abc9fb2a91e7cd88e75db9d7dc8856
+oid sha256:220da70e8d5b07914aee988a504fa73354acf257e924043667ded82f6b9629b4
 size 108113968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86063e65e350840352404f9dc32c7c6ad8f710e5edcfd435461bbe3cb6b0cce0
+oid sha256:4239d21fbc793877659bcdf9f826c47cc607ec6ee0de58d223d09b486d69e777
 size 55549892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d933810a6d2f34b6deab68d1570f97995617145841c0c90fb7835d50171afe2
+oid sha256:d3729714535361d3da6c603911f3ed24e523c8e6dffe566c724638ee5b65d672
 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": 0.00047130289065772937,
+  "epoch": 0.0005236698785085882,
   "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": 11.123,
       "eval_steps_per_second": 5.562,
       "step": 9
+    },
+    {
+      "epoch": 0.0005236698785085882,
+      "grad_norm": 0.5129334330558777,
+      "learning_rate": 0.0002,
+      "loss": 0.5634,
+      "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": 3694308511186944.0,
+  "total_flos": 4104787234652160.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null