Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c762d4f109ebbab7e0a848c25ed29c06143cf5de761f63a7de7e31bcf593c12
+oid sha256:a8f73aaff6f3cb90a4296c3435b1f927a69a2b4efb6a9cf488824d0419cb57ca
 size 5752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efd2546409f723f7cb4c7d6b486b25bcba5a56566f64729695695cf38d447ce8
+oid sha256:e6bf3308d11624c7cdce3f2182b8fb5346918c24696d869014106dfbd4cdda01
 size 15814

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb04243bb25bf686a4dbec102fd9ca7613ad5c31a6a03dfc0541d4df84930100
+oid sha256:9c4e103f057cbf52631a0f74dec69e271b2b990ec70bac9b6694c66ba4e1959d
 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": 0.0032444124008651765,
+  "epoch": 0.003604902667627974,
   "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": 162.194,
       "eval_steps_per_second": 81.166,
       "step": 9
+    },
+    {
+      "epoch": 0.003604902667627974,
+      "grad_norm": 4.368403824628331e-05,
+      "learning_rate": 0.0002,
+      "loss": 46.0,
+      "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": 338688933888.0,
+  "total_flos": 373553971200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null