Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:451a62d540f161120366f4f42a21842620863d0faf16576ea041beadd537d71f
+oid sha256:2a48834523f60b3731d50b6d2a031ecfe67f2c2e33fffeb5766be07ed089e31c
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0880603aeac0624e50d32286ffef1384332fa6056c1e0570d2371d2aeab504d3
+oid sha256:84fd419623450a68e3ad756d5508a248b05021085b3309ba8ba84be436050dfc
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9924210ab879c904501d7849ac30798dabb2a3e05d515d30a640be5f23f0e2a
+oid sha256:db0f9f65aa0cd93c40e0a377929d07ce4a0a0cdcbc01e842e3541452a536cc16
 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": 0.03293687099725526,
+  "epoch": 0.036596523330283626,
   "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": 14.668,
       "eval_steps_per_second": 7.398,
       "step": 9
+    },
+    {
+      "epoch": 0.036596523330283626,
+      "grad_norm": 0.46412548422813416,
+      "learning_rate": 0.0002,
+      "loss": 1.7856,
+      "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": 3641136245637120.0,
+  "total_flos": 4195222196060160.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null