Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c33f74d3b138e8944845a779da9ad96cf1d333185e65c553dd45de2fb97d2a7
+oid sha256:b0a1b54b6cbdfac4c66c79224fd847e51ebd50d0a9e0441c662c19701c0c26e5
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11c69ba618339223ac0ebfd513e9e5e95296e38310ced5b8eaf32e4502502a85
+oid sha256:dbd6b1c67f371167aba9860c5a33921cc292038bbefac9ffcad9773441764f25
 size 18810036

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd29b8b53e00d3bdf89a9e8d526fd650f354f055e58808e03fc1e049fea8124b
+oid sha256:eb55122e8fa4b1f5e367d7cd58f23f40898deb1b0fab7963e45bd052524282e8
 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": 0.0004523465477162782,
+  "epoch": 0.0005026072752403091,
   "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": 4.491,
       "eval_steps_per_second": 2.246,
       "step": 9
+    },
+    {
+      "epoch": 0.0005026072752403091,
+      "grad_norm": 2.020665407180786,
+      "learning_rate": 0.0002,
+      "loss": 2.2747,
+      "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": 324429435371520.0,
+  "total_flos": 360477150412800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null