Training in progress, step 129, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d33f97db196eb0b1e8327804d651a01bcc2f7895a8e9081aef4157d726e0cde
+oid sha256:ee13e110c1c3af0ec71512dc59558551d08dda01037c1eccbe6b6ef0f72e7315
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9eb9a66fa1c845e83503e63528c25754ea8643d1da2c84c2ee97bc4cda3dfc44
+oid sha256:6a2b7c2f79bc53fe9158a9b6fbab18fc993b84493d9eaa04fc1785f8c01e0335
 size 37430836

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2ae0b51ba660cfa126b7d7abadfdbef3573cd37ac31f298cbc43aa252418d4c
+oid sha256:f6009ae40798aec9a3455348f09e711b9c4dcc5cd20a9ed3080b9d3eb4bbbcea
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3511659807956104,
+  "epoch": 0.35390946502057613,
   "eval_steps": 500,
-  "global_step": 128,
+  "global_step": 129,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -903,6 +903,13 @@
       "learning_rate": 0.0001787878787878788,
       "loss": 1.3335,
       "step": 128
+    },
+    {
+      "epoch": 0.35390946502057613,
+      "grad_norm": 0.16444697976112366,
+      "learning_rate": 0.00017803030303030303,
+      "loss": 1.3234,
+      "step": 129
     }
   ],
   "logging_steps": 1,
@@ -922,7 +929,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5897480333396787e+17,
+  "total_flos": 1.6023428209154458e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null