Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b945bed4e9b50189d80389328cb4366660fa960bd834e45a1bad1c55d78956f9
+oid sha256:09a674ef67b8431e1c40ee717fdeffa6cc362f9cab9fc8af261b0268bf69ebdb
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:154a09bdf67e4563553a2c20510c24113da8a86dff2d5aa4276e81f3358e266f
+oid sha256:773bec851a89357239d41554105a2af9a081d67dc2449f46e6c2d799ff221f1b
 size 23159546

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b5fc63c96f74081eb7d3ebe7cd62cb476ba8f9a3d76715567e25f7a6ba36f4b
+oid sha256:80b62f4a986c68ed81a5aaf95500c8529ea691e3727b514836155fb550f14da0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2966808826256258,
+  "epoch": 0.37085110328203225,
   "eval_steps": 500,
-  "global_step": 400,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -35,6 +35,13 @@
       "learning_rate": 0.00017281409538757883,
       "loss": 2.5387,
       "step": 400
+    },
+    {
+      "epoch": 0.37085110328203225,
+      "grad_norm": 0.685387909412384,
+      "learning_rate": 0.0001536591729006453,
+      "loss": 2.4793,
+      "step": 500
     }
   ],
   "logging_steps": 100,
@@ -54,7 +61,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.548356111302656e+17,
+  "total_flos": 1.93544513912832e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null