Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a9867f99c80185e1b8d0dfbd9cde47afb3cd72d5abadb57ea7445d0a73daca2
+oid sha256:1cc7b9a48572694fd3b1c4f08ce5b23be1097c9f79ab4aee497359e8137b0686
 size 8077608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4f4fe80c056e18bd84899e1b326f90a753a0fc750281991ffdfe594fab53f28
+oid sha256:326973a7f5335b6a81b4d250785e9211063c2a600d8fc4cfe6388327d1a42121
 size 4052500

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab36c7e1ed0a04946d799983c3de2cbb363f87eb672e17b4cf805b9ebef0c78d
+oid sha256:2e06208607e28e2ca3d8d2d5adf6a16d90b1f9a8456b6f8f4edf65f767336fe4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0036,
+  "epoch": 0.004,
   "eval_steps": 500,
-  "global_step": 180,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -70,6 +70,13 @@
       "learning_rate": 9e-06,
       "loss": 4.6848,
       "step": 180
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 289.0603332519531,
+      "learning_rate": 9.999999999999999e-06,
+      "loss": 4.6474,
+      "step": 200
     }
   ],
   "logging_steps": 20,
@@ -77,7 +84,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 60420873019392.0,
+  "total_flos": 67385272713216.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null