Training in progress, step 220, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cc7b9a48572694fd3b1c4f08ce5b23be1097c9f79ab4aee497359e8137b0686
+oid sha256:75626c5f2e0f8aaab8ceadc55f0c38d2b548da8bc191653637ca455fbdd88eb2
 size 8077608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:326973a7f5335b6a81b4d250785e9211063c2a600d8fc4cfe6388327d1a42121
+oid sha256:ad74caba41e61db43e7c9423a4d998393851928b64a5ec7fb81bafb5e98d1ecd
 size 4052500

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e06208607e28e2ca3d8d2d5adf6a16d90b1f9a8456b6f8f4edf65f767336fe4
+oid sha256:5be14051bc6f4cf47091c382526d0b0c0e575985613375394c26c4e042510c6f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004,
+  "epoch": 0.0044,
   "eval_steps": 500,
-  "global_step": 200,
+  "global_step": 220,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -77,6 +77,13 @@
       "learning_rate": 9.999999999999999e-06,
       "loss": 4.6474,
       "step": 200
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 69.93185424804688,
+      "learning_rate": 1.1e-05,
+      "loss": 4.9724,
+      "step": 220
     }
   ],
   "logging_steps": 20,
@@ -84,7 +91,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 67385272713216.0,
+  "total_flos": 72982980575232.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null