Training in progress, step 3500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a80adce44bfdb009a8a661904d03bfb6e01ae69c7d2f433075c4792085d1441f
+oid sha256:5d574a9cfe44b6a9f1d49919f1d1075af72d4ebae831ed5168457960a110cf96
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e55f749d779476c80df8878539c00ad63f52e0da2be54f4abf3572dde9103a9
+oid sha256:43bdae8cb558222fb1e4b8ab4a8921afca3a24f6302f6ab4eb57e840888a343d
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e8b2089beb77f6eeff2596a9850dbdefb1299610dc7c930f243156d19eb2060
+oid sha256:fd37529ec6267cade7e3edbd0752da2dc70537a327ba7205cdcfdf07532b1f14
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64d404973b811ebcc9b13292a749476771ae070589fa9ceb6e87db812be374d0
+oid sha256:8c9cf56fcd440484564e22fe18b4a309200b45f2e6cb790d1d19c81f6ae46057
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2784,
+  "epoch": 0.28,
   "eval_steps": 500,
-  "global_step": 3480,
+  "global_step": 3500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1225,6 +1225,13 @@
       "learning_rate": 2.8398023208335537e-05,
       "loss": 3.5701,
       "step": 3480
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 29.031347274780273,
+      "learning_rate": 2.8376108064873216e-05,
+      "loss": 3.5228,
+      "step": 3500
     }
   ],
   "logging_steps": 20,
@@ -1232,7 +1239,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 8244716336775168.0,
+  "total_flos": 8289562019266560.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null