Training in progress, step 3360, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cb99fa64546939c539783d29a25c42425044ee987ecc3e5696b8534c4e9f345
+oid sha256:c1698d0b9850198369e888fcfaf13d37be26de99003ada18e391207f1b5ff228
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd641e98929b8b276a8de167087ef9ff9d89754bf78fd580019c0c5c609853d1
+oid sha256:d8fe17bfb83911cb927d541d4a34d80b626c32a1c080df866cc26b5c30ec4ff1
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8da95d53fc7692aea2c9104930a96fc9ba7cf5e6583572212fa22dac8a3dfc0b
+oid sha256:7db2bdbe63109eacd97a36be96f1c1369969403fe38eb6536eaee017f63bad8f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95230278efb9ecdcab5e159a83a7f79b4af787377ae2ff1f8e2e651daab268eb
+oid sha256:5d7c2d8201e8b73967831cd725d7a9e1ee970c8f0d997a055abf4549ddfa7435
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2672,
+  "epoch": 0.2688,
   "eval_steps": 500,
-  "global_step": 3340,
+  "global_step": 3360,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1176,6 +1176,13 @@
       "learning_rate": 2.8547481435507382e-05,
       "loss": 3.5292,
       "step": 3340
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 23.902685165405273,
+      "learning_rate": 2.852655480925828e-05,
+      "loss": 3.5195,
+      "step": 3360
     }
   ],
   "logging_steps": 20,
@@ -1183,7 +1190,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 7927089491214336.0,
+  "total_flos": 7983843719970816.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null