Training in progress, step 180, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e7a69d1ce9bf6667ee18a34b80700a6f021f75a39b502df24c940c33a248326
+oid sha256:7c866b681847079f3b9029f07492db9880da802a14740ef308276cbc48af7029
 size 4725640

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ffb5918dd4da0749e42b25da719356fb52e940925d48e3da3d388b6dd555958
+oid sha256:48b0feae9377bfd2ee4adc15c04b256d703f0f8cfe89d645ffa2f876e8acdd71
 size 2423738

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a31f9a55784a31138651f313f71945c76da95fef110e5c73e597379ef000db0
+oid sha256:5818eed0ee5844cae7078ebbf0cd36b392212601ec7951f21f30f58ec6711de0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a68cf1fb54f09702759cafde2c8a6d257515638ebe6138585b95a632f1a49e6
+oid sha256:10bc8edf4e1fadab9976453bf48d4affbe0fded7ba378b722041dd8223dc111e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0001245204018895971,
+  "epoch": 0.00014008545212579673,
   "eval_steps": 500,
-  "global_step": 160,
+  "global_step": 180,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -63,6 +63,13 @@
       "learning_rate": 2.6500000000000004e-05,
       "loss": 3.16,
       "step": 160
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 5.391817092895508,
+      "learning_rate": 2.9833333333333335e-05,
+      "loss": 3.2489,
+      "step": 180
     }
   ],
   "logging_steps": 20,
@@ -70,7 +77,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 817767151202304.0,
+  "total_flos": 901465913585664.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null