Training in progress, step 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21f7ffd81bc53e191d767f4e804a1995310475a7321c171efc1add12faeb7509
+oid sha256:2c2c77e1faef5360edb86fdd675b75189f7974b272c230d2370205fe561086d7
 size 60010048

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e92e42e4ba47eea1bbe1506d2565068cf87b8e515904aab82f00b93daa51a914
+oid sha256:a19147b8c5bee718d325cc69e052a9d7b1c02ff81e02f720da3c271048875c83
 size 30427860

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f8eaf268f1a2b265d04088454c5c83f84442a721cf317eb600d0b02e73b345f
+oid sha256:975a394e3f3cbbd67dfc86dc023c0bf94ad366845e30e55347ecdc023963d2d7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.035116598079561044,
+  "epoch": 0.03950617283950617,
   "eval_steps": 500,
-  "global_step": 16,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -119,6 +119,20 @@
       "learning_rate": 8.000000000000001e-06,
       "loss": 2.0443,
       "step": 16
+    },
+    {
+      "epoch": 0.03731138545953361,
+      "grad_norm": 0.5522028207778931,
+      "learning_rate": 8.500000000000002e-06,
+      "loss": 2.1187,
+      "step": 17
+    },
+    {
+      "epoch": 0.03950617283950617,
+      "grad_norm": 0.5474849343299866,
+      "learning_rate": 9e-06,
+      "loss": 2.1184,
+      "step": 18
     }
   ],
   "logging_steps": 1,
@@ -138,7 +152,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.946716325830656e+16,
+  "total_flos": 2.186071270264013e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null