Training in progress, step 800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2b7f6110bb5537c57471d720470eeef2d1e761009836dc183221541827c78da
+oid sha256:72477bdfa8af67221f7d01002bbc156d50ef30b1de2de21dc531ab3def9e1785
 size 4517152

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96a591e605f4fb0cead83d13658f176119d16c7bd8f8adcbef85cd43a90b583e
+oid sha256:bbb535d6b4d4cab97584221468627230eaa5e390096cbfba38dbcc77969f61be
 size 9085370

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:905ba6fa7d85716f5111068789bdf76b311e8746b501d15d49f74e90dcb65263
+oid sha256:235c9e9ddad0793006a4e184928cbbc1ef2c10a724f7ea2ed9159889a224424b
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c540a3f8578d73f63b431f981bbf69c1fb2dc34029a967fe9d3aa36cf848765
+oid sha256:52d9c053f828b4b4e7b8b5f67be783f74a1110e2609dcc7af7743fb825eb323c
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6be3683c9e444f0c7ada5498d1c14721fda0673bd6f85acfb0baca9048055cef
+oid sha256:2449f226ad43587a7b6284ca578c5122a86d46998334ad1787cb741cb9547ccd
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.865265760197775,
+  "epoch": 0.9888751545117429,
   "eval_steps": 500,
-  "global_step": 700,
+  "global_step": 800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -169,6 +169,27 @@
       "learning_rate": 3.267457180500659e-05,
       "loss": 0.2053,
       "step": 690
+    },
+    {
+      "epoch": 0.8899876390605687,
+      "grad_norm": 0.2570663392543793,
+      "learning_rate": 2.476943346508564e-05,
+      "loss": 0.209,
+      "step": 720
+    },
+    {
+      "epoch": 0.927070457354759,
+      "grad_norm": 0.2891826331615448,
+      "learning_rate": 1.6864295125164693e-05,
+      "loss": 0.2062,
+      "step": 750
+    },
+    {
+      "epoch": 0.9641532756489494,
+      "grad_norm": 0.2695741355419159,
+      "learning_rate": 8.959156785243742e-06,
+      "loss": 0.1892,
+      "step": 780
     }
   ],
   "logging_steps": 30,
@@ -188,7 +209,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8908150564454400.0,
+  "total_flos": 1.01807435022336e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null