Upload 4 files

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63a7666114aead033db3c4c59484cb5f219668929dcac5f9f00d65720bc36198
+oid sha256:1af9751c34e12addc233e136e878c3b1d3f0c10f54c23d7087020d627c6de0f0
 size 14575

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7d30b14c9d1bb58e338f3b52564bc77c8c6f639e2983e13372177453da337a2
+oid sha256:fbc48fb62f9028eecd909bf79fb77b9ab9369250459350d7b2efbfacf61b8bc9
 size 627

trainer_state.json

@@ -1,232 +1,28 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9023913370431644,
-  "global_step": 18000,
+  "epoch": 0.05013285205795358,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.03,
-      "learning_rate": 1.9499674136461627e-05,
-      "loss": 0.1142,
+      "learning_rate": 1e-06,
+      "loss": 0.0101,
       "step": 500
     },
     {
       "epoch": 0.05,
-      "learning_rate": 1.899834561588209e-05,
-      "loss": 0.0585,
+      "learning_rate": 9.742890934334345e-07,
+      "loss": 0.0078,
       "step": 1000
-    },
-    {
-      "epoch": 0.08,
-      "learning_rate": 1.8497017095302553e-05,
-      "loss": 0.0572,
-      "step": 1500
-    },
-    {
-      "epoch": 0.1,
-      "learning_rate": 1.7995688574723017e-05,
-      "loss": 0.053,
-      "step": 2000
-    },
-    {
-      "epoch": 0.13,
-      "learning_rate": 1.749436005414348e-05,
-      "loss": 0.0523,
-      "step": 2500
-    },
-    {
-      "epoch": 0.15,
-      "learning_rate": 1.6993031533563946e-05,
-      "loss": 0.0451,
-      "step": 3000
-    },
-    {
-      "epoch": 0.18,
-      "learning_rate": 1.6492705670025568e-05,
-      "loss": 0.0462,
-      "step": 3500
-    },
-    {
-      "epoch": 0.2,
-      "learning_rate": 1.5991377149446032e-05,
-      "loss": 0.0512,
-      "step": 4000
-    },
-    {
-      "epoch": 0.23,
-      "learning_rate": 1.5490048628866497e-05,
-      "loss": 0.0473,
-      "step": 4500
-    },
-    {
-      "epoch": 0.25,
-      "learning_rate": 1.4988720108286963e-05,
-      "loss": 0.0404,
-      "step": 5000
-    },
-    {
-      "epoch": 0.28,
-      "learning_rate": 1.4487391587707427e-05,
-      "loss": 0.0453,
-      "step": 5500
-    },
-    {
-      "epoch": 0.3,
-      "learning_rate": 1.3986063067127892e-05,
-      "loss": 0.0476,
-      "step": 6000
-    },
-    {
-      "epoch": 0.33,
-      "learning_rate": 1.3484734546548354e-05,
-      "loss": 0.0435,
-      "step": 6500
-    },
-    {
-      "epoch": 0.35,
-      "learning_rate": 1.2983406025968819e-05,
-      "loss": 0.0434,
-      "step": 7000
-    },
-    {
-      "epoch": 0.38,
-      "learning_rate": 1.248308016243044e-05,
-      "loss": 0.0419,
-      "step": 7500
-    },
-    {
-      "epoch": 0.4,
-      "learning_rate": 1.1982754298892064e-05,
-      "loss": 0.0431,
-      "step": 8000
-    },
-    {
-      "epoch": 0.43,
-      "learning_rate": 1.1481425778312529e-05,
-      "loss": 0.0406,
-      "step": 8500
-    },
-    {
-      "epoch": 0.45,
-      "learning_rate": 1.0981099914774151e-05,
-      "loss": 0.0414,
-      "step": 9000
-    },
-    {
-      "epoch": 0.48,
-      "learning_rate": 1.0479771394194615e-05,
-      "loss": 0.0412,
-      "step": 9500
-    },
-    {
-      "epoch": 0.5,
-      "learning_rate": 9.978442873615081e-06,
-      "loss": 0.0436,
-      "step": 10000
-    },
-    {
-      "epoch": 0.53,
-      "learning_rate": 9.477114353035544e-06,
-      "loss": 0.0398,
-      "step": 10500
-    },
-    {
-      "epoch": 0.55,
-      "learning_rate": 8.975785832456009e-06,
-      "loss": 0.0375,
-      "step": 11000
-    },
-    {
-      "epoch": 0.58,
-      "learning_rate": 8.474457311876473e-06,
-      "loss": 0.0393,
-      "step": 11500
-    },
-    {
-      "epoch": 0.6,
-      "learning_rate": 7.974131448338097e-06,
-      "loss": 0.0391,
-      "step": 12000
-    },
-    {
-      "epoch": 0.63,
-      "learning_rate": 7.472802927758561e-06,
-      "loss": 0.0383,
-      "step": 12500
-    },
-    {
-      "epoch": 0.65,
-      "learning_rate": 6.971474407179026e-06,
-      "loss": 0.0391,
-      "step": 13000
-    },
-    {
-      "epoch": 0.68,
-      "learning_rate": 6.470145886599489e-06,
-      "loss": 0.04,
-      "step": 13500
-    },
-    {
-      "epoch": 0.7,
-      "learning_rate": 5.968817366019954e-06,
-      "loss": 0.0412,
-      "step": 14000
-    },
-    {
-      "epoch": 0.73,
-      "learning_rate": 5.467488845440417e-06,
-      "loss": 0.0379,
-      "step": 14500
-    },
-    {
-      "epoch": 0.75,
-      "learning_rate": 4.9661603248608816e-06,
-      "loss": 0.0381,
-      "step": 15000
-    },
-    {
-      "epoch": 0.78,
-      "learning_rate": 4.464831804281346e-06,
-      "loss": 0.0408,
-      "step": 15500
-    },
-    {
-      "epoch": 0.8,
-      "learning_rate": 3.96350328370181e-06,
-      "loss": 0.0329,
-      "step": 16000
-    },
-    {
-      "epoch": 0.83,
-      "learning_rate": 3.462174763122274e-06,
-      "loss": 0.0369,
-      "step": 16500
-    },
-    {
-      "epoch": 0.85,
-      "learning_rate": 2.960846242542739e-06,
-      "loss": 0.0369,
-      "step": 17000
-    },
-    {
-      "epoch": 0.88,
-      "learning_rate": 2.4605203790043617e-06,
-      "loss": 0.0366,
-      "step": 17500
-    },
-    {
-      "epoch": 0.9,
-      "learning_rate": 1.959191858424826e-06,
-      "loss": 0.0365,
-      "step": 18000
     }
   ],
   "max_steps": 19947,
   "num_train_epochs": 1,
-  "total_flos": 3.7889352695808e+16,
+  "total_flos": 2104964038656000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc4907f1e57294ca013af340be8a8019feee701e7aa152ed188876248b129904
+oid sha256:3d00057cc96b36ca9dc0670e718bb61c7032f358c31afe1be22d1b672b365eac
 size 3579