loss 0.8

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51d27d20cdde998cb1d88b313cd19178bea36405f49380d07ba2b724e78fa381
+oid sha256:f47f9dfd4db9c9ec151a63abad536764855bc77ae7c5b51d92a7ac5356d68ac7
 size 1376950965

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:358ce931f5e26507229d83c9429320451d024717f864d4d6a135d52e15e07de0
+oid sha256:e18c81df99acab8af427dd3790e53aeb09b6ade90fb6de29bdb78209b43d114b
 size 688496379

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f98d89e1ac6e6857c68319b952f8bec21273f15b70b7b67a45964d2da0dc0b09
+oid sha256:da8a2f50723c6317cb8a013b2809dff53084c39ff9282e5af6824bf995015112
 size 14503

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0258a45a7fb992ebe682d4855747405a18c558ae88a1f131c2aa8480c9179b68
+oid sha256:23b550aa2fbfa2b125c031925d9d10c08ba2222b1d741f4334fc52524cc99d50
 size 623

trainer_state.json

@@ -1,94 +1,136 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.43444025088924487,
-  "global_step": 4000,
+  "epoch": 0.21722012544462244,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0006992397089171283,
+      "loss": 0.6909,
+      "step": 100
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0006984794178342565,
+      "loss": 0.7334,
+      "step": 200
+    },
     {
       "epoch": 0.03,
       "learning_rate": 0.0006977191267513849,
-      "loss": 0.8798,
+      "loss": 0.7397,
       "step": 300
     },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0006969588356685131,
+      "loss": 0.7262,
+      "step": 400
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0006961985445856413,
+      "loss": 0.7232,
+      "step": 500
+    },
     {
       "epoch": 0.07,
       "learning_rate": 0.0006954382535027696,
-      "loss": 0.8862,
+      "loss": 0.7182,
       "step": 600
     },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0006946779624198979,
+      "loss": 0.7438,
+      "step": 700
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0006939176713370262,
+      "loss": 0.7207,
+      "step": 800
+    },
     {
       "epoch": 0.1,
       "learning_rate": 0.0006931573802541545,
-      "loss": 0.9028,
+      "loss": 0.7147,
       "step": 900
     },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0006923970891712827,
+      "loss": 0.7547,
+      "step": 1000
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0006916367980884109,
+      "loss": 0.7609,
+      "step": 1100
+    },
     {
       "epoch": 0.13,
       "learning_rate": 0.0006908765070055393,
-      "loss": 0.9063,
+      "loss": 0.7163,
       "step": 1200
     },
     {
-      "epoch": 0.16,
-      "learning_rate": 0.0006885956337569241,
-      "loss": 0.9081,
-      "step": 1500
+      "epoch": 0.14,
+      "learning_rate": 0.0006901162159226675,
+      "loss": 0.7518,
+      "step": 1300
     },
     {
-      "epoch": 0.2,
-      "learning_rate": 0.0006863147605083089,
-      "loss": 0.9512,
-      "step": 1800
+      "epoch": 0.15,
+      "learning_rate": 0.0006893559248397958,
+      "loss": 0.7698,
+      "step": 1400
     },
     {
-      "epoch": 0.23,
-      "learning_rate": 0.0006840338872596937,
-      "loss": 0.9233,
-      "step": 2100
-    },
-    {
-      "epoch": 0.26,
-      "learning_rate": 0.0006817530140110785,
-      "loss": 0.9114,
-      "step": 2400
+      "epoch": 0.16,
+      "learning_rate": 0.0006885956337569241,
+      "loss": 0.7327,
+      "step": 1500
     },
     {
-      "epoch": 0.29,
-      "learning_rate": 0.0006794721407624634,
-      "loss": 0.8985,
-      "step": 2700
+      "epoch": 0.17,
+      "learning_rate": 0.0006878353426740524,
+      "loss": 0.7871,
+      "step": 1600
     },
     {
-      "epoch": 0.33,
-      "learning_rate": 0.0006771912675138482,
-      "loss": 0.9266,
-      "step": 3000
+      "epoch": 0.18,
+      "learning_rate": 0.0006870750515911806,
+      "loss": 0.7908,
+      "step": 1700
     },
     {
-      "epoch": 0.36,
-      "learning_rate": 0.000674910394265233,
-      "loss": 0.9169,
-      "step": 3300
+      "epoch": 0.2,
+      "learning_rate": 0.0006863147605083089,
+      "loss": 0.7646,
+      "step": 1800
     },
     {
-      "epoch": 0.39,
-      "learning_rate": 0.0006726295210166178,
-      "loss": 0.9532,
-      "step": 3600
+      "epoch": 0.21,
+      "learning_rate": 0.0006855544694254371,
+      "loss": 0.7677,
+      "step": 1900
     },
     {
-      "epoch": 0.42,
-      "learning_rate": 0.0006703486477680026,
-      "loss": 0.9537,
-      "step": 3900
+      "epoch": 0.22,
+      "learning_rate": 0.0006847941783425654,
+      "loss": 0.7533,
+      "step": 2000
     }
   ],
   "max_steps": 92070,
   "num_train_epochs": 10,
-  "total_flos": 8211242077913088.0,
+  "total_flos": 4097763812966400.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0ae2507096b2b962ccfa952ca3d392bf4282c95f702a03d6e7859bd494148b1
+oid sha256:4bf29105b2f1e653c8eadf07726bc244d198013decfeabceefd5896a51895501
 size 2607