Upload 8 files

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2b2b4d3e8b3ca0710d7da08763dd08c9fc1b6c9025b455de35158b306e28224
-size 686681861
+oid sha256:b35b770d8d9a1d972e1ca4150bc7db5473aa0d4a013a2b6da74180a3868e4824
+size 686682245

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ebed1c9c75137b486f7f2940de8644ac13858c1d6a8d3695a6a51065b153c29
+oid sha256:18c71cd7270dbc3467f6585890ab427ab26e113ba536e770b0a3e3f985666441
 size 347081849

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:066b0a5d1c6a4b9d7d21cbb83f91a0857780e54f0c0d79887ffbc027746303b7
+oid sha256:7ffe9257f4b5f6e7b196028f804debb7e03c6688f35197b7c41db7f1d92bb153
 size 14639

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f0539d160c7887cdd2d15e84b70d756c48293cc6e18cf2a2dcdbf254b4cb7de
+oid sha256:314e7fcfa86bd8b2926804a8e8c2a2f170604f936fe430e459b9b1e7c4ade27f
 size 627

trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.03954802259887,
-  "global_step": 40000,
+  "epoch": 22.598870056497177,
+  "global_step": 100000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -48,11 +48,47 @@
       "learning_rate": 7.740112994350283e-06,
       "loss": 0.9305,
       "step": 40000
+    },
+    {
+      "epoch": 11.3,
+      "learning_rate": 7.175141242937854e-06,
+      "loss": 0.8309,
+      "step": 50000
+    },
+    {
+      "epoch": 13.56,
+      "learning_rate": 6.610169491525424e-06,
+      "loss": 0.7535,
+      "step": 60000
+    },
+    {
+      "epoch": 15.82,
+      "learning_rate": 6.045197740112995e-06,
+      "loss": 0.69,
+      "step": 70000
+    },
+    {
+      "epoch": 18.08,
+      "learning_rate": 5.480225988700565e-06,
+      "loss": 0.6365,
+      "step": 80000
+    },
+    {
+      "epoch": 20.34,
+      "learning_rate": 4.915254237288136e-06,
+      "loss": 0.5881,
+      "step": 90000
+    },
+    {
+      "epoch": 22.6,
+      "learning_rate": 4.350282485875706e-06,
+      "loss": 0.5565,
+      "step": 100000
     }
   ],
   "max_steps": 177000,
   "num_train_epochs": 40,
-  "total_flos": 4.960009951683527e+19,
+  "total_flos": 1.2400055882758914e+20,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d951a2f5f0efbcf1dae67bc7db374d5cf8dc574b8d82c1b01a1d9990a79c623e
+oid sha256:9bd6820ef696af4fce6112b9d1a81049c7a5afdfb484af20448230d8f0ea1024
 size 3643