Update model

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa425935c7018018ef1120dd8f73ab99eacc91ff5b8d0943beb213c4d69f1e9a
+oid sha256:87b79b24d553e756dab9a8f94eef80974841a04f06f9fa5655cdf270676cd982
 size 242070267

trainer_state.json

@@ -2,36 +2,42 @@
   "best_metric": null,
   "best_model_checkpoint": null,
   "epoch": 5.0,
-  "global_step": 1440,
+  "global_step": 1565,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 1.74,
-      "learning_rate": 3.263888888888889e-05,
-      "loss": 0.8294,
+      "epoch": 1.6,
+      "learning_rate": 3.402555910543131e-05,
+      "loss": 0.8327,
       "step": 500
     },
     {
-      "epoch": 3.47,
-      "learning_rate": 1.527777777777778e-05,
-      "loss": 0.0362,
+      "epoch": 3.19,
+      "learning_rate": 1.805111821086262e-05,
+      "loss": 0.0413,
       "step": 1000
     },
+    {
+      "epoch": 4.79,
+      "learning_rate": 2.0766773162939296e-06,
+      "loss": 0.0192,
+      "step": 1500
+    },
     {
       "epoch": 5.0,
-      "step": 1440,
-      "total_flos": 38943546015744.0,
-      "train_loss": 0.3061259587605794,
-      "train_runtime": 100.4467,
-      "train_samples_per_second": 57.244,
-      "train_steps_per_second": 14.336
+      "step": 1565,
+      "total_flos": 42196507361280.0,
+      "train_loss": 0.2860380729547324,
+      "train_runtime": 110.266,
+      "train_samples_per_second": 56.681,
+      "train_steps_per_second": 14.193
     }
   ],
-  "max_steps": 1440,
+  "max_steps": 1565,
   "num_train_epochs": 5,
-  "total_flos": 38943546015744.0,
+  "total_flos": 42196507361280.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:898304cdeaa3627998b119e592b940bc31f4be6f0eddfe43583a3093a471bb09
+oid sha256:e4a90ffcb914c1405c51f533a1e48594cb9a0b5676ef8ad519c8c88396934fc6
 size 2991