Upload folder using huggingface_hub

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.703971119133574
+      value: 0.7111913357400722
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-large-cased](https://huggingface.co/bert-large-cased) on the GLUE RTE dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7109
-- Accuracy: 0.7040
+- Loss: 1.4630
+- Accuracy: 0.7112
 
 ## Model description
 
@@ -53,12 +53,12 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 32
+- train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3.0
+- num_epochs: 5.0
 
 ### Training results
 

all_results.json

@@ -1,14 +1,14 @@
 {
-    "epoch": 3.0,
-    "eval_accuracy": 0.703971119133574,
-    "eval_loss": 0.7108999490737915,
-    "eval_runtime": 1.628,
+    "epoch": 5.0,
+    "eval_accuracy": 0.7111913357400722,
+    "eval_loss": 1.4629547595977783,
+    "eval_runtime": 0.7868,
     "eval_samples": 277,
-    "eval_samples_per_second": 170.149,
-    "eval_steps_per_second": 21.499,
-    "train_loss": 0.4925964877136752,
-    "train_runtime": 120.7223,
+    "eval_samples_per_second": 352.04,
+    "eval_steps_per_second": 44.482,
+    "train_loss": 0.29059823354085285,
+    "train_runtime": 86.2993,
     "train_samples": 2490,
-    "train_samples_per_second": 61.878,
-    "train_steps_per_second": 1.938
+    "train_samples_per_second": 144.265,
+    "train_steps_per_second": 9.038
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 3.0,
-    "eval_accuracy": 0.703971119133574,
-    "eval_loss": 0.7108999490737915,
-    "eval_runtime": 1.628,
+    "epoch": 5.0,
+    "eval_accuracy": 0.7111913357400722,
+    "eval_loss": 1.4629547595977783,
+    "eval_runtime": 0.7868,
     "eval_samples": 277,
-    "eval_samples_per_second": 170.149,
-    "eval_steps_per_second": 21.499
+    "eval_samples_per_second": 352.04,
+    "eval_steps_per_second": 44.482
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ad0b31d43a528f235b2d0a53058a6d07df9d46ea4b8bf48a275a4580cd660c9
+oid sha256:1bd302f63dd79574574174160d4dfb43d6baf76736ccd987db986ab26670406f
 size 1334459697

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.0,
-    "train_loss": 0.4925964877136752,
-    "train_runtime": 120.7223,
+    "epoch": 5.0,
+    "train_loss": 0.29059823354085285,
+    "train_runtime": 86.2993,
     "train_samples": 2490,
-    "train_samples_per_second": 61.878,
-    "train_steps_per_second": 1.938
+    "train_samples_per_second": 144.265,
+    "train_steps_per_second": 9.038
 }

trainer_state.json

@@ -1,25 +1,31 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.0,
-  "global_step": 234,
+  "epoch": 5.0,
+  "global_step": 780,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 3.0,
-      "step": 234,
-      "total_flos": 1740381821015040.0,
-      "train_loss": 0.4925964877136752,
-      "train_runtime": 120.7223,
-      "train_samples_per_second": 61.878,
-      "train_steps_per_second": 1.938
+      "epoch": 3.21,
+      "learning_rate": 7.256410256410257e-06,
+      "loss": 0.4017,
+      "step": 500
+    },
+    {
+      "epoch": 5.0,
+      "step": 780,
+      "total_flos": 2900636368358400.0,
+      "train_loss": 0.29059823354085285,
+      "train_runtime": 86.2993,
+      "train_samples_per_second": 144.265,
+      "train_steps_per_second": 9.038
     }
   ],
-  "max_steps": 234,
-  "num_train_epochs": 3,
-  "total_flos": 1740381821015040.0,
+  "max_steps": 780,
+  "num_train_epochs": 5,
+  "total_flos": 2900636368358400.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4399aaeb798913062f8219ace308d12474eafbe83a8cc2e0ee9fb2296004ef7
+oid sha256:fa4fa4a4306e4564d195ad7d5668dae861e97971595a52cb9b0aac9538125f04
 size 3963