Upload folder using huggingface_hub

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.6534296028880866
+      value: 0.6714801444043321
 ---
 
 <!-- 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-base-cased](https://huggingface.co/bert-base-cased) on the GLUE RTE dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8931
-- Accuracy: 0.6534
+- Loss: 1.1771
+- Accuracy: 0.6715
 
 ## Model description
 
@@ -53,12 +53,12 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 8
+- 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": 0.6534296028880866,
-    "eval_loss": 0.8931174278259277,
-    "eval_runtime": 0.5398,
+    "epoch": 5.0,
+    "eval_accuracy": 0.6714801444043321,
+    "eval_loss": 1.17707359790802,
+    "eval_runtime": 0.412,
     "eval_samples": 277,
-    "eval_samples_per_second": 513.144,
-    "eval_steps_per_second": 64.838,
-    "train_loss": 0.4466698230841221,
-    "train_runtime": 55.3452,
+    "eval_samples_per_second": 672.332,
+    "eval_steps_per_second": 84.952,
+    "train_loss": 0.39309821984706783,
+    "train_runtime": 41.8687,
     "train_samples": 2490,
-    "train_samples_per_second": 134.971,
-    "train_steps_per_second": 16.912
+    "train_samples_per_second": 297.358,
+    "train_steps_per_second": 18.63
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 3.0,
-    "eval_accuracy": 0.6534296028880866,
-    "eval_loss": 0.8931174278259277,
-    "eval_runtime": 0.5398,
+    "epoch": 5.0,
+    "eval_accuracy": 0.6714801444043321,
+    "eval_loss": 1.17707359790802,
+    "eval_runtime": 0.412,
     "eval_samples": 277,
-    "eval_samples_per_second": 513.144,
-    "eval_steps_per_second": 64.838
+    "eval_samples_per_second": 672.332,
+    "eval_steps_per_second": 84.952
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eb957533357e839c4f5e5f804e8c67ebe0ac1af1e1972d3059b2db75682392c
+oid sha256:16356d06adba81986ceed99f04f2450631db4ecebd4a4b724af40ab3a0fffc16
 size 433315633

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.0,
-    "train_loss": 0.4466698230841221,
-    "train_runtime": 55.3452,
+    "epoch": 5.0,
+    "train_loss": 0.39309821984706783,
+    "train_runtime": 41.8687,
     "train_samples": 2490,
-    "train_samples_per_second": 134.971,
-    "train_steps_per_second": 16.912
+    "train_samples_per_second": 297.358,
+    "train_steps_per_second": 18.63
 }

trainer_state.json

@@ -1,31 +1,31 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.0,
-  "global_step": 936,
+  "epoch": 5.0,
+  "global_step": 780,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 1.6,
-      "learning_rate": 9.316239316239318e-06,
-      "loss": 0.5885,
+      "epoch": 3.21,
+      "learning_rate": 7.230769230769231e-06,
+      "loss": 0.5104,
       "step": 500
     },
     {
-      "epoch": 3.0,
-      "step": 936,
-      "total_flos": 491359895884800.0,
-      "train_loss": 0.4466698230841221,
-      "train_runtime": 55.3452,
-      "train_samples_per_second": 134.971,
-      "train_steps_per_second": 16.912
+      "epoch": 5.0,
+      "step": 780,
+      "total_flos": 818933159808000.0,
+      "train_loss": 0.39309821984706783,
+      "train_runtime": 41.8687,
+      "train_samples_per_second": 297.358,
+      "train_steps_per_second": 18.63
     }
   ],
-  "max_steps": 936,
-  "num_train_epochs": 3,
-  "total_flos": 491359895884800.0,
+  "max_steps": 780,
+  "num_train_epochs": 5,
+  "total_flos": 818933159808000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b582dd56e8db56a27f76e88c4936bebc5b86b460beb26ae77a7ff3eda43b8bb4
+oid sha256:e11f9ae603920249b49f55e6cff82db44494674ed95393466630e127f231159b
 size 3963