Upload folder using huggingface_hub

README.md

@@ -1,13 +1,28 @@
 ---
+language:
+- en
 license: apache-2.0
 base_model: bert-base-cased
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: bert-base-rte
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE RTE
+      type: glue
+      args: rte
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.6534296028880866
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,10 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert-base-rte
 
-This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
+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: 0.8855
-- Accuracy: 0.6426
+- Loss: 0.8931
+- Accuracy: 0.6534
 
 ## Model description
 
@@ -37,22 +52,16 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 32
-- eval_batch_size: 64
+- learning_rate: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 4
+- num_epochs: 3.0
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 78   | 0.6587          | 0.6209   |
-| No log        | 2.0   | 156  | 0.6506          | 0.6209   |
-| No log        | 3.0   | 234  | 0.7936          | 0.6209   |
-| No log        | 4.0   | 312  | 0.8855          | 0.6426   |
 
 
 ### Framework versions

all_results.json

@@ -1,14 +1,14 @@
 {
-    "epoch": 4.0,
-    "eval_accuracy": 0.6425992779783394,
-    "eval_loss": 0.8855097889900208,
-    "eval_runtime": 0.5437,
+    "epoch": 3.0,
+    "eval_accuracy": 0.6534296028880866,
+    "eval_loss": 0.8931174278259277,
+    "eval_runtime": 0.5398,
     "eval_samples": 277,
-    "eval_samples_per_second": 509.501,
-    "eval_steps_per_second": 9.197,
-    "train_loss": 0.4733937581380208,
-    "train_runtime": 55.8553,
+    "eval_samples_per_second": 513.144,
+    "eval_steps_per_second": 64.838,
+    "train_loss": 0.4466698230841221,
+    "train_runtime": 55.3452,
     "train_samples": 2490,
-    "train_samples_per_second": 178.318,
-    "train_steps_per_second": 5.586
+    "train_samples_per_second": 134.971,
+    "train_steps_per_second": 16.912
 }

config.json

@@ -5,20 +5,20 @@
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
-  "finetuning_task": "text-classification",
+  "finetuning_task": "rte",
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "id2label": {
-    "0": "0",
-    "1": "1"
+    "0": "entailment",
+    "1": "not_entailment"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "0": 0,
-    "1": 1
+    "entailment": 0,
+    "not_entailment": 1
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,

eval_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 4.0,
-    "eval_accuracy": 0.6425992779783394,
-    "eval_loss": 0.8855097889900208,
-    "eval_runtime": 0.5437,
+    "epoch": 3.0,
+    "eval_accuracy": 0.6534296028880866,
+    "eval_loss": 0.8931174278259277,
+    "eval_runtime": 0.5398,
     "eval_samples": 277,
-    "eval_samples_per_second": 509.501,
-    "eval_steps_per_second": 9.197
+    "eval_samples_per_second": 513.144,
+    "eval_steps_per_second": 64.838
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e55095a9bd6b0291f17f77a6e37283a031ae88f17c4e75b6b4fef0af87803c07
+oid sha256:5eb957533357e839c4f5e5f804e8c67ebe0ac1af1e1972d3059b2db75682392c
 size 433315633

tokenizer.json

@@ -2,13 +2,13 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 256,
+    "max_length": 128,
     "strategy": "LongestFirst",
     "stride": 0
   },
   "padding": {
     "strategy": {
-      "Fixed": 256
+      "Fixed": 128
     },
     "direction": "Right",
     "pad_to_multiple_of": null,

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 4.0,
-    "train_loss": 0.4733937581380208,
-    "train_runtime": 55.8553,
+    "epoch": 3.0,
+    "train_loss": 0.4466698230841221,
+    "train_runtime": 55.3452,
     "train_samples": 2490,
-    "train_samples_per_second": 178.318,
-    "train_steps_per_second": 5.586
+    "train_samples_per_second": 134.971,
+    "train_steps_per_second": 16.912
 }

trainer_state.json

@@ -1,61 +1,31 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.0,
-  "global_step": 312,
+  "epoch": 3.0,
+  "global_step": 936,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 1.0,
-      "eval_accuracy": 0.6209386281588448,
-      "eval_loss": 0.6587319374084473,
-      "eval_runtime": 0.8033,
-      "eval_samples_per_second": 344.835,
-      "eval_steps_per_second": 6.224,
-      "step": 78
-    },
-    {
-      "epoch": 2.0,
-      "eval_accuracy": 0.6209386281588448,
-      "eval_loss": 0.6506237387657166,
-      "eval_runtime": 0.5527,
-      "eval_samples_per_second": 501.182,
-      "eval_steps_per_second": 9.047,
-      "step": 156
+      "epoch": 1.6,
+      "learning_rate": 9.316239316239318e-06,
+      "loss": 0.5885,
+      "step": 500
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.6209386281588448,
-      "eval_loss": 0.7936134934425354,
-      "eval_runtime": 0.5447,
-      "eval_samples_per_second": 508.561,
-      "eval_steps_per_second": 9.18,
-      "step": 234
-    },
-    {
-      "epoch": 4.0,
-      "eval_accuracy": 0.6425992779783394,
-      "eval_loss": 0.8855097889900208,
-      "eval_runtime": 0.546,
-      "eval_samples_per_second": 507.309,
-      "eval_steps_per_second": 9.157,
-      "step": 312
-    },
-    {
-      "epoch": 4.0,
-      "step": 312,
-      "total_flos": 1310293055692800.0,
-      "train_loss": 0.4733937581380208,
-      "train_runtime": 55.8553,
-      "train_samples_per_second": 178.318,
-      "train_steps_per_second": 5.586
+      "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
     }
   ],
-  "max_steps": 312,
-  "num_train_epochs": 4,
-  "total_flos": 1310293055692800.0,
+  "max_steps": 936,
+  "num_train_epochs": 3,
+  "total_flos": 491359895884800.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e8128dd556278968ef3c33738dab886068819d5714ef7b8ee42c914a0fb94ca
-size 4091
+oid sha256:b582dd56e8db56a27f76e88c4936bebc5b86b460beb26ae77a7ff3eda43b8bb4
+size 3963