Upload folder using huggingface_hub

README.md

@@ -1,13 +1,28 @@
 ---
+language:
+- en
 license: apache-2.0
 base_model: bert-large-cased
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: bert-large-boolq
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE BOOLQ
+      type: glue
+      args: boolq
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.7614678899082569
 ---
 
 <!-- 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-large-boolq
 
-This model is a fine-tuned version of [bert-large-cased](https://huggingface.co/bert-large-cased) on an unknown dataset.
+This model is a fine-tuned version of [bert-large-cased](https://huggingface.co/bert-large-cased) on the GLUE BOOLQ dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6633
-- Accuracy: 0.6217
+- Loss: 1.4013
+- Accuracy: 0.7615
 
 ## Model description
 
@@ -37,24 +52,16 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
+- learning_rate: 2e-05
 - train_batch_size: 16
-- eval_batch_size: 32
+- eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 8
-- total_train_batch_size: 128
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 4
+- num_epochs: 5.0
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 0.99  | 73   | 0.6711          | 0.6217   |
-| No log        | 1.99  | 147  | 0.6679          | 0.6217   |
-| No log        | 3.0   | 221  | 0.6636          | 0.6217   |
-| No log        | 3.96  | 292  | 0.6633          | 0.6217   |
 
 
 ### Framework versions

all_results.json

@@ -1,14 +1,14 @@
 {
-    "epoch": 3.96,
-    "eval_accuracy": 0.6217125382262997,
-    "eval_loss": 0.6632964015007019,
-    "eval_runtime": 18.4327,
+    "epoch": 5.0,
+    "eval_accuracy": 0.7614678899082569,
+    "eval_loss": 1.4013047218322754,
+    "eval_runtime": 18.9743,
     "eval_samples": 3270,
-    "eval_samples_per_second": 177.402,
-    "eval_steps_per_second": 5.588,
-    "train_loss": 0.6762518686790989,
-    "train_runtime": 733.7763,
+    "eval_samples_per_second": 172.338,
+    "eval_steps_per_second": 21.555,
+    "train_loss": 0.2978504161511437,
+    "train_runtime": 903.0769,
     "train_samples": 9427,
-    "train_samples_per_second": 51.389,
-    "train_steps_per_second": 0.398
+    "train_samples_per_second": 52.194,
+    "train_steps_per_second": 3.267
 }

config.json

@@ -6,20 +6,20 @@
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
   "directionality": "bidi",
-  "finetuning_task": "text-classification",
+  "finetuning_task": "boolq",
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 1024,
   "id2label": {
-    "0": "0",
-    "1": "1"
+    "0": "False",
+    "1": "True"
   },
   "initializer_range": 0.02,
   "intermediate_size": 4096,
   "label2id": {
-    "0": 0,
-    "1": 1
+    "False": 0,
+    "True": 1
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,

eval_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 3.96,
-    "eval_accuracy": 0.6217125382262997,
-    "eval_loss": 0.6632964015007019,
-    "eval_runtime": 18.4327,
+    "epoch": 5.0,
+    "eval_accuracy": 0.7614678899082569,
+    "eval_loss": 1.4013047218322754,
+    "eval_runtime": 18.9743,
     "eval_samples": 3270,
-    "eval_samples_per_second": 177.402,
-    "eval_steps_per_second": 5.588
+    "eval_samples_per_second": 172.338,
+    "eval_steps_per_second": 21.555
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e16c57f4a155777dd383d4dedf99bc49509e95c50dc87c1bd10019db0a6d452
+oid sha256:f0ec95a4b3937605fad0b985e01db5f4aa0bb926328fe878000eb9136e2fda27
 size 1334459697

tokenizer.json

@@ -2,13 +2,13 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 512,
+    "max_length": 128,
     "strategy": "LongestFirst",
     "stride": 0
   },
   "padding": {
     "strategy": {
-      "Fixed": 512
+      "Fixed": 128
     },
     "direction": "Right",
     "pad_to_multiple_of": null,

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.96,
-    "train_loss": 0.6762518686790989,
-    "train_runtime": 733.7763,
+    "epoch": 5.0,
+    "train_loss": 0.2978504161511437,
+    "train_runtime": 903.0769,
     "train_samples": 9427,
-    "train_samples_per_second": 51.389,
-    "train_steps_per_second": 0.398
+    "train_samples_per_second": 52.194,
+    "train_steps_per_second": 3.267
 }

trainer_state.json

@@ -1,61 +1,55 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.959322033898305,
-  "global_step": 292,
+  "epoch": 5.0,
+  "global_step": 2950,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.99,
-      "eval_accuracy": 0.6217125382262997,
-      "eval_loss": 0.6710952520370483,
-      "eval_runtime": 18.6871,
-      "eval_samples_per_second": 174.987,
-      "eval_steps_per_second": 5.512,
-      "step": 73
+      "epoch": 0.85,
+      "learning_rate": 1.6610169491525424e-05,
+      "loss": 0.6459,
+      "step": 500
     },
     {
-      "epoch": 1.99,
-      "eval_accuracy": 0.6217125382262997,
-      "eval_loss": 0.667921781539917,
-      "eval_runtime": 18.6896,
-      "eval_samples_per_second": 174.964,
-      "eval_steps_per_second": 5.511,
-      "step": 147
+      "epoch": 1.69,
+      "learning_rate": 1.3220338983050848e-05,
+      "loss": 0.4886,
+      "step": 1000
     },
     {
-      "epoch": 3.0,
-      "eval_accuracy": 0.6217125382262997,
-      "eval_loss": 0.6635896563529968,
-      "eval_runtime": 18.7272,
-      "eval_samples_per_second": 174.612,
-      "eval_steps_per_second": 5.5,
-      "step": 221
+      "epoch": 2.54,
+      "learning_rate": 9.830508474576272e-06,
+      "loss": 0.292,
+      "step": 1500
     },
     {
-      "epoch": 3.96,
-      "eval_accuracy": 0.6217125382262997,
-      "eval_loss": 0.6632964015007019,
-      "eval_runtime": 18.6887,
-      "eval_samples_per_second": 174.972,
-      "eval_steps_per_second": 5.511,
-      "step": 292
+      "epoch": 3.39,
+      "learning_rate": 6.440677966101695e-06,
+      "loss": 0.1704,
+      "step": 2000
     },
     {
-      "epoch": 3.96,
-      "step": 292,
-      "total_flos": 3.4795521312577536e+16,
-      "train_loss": 0.6762518686790989,
-      "train_runtime": 733.7763,
-      "train_samples_per_second": 51.389,
-      "train_steps_per_second": 0.398
+      "epoch": 4.24,
+      "learning_rate": 3.0508474576271192e-06,
+      "loss": 0.1074,
+      "step": 2500
+    },
+    {
+      "epoch": 5.0,
+      "step": 2950,
+      "total_flos": 1.098164620261632e+16,
+      "train_loss": 0.2978504161511437,
+      "train_runtime": 903.0769,
+      "train_samples_per_second": 52.194,
+      "train_steps_per_second": 3.267
     }
   ],
-  "max_steps": 292,
-  "num_train_epochs": 4,
-  "total_flos": 3.4795521312577536e+16,
+  "max_steps": 2950,
+  "num_train_epochs": 5,
+  "total_flos": 1.098164620261632e+16,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a29dcc1637f7b320c16da7cc37c06b809c9b470839a06b41f38e4bbdbbb46bbf
-size 4155
+oid sha256:533f3a1d23e99ef6bafd35a0187598e54d91a38adf59eea1381eac16b380fe56
+size 3963