Upload folder using huggingface_hub

README.md

@@ -1,13 +1,30 @@
 ---
+language:
+- en
 license: apache-2.0
 base_model: bert-base-cased
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: bert-base-boolq
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE BOOLQ
+      type: glue
+      config: boolq
+      split: validation
+      args: boolq
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.7097859327217125
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,10 +32,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert-base-boolq
 
-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 BOOLQ dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7001
-- Accuracy: 0.7141
+- Loss: 1.1221
+- Accuracy: 0.7098
 
 ## Model description
 
@@ -37,24 +54,16 @@ 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: 16
+- eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 4
-- 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   | 0.6423          | 0.6107   |
-| No log        | 1.99  | 147  | 0.5651          | 0.7098   |
-| No log        | 3.0   | 221  | 0.6036          | 0.7150   |
-| No log        | 3.96  | 292  | 0.7001          | 0.7141   |
 
 
 ### Framework versions

all_results.json

@@ -1,14 +1,14 @@
 {
-    "epoch": 3.96,
-    "eval_accuracy": 0.7140672782874617,
-    "eval_loss": 0.7000637054443359,
-    "eval_runtime": 10.4472,
+    "epoch": 5.0,
+    "eval_accuracy": 0.7097859327217125,
+    "eval_loss": 1.1220989227294922,
+    "eval_runtime": 6.9032,
     "eval_samples": 3270,
-    "eval_samples_per_second": 313.003,
-    "eval_steps_per_second": 4.977,
-    "train_loss": 0.4717037253183861,
-    "train_runtime": 435.6602,
+    "eval_samples_per_second": 473.694,
+    "eval_steps_per_second": 59.248,
+    "train_loss": 0.37518319857322563,
+    "train_runtime": 326.8151,
     "train_samples": 9427,
-    "train_samples_per_second": 86.554,
-    "train_steps_per_second": 0.67
+    "train_samples_per_second": 144.225,
+    "train_steps_per_second": 9.027
 }

config.json

@@ -5,20 +5,20 @@
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
-  "finetuning_task": "text-classification",
+  "finetuning_task": "boolq",
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "id2label": {
-    "0": "0",
-    "1": "1"
+    "0": "False",
+    "1": "True"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "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": 0.7140672782874617,
-    "eval_loss": 0.7000637054443359,
-    "eval_runtime": 10.4472,
+    "epoch": 5.0,
+    "eval_accuracy": 0.7097859327217125,
+    "eval_loss": 1.1220989227294922,
+    "eval_runtime": 6.9032,
     "eval_samples": 3270,
-    "eval_samples_per_second": 313.003,
-    "eval_steps_per_second": 4.977
+    "eval_samples_per_second": 473.694,
+    "eval_steps_per_second": 59.248
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77a8e44c8ef25e99fb2bfbe132bdb84b7a740f8e689ee788381878b78536a21d
+oid sha256:7e15e0a8f4da13c477a997731321b300c4e67e0affef277108b00b611b47c27d
 size 433315633

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": 0.4717037253183861,
-    "train_runtime": 435.6602,
+    "epoch": 5.0,
+    "train_loss": 0.37518319857322563,
+    "train_runtime": 326.8151,
     "train_samples": 9427,
-    "train_samples_per_second": 86.554,
-    "train_steps_per_second": 0.67
+    "train_samples_per_second": 144.225,
+    "train_steps_per_second": 9.027
 }

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": 0.6107033639143731,
-      "eval_loss": 0.6423391103744507,
-      "eval_runtime": 10.5728,
-      "eval_samples_per_second": 309.284,
-      "eval_steps_per_second": 4.918,
-      "step": 73
+      "epoch": 0.85,
+      "learning_rate": 1.6610169491525424e-05,
+      "loss": 0.6634,
+      "step": 500
     },
     {
-      "epoch": 1.99,
-      "eval_accuracy": 0.7097859327217125,
-      "eval_loss": 0.5650969743728638,
-      "eval_runtime": 10.5393,
-      "eval_samples_per_second": 310.267,
-      "eval_steps_per_second": 4.934,
-      "step": 147
+      "epoch": 1.69,
+      "learning_rate": 1.3220338983050848e-05,
+      "loss": 0.5784,
+      "step": 1000
     },
     {
-      "epoch": 3.0,
-      "eval_accuracy": 0.7149847094801223,
-      "eval_loss": 0.6035652160644531,
-      "eval_runtime": 10.5633,
-      "eval_samples_per_second": 309.563,
-      "eval_steps_per_second": 4.923,
-      "step": 221
+      "epoch": 2.54,
+      "learning_rate": 9.830508474576272e-06,
+      "loss": 0.4113,
+      "step": 1500
     },
     {
-      "epoch": 3.96,
-      "eval_accuracy": 0.7140672782874617,
-      "eval_loss": 0.7000637054443359,
-      "eval_runtime": 10.5393,
-      "eval_samples_per_second": 310.266,
-      "eval_steps_per_second": 4.934,
-      "step": 292
+      "epoch": 3.39,
+      "learning_rate": 6.440677966101695e-06,
+      "loss": 0.2685,
+      "step": 2000
     },
     {
-      "epoch": 3.96,
-      "step": 292,
-      "total_flos": 9823777473976320.0,
-      "train_loss": 0.4717037253183861,
-      "train_runtime": 435.6602,
-      "train_samples_per_second": 86.554,
-      "train_steps_per_second": 0.67
+      "epoch": 4.24,
+      "learning_rate": 3.0508474576271192e-06,
+      "loss": 0.1735,
+      "step": 2500
+    },
+    {
+      "epoch": 5.0,
+      "step": 2950,
+      "total_flos": 3100434898598400.0,
+      "train_loss": 0.37518319857322563,
+      "train_runtime": 326.8151,
+      "train_samples_per_second": 144.225,
+      "train_steps_per_second": 9.027
     }
   ],
-  "max_steps": 292,
-  "num_train_epochs": 4,
-  "total_flos": 9823777473976320.0,
+  "max_steps": 2950,
+  "num_train_epochs": 5,
+  "total_flos": 3100434898598400.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f356c17f13a095454962dd661683f0fd0f3c76a7eba49861e4dae2364f9e86ad
-size 4091
+oid sha256:5c41f5615188e374b7e0a00d54c3c74e42c1c1e8ec7c5c33fbba2a9f0aef5e36
+size 3963