add model

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,79 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- boolq
+metrics:
+- accuracy
+model_index:
+- name: distilbert-base-uncased-boolq
+  results:
+  - task:
+      name: Question Answering
+      type: question-answering
+    dataset:
+      name: boolq
+      type: boolq
+      args: default
+    metric:
+      name: Accuracy
+      type: accuracy
+      value: 0.7314984709480122
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# distilbert-base-uncased-boolq
+
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the boolq dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2071
+- Accuracy: 0.7315
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 16
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 1000
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.6506        | 1.0   | 531  | 0.6075          | 0.6681   |
+| 0.575         | 2.0   | 1062 | 0.5816          | 0.6978   |
+| 0.4397        | 3.0   | 1593 | 0.6137          | 0.7253   |
+| 0.2524        | 4.0   | 2124 | 0.8124          | 0.7466   |
+| 0.126         | 5.0   | 2655 | 1.1437          | 0.7370   |
+
+
+### Framework versions
+
+- Transformers 4.8.2
+- Pytorch 1.8.1+cu111
+- Datasets 1.8.0
+- Tokenizers 0.10.3

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.7314984709480122,
+    "eval_loss": 1.2070553302764893,
+    "eval_runtime": 10.6939,
+    "eval_samples_per_second": 305.782,
+    "eval_steps_per_second": 9.632
+}

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "False",
+    "1": "True"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "False": 0,
+    "True": 1
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "transformers_version": "4.8.2",
+  "vocab_size": 30522
+}

log.log

@@ -0,0 +1,16 @@
+Training dataset length:
+8484
+Validation dataset length:
+943
+Test dataset length:
+3270
+Current performance:
+Eval:
+{'eval_loss': 0.7018890380859375, 'eval_accuracy': 0.40827147401908803, 'eval_runtime': 3.2526, 'eval_samples_per_second': 289.923, 'eval_steps_per_second': 9.223}
+Test:
+{'eval_loss': 0.7028740644454956, 'eval_accuracy': 0.39847094801223243, 'eval_runtime': 10.3848, 'eval_samples_per_second': 314.882, 'eval_steps_per_second': 9.918}
+Training complete performance:
+Eval:
+{'eval_loss': 1.1437411308288574, 'eval_accuracy': 0.7370095440084835, 'eval_runtime': 3.1329, 'eval_samples_per_second': 301.0, 'eval_steps_per_second': 9.576, 'epoch': 5.0}
+Test:
+{'eval_loss': 1.2070553302764893, 'eval_accuracy': 0.7314984709480122, 'eval_runtime': 10.6939, 'eval_samples_per_second': 305.782, 'eval_steps_per_second': 9.632, 'epoch': 5.0}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:364d06f2321d04dbdac461a7b7affdf3c81adb8c2864b7c2a8d663843598e0c4
+size 267863191

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "distilbert-base-uncased", "tokenizer_class": "DistilBertTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.7314984709480122,
+    "eval_loss": 1.2070553302764893,
+    "eval_runtime": 10.6939,
+    "eval_samples_per_second": 305.782,
+    "eval_steps_per_second": 9.632
+}

trainer_state.json

@@ -0,0 +1,118 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "global_step": 2655,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.5e-05,
+      "loss": 0.6506,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6680805938494168,
+      "eval_loss": 0.6074808239936829,
+      "eval_runtime": 3.0467,
+      "eval_samples_per_second": 309.518,
+      "eval_steps_per_second": 9.847,
+      "step": 531
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 5e-05,
+      "loss": 0.575,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6977730646871686,
+      "eval_loss": 0.5816474556922913,
+      "eval_runtime": 3.0782,
+      "eval_samples_per_second": 306.344,
+      "eval_steps_per_second": 9.746,
+      "step": 1062
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 3.489425981873112e-05,
+      "loss": 0.4397,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7253446447507953,
+      "eval_loss": 0.6136603951454163,
+      "eval_runtime": 3.1046,
+      "eval_samples_per_second": 303.739,
+      "eval_steps_per_second": 9.663,
+      "step": 1593
+    },
+    {
+      "epoch": 3.77,
+      "learning_rate": 1.9788519637462235e-05,
+      "loss": 0.2524,
+      "step": 2000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7465535524920467,
+      "eval_loss": 0.8123661279678345,
+      "eval_runtime": 3.1044,
+      "eval_samples_per_second": 303.766,
+      "eval_steps_per_second": 9.664,
+      "step": 2124
+    },
+    {
+      "epoch": 4.71,
+      "learning_rate": 4.682779456193353e-06,
+      "loss": 0.126,
+      "step": 2500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7370095440084835,
+      "eval_loss": 1.1437411308288574,
+      "eval_runtime": 3.1169,
+      "eval_samples_per_second": 302.541,
+      "eval_steps_per_second": 9.625,
+      "step": 2655
+    },
+    {
+      "epoch": 5.0,
+      "step": 2655,
+      "total_flos": 4866474386987520.0,
+      "train_loss": 0.3910632814166685,
+      "train_runtime": 432.5593,
+      "train_samples_per_second": 98.067,
+      "train_steps_per_second": 6.138
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7370095440084835,
+      "eval_loss": 1.1437411308288574,
+      "eval_runtime": 3.1329,
+      "eval_samples_per_second": 301.0,
+      "eval_steps_per_second": 9.576,
+      "step": 2655
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7314984709480122,
+      "eval_loss": 1.2070553302764893,
+      "eval_runtime": 10.6939,
+      "eval_samples_per_second": 305.782,
+      "eval_steps_per_second": 9.632,
+      "step": 2655
+    }
+  ],
+  "max_steps": 2655,
+  "num_train_epochs": 5,
+  "total_flos": 4866474386987520.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:523ad77b6426b847f727ece175def7814962d019bec45d84aaec67afaa90ffc7
+size 2735