add model

.gitignore

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

README.md

@@ -0,0 +1,76 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- glue
+metrics:
+- accuracy
+model-index:
+- name: distilbert-base-uncased-finetuned-mnli
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: glue
+      type: glue
+      args: mnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8205807437595517
+---
+
+<!-- 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-finetuned-mnli
+
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the glue dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6753
+- Accuracy: 0.8206
+
+## 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: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step   | Validation Loss | Accuracy |
+|:-------------:|:-----:|:------:|:---------------:|:--------:|
+| 0.5146        | 1.0   | 24544  | 0.4925          | 0.8049   |
+| 0.4093        | 2.0   | 49088  | 0.5090          | 0.8164   |
+| 0.3122        | 3.0   | 73632  | 0.5299          | 0.8185   |
+| 0.2286        | 4.0   | 98176  | 0.6753          | 0.8206   |
+| 0.182         | 5.0   | 122720 | 0.8372          | 0.8195   |
+
+
+### Framework versions
+
+- Transformers 4.10.2
+- Pytorch 1.9.0+cu102
+- Datasets 1.11.0
+- Tokenizers 0.10.3

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.10.2",
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f458a332c6dde526149b12e4eed6e5acad0d4426bf0956046675a45575e59241
+size 267863153

runs/Sep11_14-50-51_01355585b404/1631371866.756383/events.out.tfevents.1631371866.01355585b404.91.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37cb0d8e62224b571c6339d720aefbb56eda2abdf95f293dffdf3c0ad89071e4
+size 4209

runs/Sep11_14-50-51_01355585b404/events.out.tfevents.1631371866.01355585b404.91.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a6da37c55539015f0bfe39df82ec8dac3c95338626523558e3792362834eefe
+size 44119

runs/Sep11_14-50-51_01355585b404/events.out.tfevents.1631388698.01355585b404.91.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d96e4f047bef34ad184c44edee919d7ada64c4fd206f63d8381f89a8a911531
+size 369

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"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c4eeb7b60cbb4b3ed7b53e3240177617302a981c70ddfe68d4af7084d06ac94
+size 2671