add model

.gitignore

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

README.md

@@ -0,0 +1,61 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- swag
+model_index:
+- name: bert-base-uncased-finetuned-swag
+  results:
+  - dataset:
+      name: swag
+      type: swag
+      args: regular
+---
+
+<!-- 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. -->
+
+# bert-base-uncased-finetuned-swag
+
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the swag dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 0.6189
+- eval_accuracy: 0.7647
+- eval_runtime: 274.5502
+- eval_samples_per_second: 72.868
+- eval_steps_per_second: 4.557
+- epoch: 1.0
+- step: 4597
+
+## 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: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Framework versions
+
+- Transformers 4.9.1
+- Pytorch 1.9.0+cu102
+- Datasets 1.11.0
+- Tokenizers 0.10.3

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForMultipleChoice"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.9.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a5bcd060ab628efdb4146359539348348ec84a4fda56d3f1e612811c2d4e7c6
+size 438016173

runs/Aug07_04-15-58_ea3e619b12d3/1628310188.8682177/events.out.tfevents.1628310188.ea3e619b12d3.67.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30e8918b2e4dfda3bcb2c36efdc083b8a8914fba0e4d1d23a449368f836dd5d5
+size 4196

runs/Aug07_04-15-58_ea3e619b12d3/events.out.tfevents.1628310188.ea3e619b12d3.67.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7df9a89d4577202885719caf4ef0d5c762f4ab7f4c0387c8d7a6a2b54c633aba
+size 4976

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": "bert-base-uncased", "tokenizer_class": "BertTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77ffc0741b591395e30ecd289500d86dd345675ffc61892db6824b16aa175b75
+size 2671