add model

.gitignore

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

README.md

@@ -0,0 +1,67 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- squad
+model_index:
+- name: distilbert-base-uncased-finetuned-squad
+  results:
+  - task:
+      name: Question Answering
+      type: question-answering
+    dataset:
+      name: squad
+      type: squad
+      args: plain_text
+---
+
+<!-- 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-squad
+
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the squad dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1520
+
+## 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: 3
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 1.2177        | 1.0   | 5533  | 1.1565          |
+| 0.9472        | 2.0   | 11066 | 1.1174          |
+| 0.7634        | 3.0   | 16599 | 1.1520          |
+
+
+### Framework versions
+
+- Transformers 4.9.1
+- Pytorch 1.9.0+cu102
+- Datasets 1.10.2
+- Tokenizers 0.10.3

config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForQuestionAnswering"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.9.1",
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29b63cc08fb6f16f4c43fa9a9c654ad92b20514b09ca601fc1187c5c0d0fc20a
+size 265497077

runs/Jul28_06-26-26_b4754c649fcd/1627453595.8276005/events.out.tfevents.1627453595.b4754c649fcd.63.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b1a2716f26ac28c131267f870a84b26fec3a7d1afa84d5bff8ef5ed47d35967
+size 4206

runs/Jul28_06-26-26_b4754c649fcd/events.out.tfevents.1627453595.b4754c649fcd.63.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1de4b086b313a138bee8953c8405fbd1fd97cee2f381902f77113469b6b4c3d7
+size 9216

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 sha256:5e4b9db74858cf903e75749e481db62c58a1fdf11e7e17757a93caa49072cb16
+size 2671