haibotamiu commited on
Commit
ee5ddf3
1 Parent(s): 054954f

Model save

Browse files
README.md CHANGED
@@ -1,11 +1,8 @@
1
  ---
2
  license: apache-2.0
3
- base_model: bert-large-uncased
4
  tags:
5
- - question-answering
6
  - generated_from_trainer
7
- datasets:
8
- - squad
9
  model-index:
10
  - name: out
11
  results: []
@@ -16,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  # out
18
 
19
- This model is a fine-tuned version of [bert-large-uncased](https://huggingface.co/bert-large-uncased) on the squad dataset.
20
 
21
  ## Model description
22
 
@@ -36,12 +33,12 @@ More information needed
36
 
37
  The following hyperparameters were used during training:
38
  - learning_rate: 5e-05
39
- - train_batch_size: 32
40
  - eval_batch_size: 16
41
  - seed: 42
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: linear
44
- - num_epochs: 100.0
45
 
46
  ### Training results
47
 
 
1
  ---
2
  license: apache-2.0
3
+ base_model: distilbert-base-uncased
4
  tags:
 
5
  - generated_from_trainer
 
 
6
  model-index:
7
  - name: out
8
  results: []
 
13
 
14
  # out
15
 
16
+ This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
17
 
18
  ## Model description
19
 
 
33
 
34
  The following hyperparameters were used during training:
35
  - learning_rate: 5e-05
36
+ - train_batch_size: 256
37
  - eval_batch_size: 16
38
  - seed: 42
39
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
  - lr_scheduler_type: linear
41
+ - num_epochs: 3.0
42
 
43
  ### Training results
44
 
config.json CHANGED
@@ -1,26 +1,24 @@
1
  {
2
- "_name_or_path": "bert-large-uncased",
 
3
  "architectures": [
4
- "BertForQuestionAnswering"
5
  ],
6
- "attention_probs_dropout_prob": 0.1,
7
- "classifier_dropout": null,
8
- "gradient_checkpointing": false,
9
- "hidden_act": "gelu",
10
- "hidden_dropout_prob": 0.1,
11
- "hidden_size": 1024,
12
  "initializer_range": 0.02,
13
- "intermediate_size": 4096,
14
- "layer_norm_eps": 1e-12,
15
  "max_position_embeddings": 512,
16
- "model_type": "bert",
17
- "num_attention_heads": 16,
18
- "num_hidden_layers": 24,
19
  "pad_token_id": 0,
20
- "position_embedding_type": "absolute",
 
 
 
21
  "torch_dtype": "float32",
22
  "transformers_version": "4.35.0.dev0",
23
- "type_vocab_size": 2,
24
- "use_cache": true,
25
  "vocab_size": 30522
26
  }
 
1
  {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
  "architectures": [
5
+ "DistilBertForQuestionAnswering"
6
  ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
 
 
11
  "initializer_range": 0.02,
 
 
12
  "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
  "pad_token_id": 0,
17
+ "qa_dropout": 0.1,
18
+ "seq_classif_dropout": 0.2,
19
+ "sinusoidal_pos_embds": false,
20
+ "tie_weights_": true,
21
  "torch_dtype": "float32",
22
  "transformers_version": "4.35.0.dev0",
 
 
23
  "vocab_size": 30522
24
  }
pruning_config.json CHANGED
@@ -18,7 +18,7 @@
18
  },
19
  "pruning_fn": "unstructured_magnitude",
20
  "pruning_fn_default_kwargs": {
21
- "target_sparsity": 0.9
22
  },
23
  "pruning_frequency": 100,
24
  "scheduler": "iterative",
 
18
  },
19
  "pruning_fn": "unstructured_magnitude",
20
  "pruning_fn_default_kwargs": {
21
+ "target_sparsity": 0.8
22
  },
23
  "pruning_frequency": 100,
24
  "scheduler": "iterative",
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7143a72753b88f1c9b7c271a75d22e68bbcee962d0f820bb443b93c5d36efaf
3
- size 1336511590
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45f49d0d4ef9d2b6a142d56f5151687051e5e54606390c6de709e339848665c4
3
+ size 265493026
raw_pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e3d4e334964d58306dd7a63b61d801e81fec6bcb4013a3749904c8bc3fe93bd3
3
- size 2544552978
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ace5d339b09a1b5d89214c499f75ccb2fefdcce154e576b06cc71a1361c8eb03
3
+ size 435382250
tokenizer_config.json CHANGED
@@ -51,6 +51,6 @@
51
  "sep_token": "[SEP]",
52
  "strip_accents": null,
53
  "tokenize_chinese_chars": true,
54
- "tokenizer_class": "BertTokenizer",
55
  "unk_token": "[UNK]"
56
  }
 
51
  "sep_token": "[SEP]",
52
  "strip_accents": null,
53
  "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "DistilBertTokenizer",
55
  "unk_token": "[UNK]"
56
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fc05332e6a39a03af4ea330f9908464443c1338ac7c0203ccbc2360fd8ac9459
3
  size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d576f8b15f7b44f5a058f1b32229a3e2d92d39fc7ea720846da99de0a64ec31a
3
  size 4664