haibotamiu commited on
Commit
2b57875
1 Parent(s): ed13d45

Model save

Browse files
Files changed (5) hide show
  1. README.md +4 -7
  2. config.json +5 -5
  3. pytorch_model.bin +2 -2
  4. raw_pytorch_model.bin +2 -2
  5. training_args.bin +1 -1
README.md CHANGED
@@ -1,11 +1,8 @@
1
  ---
2
  license: apache-2.0
3
- base_model: bert-base-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-base-uncased](https://huggingface.co/bert-base-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: bert-large-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 [bert-large-uncased](https://huggingface.co/bert-large-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: 128
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
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "bert-base-uncased",
3
  "architectures": [
4
  "BertForQuestionAnswering"
5
  ],
@@ -8,14 +8,14 @@
8
  "gradient_checkpointing": false,
9
  "hidden_act": "gelu",
10
  "hidden_dropout_prob": 0.1,
11
- "hidden_size": 768,
12
  "initializer_range": 0.02,
13
- "intermediate_size": 3072,
14
  "layer_norm_eps": 1e-12,
15
  "max_position_embeddings": 512,
16
  "model_type": "bert",
17
- "num_attention_heads": 12,
18
- "num_hidden_layers": 12,
19
  "pad_token_id": 0,
20
  "position_embedding_type": "absolute",
21
  "torch_dtype": "float32",
 
1
  {
2
+ "_name_or_path": "bert-large-uncased",
3
  "architectures": [
4
  "BertForQuestionAnswering"
5
  ],
 
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",
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:284c6b9426b3765f6469ad78efe1421fde2517b66d121ef9ca0dd30f8d866da5
3
- size 435640934
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dec12a84bbad95fec4d0dd59676d610a9ed3361c2505b6596e91d2ebe7af049
3
+ size 1336511590
raw_pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:17a064e3b9ca9d2a356afedc39cf64f90f9ac72d029c3d29106910ef54aeb691
3
- size 775420626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f17148cf060244258e6300ced0590f81dc1b3e4419e0e02562ea60239eb5cead
3
+ size 2544552978
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0cc890072964ff292428e442369dd117aad7c492cdfa148ac3da433ba33bdb4b
3
  size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9175e68671c44dbc0a0f1654e18adaa930e3b54f6d05e7efe6e93ec1992468d
3
  size 4664