Hugging Face's logo

gaotianyu1350
/
roberta-large-squad

Question Answering
Transformers
PyTorch
roberta
Inference Endpoints
Model card Files Community
1
princeton-nlp commited on
Commit
877f4b9
路
1 Parent(s): 7540bc7

init

Browse files
Files changed (8) hide show
  1. config.json +27 -0
  2. pytorch_model.bin +3 -0
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +1 -0
  5. train_results.json +8 -0
  6. trainer_state.json +121 -0
  7. training_args.bin +3 -0
  8. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-large",
3
+ "architectures": [
4
+ "RobertaForQuestionAnswering"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 4096,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "roberta",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 24,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.13.0.dev0",
24
+ "type_vocab_size": 1,
25
+ "use_cache": true,
26
+ "vocab_size": 50265
27
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b102b389052d85c6594989f6d6b0cc85bdd8721db02441f7face0f6857fd6b5f
3
+ size 1417412145
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-large", "tokenizer_class": "RobertaTokenizer"}
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 0.6024896357623918,
4
+ "train_runtime": 2829.1187,
5
+ "train_samples": 131823,
6
+ "train_samples_per_second": 139.785,
7
+ "train_steps_per_second": 2.913
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,121 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "global_step": 8241,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.18,
12
+ "learning_rate": 2.8179832544594102e-05,
13
+ "loss": 1.3765,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.36,
18
+ "learning_rate": 2.6359665089188204e-05,
19
+ "loss": 0.903,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.55,
24
+ "learning_rate": 2.4539497633782306e-05,
25
+ "loss": 0.8343,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.73,
30
+ "learning_rate": 2.271933017837641e-05,
31
+ "loss": 0.7909,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.91,
36
+ "learning_rate": 2.0899162722970516e-05,
37
+ "loss": 0.7492,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 1.09,
42
+ "learning_rate": 1.9078995267564617e-05,
43
+ "loss": 0.6332,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 1.27,
48
+ "learning_rate": 1.725882781215872e-05,
49
+ "loss": 0.5434,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 1.46,
54
+ "learning_rate": 1.543866035675282e-05,
55
+ "loss": 0.5355,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 1.64,
60
+ "learning_rate": 1.3618492901346924e-05,
61
+ "loss": 0.549,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 1.82,
66
+ "learning_rate": 1.1798325445941026e-05,
67
+ "loss": 0.521,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 2.0,
72
+ "learning_rate": 9.97815799053513e-06,
73
+ "loss": 0.5263,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 2.18,
78
+ "learning_rate": 8.157990535129232e-06,
79
+ "loss": 0.3775,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 2.37,
84
+ "learning_rate": 6.337823079723334e-06,
85
+ "loss": 0.3725,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 2.55,
90
+ "learning_rate": 4.517655624317437e-06,
91
+ "loss": 0.363,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 2.73,
96
+ "learning_rate": 2.69748816891154e-06,
97
+ "loss": 0.3497,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 2.91,
102
+ "learning_rate": 8.773207135056426e-07,
103
+ "loss": 0.3415,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 3.0,
108
+ "step": 8241,
109
+ "total_flos": 2.7545611910240102e+17,
110
+ "train_loss": 0.6024896357623918,
111
+ "train_runtime": 2829.1187,
112
+ "train_samples_per_second": 139.785,
113
+ "train_steps_per_second": 2.913
114
+ }
115
+ ],
116
+ "max_steps": 8241,
117
+ "num_train_epochs": 3,
118
+ "total_flos": 2.7545611910240102e+17,
119
+ "trial_name": null,
120
+ "trial_params": null
121
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b499c56aad72b6fc62ff803de4590e778304c58633b48599205ddb95cea36f8a
3
+ size 2863
vocab.json ADDED
The diff for this file is too large to render. See raw diff