Hugging Face's logo

Zhengping
/
roberta-large-unli

Text Classification
Transformers
Safetensors
English
roberta
Inference Endpoints
Model card Files Community
Zhengping commited on
Commit
0c9176b
•
1 Parent(s): 58de087

Upload 12 files

Browse files
Files changed (12) hide show
  1. config.json +35 -0
  2. merges.txt +0 -0
  3. model.safetensors +3 -0
  4. optimizer.pt +3 -0
  5. rng_state.pth +3 -0
  6. scheduler.pt +3 -0
  7. special_tokens_map.json +51 -0
  8. tokenizer.json +0 -0
  9. tokenizer_config.json +58 -0
  10. trainer_state.json +134 -0
  11. training_args.bin +3 -0
  12. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ynie/roberta-large-snli_mnli_fever_anli_R1_R2_R3-nli",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 1024,
14
+ "id2label": {
15
+ "0": "LABEL_0"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 4096,
19
+ "label2id": {
20
+ "LABEL_0": 0
21
+ },
22
+ "layer_norm_eps": 1e-05,
23
+ "max_position_embeddings": 514,
24
+ "model_type": "roberta",
25
+ "num_attention_heads": 16,
26
+ "num_hidden_layers": 24,
27
+ "pad_token_id": 1,
28
+ "position_embedding_type": "absolute",
29
+ "problem_type": "multi_label_classification",
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.39.3",
32
+ "type_vocab_size": 1,
33
+ "use_cache": true,
34
+ "vocab_size": 50265
35
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98f0ccbbcc5073adffd0c294e124753c420b1399e7e74dfdec43b768177c7ce5
3
+ size 1421491316
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07fff6162e61ab65d5f0530afebedfe92754b10aa68f1b92ee57dbf3015ab16d
3
+ size 2843214648
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3ad708c62cb3390f165d3052a2f439d00cd8d2b66559804a8232420762b2f2d
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86a6539a3158604b092ccbaa3e8d2814030de41c97e7ff255374245267ebf10d
3
+ size 627
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "do_lower_case": false,
49
+ "eos_token": "</s>",
50
+ "errors": "replace",
51
+ "mask_token": "<mask>",
52
+ "model_max_length": 512,
53
+ "pad_token": "<pad>",
54
+ "sep_token": "</s>",
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": "<unk>"
58
+ }
trainer_state.json ADDED
@@ -0,0 +1,134 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7533459966277345,
3
+ "best_model_checkpoint": "ckpt/tuned_unli/checkpoint-6940",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 6940,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.14,
13
+ "grad_norm": 11.59940242767334,
14
+ "learning_rate": 4.855907780979828e-06,
15
+ "loss": 0.4912,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.29,
20
+ "grad_norm": 4.5099921226501465,
21
+ "learning_rate": 4.711815561959655e-06,
22
+ "loss": 0.4898,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.43,
27
+ "grad_norm": 4.301983833312988,
28
+ "learning_rate": 4.567723342939482e-06,
29
+ "loss": 0.4803,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 0.58,
34
+ "grad_norm": 8.535087585449219,
35
+ "learning_rate": 4.423631123919308e-06,
36
+ "loss": 0.486,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 0.72,
41
+ "grad_norm": 6.304492473602295,
42
+ "learning_rate": 4.279538904899136e-06,
43
+ "loss": 0.4725,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 0.86,
48
+ "grad_norm": 5.865860939025879,
49
+ "learning_rate": 4.135446685878963e-06,
50
+ "loss": 0.4738,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 1.0,
55
+ "eval_loss": 0.5043371915817261,
56
+ "eval_mse": 0.05504356324672699,
57
+ "eval_pearson": 0.7481511352198802,
58
+ "eval_runtime": 11.1028,
59
+ "eval_samples_per_second": 273.805,
60
+ "eval_spearman": 0.7563540381881723,
61
+ "eval_steps_per_second": 17.113,
62
+ "step": 3470
63
+ },
64
+ {
65
+ "epoch": 1.01,
66
+ "grad_norm": 9.249129295349121,
67
+ "learning_rate": 3.99135446685879e-06,
68
+ "loss": 0.4737,
69
+ "step": 3500
70
+ },
71
+ {
72
+ "epoch": 1.15,
73
+ "grad_norm": 5.8351874351501465,
74
+ "learning_rate": 3.847262247838617e-06,
75
+ "loss": 0.4416,
76
+ "step": 4000
77
+ },
78
+ {
79
+ "epoch": 1.3,
80
+ "grad_norm": 5.798779010772705,
81
+ "learning_rate": 3.703170028818444e-06,
82
+ "loss": 0.4457,
83
+ "step": 4500
84
+ },
85
+ {
86
+ "epoch": 1.44,
87
+ "grad_norm": 6.772558212280273,
88
+ "learning_rate": 3.5590778097982716e-06,
89
+ "loss": 0.4448,
90
+ "step": 5000
91
+ },
92
+ {
93
+ "epoch": 1.59,
94
+ "grad_norm": 12.370868682861328,
95
+ "learning_rate": 3.4149855907780984e-06,
96
+ "loss": 0.4499,
97
+ "step": 5500
98
+ },
99
+ {
100
+ "epoch": 1.73,
101
+ "grad_norm": 7.551795482635498,
102
+ "learning_rate": 3.2708933717579256e-06,
103
+ "loss": 0.4441,
104
+ "step": 6000
105
+ },
106
+ {
107
+ "epoch": 1.87,
108
+ "grad_norm": 3.4603450298309326,
109
+ "learning_rate": 3.1268011527377524e-06,
110
+ "loss": 0.4466,
111
+ "step": 6500
112
+ },
113
+ {
114
+ "epoch": 2.0,
115
+ "eval_loss": 0.5080664157867432,
116
+ "eval_mse": 0.055369943380355835,
117
+ "eval_pearson": 0.7533459966277345,
118
+ "eval_runtime": 10.7962,
119
+ "eval_samples_per_second": 281.582,
120
+ "eval_spearman": 0.7597360368405089,
121
+ "eval_steps_per_second": 17.599,
122
+ "step": 6940
123
+ }
124
+ ],
125
+ "logging_steps": 500,
126
+ "max_steps": 17350,
127
+ "num_input_tokens_seen": 0,
128
+ "num_train_epochs": 5,
129
+ "save_steps": 500,
130
+ "total_flos": 1.0217853882348156e+16,
131
+ "train_batch_size": 16,
132
+ "trial_name": null,
133
+ "trial_params": null
134
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:feb3c63803e1eb6340029cbd5c14dda962d661c9dae6a1f0df4b97955260d038
3
+ size 4475
vocab.json ADDED
The diff for this file is too large to render. See raw diff