Hugging Face's logo

researchaccount
/
sa_sub6

Model card Files
xet
 Community
researchaccount commited on
Commit
6b70868
·
1 Parent(s): 9cb6838

Added files

Browse files
Files changed (31) hide show
  1. results.txt +85 -0
  2. train_0/best_model/config.json +40 -0
  3. train_0/best_model/pytorch_model.bin +3 -0
  4. train_0/best_model/special_tokens_map.json +1 -0
  5. train_0/best_model/tokenizer_config.json +1 -0
  6. train_0/best_model/training_args.bin +3 -0
  7. train_0/best_model/vocab.txt +0 -0
  8. train_1/best_model/config.json +40 -0
  9. train_1/best_model/pytorch_model.bin +3 -0
  10. train_1/best_model/special_tokens_map.json +1 -0
  11. train_1/best_model/tokenizer_config.json +1 -0
  12. train_1/best_model/training_args.bin +3 -0
  13. train_1/best_model/vocab.txt +0 -0
  14. train_2/best_model/config.json +40 -0
  15. train_2/best_model/pytorch_model.bin +3 -0
  16. train_2/best_model/special_tokens_map.json +1 -0
  17. train_2/best_model/tokenizer_config.json +1 -0
  18. train_2/best_model/training_args.bin +3 -0
  19. train_2/best_model/vocab.txt +0 -0
  20. train_3/best_model/config.json +40 -0
  21. train_3/best_model/pytorch_model.bin +3 -0
  22. train_3/best_model/special_tokens_map.json +1 -0
  23. train_3/best_model/tokenizer_config.json +1 -0
  24. train_3/best_model/training_args.bin +3 -0
  25. train_3/best_model/vocab.txt +0 -0
  26. train_4/best_model/config.json +40 -0
  27. train_4/best_model/pytorch_model.bin +3 -0
  28. train_4/best_model/special_tokens_map.json +1 -0
  29. train_4/best_model/tokenizer_config.json +1 -0
  30. train_4/best_model/training_args.bin +3 -0
  31. train_4/best_model/vocab.txt +0 -0
results.txt ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [{'epoch': 2.0,
2
+ 'eval_accuracy': 0.8541818181818182,
3
+ 'eval_average_recall': 0.8174534468293609,
4
+ 'eval_loss': 0.41029417514801025,
5
+ 'eval_macro_f1': 0.8105876339953134,
6
+ 'eval_macro_f1_neg': 0.7162350320245057,
7
+ 'eval_macro_f1_pos': 0.8200455580865603,
8
+ 'eval_macro_f1_pos_neg': 0.7681402950555329,
9
+ 'eval_mem_cpu_alloc_delta': 0,
10
+ 'eval_mem_cpu_peaked_delta': 0,
11
+ 'eval_mem_gpu_alloc_delta': -33792,
12
+ 'eval_mem_gpu_peaked_delta': 428268032,
13
+ 'eval_rec_neg': 0.730266893810335,
14
+ 'eval_rec_neu': 0.8877944895514441,
15
+ 'eval_rec_pos': 0.8342989571263036,
16
+ 'eval_runtime': 11.1078,
17
+ 'eval_samples_per_second': 990.296},
18
+ {'epoch': 2.0,
19
+ 'eval_accuracy': 0.8588181818181818,
20
+ 'eval_average_recall': 0.8303252727460229,
21
+ 'eval_loss': 0.37830352783203125,
22
+ 'eval_macro_f1': 0.8191978553141525,
23
+ 'eval_macro_f1_neg': 0.7366666666666668,
24
+ 'eval_macro_f1_pos': 0.8233062330623308,
25
+ 'eval_macro_f1_pos_neg': 0.7799864498644988,
26
+ 'eval_mem_cpu_alloc_delta': 0,
27
+ 'eval_mem_cpu_peaked_delta': 0,
28
+ 'eval_mem_gpu_alloc_delta': -33792,
29
+ 'eval_mem_gpu_peaked_delta': 453289472,
30
+ 'eval_rec_neg': 0.7616312464101092,
31
+ 'eval_rec_neu': 0.8849865951742627,
32
+ 'eval_rec_pos': 0.8443579766536965,
33
+ 'eval_runtime': 11.1006,
34
+ 'eval_samples_per_second': 990.941},
35
+ {'epoch': 2.0,
36
+ 'eval_accuracy': 0.8621818181818182,
37
+ 'eval_average_recall': 0.8242145953756737,
38
+ 'eval_loss': 0.37589043378829956,
39
+ 'eval_macro_f1': 0.8224607410381614,
40
+ 'eval_macro_f1_neg': 0.7434672660859792,
41
+ 'eval_macro_f1_pos': 0.8238542241855328,
42
+ 'eval_macro_f1_pos_neg': 0.783660745135756,
43
+ 'eval_mem_cpu_alloc_delta': 270336,
44
+ 'eval_mem_cpu_peaked_delta': 0,
45
+ 'eval_mem_gpu_alloc_delta': 0,
46
+ 'eval_mem_gpu_peaked_delta': 428292608,
47
+ 'eval_rec_neg': 0.7466139954853274,
48
+ 'eval_rec_neu': 0.8980608672232696,
49
+ 'eval_rec_pos': 0.827968923418424,
50
+ 'eval_runtime': 11.0974,
51
+ 'eval_samples_per_second': 991.221},
52
+ {'epoch': 2.0,
53
+ 'eval_accuracy': 0.8502727272727273,
54
+ 'eval_average_recall': 0.8254777783488995,
55
+ 'eval_loss': 0.3594415485858917,
56
+ 'eval_macro_f1': 0.8093425461714047,
57
+ 'eval_macro_f1_neg': 0.7389756231169543,
58
+ 'eval_macro_f1_pos': 0.7979359043997826,
59
+ 'eval_macro_f1_pos_neg': 0.7684557637583684,
60
+ 'eval_mem_cpu_alloc_delta': 0,
61
+ 'eval_mem_cpu_peaked_delta': 0,
62
+ 'eval_mem_gpu_alloc_delta': -33792,
63
+ 'eval_mem_gpu_peaked_delta': 277316096,
64
+ 'eval_rec_neg': 0.7612866817155757,
65
+ 'eval_rec_neu': 0.8733128424428706,
66
+ 'eval_rec_pos': 0.8418338108882522,
67
+ 'eval_runtime': 11.1122,
68
+ 'eval_samples_per_second': 989.902},
69
+ {'epoch': 2.0,
70
+ 'eval_accuracy': 0.8570909090909091,
71
+ 'eval_average_recall': 0.8261770590388532,
72
+ 'eval_loss': 0.37819385528564453,
73
+ 'eval_macro_f1': 0.8157430943820648,
74
+ 'eval_macro_f1_neg': 0.73,
75
+ 'eval_macro_f1_pos': 0.8200330214639516,
76
+ 'eval_macro_f1_pos_neg': 0.7750165107319757,
77
+ 'eval_mem_cpu_alloc_delta': -7553024,
78
+ 'eval_mem_cpu_peaked_delta': 7553024,
79
+ 'eval_mem_gpu_alloc_delta': 0,
80
+ 'eval_mem_gpu_peaked_delta': 327420416,
81
+ 'eval_rec_neg': 0.7406989853438557,
82
+ 'eval_rec_neu': 0.8859168115554367,
83
+ 'eval_rec_pos': 0.851915380217267,
84
+ 'eval_runtime': 11.0775,
85
+ 'eval_samples_per_second': 993.008}]
train_0/best_model/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./train_0/checkpoint-2750",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "directionality": "bidi",
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "Positive",
14
+ "1": "Neutral",
15
+ "2": "Negative"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "Negative": 2,
21
+ "Neutral": 1,
22
+ "Positive": 0
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "bert",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
+ "pad_token_id": 0,
30
+ "pooler_fc_size": 768,
31
+ "pooler_num_attention_heads": 12,
32
+ "pooler_num_fc_layers": 3,
33
+ "pooler_size_per_head": 128,
34
+ "pooler_type": "first_token_transform",
35
+ "position_embedding_type": "absolute",
36
+ "transformers_version": "4.5.0",
37
+ "type_vocab_size": 2,
38
+ "use_cache": true,
39
+ "vocab_size": 100000
40
+ }
train_0/best_model/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0efbf3abb14ce2ab8a4b78c3eab9dc9db1adca819cb8038e6c3d759ecd766aa6
3
+ size 651463945
train_0/best_model/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
train_0/best_model/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
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, "do_basic_tokenize": true, "never_split": null, "special_tokens_map_file": null, "name_or_path": "researchaccount/continue_mlm"}
train_0/best_model/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b820b80f7c4ee598fb3e763db777e26e739afa329b5b4ec0267cea6eda0f17d5
3
+ size 2351
train_0/best_model/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
train_1/best_model/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./train_1/checkpoint-2750",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "directionality": "bidi",
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "Positive",
14
+ "1": "Neutral",
15
+ "2": "Negative"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "Negative": 2,
21
+ "Neutral": 1,
22
+ "Positive": 0
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "bert",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
+ "pad_token_id": 0,
30
+ "pooler_fc_size": 768,
31
+ "pooler_num_attention_heads": 12,
32
+ "pooler_num_fc_layers": 3,
33
+ "pooler_size_per_head": 128,
34
+ "pooler_type": "first_token_transform",
35
+ "position_embedding_type": "absolute",
36
+ "transformers_version": "4.5.0",
37
+ "type_vocab_size": 2,
38
+ "use_cache": true,
39
+ "vocab_size": 100000
40
+ }
train_1/best_model/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d1d2e4bf23289744b409cf0cb219491534a01ee1ef653fb8e66291c8b826292
3
+ size 651463945
train_1/best_model/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
train_1/best_model/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
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, "do_basic_tokenize": true, "never_split": null, "special_tokens_map_file": null, "name_or_path": "researchaccount/continue_mlm"}
train_1/best_model/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6a098288da037f20371e675e0cdb787d77dee7306d6dc86fd48237407c35137
3
+ size 2351
train_1/best_model/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
train_2/best_model/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./train_2/checkpoint-2750",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "directionality": "bidi",
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "Positive",
14
+ "1": "Neutral",
15
+ "2": "Negative"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "Negative": 2,
21
+ "Neutral": 1,
22
+ "Positive": 0
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "bert",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
+ "pad_token_id": 0,
30
+ "pooler_fc_size": 768,
31
+ "pooler_num_attention_heads": 12,
32
+ "pooler_num_fc_layers": 3,
33
+ "pooler_size_per_head": 128,
34
+ "pooler_type": "first_token_transform",
35
+ "position_embedding_type": "absolute",
36
+ "transformers_version": "4.5.0",
37
+ "type_vocab_size": 2,
38
+ "use_cache": true,
39
+ "vocab_size": 100000
40
+ }
train_2/best_model/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef2da474c196e5a609c78ee35a0ad1b170eb6a95e506a8d29adebf5f485d70f2
3
+ size 651463945
train_2/best_model/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
train_2/best_model/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
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, "do_basic_tokenize": true, "never_split": null, "special_tokens_map_file": null, "name_or_path": "researchaccount/continue_mlm"}
train_2/best_model/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24b0f6d1c13cf21004c1cdcc8dd31797958952977dd6d0416df51066f6b700aa
3
+ size 2351
train_2/best_model/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
train_3/best_model/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./train_3/checkpoint-1375",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "directionality": "bidi",
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "Positive",
14
+ "1": "Neutral",
15
+ "2": "Negative"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "Negative": 2,
21
+ "Neutral": 1,
22
+ "Positive": 0
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "bert",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
+ "pad_token_id": 0,
30
+ "pooler_fc_size": 768,
31
+ "pooler_num_attention_heads": 12,
32
+ "pooler_num_fc_layers": 3,
33
+ "pooler_size_per_head": 128,
34
+ "pooler_type": "first_token_transform",
35
+ "position_embedding_type": "absolute",
36
+ "transformers_version": "4.5.0",
37
+ "type_vocab_size": 2,
38
+ "use_cache": true,
39
+ "vocab_size": 100000
40
+ }
train_3/best_model/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97a9eac7d63fb5c5204b35d23aa87d1618862ebbad38b51cf1b7f5ee8a478926
3
+ size 651463945
train_3/best_model/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
train_3/best_model/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
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, "do_basic_tokenize": true, "never_split": null, "special_tokens_map_file": null, "name_or_path": "researchaccount/continue_mlm"}
train_3/best_model/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1763b6f18d2a991fcce84598e4f67b1b678b35943f7f1bae05405fc044b1e12
3
+ size 2351
train_3/best_model/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
train_4/best_model/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./train_4/checkpoint-2750",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "directionality": "bidi",
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "Positive",
14
+ "1": "Neutral",
15
+ "2": "Negative"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "Negative": 2,
21
+ "Neutral": 1,
22
+ "Positive": 0
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "bert",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
+ "pad_token_id": 0,
30
+ "pooler_fc_size": 768,
31
+ "pooler_num_attention_heads": 12,
32
+ "pooler_num_fc_layers": 3,
33
+ "pooler_size_per_head": 128,
34
+ "pooler_type": "first_token_transform",
35
+ "position_embedding_type": "absolute",
36
+ "transformers_version": "4.5.0",
37
+ "type_vocab_size": 2,
38
+ "use_cache": true,
39
+ "vocab_size": 100000
40
+ }
train_4/best_model/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:029c59cbe0678bde6a1776d67a2bd4733c566378d0dec5dd852ee4f925d737c0
3
+ size 651463945
train_4/best_model/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
train_4/best_model/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
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, "do_basic_tokenize": true, "never_split": null, "special_tokens_map_file": null, "name_or_path": "researchaccount/continue_mlm"}
train_4/best_model/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c585bf52c48fb9ded6d13783af9c858f1f57cacb8aa2789e3b017864c15e183
3
+ size 2351
train_4/best_model/vocab.txt ADDED
The diff for this file is too large to render. See raw diff