Hugging Face's logo

adriansanz
/
te-zsc-hybrid_VIC

Text Classification
Transformers
TensorBoard
Safetensors
roberta
Generated from Trainer
Model card Files Metrics Community
adriansanz commited on
Commit
83d654f
·
verified ·
1 Parent(s): c537b36

End of training

Browse files
Files changed (11) hide show
  1. README.md +134 -0
  2. config.json +40 -0
  3. logs/events.out.tfevents.1722336885.183c440d058f.2175.1 +3 -0
  4. logs/events.out.tfevents.1722340752.183c440d058f.2175.2 +3 -0
  5. merges.txt +0 -0
  6. model.safetensors +3 -0
  7. special_tokens_map.json +51 -0
  8. tokenizer.json +0 -0
  9. tokenizer_config.json +65 -0
  10. training_args.bin +3 -0
  11. vocab.json +0 -0
README.md ADDED
@@ -0,0 +1,134 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: projecte-aina/roberta-base-ca-v2-cased-te
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ - precision
9
+ - recall
10
+ - f1
11
+ model-index:
12
+ - name: VICH_300524_epoch_1
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # VICH_300524_epoch_1
20
+
21
+ This model is a fine-tuned version of [projecte-aina/roberta-base-ca-v2-cased-te](https://huggingface.co/projecte-aina/roberta-base-ca-v2-cased-te) on the None dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.4621
24
+ - Accuracy: 0.906
25
+ - Precision: 0.9081
26
+ - Recall: 0.9060
27
+ - F1: 0.9059
28
+ - Ratio: 0.464
29
+
30
+ ## Model description
31
+
32
+ More information needed
33
+
34
+ ## Intended uses & limitations
35
+
36
+ More information needed
37
+
38
+ ## Training and evaluation data
39
+
40
+ More information needed
41
+
42
+ ## Training procedure
43
+
44
+ ### Training hyperparameters
45
+
46
+ The following hyperparameters were used during training:
47
+ - learning_rate: 2e-05
48
+ - train_batch_size: 16
49
+ - eval_batch_size: 16
50
+ - seed: 47
51
+ - gradient_accumulation_steps: 2
52
+ - total_train_batch_size: 32
53
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
54
+ - lr_scheduler_type: linear
55
+ - lr_scheduler_warmup_ratio: 0.06
56
+ - lr_scheduler_warmup_steps: 4
57
+ - num_epochs: 1
58
+ - label_smoothing_factor: 0.1
59
+
60
+ ### Training results
61
+
62
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Ratio |
63
+ |:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:-----:|
64
+ | 1.6339 | 0.0157 | 10 | 1.1764 | 0.608 | 0.6081 | 0.608 | 0.6079 | 0.482 |
65
+ | 0.978 | 0.0314 | 20 | 0.9387 | 0.623 | 0.6602 | 0.623 | 0.5998 | 0.741 |
66
+ | 0.8 | 0.0472 | 30 | 0.7466 | 0.68 | 0.6914 | 0.68 | 0.6752 | 0.378 |
67
+ | 0.7271 | 0.0629 | 40 | 0.6887 | 0.741 | 0.7504 | 0.741 | 0.7385 | 0.403 |
68
+ | 0.699 | 0.0786 | 50 | 0.6675 | 0.76 | 0.7676 | 0.76 | 0.7583 | 0.416 |
69
+ | 0.6985 | 0.0943 | 60 | 0.6259 | 0.779 | 0.7815 | 0.7790 | 0.7785 | 0.453 |
70
+ | 0.6617 | 0.1101 | 70 | 0.6078 | 0.796 | 0.7960 | 0.796 | 0.7960 | 0.502 |
71
+ | 0.6739 | 0.1258 | 80 | 0.6071 | 0.789 | 0.8057 | 0.789 | 0.7861 | 0.383 |
72
+ | 0.6381 | 0.1415 | 90 | 0.5997 | 0.806 | 0.8114 | 0.806 | 0.8052 | 0.566 |
73
+ | 0.6455 | 0.1572 | 100 | 0.5914 | 0.808 | 0.8102 | 0.808 | 0.8077 | 0.458 |
74
+ | 0.6816 | 0.1730 | 110 | 0.5775 | 0.822 | 0.8239 | 0.8220 | 0.8217 | 0.462 |
75
+ | 0.6346 | 0.1887 | 120 | 0.5757 | 0.82 | 0.8302 | 0.8200 | 0.8186 | 0.412 |
76
+ | 0.5773 | 0.2044 | 130 | 0.5799 | 0.823 | 0.8336 | 0.823 | 0.8216 | 0.411 |
77
+ | 0.6138 | 0.2201 | 140 | 0.5693 | 0.839 | 0.8435 | 0.839 | 0.8385 | 0.557 |
78
+ | 0.5819 | 0.2358 | 150 | 0.6291 | 0.785 | 0.8291 | 0.7850 | 0.7776 | 0.317 |
79
+ | 0.602 | 0.2516 | 160 | 0.5476 | 0.853 | 0.8531 | 0.853 | 0.8530 | 0.491 |
80
+ | 0.5285 | 0.2673 | 170 | 0.5480 | 0.856 | 0.8573 | 0.856 | 0.8559 | 0.47 |
81
+ | 0.6021 | 0.2830 | 180 | 0.5558 | 0.862 | 0.8701 | 0.8620 | 0.8612 | 0.426 |
82
+ | 0.5645 | 0.2987 | 190 | 0.5382 | 0.863 | 0.8681 | 0.863 | 0.8625 | 0.441 |
83
+ | 0.5233 | 0.3145 | 200 | 0.5309 | 0.857 | 0.8574 | 0.857 | 0.8570 | 0.517 |
84
+ | 0.5398 | 0.3302 | 210 | 0.5396 | 0.854 | 0.8585 | 0.8540 | 0.8535 | 0.444 |
85
+ | 0.5342 | 0.3459 | 220 | 0.5288 | 0.873 | 0.8731 | 0.873 | 0.8730 | 0.491 |
86
+ | 0.5428 | 0.3616 | 230 | 0.5513 | 0.862 | 0.8710 | 0.862 | 0.8612 | 0.422 |
87
+ | 0.5354 | 0.3774 | 240 | 0.5289 | 0.873 | 0.8760 | 0.873 | 0.8727 | 0.455 |
88
+ | 0.5243 | 0.3931 | 250 | 0.5202 | 0.872 | 0.8755 | 0.872 | 0.8717 | 0.452 |
89
+ | 0.5068 | 0.4088 | 260 | 0.5194 | 0.873 | 0.8776 | 0.873 | 0.8726 | 0.445 |
90
+ | 0.5256 | 0.4245 | 270 | 0.5194 | 0.869 | 0.8753 | 0.869 | 0.8684 | 0.435 |
91
+ | 0.5177 | 0.4403 | 280 | 0.5040 | 0.884 | 0.8852 | 0.884 | 0.8839 | 0.472 |
92
+ | 0.5088 | 0.4560 | 290 | 0.5037 | 0.881 | 0.8825 | 0.881 | 0.8809 | 0.469 |
93
+ | 0.5133 | 0.4717 | 300 | 0.5326 | 0.867 | 0.8774 | 0.867 | 0.8661 | 0.417 |
94
+ | 0.5078 | 0.4874 | 310 | 0.4998 | 0.885 | 0.8869 | 0.885 | 0.8849 | 0.465 |
95
+ | 0.5065 | 0.5031 | 320 | 0.4965 | 0.892 | 0.8948 | 0.892 | 0.8918 | 0.458 |
96
+ | 0.502 | 0.5189 | 330 | 0.4947 | 0.89 | 0.8920 | 0.89 | 0.8899 | 0.464 |
97
+ | 0.5119 | 0.5346 | 340 | 0.4931 | 0.889 | 0.8893 | 0.889 | 0.8890 | 0.487 |
98
+ | 0.5426 | 0.5503 | 350 | 0.5012 | 0.882 | 0.8880 | 0.8820 | 0.8815 | 0.438 |
99
+ | 0.5861 | 0.5660 | 360 | 0.4899 | 0.891 | 0.8958 | 0.891 | 0.8907 | 0.445 |
100
+ | 0.5477 | 0.5818 | 370 | 0.4839 | 0.891 | 0.8929 | 0.891 | 0.8909 | 0.465 |
101
+ | 0.5026 | 0.5975 | 380 | 0.4788 | 0.892 | 0.8920 | 0.892 | 0.8920 | 0.498 |
102
+ | 0.4688 | 0.6132 | 390 | 0.4863 | 0.902 | 0.9037 | 0.902 | 0.9019 | 0.468 |
103
+ | 0.4842 | 0.6289 | 400 | 0.4846 | 0.902 | 0.9041 | 0.9020 | 0.9019 | 0.464 |
104
+ | 0.4897 | 0.6447 | 410 | 0.4848 | 0.9 | 0.9047 | 0.9000 | 0.8997 | 0.446 |
105
+ | 0.491 | 0.6604 | 420 | 0.4742 | 0.901 | 0.9030 | 0.901 | 0.9009 | 0.465 |
106
+ | 0.4557 | 0.6761 | 430 | 0.4827 | 0.891 | 0.8910 | 0.891 | 0.8910 | 0.495 |
107
+ | 0.4858 | 0.6918 | 440 | 0.4803 | 0.896 | 0.8968 | 0.896 | 0.8959 | 0.478 |
108
+ | 0.4802 | 0.7075 | 450 | 0.4841 | 0.897 | 0.8997 | 0.897 | 0.8968 | 0.459 |
109
+ | 0.5116 | 0.7233 | 460 | 0.4761 | 0.896 | 0.8981 | 0.896 | 0.8959 | 0.464 |
110
+ | 0.5021 | 0.7390 | 470 | 0.4727 | 0.905 | 0.9060 | 0.905 | 0.9049 | 0.475 |
111
+ | 0.4986 | 0.7547 | 480 | 0.4717 | 0.903 | 0.9063 | 0.903 | 0.9028 | 0.455 |
112
+ | 0.4721 | 0.7704 | 490 | 0.4757 | 0.906 | 0.9104 | 0.9060 | 0.9057 | 0.448 |
113
+ | 0.42 | 0.7862 | 500 | 0.4705 | 0.905 | 0.9072 | 0.905 | 0.9049 | 0.463 |
114
+ | 0.4596 | 0.8019 | 510 | 0.4706 | 0.9 | 0.9011 | 0.9 | 0.8999 | 0.474 |
115
+ | 0.5301 | 0.8176 | 520 | 0.4741 | 0.903 | 0.9055 | 0.903 | 0.9029 | 0.461 |
116
+ | 0.486 | 0.8333 | 530 | 0.4731 | 0.903 | 0.9063 | 0.903 | 0.9028 | 0.455 |
117
+ | 0.4794 | 0.8491 | 540 | 0.4694 | 0.903 | 0.9055 | 0.903 | 0.9029 | 0.461 |
118
+ | 0.4848 | 0.8648 | 550 | 0.4667 | 0.906 | 0.9071 | 0.906 | 0.9059 | 0.474 |
119
+ | 0.4958 | 0.8805 | 560 | 0.4663 | 0.901 | 0.9037 | 0.901 | 0.9008 | 0.459 |
120
+ | 0.4577 | 0.8962 | 570 | 0.4675 | 0.902 | 0.9054 | 0.9020 | 0.9018 | 0.454 |
121
+ | 0.5405 | 0.9119 | 580 | 0.4637 | 0.903 | 0.9055 | 0.903 | 0.9029 | 0.461 |
122
+ | 0.4792 | 0.9277 | 590 | 0.4622 | 0.907 | 0.9090 | 0.907 | 0.9069 | 0.465 |
123
+ | 0.4419 | 0.9434 | 600 | 0.4622 | 0.908 | 0.9101 | 0.9080 | 0.9079 | 0.464 |
124
+ | 0.4685 | 0.9591 | 610 | 0.4624 | 0.906 | 0.9084 | 0.9060 | 0.9059 | 0.462 |
125
+ | 0.4794 | 0.9748 | 620 | 0.4623 | 0.904 | 0.9063 | 0.9040 | 0.9039 | 0.462 |
126
+ | 0.4673 | 0.9906 | 630 | 0.4622 | 0.905 | 0.9072 | 0.905 | 0.9049 | 0.463 |
127
+
128
+
129
+ ### Framework versions
130
+
131
+ - Transformers 4.42.4
132
+ - Pytorch 2.3.1+cu121
133
+ - Datasets 2.20.0
134
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "projecte-aina/roberta-base-ca-v2-cased-te",
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
+ "finetuning_task": "mnli",
11
+ "gradient_checkpointing": false,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 768,
15
+ "id2label": {
16
+ "0": "ENTAILMENT",
17
+ "1": "NEUTRAL",
18
+ "2": "CONTRADICTION"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "label2id": {
23
+ "CONTRADICTION": 2,
24
+ "ENTAILMENT": 0,
25
+ "NEUTRAL": 1
26
+ },
27
+ "layer_norm_eps": 1e-05,
28
+ "max_position_embeddings": 514,
29
+ "model_type": "roberta",
30
+ "num_attention_heads": 12,
31
+ "num_hidden_layers": 12,
32
+ "pad_token_id": 1,
33
+ "position_embedding_type": "absolute",
34
+ "problem_type": "single_label_classification",
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.42.4",
37
+ "type_vocab_size": 1,
38
+ "use_cache": true,
39
+ "vocab_size": 50262
40
+ }
logs/events.out.tfevents.1722336885.183c440d058f.2175.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ecb58d1199d147ceac043c98e3a8b4d6646b5ce5cbe156b557def357931a2f3
3
+ size 51666
logs/events.out.tfevents.1722340752.183c440d058f.2175.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e48f3873b45ab043a2bac7a1956176dad5d73ce5a262b919c716805ea18e1ae7
3
+ size 609
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 sha256:9a604ff801fb560f906d7a8363af9d371d3994454b533d3da307261b259ae871
3
+ size 498606684
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 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
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
+ "4": {
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
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "max_len": 512,
52
+ "max_length": 512,
53
+ "model_max_length": 512,
54
+ "pad_to_multiple_of": null,
55
+ "pad_token": "<pad>",
56
+ "pad_token_type_id": 0,
57
+ "padding_side": "right",
58
+ "sep_token": "</s>",
59
+ "stride": 0,
60
+ "tokenizer_class": "RobertaTokenizer",
61
+ "trim_offsets": true,
62
+ "truncation_side": "right",
63
+ "truncation_strategy": "longest_first",
64
+ "unk_token": "<unk>"
65
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0d889fd179914f6d99682defe7f718368fbc64d5df1587da3e32754915b1362
3
+ size 5176
vocab.json ADDED
The diff for this file is too large to render. See raw diff