adriansanz commited on
Commit
789dcad
·
verified ·
1 Parent(s): 605791d
README.md ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: stocks
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
+ # stocks
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: 0.7277
24
+ - Accuracy: 0.8042
25
+ - Precision: 0.8164
26
+ - Recall: 0.8082
27
+ - F1: 0.8034
28
+ - Ratio: 0.5833
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: 4
49
+ - eval_batch_size: 2
50
+ - seed: 42
51
+ - gradient_accumulation_steps: 2
52
+ - total_train_batch_size: 8
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: 2
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
+ | 3.4817 | 0.1429 | 10 | 1.8123 | 0.55 | 0.5523 | 0.552 | 0.5497 | 0.5458 |
65
+ | 1.3575 | 0.2857 | 20 | 1.3976 | 0.5542 | 0.5525 | 0.5483 | 0.5421 | 0.3583 |
66
+ | 1.0748 | 0.4286 | 30 | 0.9633 | 0.5917 | 0.5908 | 0.5906 | 0.5906 | 0.4708 |
67
+ | 0.878 | 0.5714 | 40 | 0.8403 | 0.6583 | 0.6646 | 0.6616 | 0.6575 | 0.5708 |
68
+ | 0.8718 | 0.7143 | 50 | 0.7818 | 0.7125 | 0.7277 | 0.7174 | 0.7103 | 0.6083 |
69
+ | 0.7897 | 0.8571 | 60 | 0.7231 | 0.7833 | 0.7921 | 0.7868 | 0.7828 | 0.5708 |
70
+ | 0.6933 | 1.0 | 70 | 0.7606 | 0.7917 | 0.8026 | 0.7955 | 0.7910 | 0.5792 |
71
+ | 0.6953 | 1.1429 | 80 | 0.7457 | 0.7875 | 0.7939 | 0.7904 | 0.7872 | 0.5583 |
72
+ | 0.5491 | 1.2857 | 90 | 0.7324 | 0.7917 | 0.7939 | 0.7934 | 0.7917 | 0.5292 |
73
+ | 0.5106 | 1.4286 | 100 | 0.7595 | 0.8042 | 0.8093 | 0.8068 | 0.8040 | 0.55 |
74
+ | 0.7078 | 1.5714 | 110 | 0.7645 | 0.8042 | 0.8108 | 0.8071 | 0.8039 | 0.5583 |
75
+ | 0.7572 | 1.7143 | 120 | 0.7544 | 0.8 | 0.8111 | 0.8038 | 0.7993 | 0.5792 |
76
+ | 0.6879 | 1.8571 | 130 | 0.7307 | 0.8042 | 0.8164 | 0.8082 | 0.8034 | 0.5833 |
77
+ | 0.6025 | 2.0 | 140 | 0.7277 | 0.8042 | 0.8164 | 0.8082 | 0.8034 | 0.5833 |
78
+
79
+
80
+ ### Framework versions
81
+
82
+ - Transformers 4.40.0
83
+ - Pytorch 2.1.0+cu121
84
+ - Datasets 2.19.0
85
+ - 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": "4.40.0",
37
+ "type_vocab_size": 1,
38
+ "use_cache": true,
39
+ "vocab_size": 50262
40
+ }
logs/events.out.tfevents.1713874916.d627388554e9.3459.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3e802120ebfe73433f79edacd3442ca9d6153dc70ccc349fdb1e6bebb61724b
3
+ size 10965
logs/events.out.tfevents.1713875042.d627388554e9.3459.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f08c9943e42f5c4cf93965c4807f8f346cfb11516a2bbe2f549ee84efb6fb103
3
+ size 599
logs/events.out.tfevents.1713875326.d627388554e9.6190.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa8e8bc9f4d1dbb49f7ce4cd380963e72600beb27f805c6818047e394a5006b0
3
+ size 16025
logs/events.out.tfevents.1713875828.d627388554e9.6190.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:282f8726161cdcf3a5dc700e3a5825f1b48a4283511857e0d181b201b48554e4
3
+ size 7060
logs/events.out.tfevents.1713875949.d627388554e9.9129.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5751a5339fd7f442ec170444b308ec011b41ba8bba9ab9975bb699065a346549
3
+ size 16030
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 sha256:8aa05b328892808d66e797511637d38e49b4d9afc6b7f166ef2b3c0c0d6d6721
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 sha256:15c41e4d3693d5eca59930040edf5adba8f010e8af4bd40ac7a3f7213d495b1c
3
+ size 4920
vocab.json ADDED
The diff for this file is too large to render. See raw diff