adriansanz
commited on
Commit
•
43995d4
1
Parent(s):
d7c0046
End of training
Browse files- README.md +96 -0
- config.json +40 -0
- logs/events.out.tfevents.1717059144.d9f832161b1b.207.5 +3 -0
- logs/events.out.tfevents.1717059151.d9f832161b1b.207.6 +3 -0
- logs/events.out.tfevents.1717060736.d9f832161b1b.207.7 +3 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +65 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: hib30_0524_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 |
+
# hib30_0524_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: 0.4210
|
24 |
+
- Accuracy: 0.939
|
25 |
+
- Precision: 0.9395
|
26 |
+
- Recall: 0.9390
|
27 |
+
- F1: 0.9390
|
28 |
+
- Ratio: 0.483
|
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 |
+
| 3.0959 | 0.04 | 10 | 1.4009 | 0.676 | 0.6972 | 0.6760 | 0.6670 | 0.664 |
|
65 |
+
| 1.1113 | 0.08 | 20 | 0.8087 | 0.762 | 0.7625 | 0.762 | 0.7619 | 0.478 |
|
66 |
+
| 0.7612 | 0.12 | 30 | 0.6509 | 0.829 | 0.8370 | 0.829 | 0.8280 | 0.423 |
|
67 |
+
| 0.6255 | 0.16 | 40 | 0.5520 | 0.889 | 0.8890 | 0.889 | 0.8890 | 0.497 |
|
68 |
+
| 0.6143 | 0.2 | 50 | 0.5165 | 0.902 | 0.9020 | 0.902 | 0.9020 | 0.498 |
|
69 |
+
| 0.5531 | 0.24 | 60 | 0.4875 | 0.914 | 0.9140 | 0.914 | 0.9140 | 0.502 |
|
70 |
+
| 0.504 | 0.28 | 70 | 0.4794 | 0.906 | 0.9067 | 0.906 | 0.9060 | 0.52 |
|
71 |
+
| 0.4985 | 0.32 | 80 | 0.4876 | 0.907 | 0.9090 | 0.907 | 0.9069 | 0.465 |
|
72 |
+
| 0.5141 | 0.36 | 90 | 0.4635 | 0.916 | 0.9160 | 0.916 | 0.9160 | 0.496 |
|
73 |
+
| 0.4829 | 0.4 | 100 | 0.4521 | 0.923 | 0.9246 | 0.923 | 0.9229 | 0.469 |
|
74 |
+
| 0.4957 | 0.44 | 110 | 0.4505 | 0.922 | 0.9240 | 0.9220 | 0.9219 | 0.466 |
|
75 |
+
| 0.4618 | 0.48 | 120 | 0.4377 | 0.931 | 0.9318 | 0.931 | 0.9310 | 0.479 |
|
76 |
+
| 0.4385 | 0.52 | 130 | 0.4361 | 0.937 | 0.9370 | 0.937 | 0.9370 | 0.495 |
|
77 |
+
| 0.4671 | 0.56 | 140 | 0.4443 | 0.925 | 0.9264 | 0.925 | 0.9249 | 0.471 |
|
78 |
+
| 0.4563 | 0.6 | 150 | 0.4327 | 0.933 | 0.9332 | 0.933 | 0.9330 | 0.489 |
|
79 |
+
| 0.3977 | 0.64 | 160 | 0.4369 | 0.93 | 0.9301 | 0.93 | 0.9300 | 0.494 |
|
80 |
+
| 0.4245 | 0.68 | 170 | 0.4520 | 0.93 | 0.9328 | 0.9300 | 0.9299 | 0.46 |
|
81 |
+
| 0.4108 | 0.72 | 180 | 0.4347 | 0.933 | 0.9331 | 0.933 | 0.9330 | 0.493 |
|
82 |
+
| 0.4498 | 0.76 | 190 | 0.4296 | 0.93 | 0.93 | 0.93 | 0.93 | 0.5 |
|
83 |
+
| 0.4476 | 0.8 | 200 | 0.4259 | 0.936 | 0.9363 | 0.9360 | 0.9360 | 0.486 |
|
84 |
+
| 0.446 | 0.84 | 210 | 0.4231 | 0.936 | 0.9363 | 0.9360 | 0.9360 | 0.486 |
|
85 |
+
| 0.4218 | 0.88 | 220 | 0.4249 | 0.94 | 0.9406 | 0.94 | 0.9400 | 0.482 |
|
86 |
+
| 0.4645 | 0.92 | 230 | 0.4218 | 0.937 | 0.9374 | 0.937 | 0.9370 | 0.485 |
|
87 |
+
| 0.4955 | 0.96 | 240 | 0.4212 | 0.939 | 0.9395 | 0.9390 | 0.9390 | 0.483 |
|
88 |
+
| 0.4513 | 1.0 | 250 | 0.4210 | 0.939 | 0.9395 | 0.9390 | 0.9390 | 0.483 |
|
89 |
+
|
90 |
+
|
91 |
+
### Framework versions
|
92 |
+
|
93 |
+
- Transformers 4.41.1
|
94 |
+
- Pytorch 2.3.0+cu121
|
95 |
+
- Datasets 2.19.1
|
96 |
+
- 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": "4.41.1",
|
37 |
+
"type_vocab_size": 1,
|
38 |
+
"use_cache": true,
|
39 |
+
"vocab_size": 50262
|
40 |
+
}
|
logs/events.out.tfevents.1717059144.d9f832161b1b.207.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc3a50db273dac9a0d836139b1cdec583438364c0e3f3307c3db9f13dd4757df
|
3 |
+
size 5127
|
logs/events.out.tfevents.1717059151.d9f832161b1b.207.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed1b95c1deeef6add950f27a7012cb5104a79a26d97851bb358db11f43e75f4a
|
3 |
+
size 23820
|
logs/events.out.tfevents.1717060736.d9f832161b1b.207.7
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64d5321dac7f3853adfa0780a49b29b7b7e262f515cd5f24ca465a06de44e56a
|
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 sha256:3b1c03c774e6c1fb724ccf6846c5b86aa4e5b2f53921e48bd9e8f70a9eb1067b
|
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:f903487e3aca7e9fc02648be72c4c8bf331ab92e5c07383e644d23147a298452
|
3 |
+
size 5112
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|