arielcerdap
commited on
End of training
Browse files- README.md +76 -0
- merges.txt +0 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
license: mit
|
6 |
+
base_model: FacebookAI/roberta-large
|
7 |
+
tags:
|
8 |
+
- generated_from_trainer
|
9 |
+
datasets:
|
10 |
+
- arielcerdap/TimeStamped
|
11 |
+
metrics:
|
12 |
+
- precision
|
13 |
+
- recall
|
14 |
+
- f1
|
15 |
+
- accuracy
|
16 |
+
model-index:
|
17 |
+
- name: Disfluency Labeling - Ariel Cerda
|
18 |
+
results: []
|
19 |
+
---
|
20 |
+
|
21 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
22 |
+
should probably proofread and complete it, then remove this comment. -->
|
23 |
+
|
24 |
+
# Disfluency Labeling - Ariel Cerda
|
25 |
+
|
26 |
+
This model is a fine-tuned version of [FacebookAI/roberta-large](https://huggingface.co/FacebookAI/roberta-large) on the TimeStamped dataset.
|
27 |
+
It achieves the following results on the evaluation set:
|
28 |
+
- Loss: 0.3900
|
29 |
+
- Precision: 0.9614
|
30 |
+
- Recall: 0.3542
|
31 |
+
- F1: 0.5177
|
32 |
+
- Accuracy: 0.9399
|
33 |
+
|
34 |
+
## Model description
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Intended uses & limitations
|
39 |
+
|
40 |
+
More information needed
|
41 |
+
|
42 |
+
## Training and evaluation data
|
43 |
+
|
44 |
+
More information needed
|
45 |
+
|
46 |
+
## Training procedure
|
47 |
+
|
48 |
+
### Training hyperparameters
|
49 |
+
|
50 |
+
The following hyperparameters were used during training:
|
51 |
+
- learning_rate: 1e-05
|
52 |
+
- train_batch_size: 8
|
53 |
+
- eval_batch_size: 8
|
54 |
+
- seed: 42
|
55 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
56 |
+
- lr_scheduler_type: linear
|
57 |
+
- num_epochs: 5
|
58 |
+
- mixed_precision_training: Native AMP
|
59 |
+
|
60 |
+
### Training results
|
61 |
+
|
62 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
63 |
+
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
64 |
+
| 0.3749 | 1.0 | 4557 | 0.3361 | 0.9683 | 0.3418 | 0.5053 | 0.9389 |
|
65 |
+
| 0.2825 | 2.0 | 9114 | 0.3920 | 0.9741 | 0.3297 | 0.4926 | 0.9378 |
|
66 |
+
| 0.6078 | 3.0 | 13671 | 0.3821 | 0.9651 | 0.3436 | 0.5068 | 0.9391 |
|
67 |
+
| 0.4052 | 4.0 | 18228 | 0.3838 | 0.9624 | 0.3485 | 0.5117 | 0.9395 |
|
68 |
+
| 0.4096 | 5.0 | 22785 | 0.3900 | 0.9614 | 0.3542 | 0.5177 | 0.9399 |
|
69 |
+
|
70 |
+
|
71 |
+
### Framework versions
|
72 |
+
|
73 |
+
- Transformers 4.47.0
|
74 |
+
- Pytorch 2.5.1+cu121
|
75 |
+
- Datasets 3.2.0
|
76 |
+
- Tokenizers 0.21.0
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
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": 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 |
+
"50264": {
|
37 |
+
"content": "<mask>",
|
38 |
+
"lstrip": true,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"bos_token": "<s>",
|
46 |
+
"clean_up_tokenization_spaces": false,
|
47 |
+
"cls_token": "<s>",
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"errors": "replace",
|
50 |
+
"extra_special_tokens": {},
|
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 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|