End of training
Browse files- README.md +85 -0
- config.json +39 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- runs/Jun23_08-12-57_4a31ffc4fc93/events.out.tfevents.1719130382.4a31ffc4fc93.541.1 +3 -0
- runs/Jun23_08-32-24_4a31ffc4fc93/events.out.tfevents.1719131565.4a31ffc4fc93.541.2 +3 -0
- runs/Jun23_08-32-24_4a31ffc4fc93/events.out.tfevents.1719134635.4a31ffc4fc93.541.3 +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: cc-by-nc-4.0
|
3 |
+
base_model: mental/mental-roberta-base
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- precision
|
8 |
+
- recall
|
9 |
+
- f1
|
10 |
+
- accuracy
|
11 |
+
model-index:
|
12 |
+
- name: mental-roberta-base-finetuned-depression
|
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 |
+
# mental-roberta-base-finetuned-depression
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [mental/mental-roberta-base](https://huggingface.co/mental/mental-roberta-base) on the None dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.6567
|
24 |
+
- Precision: 0.8863
|
25 |
+
- Recall: 0.9168
|
26 |
+
- F1: 0.8996
|
27 |
+
- Accuracy: 0.9115
|
28 |
+
|
29 |
+
## Model description
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Intended uses & limitations
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training and evaluation data
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Training procedure
|
42 |
+
|
43 |
+
### Training hyperparameters
|
44 |
+
|
45 |
+
The following hyperparameters were used during training:
|
46 |
+
- learning_rate: 2e-05
|
47 |
+
- train_batch_size: 8
|
48 |
+
- eval_batch_size: 8
|
49 |
+
- seed: 42
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: linear
|
52 |
+
- num_epochs: 20
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
57 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
58 |
+
| No log | 1.0 | 469 | 0.3852 | 0.7878 | 0.8253 | 0.7958 | 0.8667 |
|
59 |
+
| 0.5249 | 2.0 | 938 | 0.4720 | 0.8778 | 0.8722 | 0.8662 | 0.8913 |
|
60 |
+
| 0.2598 | 3.0 | 1407 | 0.5459 | 0.8975 | 0.8791 | 0.8865 | 0.8977 |
|
61 |
+
| 0.1624 | 4.0 | 1876 | 0.5022 | 0.9004 | 0.8979 | 0.8976 | 0.9072 |
|
62 |
+
| 0.1036 | 5.0 | 2345 | 0.6257 | 0.8910 | 0.8968 | 0.8931 | 0.9009 |
|
63 |
+
| 0.0668 | 6.0 | 2814 | 0.6531 | 0.9145 | 0.8927 | 0.9026 | 0.9104 |
|
64 |
+
| 0.0539 | 7.0 | 3283 | 0.6209 | 0.8552 | 0.9115 | 0.8802 | 0.8945 |
|
65 |
+
| 0.057 | 8.0 | 3752 | 0.6567 | 0.8863 | 0.9168 | 0.8996 | 0.9115 |
|
66 |
+
| 0.0523 | 9.0 | 4221 | 0.7184 | 0.9067 | 0.8984 | 0.8993 | 0.9083 |
|
67 |
+
| 0.0354 | 10.0 | 4690 | 0.7112 | 0.8874 | 0.9014 | 0.8914 | 0.9072 |
|
68 |
+
| 0.0268 | 11.0 | 5159 | 0.7168 | 0.8996 | 0.9012 | 0.8979 | 0.9083 |
|
69 |
+
| 0.0297 | 12.0 | 5628 | 0.7499 | 0.8667 | 0.9096 | 0.8847 | 0.9030 |
|
70 |
+
| 0.0242 | 13.0 | 6097 | 0.7554 | 0.8946 | 0.9014 | 0.8955 | 0.9072 |
|
71 |
+
| 0.0238 | 14.0 | 6566 | 0.7990 | 0.8909 | 0.9014 | 0.8934 | 0.9072 |
|
72 |
+
| 0.0178 | 15.0 | 7035 | 0.8298 | 0.8965 | 0.8933 | 0.8925 | 0.9051 |
|
73 |
+
| 0.0226 | 16.0 | 7504 | 0.8428 | 0.9099 | 0.8890 | 0.8973 | 0.9062 |
|
74 |
+
| 0.0226 | 17.0 | 7973 | 0.8490 | 0.8742 | 0.8983 | 0.8816 | 0.9041 |
|
75 |
+
| 0.0183 | 18.0 | 8442 | 0.8148 | 0.8940 | 0.8965 | 0.8930 | 0.9072 |
|
76 |
+
| 0.0188 | 19.0 | 8911 | 0.8146 | 0.8927 | 0.8960 | 0.8921 | 0.9062 |
|
77 |
+
| 0.015 | 20.0 | 9380 | 0.8216 | 0.8927 | 0.8960 | 0.8921 | 0.9062 |
|
78 |
+
|
79 |
+
|
80 |
+
### Framework versions
|
81 |
+
|
82 |
+
- Transformers 4.41.2
|
83 |
+
- Pytorch 2.3.0+cu121
|
84 |
+
- Datasets 2.20.0
|
85 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "mental/mental-roberta-base",
|
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 |
+
"gradient_checkpointing": false,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "NEGATIVE",
|
16 |
+
"1": "POSITIVE",
|
17 |
+
"2": "MODERATE"
|
18 |
+
},
|
19 |
+
"initializer_range": 0.02,
|
20 |
+
"intermediate_size": 3072,
|
21 |
+
"label2id": {
|
22 |
+
"MODERATE": 2,
|
23 |
+
"NEGATIVE": 0,
|
24 |
+
"POSITIVE": 1
|
25 |
+
},
|
26 |
+
"layer_norm_eps": 1e-05,
|
27 |
+
"max_position_embeddings": 514,
|
28 |
+
"model_type": "roberta",
|
29 |
+
"num_attention_heads": 12,
|
30 |
+
"num_hidden_layers": 12,
|
31 |
+
"pad_token_id": 1,
|
32 |
+
"position_embedding_type": "absolute",
|
33 |
+
"problem_type": "single_label_classification",
|
34 |
+
"torch_dtype": "float32",
|
35 |
+
"transformers_version": "4.41.2",
|
36 |
+
"type_vocab_size": 1,
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 50265
|
39 |
+
}
|
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 sha256:371415df594d96103b13026c2529266204afd2c532832e4f62a53e3facb82953
|
3 |
+
size 498615900
|
runs/Jun23_08-12-57_4a31ffc4fc93/events.out.tfevents.1719130382.4a31ffc4fc93.541.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49fb462cef3193e72803d6deb8bff0fc5c50cf72d9b23bb13221dd4a4864e202
|
3 |
+
size 12142
|
runs/Jun23_08-32-24_4a31ffc4fc93/events.out.tfevents.1719131565.4a31ffc4fc93.541.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d04156553f08c2cb0eae54156cac57541168ace611bdaf177df200e3cd9a336e
|
3 |
+
size 18712
|
runs/Jun23_08-32-24_4a31ffc4fc93/events.out.tfevents.1719134635.4a31ffc4fc93.541.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:953d941d0594db6cef263333c334b03ad6edf45ad699ff0fb060e3fc66a87d25
|
3 |
+
size 560
|
special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "<mask>",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
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 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<pad>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
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": true,
|
47 |
+
"cls_token": "<s>",
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"errors": "replace",
|
50 |
+
"mask_token": "<mask>",
|
51 |
+
"model_max_length": 512,
|
52 |
+
"pad_token": "<pad>",
|
53 |
+
"sep_token": "</s>",
|
54 |
+
"tokenizer_class": "RobertaTokenizer",
|
55 |
+
"trim_offsets": true,
|
56 |
+
"unk_token": "<unk>"
|
57 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cdeb7148e24fc0d0a7865d3c97704c133021e27beb2f14f1ed8502dff7fd8de9
|
3 |
+
size 5176
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|