End of training
Browse files- README.md +85 -0
- config.json +51 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- runs/Jun23_14-39-02_fc0c4a274fb1/events.out.tfevents.1719153550.fc0c4a274fb1.161.0 +3 -0
- runs/Jun23_15-05-30_fc0c4a274fb1/events.out.tfevents.1719155140.fc0c4a274fb1.161.1 +3 -0
- runs/Jun23_15-05-30_fc0c4a274fb1/events.out.tfevents.1719157547.fc0c4a274fb1.161.2 +3 -0
- special_tokens_map.json +24 -0
- tokenizer_config.json +22 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: gpt2
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- precision
|
8 |
+
- recall
|
9 |
+
- f1
|
10 |
+
- accuracy
|
11 |
+
model-index:
|
12 |
+
- name: gpt2-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 |
+
# gpt2-finetuned-depression
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the None dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.6647
|
24 |
+
- Precision: 0.8917
|
25 |
+
- Recall: 0.8648
|
26 |
+
- F1: 0.8772
|
27 |
+
- Accuracy: 0.9104
|
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 | 0.4102 | 0.8382 | 0.7154 | 0.7590 | 0.8614 |
|
59 |
+
| 0.652 | 2.0 | 938 | 0.3335 | 0.8669 | 0.8254 | 0.8439 | 0.8838 |
|
60 |
+
| 0.3283 | 3.0 | 1407 | 0.4627 | 0.8978 | 0.8464 | 0.8689 | 0.9041 |
|
61 |
+
| 0.1988 | 4.0 | 1876 | 0.5853 | 0.9021 | 0.8324 | 0.8628 | 0.8987 |
|
62 |
+
| 0.1613 | 5.0 | 2345 | 0.6426 | 0.9034 | 0.8385 | 0.8672 | 0.8987 |
|
63 |
+
| 0.1013 | 6.0 | 2814 | 0.6247 | 0.8682 | 0.8611 | 0.8643 | 0.9041 |
|
64 |
+
| 0.0863 | 7.0 | 3283 | 0.7673 | 0.8930 | 0.8375 | 0.8617 | 0.8987 |
|
65 |
+
| 0.0757 | 8.0 | 3752 | 0.6647 | 0.8917 | 0.8648 | 0.8772 | 0.9104 |
|
66 |
+
| 0.0511 | 9.0 | 4221 | 0.6658 | 0.8768 | 0.8674 | 0.8720 | 0.9030 |
|
67 |
+
| 0.0581 | 10.0 | 4690 | 0.7686 | 0.9104 | 0.8595 | 0.8824 | 0.9094 |
|
68 |
+
| 0.0311 | 11.0 | 5159 | 0.6830 | 0.8918 | 0.8488 | 0.8685 | 0.8977 |
|
69 |
+
| 0.0537 | 12.0 | 5628 | 0.7438 | 0.9078 | 0.8563 | 0.8795 | 0.9062 |
|
70 |
+
| 0.0436 | 13.0 | 6097 | 0.7950 | 0.8933 | 0.8438 | 0.8663 | 0.8987 |
|
71 |
+
| 0.042 | 14.0 | 6566 | 0.7248 | 0.8986 | 0.8507 | 0.8726 | 0.9030 |
|
72 |
+
| 0.0374 | 15.0 | 7035 | 0.6973 | 0.8884 | 0.8504 | 0.8681 | 0.9009 |
|
73 |
+
| 0.0371 | 16.0 | 7504 | 0.7294 | 0.8874 | 0.8554 | 0.8703 | 0.9030 |
|
74 |
+
| 0.0371 | 17.0 | 7973 | 0.7649 | 0.8937 | 0.8486 | 0.8692 | 0.9030 |
|
75 |
+
| 0.0318 | 18.0 | 8442 | 0.7576 | 0.8879 | 0.8467 | 0.8657 | 0.9009 |
|
76 |
+
| 0.0307 | 19.0 | 8911 | 0.7556 | 0.8937 | 0.8486 | 0.8692 | 0.9030 |
|
77 |
+
| 0.0264 | 20.0 | 9380 | 0.7647 | 0.8930 | 0.8486 | 0.8689 | 0.9030 |
|
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 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "gpt2",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2ForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"id2label": {
|
12 |
+
"0": "NEGATIVE",
|
13 |
+
"1": "POSITIVE",
|
14 |
+
"2": "MODERATE"
|
15 |
+
},
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"label2id": {
|
18 |
+
"MODERATE": 2,
|
19 |
+
"NEGATIVE": 0,
|
20 |
+
"POSITIVE": 1
|
21 |
+
},
|
22 |
+
"layer_norm_epsilon": 1e-05,
|
23 |
+
"model_type": "gpt2",
|
24 |
+
"n_ctx": 1024,
|
25 |
+
"n_embd": 768,
|
26 |
+
"n_head": 12,
|
27 |
+
"n_inner": null,
|
28 |
+
"n_layer": 12,
|
29 |
+
"n_positions": 1024,
|
30 |
+
"pad_token_id": 50256,
|
31 |
+
"problem_type": "single_label_classification",
|
32 |
+
"reorder_and_upcast_attn": false,
|
33 |
+
"resid_pdrop": 0.1,
|
34 |
+
"scale_attn_by_inverse_layer_idx": false,
|
35 |
+
"scale_attn_weights": true,
|
36 |
+
"summary_activation": null,
|
37 |
+
"summary_first_dropout": 0.1,
|
38 |
+
"summary_proj_to_labels": true,
|
39 |
+
"summary_type": "cls_index",
|
40 |
+
"summary_use_proj": true,
|
41 |
+
"task_specific_params": {
|
42 |
+
"text-generation": {
|
43 |
+
"do_sample": true,
|
44 |
+
"max_length": 50
|
45 |
+
}
|
46 |
+
},
|
47 |
+
"torch_dtype": "float32",
|
48 |
+
"transformers_version": "4.41.2",
|
49 |
+
"use_cache": true,
|
50 |
+
"vocab_size": 50257
|
51 |
+
}
|
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 sha256:99715ca024f35ab359c65be38762b6e97934f4a1f13f8cd638ece299f4ee912b
|
3 |
+
size 497783504
|
runs/Jun23_14-39-02_fc0c4a274fb1/events.out.tfevents.1719153550.fc0c4a274fb1.161.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f9ae7263440ba1f0284a3eddfce4850a13262540202615d2a4eccdba8193eef0
|
3 |
+
size 12231
|
runs/Jun23_15-05-30_fc0c4a274fb1/events.out.tfevents.1719155140.fc0c4a274fb1.161.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d2adb22c172fa0e8fe6767fcafb7090dbfeadfb08267fbb3c166e3ddf985ce4
|
3 |
+
size 18850
|
runs/Jun23_15-05-30_fc0c4a274fb1/events.out.tfevents.1719157547.fc0c4a274fb1.161.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5df517bc9888b15a0abadca6bed3bb13ed94e8d22fd861764cc03eb0ae458f29
|
3 |
+
size 560
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|endoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<|endoftext|>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<|endoftext|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": true,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"50256": {
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
}
|
13 |
+
},
|
14 |
+
"bos_token": "<|endoftext|>",
|
15 |
+
"clean_up_tokenization_spaces": true,
|
16 |
+
"eos_token": "<|endoftext|>",
|
17 |
+
"errors": "replace",
|
18 |
+
"model_max_length": 1024,
|
19 |
+
"pad_token": "<|endoftext|>",
|
20 |
+
"tokenizer_class": "GPT2Tokenizer",
|
21 |
+
"unk_token": "<|endoftext|>"
|
22 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:448539a2f7fdc2540ab90904c094e96e6bcf89a86de60c00277e227b3b47fa7f
|
3 |
+
size 5112
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|