mahdibaghbanzadeh
commited on
Commit
•
ab6901e
1
Parent(s):
10001b5
End of training
Browse files- README.md +111 -0
- adapter_config.json +31 -0
- adapter_model.safetensors +3 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +52 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
base_model: mahdibaghbanzadeh/seqsight_4096_512_27M
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
model-index:
|
9 |
+
- name: GUE_EMP_H4-seqsight_4096_512_27M-L8_f
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# GUE_EMP_H4-seqsight_4096_512_27M-L8_f
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_27M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_27M) on the [mahdibaghbanzadeh/GUE_EMP_H4](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_EMP_H4) dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.2551
|
21 |
+
- F1 Score: 0.9068
|
22 |
+
- Accuracy: 0.9069
|
23 |
+
|
24 |
+
## Model description
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Intended uses & limitations
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training and evaluation data
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training procedure
|
37 |
+
|
38 |
+
### Training hyperparameters
|
39 |
+
|
40 |
+
The following hyperparameters were used during training:
|
41 |
+
- learning_rate: 0.0005
|
42 |
+
- train_batch_size: 128
|
43 |
+
- eval_batch_size: 128
|
44 |
+
- seed: 42
|
45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
+
- lr_scheduler_type: linear
|
47 |
+
- training_steps: 10000
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy |
|
52 |
+
|:-------------:|:------:|:-----:|:---------------:|:--------:|:--------:|
|
53 |
+
| 0.3471 | 2.17 | 200 | 0.2845 | 0.8905 | 0.8905 |
|
54 |
+
| 0.2699 | 4.35 | 400 | 0.2771 | 0.8975 | 0.8973 |
|
55 |
+
| 0.256 | 6.52 | 600 | 0.2791 | 0.8980 | 0.8980 |
|
56 |
+
| 0.2524 | 8.7 | 800 | 0.2844 | 0.8968 | 0.8966 |
|
57 |
+
| 0.2355 | 10.87 | 1000 | 0.2721 | 0.8974 | 0.8973 |
|
58 |
+
| 0.2317 | 13.04 | 1200 | 0.2751 | 0.8959 | 0.8960 |
|
59 |
+
| 0.2212 | 15.22 | 1400 | 0.2724 | 0.9009 | 0.9008 |
|
60 |
+
| 0.2121 | 17.39 | 1600 | 0.2963 | 0.8929 | 0.8925 |
|
61 |
+
| 0.2091 | 19.57 | 1800 | 0.2757 | 0.8958 | 0.8960 |
|
62 |
+
| 0.2005 | 21.74 | 2000 | 0.2915 | 0.8928 | 0.8925 |
|
63 |
+
| 0.1924 | 23.91 | 2200 | 0.3004 | 0.8967 | 0.8966 |
|
64 |
+
| 0.1899 | 26.09 | 2400 | 0.2886 | 0.8939 | 0.8939 |
|
65 |
+
| 0.1833 | 28.26 | 2600 | 0.3037 | 0.8904 | 0.8905 |
|
66 |
+
| 0.1757 | 30.43 | 2800 | 0.3066 | 0.8878 | 0.8877 |
|
67 |
+
| 0.1697 | 32.61 | 3000 | 0.3119 | 0.8913 | 0.8912 |
|
68 |
+
| 0.1624 | 34.78 | 3200 | 0.3126 | 0.8886 | 0.8884 |
|
69 |
+
| 0.162 | 36.96 | 3400 | 0.3169 | 0.8927 | 0.8925 |
|
70 |
+
| 0.1543 | 39.13 | 3600 | 0.3352 | 0.8842 | 0.8843 |
|
71 |
+
| 0.1493 | 41.3 | 3800 | 0.3331 | 0.8896 | 0.8898 |
|
72 |
+
| 0.147 | 43.48 | 4000 | 0.3379 | 0.8857 | 0.8857 |
|
73 |
+
| 0.1452 | 45.65 | 4200 | 0.3330 | 0.8855 | 0.8857 |
|
74 |
+
| 0.1398 | 47.83 | 4400 | 0.3484 | 0.8816 | 0.8816 |
|
75 |
+
| 0.1334 | 50.0 | 4600 | 0.3562 | 0.8792 | 0.8795 |
|
76 |
+
| 0.1307 | 52.17 | 4800 | 0.3630 | 0.8795 | 0.8795 |
|
77 |
+
| 0.1298 | 54.35 | 5000 | 0.3667 | 0.8813 | 0.8816 |
|
78 |
+
| 0.124 | 56.52 | 5200 | 0.3706 | 0.8791 | 0.8789 |
|
79 |
+
| 0.1249 | 58.7 | 5400 | 0.3701 | 0.8814 | 0.8816 |
|
80 |
+
| 0.12 | 60.87 | 5600 | 0.3806 | 0.8796 | 0.8795 |
|
81 |
+
| 0.1154 | 63.04 | 5800 | 0.3927 | 0.8754 | 0.8754 |
|
82 |
+
| 0.1164 | 65.22 | 6000 | 0.3902 | 0.8793 | 0.8795 |
|
83 |
+
| 0.1063 | 67.39 | 6200 | 0.3974 | 0.8769 | 0.8768 |
|
84 |
+
| 0.1064 | 69.57 | 6400 | 0.4084 | 0.8718 | 0.8720 |
|
85 |
+
| 0.1069 | 71.74 | 6600 | 0.4106 | 0.8809 | 0.8809 |
|
86 |
+
| 0.1047 | 73.91 | 6800 | 0.4167 | 0.8781 | 0.8782 |
|
87 |
+
| 0.0999 | 76.09 | 7000 | 0.4229 | 0.8760 | 0.8761 |
|
88 |
+
| 0.1023 | 78.26 | 7200 | 0.4182 | 0.8774 | 0.8775 |
|
89 |
+
| 0.098 | 80.43 | 7400 | 0.4268 | 0.8835 | 0.8836 |
|
90 |
+
| 0.0951 | 82.61 | 7600 | 0.4444 | 0.8688 | 0.8693 |
|
91 |
+
| 0.0957 | 84.78 | 7800 | 0.4376 | 0.8829 | 0.8830 |
|
92 |
+
| 0.0928 | 86.96 | 8000 | 0.4476 | 0.8786 | 0.8789 |
|
93 |
+
| 0.094 | 89.13 | 8200 | 0.4529 | 0.8717 | 0.8720 |
|
94 |
+
| 0.0912 | 91.3 | 8400 | 0.4487 | 0.8752 | 0.8754 |
|
95 |
+
| 0.0863 | 93.48 | 8600 | 0.4661 | 0.8724 | 0.8727 |
|
96 |
+
| 0.086 | 95.65 | 8800 | 0.4712 | 0.8718 | 0.8720 |
|
97 |
+
| 0.0875 | 97.83 | 9000 | 0.4598 | 0.8718 | 0.8720 |
|
98 |
+
| 0.0849 | 100.0 | 9200 | 0.4680 | 0.8712 | 0.8713 |
|
99 |
+
| 0.084 | 102.17 | 9400 | 0.4662 | 0.8725 | 0.8727 |
|
100 |
+
| 0.0833 | 104.35 | 9600 | 0.4652 | 0.8718 | 0.8720 |
|
101 |
+
| 0.0823 | 106.52 | 9800 | 0.4745 | 0.8724 | 0.8727 |
|
102 |
+
| 0.0855 | 108.7 | 10000 | 0.4703 | 0.8711 | 0.8713 |
|
103 |
+
|
104 |
+
|
105 |
+
### Framework versions
|
106 |
+
|
107 |
+
- PEFT 0.9.0
|
108 |
+
- Transformers 4.38.2
|
109 |
+
- Pytorch 2.2.0+cu121
|
110 |
+
- Datasets 2.17.1
|
111 |
+
- Tokenizers 0.15.2
|
adapter_config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "mahdibaghbanzadeh/seqsight_4096_512_27M",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"loftq_config": {},
|
12 |
+
"lora_alpha": 2.0,
|
13 |
+
"lora_dropout": 0.1,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": [
|
17 |
+
"classifier",
|
18 |
+
"pooler"
|
19 |
+
],
|
20 |
+
"peft_type": "LORA",
|
21 |
+
"r": 8,
|
22 |
+
"rank_pattern": {},
|
23 |
+
"revision": null,
|
24 |
+
"target_modules": [
|
25 |
+
"query_proj",
|
26 |
+
"value_proj"
|
27 |
+
],
|
28 |
+
"task_type": "SEQ_CLS",
|
29 |
+
"use_dora": false,
|
30 |
+
"use_rslora": false
|
31 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eff39ecfc587aed68d44a1be869d95b65a12d8b37ed2131637536830c1de351d
|
3 |
+
size 1584096
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": {
|
3 |
+
"content": "<cls>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<eos>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"mask_token": {
|
17 |
+
"content": "<sos>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"pad_token": {
|
24 |
+
"content": "<pad>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<sos>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<eos>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "<pad>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<cls>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
}
|
35 |
+
},
|
36 |
+
"clean_up_tokenization_spaces": true,
|
37 |
+
"cls_token": "<cls>",
|
38 |
+
"eos_token": "<eos>",
|
39 |
+
"mask_token": "<sos>",
|
40 |
+
"max_length": 512,
|
41 |
+
"model_max_length": 512,
|
42 |
+
"pad_to_multiple_of": null,
|
43 |
+
"pad_token": "<pad>",
|
44 |
+
"pad_token_type_id": 0,
|
45 |
+
"padding": "max_length",
|
46 |
+
"padding_side": "right",
|
47 |
+
"stride": 0,
|
48 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
49 |
+
"truncation": true,
|
50 |
+
"truncation_side": "right",
|
51 |
+
"truncation_strategy": "longest_first"
|
52 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:938b28f14371a73779e2a7fc00c3ecfc474b5c8449f466c4d4aae3c0d29e4580
|
3 |
+
size 4920
|