Hugging Face's logo

CoCoRooXin
/
finetuned_bart_mnli

PEFT
Safetensors
Generated from Trainer
Model card Files Community
CoCoRooXin commited on
Commit
ef2ff0c
•
1 Parent(s): 4368021

./finetuned_bart

Browse files
Files changed (8) hide show
  1. README.md +103 -0
  2. adapter_config.json +31 -0
  3. adapter_model.safetensors +3 -0
  4. merges.txt +0 -0
  5. special_tokens_map.json +51 -0
  6. tokenizer_config.json +56 -0
  7. training_args.bin +3 -0
  8. vocab.json +0 -0
README.md ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ library_name: peft
4
+ tags:
5
+ - generated_from_trainer
6
+ base_model: facebook/bart-large-mnli
7
+ metrics:
8
+ - f1
9
+ - precision
10
+ - recall
11
+ - accuracy
12
+ model-index:
13
+ - name: results
14
+ results: []
15
+ ---
16
+
17
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
18
+ should probably proofread and complete it, then remove this comment. -->
19
+
20
+ # results
21
+
22
+ This model is a fine-tuned version of [facebook/bart-large-mnli](https://huggingface.co/facebook/bart-large-mnli) on an unknown dataset.
23
+ It achieves the following results on the evaluation set:
24
+ - Loss: 0.1726
25
+ - F1: 0.9412
26
+ - Precision: 0.9524
27
+ - Recall: 0.9302
28
+ - Accuracy: 0.9333
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: 0.0002
48
+ - train_batch_size: 16
49
+ - eval_batch_size: 16
50
+ - seed: 42
51
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
+ - lr_scheduler_type: linear
53
+ - num_epochs: 5
54
+
55
+ ### Training results
56
+
57
+ | Training Loss | Epoch | Step | Validation Loss | F1 | Precision | Recall | Accuracy |
58
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:---------:|:------:|:--------:|
59
+ | 0.5809 | 0.14 | 10 | 0.3912 | 0.8671 | 0.8621 | 0.8721 | 0.8467 |
60
+ | 0.3659 | 0.28 | 20 | 0.3689 | 0.8790 | 0.9718 | 0.8023 | 0.8733 |
61
+ | 0.3805 | 0.42 | 30 | 0.2890 | 0.9133 | 0.9080 | 0.9186 | 0.9 |
62
+ | 0.4068 | 0.56 | 40 | 0.3249 | 0.9068 | 0.9733 | 0.8488 | 0.9 |
63
+ | 0.3183 | 0.69 | 50 | 0.2801 | 0.9133 | 0.9080 | 0.9186 | 0.9 |
64
+ | 0.1929 | 0.83 | 60 | 0.2832 | 0.9123 | 0.9176 | 0.9070 | 0.9 |
65
+ | 0.2861 | 0.97 | 70 | 0.2883 | 0.9195 | 0.9091 | 0.9302 | 0.9067 |
66
+ | 0.209 | 1.11 | 80 | 0.3000 | 0.9222 | 0.9506 | 0.8953 | 0.9133 |
67
+ | 0.2192 | 1.25 | 90 | 0.2845 | 0.9176 | 0.9286 | 0.9070 | 0.9067 |
68
+ | 0.3116 | 1.39 | 100 | 0.2520 | 0.9249 | 0.9195 | 0.9302 | 0.9133 |
69
+ | 0.2512 | 1.53 | 110 | 0.2650 | 0.9222 | 0.9506 | 0.8953 | 0.9133 |
70
+ | 0.1774 | 1.67 | 120 | 0.2571 | 0.9231 | 0.9398 | 0.9070 | 0.9133 |
71
+ | 0.1126 | 1.81 | 130 | 0.2668 | 0.9364 | 0.9310 | 0.9419 | 0.9267 |
72
+ | 0.2379 | 1.94 | 140 | 0.3075 | 0.9012 | 0.9605 | 0.8488 | 0.8933 |
73
+ | 0.2753 | 2.08 | 150 | 0.2254 | 0.9240 | 0.9294 | 0.9186 | 0.9133 |
74
+ | 0.1727 | 2.22 | 160 | 0.2707 | 0.9310 | 0.9205 | 0.9419 | 0.92 |
75
+ | 0.224 | 2.36 | 170 | 0.3118 | 0.9057 | 0.9863 | 0.8372 | 0.9 |
76
+ | 0.2056 | 2.5 | 180 | 0.2673 | 0.9302 | 0.9302 | 0.9302 | 0.92 |
77
+ | 0.2274 | 2.64 | 190 | 0.2515 | 0.9302 | 0.9302 | 0.9302 | 0.92 |
78
+ | 0.1193 | 2.78 | 200 | 0.2250 | 0.9357 | 0.9412 | 0.9302 | 0.9267 |
79
+ | 0.2806 | 2.92 | 210 | 0.2268 | 0.9286 | 0.9512 | 0.9070 | 0.92 |
80
+ | 0.1272 | 3.06 | 220 | 0.2031 | 0.9349 | 0.9518 | 0.9186 | 0.9267 |
81
+ | 0.1879 | 3.19 | 230 | 0.1730 | 0.9480 | 0.9425 | 0.9535 | 0.94 |
82
+ | 0.1341 | 3.33 | 240 | 0.1867 | 0.9419 | 0.9419 | 0.9419 | 0.9333 |
83
+ | 0.1376 | 3.47 | 250 | 0.2628 | 0.9341 | 0.9630 | 0.9070 | 0.9267 |
84
+ | 0.1599 | 3.61 | 260 | 0.2484 | 0.9405 | 0.9634 | 0.9186 | 0.9333 |
85
+ | 0.1899 | 3.75 | 270 | 0.1847 | 0.9480 | 0.9425 | 0.9535 | 0.94 |
86
+ | 0.0828 | 3.89 | 280 | 0.1869 | 0.9412 | 0.9524 | 0.9302 | 0.9333 |
87
+ | 0.1025 | 4.03 | 290 | 0.1876 | 0.9349 | 0.9518 | 0.9186 | 0.9267 |
88
+ | 0.118 | 4.17 | 300 | 0.1811 | 0.9419 | 0.9419 | 0.9419 | 0.9333 |
89
+ | 0.1475 | 4.31 | 310 | 0.1901 | 0.9294 | 0.9405 | 0.9186 | 0.92 |
90
+ | 0.1354 | 4.44 | 320 | 0.1805 | 0.9357 | 0.9412 | 0.9302 | 0.9267 |
91
+ | 0.1444 | 4.58 | 330 | 0.1706 | 0.9540 | 0.9432 | 0.9651 | 0.9467 |
92
+ | 0.1068 | 4.72 | 340 | 0.1693 | 0.9480 | 0.9425 | 0.9535 | 0.94 |
93
+ | 0.0875 | 4.86 | 350 | 0.1715 | 0.9412 | 0.9524 | 0.9302 | 0.9333 |
94
+ | 0.0922 | 5.0 | 360 | 0.1726 | 0.9412 | 0.9524 | 0.9302 | 0.9333 |
95
+
96
+
97
+ ### Framework versions
98
+
99
+ - PEFT 0.9.0
100
+ - Transformers 4.39.1
101
+ - Pytorch 2.2.1+cu121
102
+ - Datasets 2.18.0
103
+ - 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": "facebook/bart-large-mnli",
5
+ "bias": "all",
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": 16,
13
+ "lora_dropout": 0.1,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": [
17
+ "classifier"
18
+ ],
19
+ "peft_type": "LORA",
20
+ "r": 32,
21
+ "rank_pattern": {},
22
+ "revision": null,
23
+ "target_modules": [
24
+ "v_proj",
25
+ "q_proj",
26
+ "k_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:fb575f58dd089dfd11afc465adac1cdf2fb423939695c0f7772b23b28a28d4e3
3
+ size 29715792
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
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_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
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": 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
+ "model_max_length": 1024,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "BartTokenizer",
55
+ "unk_token": "<unk>"
56
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08fd4e58056a20f4e187518f37efc41da6083a417ae812a4901e79975171b06f
3
+ size 4856
vocab.json ADDED
The diff for this file is too large to render. See raw diff