Hugging Face's logo

hcene
/
results

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
hcene commited on
Commit
f545141
·
verified ·
1 Parent(s): d7c53c7

hcene/finetuned-mDEBERTa-v3-mnli-xnli

Browse files
Files changed (5) hide show
  1. README.md +124 -0
  2. adapter_config.json +27 -0
  3. adapter_model.safetensors +3 -0
  4. logs/events.out.tfevents.1709148966.d79675d90a22.405.0 +3 -0
  5. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,124 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ library_name: peft
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ - precision
9
+ - recall
10
+ - f1
11
+ base_model: MoritzLaurer/mDeBERTa-v3-base-mnli-xnli
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 [MoritzLaurer/mDeBERTa-v3-base-mnli-xnli](https://huggingface.co/MoritzLaurer/mDeBERTa-v3-base-mnli-xnli) on the None dataset.
23
+ It achieves the following results on the evaluation set:
24
+ - Loss: 0.6765
25
+ - Accuracy: 0.7634
26
+ - Precision: 0.7675
27
+ - Recall: 0.7644
28
+ - F1: 0.7627
29
+ - Ratio: 0.3297
30
+
31
+ ## Model description
32
+
33
+ More information needed
34
+
35
+ ## Intended uses & limitations
36
+
37
+ More information needed
38
+
39
+ ## Training and evaluation data
40
+
41
+ More information needed
42
+
43
+ ## Training procedure
44
+
45
+ ### Training hyperparameters
46
+
47
+ The following hyperparameters were used during training:
48
+ - learning_rate: 0.0005
49
+ - train_batch_size: 20
50
+ - eval_batch_size: 20
51
+ - seed: 42
52
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
+ - lr_scheduler_type: linear
54
+ - lr_scheduler_warmup_ratio: 0.1
55
+ - lr_scheduler_warmup_steps: 4
56
+ - num_epochs: 20
57
+ - label_smoothing_factor: 0.1
58
+
59
+ ### Training results
60
+
61
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Ratio |
62
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:------:|
63
+ | 1.7741 | 0.17 | 10 | 1.0961 | 0.7061 | 0.7103 | 0.7073 | 0.7078 | 0.3262 |
64
+ | 1.2149 | 0.34 | 20 | 0.8783 | 0.7025 | 0.7066 | 0.7038 | 0.7044 | 0.3262 |
65
+ | 0.959 | 0.52 | 30 | 0.8413 | 0.6774 | 0.6981 | 0.6784 | 0.6854 | 0.2939 |
66
+ | 0.9582 | 0.69 | 40 | 0.7705 | 0.7312 | 0.7417 | 0.7321 | 0.7314 | 0.3190 |
67
+ | 0.8706 | 0.86 | 50 | 0.6728 | 0.7419 | 0.7545 | 0.7437 | 0.7385 | 0.3190 |
68
+ | 0.8804 | 1.03 | 60 | 0.6933 | 0.7133 | 0.7402 | 0.7157 | 0.6919 | 0.3190 |
69
+ | 0.8999 | 1.21 | 70 | 0.7167 | 0.7133 | 0.7208 | 0.7144 | 0.7158 | 0.3190 |
70
+ | 0.8914 | 1.38 | 80 | 0.6910 | 0.7384 | 0.7549 | 0.7390 | 0.7325 | 0.3226 |
71
+ | 0.8578 | 1.55 | 90 | 0.6862 | 0.7348 | 0.7533 | 0.7369 | 0.7243 | 0.3262 |
72
+ | 0.8755 | 1.72 | 100 | 0.6889 | 0.7240 | 0.7449 | 0.7263 | 0.7095 | 0.3262 |
73
+ | 0.8551 | 1.9 | 110 | 0.7090 | 0.7133 | 0.7408 | 0.7158 | 0.6899 | 0.3262 |
74
+ | 0.8736 | 2.07 | 120 | 0.7019 | 0.7097 | 0.7236 | 0.7120 | 0.6975 | 0.3262 |
75
+ | 0.8647 | 2.24 | 130 | 0.7078 | 0.7240 | 0.7354 | 0.7261 | 0.7174 | 0.3262 |
76
+ | 0.8755 | 2.41 | 140 | 0.7023 | 0.7527 | 0.7716 | 0.7533 | 0.7448 | 0.3262 |
77
+ | 0.858 | 2.59 | 150 | 0.6745 | 0.7384 | 0.7450 | 0.7393 | 0.7372 | 0.3262 |
78
+ | 0.8912 | 2.76 | 160 | 0.6842 | 0.7491 | 0.7635 | 0.7511 | 0.7424 | 0.3297 |
79
+ | 0.8294 | 2.93 | 170 | 0.6623 | 0.7599 | 0.7624 | 0.7609 | 0.7602 | 0.3297 |
80
+ | 0.8481 | 3.1 | 180 | 0.6652 | 0.7599 | 0.7715 | 0.7617 | 0.7551 | 0.3333 |
81
+ | 0.8488 | 3.28 | 190 | 0.6782 | 0.7312 | 0.7609 | 0.7335 | 0.7131 | 0.3297 |
82
+ | 0.8418 | 3.45 | 200 | 0.6884 | 0.7706 | 0.7738 | 0.7719 | 0.7720 | 0.3262 |
83
+ | 0.8774 | 3.62 | 210 | 0.7066 | 0.7419 | 0.7523 | 0.7438 | 0.7381 | 0.3262 |
84
+ | 0.8496 | 3.79 | 220 | 0.6687 | 0.7133 | 0.7214 | 0.7154 | 0.7060 | 0.3333 |
85
+ | 0.825 | 3.97 | 230 | 0.6618 | 0.7634 | 0.7833 | 0.7639 | 0.7547 | 0.3297 |
86
+ | 0.8933 | 4.14 | 240 | 0.6946 | 0.7419 | 0.7692 | 0.7424 | 0.7278 | 0.3262 |
87
+ | 0.8579 | 4.31 | 250 | 0.6795 | 0.7491 | 0.7786 | 0.7495 | 0.7353 | 0.3262 |
88
+ | 0.8023 | 4.48 | 260 | 0.6595 | 0.7563 | 0.7727 | 0.7569 | 0.7501 | 0.3262 |
89
+ | 0.8736 | 4.66 | 270 | 0.6703 | 0.7491 | 0.7558 | 0.7508 | 0.7482 | 0.3262 |
90
+ | 0.8291 | 4.83 | 280 | 0.7102 | 0.6989 | 0.7630 | 0.7019 | 0.6499 | 0.3262 |
91
+ | 0.8923 | 5.0 | 290 | 0.7004 | 0.7097 | 0.7571 | 0.7124 | 0.6756 | 0.3262 |
92
+ | 0.8571 | 5.17 | 300 | 0.6739 | 0.7634 | 0.7717 | 0.7642 | 0.7621 | 0.3262 |
93
+ | 0.8521 | 5.34 | 310 | 0.6666 | 0.7563 | 0.7710 | 0.7569 | 0.7511 | 0.3262 |
94
+ | 0.8369 | 5.52 | 320 | 0.6815 | 0.7455 | 0.7487 | 0.7467 | 0.7472 | 0.3262 |
95
+ | 0.7897 | 5.69 | 330 | 0.6731 | 0.7097 | 0.7343 | 0.7122 | 0.6871 | 0.3262 |
96
+ | 0.8801 | 5.86 | 340 | 0.6773 | 0.7419 | 0.7631 | 0.7441 | 0.7304 | 0.3297 |
97
+ | 0.891 | 6.03 | 350 | 0.7107 | 0.7491 | 0.7556 | 0.7509 | 0.7473 | 0.3297 |
98
+ | 0.8444 | 6.21 | 360 | 0.6805 | 0.7634 | 0.7879 | 0.7639 | 0.7543 | 0.3262 |
99
+ | 0.8375 | 6.38 | 370 | 0.6562 | 0.7599 | 0.7725 | 0.7605 | 0.7560 | 0.3262 |
100
+ | 0.8141 | 6.55 | 380 | 0.6578 | 0.7276 | 0.7409 | 0.7296 | 0.7217 | 0.3262 |
101
+ | 0.8792 | 6.72 | 390 | 0.6790 | 0.7204 | 0.7355 | 0.7226 | 0.7121 | 0.3262 |
102
+ | 0.8868 | 6.9 | 400 | 0.7063 | 0.7384 | 0.7411 | 0.7397 | 0.7404 | 0.3262 |
103
+ | 0.8767 | 7.07 | 410 | 0.7074 | 0.7240 | 0.7440 | 0.7262 | 0.7126 | 0.3262 |
104
+ | 0.8545 | 7.24 | 420 | 0.6725 | 0.7276 | 0.7520 | 0.7300 | 0.7108 | 0.3297 |
105
+ | 0.8589 | 7.41 | 430 | 0.6712 | 0.7276 | 0.7473 | 0.7299 | 0.7139 | 0.3297 |
106
+ | 0.8522 | 7.59 | 440 | 0.6853 | 0.7634 | 0.7655 | 0.7649 | 0.7644 | 0.3297 |
107
+ | 0.777 | 7.76 | 450 | 0.6623 | 0.7634 | 0.7714 | 0.7642 | 0.7604 | 0.3297 |
108
+ | 0.8903 | 7.93 | 460 | 0.6629 | 0.7599 | 0.7629 | 0.7609 | 0.7598 | 0.3297 |
109
+ | 0.8168 | 8.1 | 470 | 0.6714 | 0.7599 | 0.7650 | 0.7608 | 0.7584 | 0.3297 |
110
+ | 0.7979 | 8.28 | 480 | 0.6469 | 0.7491 | 0.7505 | 0.7505 | 0.7504 | 0.3297 |
111
+ | 0.8674 | 8.45 | 490 | 0.6553 | 0.7455 | 0.7603 | 0.7475 | 0.7382 | 0.3297 |
112
+ | 0.8475 | 8.62 | 500 | 0.6788 | 0.7563 | 0.7576 | 0.7576 | 0.7576 | 0.3297 |
113
+ | 0.8723 | 8.79 | 510 | 0.6862 | 0.7599 | 0.7613 | 0.7612 | 0.7611 | 0.3297 |
114
+ | 0.8684 | 8.97 | 520 | 0.6938 | 0.7563 | 0.7604 | 0.7579 | 0.7560 | 0.3297 |
115
+ | 0.8278 | 9.14 | 530 | 0.6765 | 0.7634 | 0.7675 | 0.7644 | 0.7627 | 0.3297 |
116
+
117
+
118
+ ### Framework versions
119
+
120
+ - PEFT 0.9.0
121
+ - Transformers 4.39.0.dev0
122
+ - Pytorch 2.1.0+cu121
123
+ - Datasets 2.17.1
124
+ - Tokenizers 0.15.2
adapter_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "MoritzLaurer/mDeBERTa-v3-base-mnli-xnli",
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": 8,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 16,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "classifier"
23
+ ],
24
+ "task_type": "SEQ_CLS",
25
+ "use_dora": false,
26
+ "use_rslora": false
27
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0a2a9a902e804d199fac33a014f1577378c6fdf4459645ce1dd39686a680ccc
3
+ size 768987780
logs/events.out.tfevents.1709148966.d79675d90a22.405.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16f961d528c63c9e993c11849867b14e1826a21523257333d09e35f0997387da
3
+ size 45011
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfd342eff91d0c0167627d75783bdc6dc3986996b5a3ffef26d04e3c36532650
3
+ size 4856