xshubhamx commited on
Commit
9d2f03f
1 Parent(s): 62ac2d0

Upload folder using huggingface_hub

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ training_checkpoints/*
README.md ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - accuracy
7
+ - precision
8
+ - recall
9
+ base_model: facebook/bart-base
10
+ model-index:
11
+ - name: bart-base-lora
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # bart-base-lora
19
+
20
+ This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on an unknown dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 0.6655
23
+ - Accuracy: 0.7963
24
+ - Precision: 0.7841
25
+ - Recall: 0.7963
26
+ - Precision Macro: 0.5968
27
+ - Recall Macro: 0.6325
28
+ - Macro Fpr: 0.0186
29
+ - Weighted Fpr: 0.0179
30
+ - Weighted Specificity: 0.9749
31
+ - Macro Specificity: 0.9847
32
+ - Weighted Sensitivity: 0.7963
33
+ - Macro Sensitivity: 0.6325
34
+ - F1 Micro: 0.7963
35
+ - F1 Macro: 0.6074
36
+ - F1 Weighted: 0.7859
37
+
38
+ ## Model description
39
+
40
+ More information needed
41
+
42
+ ## Intended uses & limitations
43
+
44
+ More information needed
45
+
46
+ ## Training and evaluation data
47
+
48
+ More information needed
49
+
50
+ ## Training procedure
51
+
52
+ ### Training hyperparameters
53
+
54
+ The following hyperparameters were used during training:
55
+ - learning_rate: 5e-05
56
+ - train_batch_size: 8
57
+ - eval_batch_size: 8
58
+ - seed: 42
59
+ - gradient_accumulation_steps: 4
60
+ - total_train_batch_size: 32
61
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
+ - lr_scheduler_type: linear
63
+ - num_epochs: 15
64
+
65
+ ### Training results
66
+
67
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | Precision Macro | Recall Macro | Macro Fpr | Weighted Fpr | Weighted Specificity | Macro Specificity | Weighted Sensitivity | Macro Sensitivity | F1 Micro | F1 Macro | F1 Weighted |
68
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:---------------:|:------------:|:---------:|:------------:|:--------------------:|:-----------------:|:--------------------:|:-----------------:|:--------:|:--------:|:-----------:|
69
+ | No log | 1.0 | 160 | 1.2642 | 0.6313 | 0.5477 | 0.6313 | 0.3009 | 0.3127 | 0.0428 | 0.0400 | 0.9351 | 0.9711 | 0.6313 | 0.3127 | 0.6313 | 0.2941 | 0.5769 |
70
+ | No log | 2.0 | 321 | 0.8962 | 0.7119 | 0.6939 | 0.7119 | 0.3937 | 0.4525 | 0.0285 | 0.0281 | 0.9669 | 0.9786 | 0.7119 | 0.4525 | 0.7119 | 0.4107 | 0.6960 |
71
+ | No log | 3.0 | 482 | 0.8204 | 0.7196 | 0.6953 | 0.7196 | 0.3974 | 0.4468 | 0.0278 | 0.0271 | 0.9653 | 0.9790 | 0.7196 | 0.4468 | 0.7196 | 0.3998 | 0.6885 |
72
+ | 1.2731 | 4.0 | 643 | 0.7519 | 0.7436 | 0.7186 | 0.7436 | 0.4131 | 0.4673 | 0.0244 | 0.0240 | 0.9695 | 0.9809 | 0.7436 | 0.4673 | 0.7436 | 0.4272 | 0.7248 |
73
+ | 1.2731 | 5.0 | 803 | 0.7364 | 0.7475 | 0.7524 | 0.7475 | 0.6132 | 0.5050 | 0.0243 | 0.0236 | 0.9679 | 0.9810 | 0.7475 | 0.5050 | 0.7475 | 0.4905 | 0.7286 |
74
+ | 1.2731 | 6.0 | 964 | 0.7273 | 0.7514 | 0.7423 | 0.7514 | 0.5784 | 0.5258 | 0.0237 | 0.0231 | 0.9699 | 0.9814 | 0.7514 | 0.5258 | 0.7514 | 0.5150 | 0.7311 |
75
+ | 0.7243 | 7.0 | 1125 | 0.6993 | 0.7645 | 0.7478 | 0.7645 | 0.5498 | 0.5565 | 0.0222 | 0.0215 | 0.9721 | 0.9824 | 0.7645 | 0.5565 | 0.7645 | 0.5453 | 0.7538 |
76
+ | 0.7243 | 8.0 | 1286 | 0.6952 | 0.7769 | 0.7639 | 0.7769 | 0.5682 | 0.5888 | 0.0207 | 0.0201 | 0.9731 | 0.9833 | 0.7769 | 0.5888 | 0.7769 | 0.5700 | 0.7649 |
77
+ | 0.7243 | 9.0 | 1446 | 0.6759 | 0.7823 | 0.7708 | 0.7823 | 0.5764 | 0.5877 | 0.0201 | 0.0195 | 0.9739 | 0.9838 | 0.7823 | 0.5877 | 0.7823 | 0.5699 | 0.7697 |
78
+ | 0.6098 | 10.0 | 1607 | 0.6705 | 0.7847 | 0.7720 | 0.7847 | 0.5899 | 0.6176 | 0.0199 | 0.0192 | 0.9732 | 0.9839 | 0.7847 | 0.6176 | 0.7847 | 0.5935 | 0.7724 |
79
+ | 0.6098 | 11.0 | 1768 | 0.6794 | 0.7909 | 0.7737 | 0.7909 | 0.5882 | 0.6237 | 0.0193 | 0.0185 | 0.9736 | 0.9843 | 0.7909 | 0.6237 | 0.7909 | 0.5988 | 0.7773 |
80
+ | 0.6098 | 12.0 | 1929 | 0.6836 | 0.7909 | 0.7816 | 0.7909 | 0.5973 | 0.6285 | 0.0192 | 0.0185 | 0.9742 | 0.9843 | 0.7909 | 0.6285 | 0.7909 | 0.6034 | 0.7802 |
81
+ | 0.5239 | 13.0 | 2089 | 0.6508 | 0.7932 | 0.7783 | 0.7932 | 0.5965 | 0.6273 | 0.0189 | 0.0183 | 0.9738 | 0.9845 | 0.7932 | 0.6273 | 0.7932 | 0.6046 | 0.7821 |
82
+ | 0.5239 | 14.0 | 2250 | 0.6588 | 0.7963 | 0.7823 | 0.7963 | 0.5957 | 0.6290 | 0.0186 | 0.0179 | 0.9746 | 0.9847 | 0.7963 | 0.6290 | 0.7963 | 0.6055 | 0.7852 |
83
+ | 0.5239 | 14.93 | 2400 | 0.6655 | 0.7963 | 0.7841 | 0.7963 | 0.5968 | 0.6325 | 0.0186 | 0.0179 | 0.9749 | 0.9847 | 0.7963 | 0.6325 | 0.7963 | 0.6074 | 0.7859 |
84
+
85
+
86
+ ### Framework versions
87
+
88
+ - Transformers 4.35.2
89
+ - Pytorch 2.1.0+cu121
90
+ - Datasets 2.18.0
91
+ - Tokenizers 0.15.1
adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "facebook/bart-base",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 64,
14
+ "lora_dropout": 0.1,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 16,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "fc1",
24
+ "fc2",
25
+ "dense",
26
+ "v_proj",
27
+ "k_proj",
28
+ "out_proj",
29
+ "q_proj"
30
+ ],
31
+ "task_type": "SEQ_CLS",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb59328b66a60c29eb9c4ab84d161596a4c7a54645890665a277b567f1f68beb
3
+ size 13151448
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Apr19_00-35-34_283a737e9518/events.out.tfevents.1713486935.283a737e9518.11399.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:031cb59aa4c5671a0e8f46c5977652d007972386a62e4645f196ac9d36cf9aae
3
+ size 130
runs/Apr19_00-35-34_283a737e9518/events.out.tfevents.1713494655.283a737e9518.11399.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62a03d234d814ff0e0d588ef5b69801ef259f864e275e5c5ae2245ff1989a958
3
+ size 129
runs/Apr19_07-14-25_283a737e9518/events.out.tfevents.1713510866.283a737e9518.96518.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9f09dea6c266ce027c026a629dc366f6502658c1f04bab675ad44c061cfc838
3
+ size 130
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
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": 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
+ "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 sha256:0fe940a9c002ad1d53c9e259b630e68ebb8119312584775d62bcf48d42265e90
3
+ size 4600
vocab.json ADDED
The diff for this file is too large to render. See raw diff