Chung-Fan commited on
Commit
14b5d75
1 Parent(s): 00e9ddb

Training done for longformer-pubmed-20k

Browse files
README.md ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: hyesunyun/update-summarization-bart-large-longformer
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: longformer-pubmed-20k
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # longformer-pubmed-20k
15
+
16
+ This model is a fine-tuned version of [hyesunyun/update-summarization-bart-large-longformer](https://huggingface.co/hyesunyun/update-summarization-bart-large-longformer) on the None dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 1.1843
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 5e-05
38
+ - train_batch_size: 1
39
+ - eval_batch_size: 1
40
+ - seed: 42
41
+ - gradient_accumulation_steps: 16
42
+ - total_train_batch_size: 16
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - lr_scheduler_warmup_steps: 500
46
+ - num_epochs: 1
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:-----:|:----:|:---------------:|
52
+ | 1.3306 | 0.75 | 500 | 1.1843 |
53
+
54
+
55
+ ### Framework versions
56
+
57
+ - Transformers 4.38.2
58
+ - Pytorch 2.2.1+cu121
59
+ - Datasets 2.18.0
60
+ - Tokenizers 0.15.2
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<EV>": 50265,
3
+ "<abs>": 50267,
4
+ "<t>": 50266
5
+ }
config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "hyesunyun/update-summarization-bart-large-longformer",
3
+ "_num_labels": 3,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "gelu",
6
+ "architectures": [
7
+ "LEDForConditionalGeneration"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "attention_window": [
11
+ 1024,
12
+ 1024,
13
+ 1024,
14
+ 1024,
15
+ 1024,
16
+ 1024,
17
+ 1024,
18
+ 1024,
19
+ 1024,
20
+ 1024,
21
+ 1024,
22
+ 1024
23
+ ],
24
+ "bos_token_id": 0,
25
+ "classif_dropout": 0.0,
26
+ "classifier_dropout": 0.0,
27
+ "d_model": 1024,
28
+ "decoder_attention_heads": 16,
29
+ "decoder_ffn_dim": 4096,
30
+ "decoder_layerdrop": 0.0,
31
+ "decoder_layers": 12,
32
+ "decoder_start_token_id": 2,
33
+ "dropout": 0.1,
34
+ "early_stopping": true,
35
+ "encoder_attention_heads": 16,
36
+ "encoder_ffn_dim": 4096,
37
+ "encoder_layerdrop": 0.0,
38
+ "encoder_layers": 12,
39
+ "eos_token_id": 2,
40
+ "id2label": {
41
+ "0": "LABEL_0",
42
+ "1": "LABEL_1",
43
+ "2": "LABEL_2"
44
+ },
45
+ "init_std": 0.02,
46
+ "is_encoder_decoder": true,
47
+ "label2id": {
48
+ "LABEL_0": 0,
49
+ "LABEL_1": 1,
50
+ "LABEL_2": 2
51
+ },
52
+ "length_penalty": 2.0,
53
+ "max_decoder_position_embeddings": 1024,
54
+ "max_encoder_position_embeddings": 16384,
55
+ "max_length": 512,
56
+ "min_length": 128,
57
+ "model_type": "led",
58
+ "no_repeat_ngram_size": 3,
59
+ "num_beams": 4,
60
+ "num_hidden_layers": 12,
61
+ "output_past": false,
62
+ "pad_token_id": 1,
63
+ "prefix": " ",
64
+ "torch_dtype": "float32",
65
+ "transformers_version": "4.38.2",
66
+ "use_cache": false,
67
+ "vocab_size": 50268
68
+ }
generation_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 2,
5
+ "early_stopping": true,
6
+ "eos_token_id": 2,
7
+ "length_penalty": 2.0,
8
+ "max_length": 512,
9
+ "min_length": 128,
10
+ "no_repeat_ngram_size": 3,
11
+ "num_beams": 4,
12
+ "pad_token_id": 1,
13
+ "transformers_version": "4.38.2",
14
+ "use_cache": false
15
+ }
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:c0bdb8726f8f7bffb28f292ddba83b67c8ac22f990d2e78fa6bff28aa40ec4cf
3
+ size 1839490664
special_tokens_map.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<EV>",
4
+ "<t>",
5
+ "<abs>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<s>",
9
+ "lstrip": false,
10
+ "normalized": true,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "cls_token": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "eos_token": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "mask_token": {
29
+ "content": "<mask>",
30
+ "lstrip": true,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ },
35
+ "pad_token": {
36
+ "content": "<pad>",
37
+ "lstrip": false,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false
41
+ },
42
+ "sep_token": {
43
+ "content": "</s>",
44
+ "lstrip": false,
45
+ "normalized": true,
46
+ "rstrip": false,
47
+ "single_word": false
48
+ },
49
+ "unk_token": {
50
+ "content": "<unk>",
51
+ "lstrip": false,
52
+ "normalized": true,
53
+ "rstrip": false,
54
+ "single_word": false
55
+ }
56
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "50265": {
45
+ "content": "<EV>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "50266": {
53
+ "content": "<t>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "50267": {
61
+ "content": "<abs>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ }
68
+ },
69
+ "additional_special_tokens": [
70
+ "<EV>",
71
+ "<t>",
72
+ "<abs>"
73
+ ],
74
+ "bos_token": "<s>",
75
+ "clean_up_tokenization_spaces": true,
76
+ "cls_token": "<s>",
77
+ "eos_token": "</s>",
78
+ "errors": "replace",
79
+ "mask_token": "<mask>",
80
+ "max_length": 1024,
81
+ "model_max_length": 16384,
82
+ "pad_to_multiple_of": null,
83
+ "pad_token": "<pad>",
84
+ "pad_token_type_id": 0,
85
+ "padding_side": "right",
86
+ "sep_token": "</s>",
87
+ "stride": 0,
88
+ "tokenizer_class": "LEDTokenizer",
89
+ "trim_offsets": true,
90
+ "truncation_side": "right",
91
+ "truncation_strategy": "longest_first",
92
+ "unk_token": "<unk>"
93
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:feb681b43c39dea62d5755b0871b4ae63000b02912d1f692b63c2d6a3fb75d90
3
+ size 4856
vocab.json ADDED
The diff for this file is too large to render. See raw diff