LA1512 commited on
Commit
99f55e2
1 Parent(s): 32e68cd

LA1512/led-pubmed-20K-ORC-4096-epoch2

Browse files
README.md ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: bsd-3-clause
3
+ base_model: LA1512/led-pubmed-20K-ORC-4096
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: results
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
+ # results
15
+
16
+ This model is a fine-tuned version of [LA1512/led-pubmed-20K-ORC-4096](https://huggingface.co/LA1512/led-pubmed-20K-ORC-4096) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 3.2494
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: 3e-05
38
+ - train_batch_size: 2
39
+ - eval_batch_size: 2
40
+ - seed: 42
41
+ - gradient_accumulation_steps: 8
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: 400
46
+ - num_epochs: 1
47
+ - label_smoothing_factor: 0.1
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss |
52
+ |:-------------:|:-----:|:----:|:---------------:|
53
+ | 3.2974 | 0.16 | 200 | 3.2981 |
54
+ | 3.1752 | 0.32 | 400 | 3.3060 |
55
+ | 3.1366 | 0.48 | 600 | 3.3115 |
56
+ | 3.1612 | 0.64 | 800 | 3.2834 |
57
+ | 3.172 | 0.8 | 1000 | 3.2593 |
58
+ | 3.2953 | 0.96 | 1200 | 3.2494 |
59
+
60
+
61
+ ### Framework versions
62
+
63
+ - Transformers 4.39.3
64
+ - Pytorch 2.1.2
65
+ - Datasets 2.18.0
66
+ - Tokenizers 0.15.2
config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "LA1512/led-pubmed-20K-ORC-4096",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "architectures": [
6
+ "LEDForConditionalGeneration"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "attention_window": [
10
+ 1024,
11
+ 1024,
12
+ 1024,
13
+ 1024,
14
+ 1024,
15
+ 1024
16
+ ],
17
+ "bos_token_id": 0,
18
+ "classif_dropout": 0.0,
19
+ "classifier_dropout": 0.0,
20
+ "d_model": 768,
21
+ "decoder_attention_heads": 12,
22
+ "decoder_ffn_dim": 3072,
23
+ "decoder_layerdrop": 0.0,
24
+ "decoder_layers": 6,
25
+ "decoder_start_token_id": 2,
26
+ "dropout": 0.1,
27
+ "early_stopping": true,
28
+ "encoder_attention_heads": 12,
29
+ "encoder_ffn_dim": 3072,
30
+ "encoder_layerdrop": 0.0,
31
+ "encoder_layers": 6,
32
+ "eos_token_id": 2,
33
+ "id2label": {
34
+ "0": "LABEL_0",
35
+ "1": "LABEL_1",
36
+ "2": "LABEL_2"
37
+ },
38
+ "init_std": 0.02,
39
+ "is_encoder_decoder": true,
40
+ "label2id": {
41
+ "LABEL_0": 0,
42
+ "LABEL_1": 1,
43
+ "LABEL_2": 2
44
+ },
45
+ "length_penalty": 2.0,
46
+ "max_decoder_position_embeddings": 1024,
47
+ "max_encoder_position_embeddings": 16384,
48
+ "max_length": 512,
49
+ "min_length": 100,
50
+ "model_type": "led",
51
+ "no_repeat_ngram_size": 3,
52
+ "num_beams": 4,
53
+ "num_hidden_layers": 6,
54
+ "pad_token_id": 1,
55
+ "repetition_penalty": 3.5,
56
+ "torch_dtype": "float32",
57
+ "transformers_version": "4.39.3",
58
+ "use_cache": false,
59
+ "vocab_size": 50265
60
+ }
generation_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8,
8
+ "max_length": 1024,
9
+ "min_length": 8,
10
+ "no_repeat_ngram_size": 3,
11
+ "num_beams": 4,
12
+ "pad_token_id": 1,
13
+ "repetition_penalty": 3.5,
14
+ "transformers_version": "4.39.3",
15
+ "use_cache": false
16
+ }
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 sha256:02551be3e10df6add5950d8c7593ebaa32c0d402dfab5ac84c09f1d775495add
3
+ size 647614116
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.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "max_length": 1024,
52
+ "model_max_length": 16384,
53
+ "pad_to_multiple_of": null,
54
+ "pad_token": "<pad>",
55
+ "pad_token_type_id": 0,
56
+ "padding_side": "right",
57
+ "sep_token": "</s>",
58
+ "stride": 0,
59
+ "tokenizer_class": "LEDTokenizer",
60
+ "trim_offsets": true,
61
+ "truncation_side": "right",
62
+ "truncation_strategy": "longest_first",
63
+ "unk_token": "<unk>"
64
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd3791dc7f37d1702b2037b751e43846c5fcaef95546e36d7e4068e8874d01b5
3
+ size 5048
vocab.json ADDED
The diff for this file is too large to render. See raw diff