MarPla commited on
Commit
bcc042f
1 Parent(s): d25270e

End of training

Browse files
README.md ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: facebook/bart-large-cnn
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - rouge
8
+ - bleu
9
+ model-index:
10
+ - name: HealthScienceBARTPrincipal
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # HealthScienceBARTPrincipal
18
+
19
+ This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 3.8639
22
+ - Rouge1: 57.9681
23
+ - Rouge2: 23.5702
24
+ - Rougel: 42.298
25
+ - Rougelsum: 54.4306
26
+ - Bertscore Precision: 83.6132
27
+ - Bertscore Recall: 84.9752
28
+ - Bertscore F1: 84.2861
29
+ - Bleu: 0.1834
30
+ - Gen Len: 234.8649
31
+
32
+ ## Model description
33
+
34
+ More information needed
35
+
36
+ ## Intended uses & limitations
37
+
38
+ More information needed
39
+
40
+ ## Training and evaluation data
41
+
42
+ More information needed
43
+
44
+ ## Training procedure
45
+
46
+ ### Training hyperparameters
47
+
48
+ The following hyperparameters were used during training:
49
+ - learning_rate: 5e-05
50
+ - train_batch_size: 1
51
+ - eval_batch_size: 1
52
+ - seed: 42
53
+ - gradient_accumulation_steps: 16
54
+ - total_train_batch_size: 16
55
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
56
+ - lr_scheduler_type: linear
57
+ - lr_scheduler_warmup_steps: 500
58
+ - num_epochs: 1
59
+
60
+ ### Training results
61
+
62
+ | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Bertscore Precision | Bertscore Recall | Bertscore F1 | Bleu | Gen Len |
63
+ |:-------------:|:------:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------------------:|:----------------:|:------------:|:------:|:--------:|
64
+ | 5.8822 | 0.0826 | 100 | 5.6709 | 48.7438 | 17.0806 | 33.6533 | 45.9891 | 80.2777 | 82.0236 | 81.1384 | 0.1276 | 234.8898 |
65
+ | 5.2537 | 0.1653 | 200 | 5.1160 | 48.5934 | 17.8578 | 34.7839 | 45.8306 | 80.2943 | 82.3539 | 81.3073 | 0.1358 | 234.8898 |
66
+ | 4.8915 | 0.2479 | 300 | 4.7665 | 53.8863 | 19.5528 | 37.1095 | 50.6262 | 81.6835 | 83.1962 | 82.4302 | 0.1499 | 234.8898 |
67
+ | 4.6879 | 0.3305 | 400 | 4.5500 | 53.0399 | 20.3314 | 38.0481 | 49.3041 | 81.2912 | 83.6329 | 82.4409 | 0.1582 | 234.8898 |
68
+ | 4.4472 | 0.4131 | 500 | 4.3787 | 55.7809 | 21.4354 | 39.5787 | 52.1713 | 82.3882 | 84.0466 | 83.2062 | 0.1663 | 234.8898 |
69
+ | 4.4391 | 0.4958 | 600 | 4.2267 | 55.0551 | 21.5312 | 39.9051 | 51.3866 | 82.1951 | 84.1433 | 83.1541 | 0.1686 | 234.8898 |
70
+ | 4.386 | 0.5784 | 700 | 4.1013 | 56.2812 | 22.3834 | 40.9161 | 52.93 | 82.9407 | 84.4308 | 83.6764 | 0.1738 | 234.8898 |
71
+ | 4.198 | 0.6610 | 800 | 4.0168 | 56.3251 | 22.6045 | 41.1441 | 52.8715 | 83.2275 | 84.6518 | 83.931 | 0.1762 | 234.8898 |
72
+ | 3.9607 | 0.7436 | 900 | 3.9377 | 57.4072 | 22.9187 | 41.6959 | 53.899 | 83.4352 | 84.8095 | 84.1141 | 0.1787 | 234.8898 |
73
+ | 3.9771 | 0.8263 | 1000 | 3.8963 | 58.1506 | 23.5231 | 42.1596 | 54.4019 | 83.6132 | 85.0153 | 84.3057 | 0.1842 | 234.8898 |
74
+ | 3.8807 | 0.9089 | 1100 | 3.8447 | 57.9746 | 23.8219 | 42.4743 | 54.4461 | 83.6303 | 85.03 | 84.3217 | 0.1867 | 234.8898 |
75
+ | 4.0011 | 0.9915 | 1200 | 3.8214 | 58.2153 | 23.8513 | 42.5964 | 54.7631 | 83.7005 | 85.0498 | 84.3672 | 0.1867 | 234.8898 |
76
+
77
+
78
+ ### Framework versions
79
+
80
+ - Transformers 4.41.2
81
+ - Pytorch 2.3.1+cu121
82
+ - Datasets 2.20.0
83
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/bart-large-cnn",
3
+ "_num_labels": 3,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "gelu",
6
+ "add_final_layer_norm": false,
7
+ "architectures": [
8
+ "BartForConditionalGeneration"
9
+ ],
10
+ "attention_dropout": 0.0,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.0,
13
+ "classifier_dropout": 0.0,
14
+ "d_model": 1024,
15
+ "decoder_attention_heads": 16,
16
+ "decoder_ffn_dim": 4096,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 12,
19
+ "decoder_start_token_id": 2,
20
+ "dropout": 0.1,
21
+ "early_stopping": true,
22
+ "encoder_attention_heads": 16,
23
+ "encoder_ffn_dim": 4096,
24
+ "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 12,
26
+ "eos_token_id": 2,
27
+ "force_bos_token_to_be_generated": true,
28
+ "forced_bos_token_id": 0,
29
+ "forced_eos_token_id": 2,
30
+ "gradient_checkpointing": false,
31
+ "id2label": {
32
+ "0": "LABEL_0",
33
+ "1": "LABEL_1",
34
+ "2": "LABEL_2"
35
+ },
36
+ "init_std": 0.02,
37
+ "is_encoder_decoder": true,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1,
41
+ "LABEL_2": 2
42
+ },
43
+ "length_penalty": 2.0,
44
+ "max_length": 142,
45
+ "max_position_embeddings": 1024,
46
+ "min_length": 56,
47
+ "model_type": "bart",
48
+ "no_repeat_ngram_size": 3,
49
+ "normalize_before": false,
50
+ "num_beams": 4,
51
+ "num_hidden_layers": 12,
52
+ "output_past": true,
53
+ "pad_token_id": 1,
54
+ "prefix": " ",
55
+ "scale_embedding": false,
56
+ "task_specific_params": {
57
+ "summarization": {
58
+ "early_stopping": true,
59
+ "length_penalty": 2.0,
60
+ "max_length": 142,
61
+ "min_length": 56,
62
+ "no_repeat_ngram_size": 3,
63
+ "num_beams": 4
64
+ }
65
+ },
66
+ "torch_dtype": "float32",
67
+ "transformers_version": "4.41.2",
68
+ "use_cache": true,
69
+ "vocab_size": 50264
70
+ }
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
+ "forced_bos_token_id": 0,
8
+ "forced_eos_token_id": 2,
9
+ "length_penalty": 2.0,
10
+ "max_length": 142,
11
+ "min_length": 56,
12
+ "no_repeat_ngram_size": 3,
13
+ "num_beams": 4,
14
+ "pad_token_id": 1,
15
+ "transformers_version": "4.41.2"
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 sha256:6b53764db00a1bf06e24f47580d5f6a8fd88b6935fec0ffbe51eae4b441003c6
3
+ size 1625422896
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
+ "4": {
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": 1000000000000000019884624838656,
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:fe5ee8ac1fb678a18010b9da6837b982c8f7c322af33678dd95b5cd1876af76f
3
+ size 5112
vocab.json ADDED
The diff for this file is too large to render. See raw diff