End of training
Browse files- README.md +87 -0
- config.json +70 -0
- generation_config.json +16 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: PhysicalScienceBART
|
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 |
+
# PhysicalScienceBART
|
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: 4.2991
|
22 |
+
- Rouge1: 53.186
|
23 |
+
- Rouge2: 19.5939
|
24 |
+
- Rougel: 38.452
|
25 |
+
- Rougelsum: 49.3854
|
26 |
+
- Bertscore Precision: 82.8832
|
27 |
+
- Bertscore Recall: 84.3034
|
28 |
+
- Bertscore F1: 83.5838
|
29 |
+
- Bleu: 0.1422
|
30 |
+
- Gen Len: 196.4045
|
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 |
+
| 6.1797 | 0.0620 | 100 | 5.9428 | 45.7148 | 14.7784 | 32.4391 | 42.4853 | 79.9576 | 82.0698 | 80.9951 | 0.1054 | 196.4045 |
|
65 |
+
| 5.7661 | 0.1239 | 200 | 5.5214 | 44.5312 | 15.1622 | 32.5105 | 41.2065 | 79.981 | 82.4 | 81.1665 | 0.1088 | 196.4045 |
|
66 |
+
| 5.2648 | 0.1859 | 300 | 5.2101 | 45.5969 | 15.6417 | 33.588 | 42.4324 | 80.1261 | 82.5551 | 81.3158 | 0.1119 | 196.4045 |
|
67 |
+
| 5.2069 | 0.2478 | 400 | 5.0522 | 49.0072 | 16.6961 | 34.477 | 45.2146 | 80.7244 | 83.1085 | 81.8929 | 0.1201 | 196.4045 |
|
68 |
+
| 4.9897 | 0.3098 | 500 | 4.9185 | 48.8492 | 16.7109 | 35.2037 | 45.3551 | 81.2776 | 83.2272 | 82.236 | 0.1207 | 196.4045 |
|
69 |
+
| 4.8413 | 0.3717 | 600 | 4.8053 | 48.7091 | 16.9882 | 35.3917 | 45.1652 | 81.4957 | 83.4015 | 82.4325 | 0.1226 | 196.4045 |
|
70 |
+
| 4.829 | 0.4337 | 700 | 4.6973 | 50.548 | 17.8895 | 36.2198 | 47.0729 | 81.8959 | 83.5895 | 82.73 | 0.1278 | 196.4045 |
|
71 |
+
| 4.6419 | 0.4957 | 800 | 4.6161 | 50.6164 | 18.2248 | 36.6206 | 46.8571 | 81.8709 | 83.7859 | 82.8123 | 0.1313 | 196.4045 |
|
72 |
+
| 4.5451 | 0.5576 | 900 | 4.5494 | 51.9353 | 18.3864 | 37.1004 | 48.168 | 82.3316 | 83.9031 | 83.1059 | 0.1326 | 196.4045 |
|
73 |
+
| 4.4911 | 0.6196 | 1000 | 4.4939 | 51.8997 | 18.8308 | 37.4581 | 47.9484 | 82.3519 | 83.9865 | 83.1569 | 0.1361 | 196.4045 |
|
74 |
+
| 4.5189 | 0.6815 | 1100 | 4.4391 | 52.0976 | 19.0604 | 37.6501 | 48.4561 | 82.5212 | 84.0028 | 83.2516 | 0.1365 | 196.4045 |
|
75 |
+
| 4.4382 | 0.7435 | 1200 | 4.4061 | 53.1857 | 19.3566 | 37.9447 | 49.2686 | 82.7376 | 84.2523 | 83.4844 | 0.1401 | 196.4045 |
|
76 |
+
| 4.4027 | 0.8055 | 1300 | 4.3583 | 52.2536 | 19.1902 | 37.9482 | 48.549 | 82.6541 | 84.1335 | 83.3833 | 0.1388 | 196.4045 |
|
77 |
+
| 4.3911 | 0.8674 | 1400 | 4.3376 | 52.243 | 19.139 | 38.0374 | 48.6274 | 82.6627 | 84.1627 | 83.4023 | 0.1385 | 196.4045 |
|
78 |
+
| 4.29 | 0.9294 | 1500 | 4.3162 | 53.3823 | 19.4988 | 38.381 | 49.4473 | 82.9505 | 84.3617 | 83.6468 | 0.1419 | 196.4045 |
|
79 |
+
| 4.3218 | 0.9913 | 1600 | 4.2991 | 53.186 | 19.5939 | 38.452 | 49.3854 | 82.8832 | 84.3034 | 83.5838 | 0.1422 | 196.4045 |
|
80 |
+
|
81 |
+
|
82 |
+
### Framework versions
|
83 |
+
|
84 |
+
- Transformers 4.41.2
|
85 |
+
- Pytorch 2.3.1+cu121
|
86 |
+
- Datasets 2.20.0
|
87 |
+
- 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:afe58b0f245e4294e7f24c844c7d6836189024d448f2343e88cf11fa6bbc137b
|
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 sha256:843d1a76e4da7083ed2b22f9c852d445a81f247573b7f204bdde3a44c1e01c9d
|
3 |
+
size 5112
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|