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: PhysicalScienceBARTMainSections
|
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 |
+
# PhysicalScienceBARTMainSections
|
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: 4.2611
|
22 |
+
- Rouge1: 53.3257
|
23 |
+
- Rouge2: 19.9372
|
24 |
+
- Rougel: 38.7516
|
25 |
+
- Rougelsum: 49.5491
|
26 |
+
- Bertscore Precision: 82.9683
|
27 |
+
- Bertscore Recall: 84.3765
|
28 |
+
- Bertscore F1: 83.6629
|
29 |
+
- Bleu: 0.1444
|
30 |
+
- Gen Len: 195.4093
|
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 |
+
| 6.0567 | 0.0622 | 100 | 5.9024 | 44.7542 | 14.8626 | 32.3438 | 41.6627 | 79.6577 | 81.9972 | 80.8049 | 0.1058 | 195.4093 |
|
65 |
+
| 5.628 | 0.1244 | 200 | 5.5009 | 44.7374 | 15.4406 | 32.7203 | 41.5684 | 79.7952 | 82.4154 | 81.0775 | 0.1106 | 195.4093 |
|
66 |
+
| 5.3608 | 0.1866 | 300 | 5.2016 | 47.9813 | 16.6932 | 34.1908 | 44.4923 | 80.6116 | 82.8487 | 81.709 | 0.1189 | 195.4093 |
|
67 |
+
| 5.1172 | 0.2489 | 400 | 5.0247 | 49.6117 | 17.0694 | 35.1947 | 46.0939 | 81.4181 | 83.2142 | 82.3018 | 0.1228 | 195.4093 |
|
68 |
+
| 5.1058 | 0.3111 | 500 | 4.8769 | 49.7791 | 17.282 | 35.3202 | 45.4459 | 80.9748 | 83.2981 | 82.1135 | 0.1250 | 195.4093 |
|
69 |
+
| 4.9831 | 0.3733 | 600 | 4.7486 | 49.7885 | 17.5964 | 36.1885 | 46.1291 | 81.8182 | 83.5683 | 82.6792 | 0.1263 | 195.4093 |
|
70 |
+
| 4.7239 | 0.4355 | 700 | 4.6365 | 49.9977 | 18.0061 | 36.4943 | 46.3477 | 81.7979 | 83.6503 | 82.7089 | 0.1299 | 195.4093 |
|
71 |
+
| 4.6893 | 0.4977 | 800 | 4.5773 | 51.7141 | 18.7056 | 37.2897 | 48.1051 | 82.4355 | 83.9204 | 83.1676 | 0.1347 | 195.4093 |
|
72 |
+
| 4.641 | 0.5599 | 900 | 4.5179 | 51.337 | 18.6106 | 37.3188 | 47.6183 | 82.1666 | 83.9203 | 83.0297 | 0.1355 | 195.4093 |
|
73 |
+
| 4.4518 | 0.6222 | 1000 | 4.4457 | 52.5898 | 18.9865 | 37.7363 | 48.9758 | 82.5619 | 84.028 | 83.2849 | 0.1363 | 195.4093 |
|
74 |
+
| 4.4246 | 0.6844 | 1100 | 4.4001 | 52.5771 | 19.1928 | 37.92 | 48.9098 | 82.5426 | 84.0673 | 83.2942 | 0.1392 | 195.4093 |
|
75 |
+
| 4.549 | 0.7466 | 1200 | 4.3539 | 52.3117 | 19.2452 | 38.0721 | 48.7304 | 82.7547 | 84.1096 | 83.4232 | 0.1383 | 195.4093 |
|
76 |
+
| 4.3528 | 0.8088 | 1300 | 4.3296 | 52.5899 | 19.6953 | 38.3709 | 48.8248 | 82.7757 | 84.2642 | 83.5094 | 0.1424 | 195.4093 |
|
77 |
+
| 4.3692 | 0.8710 | 1400 | 4.2972 | 53.2821 | 19.763 | 38.4702 | 49.3072 | 82.9332 | 84.4115 | 83.6622 | 0.1434 | 195.4093 |
|
78 |
+
| 4.2056 | 0.9332 | 1500 | 4.2795 | 53.4962 | 19.9871 | 38.7098 | 49.5905 | 83.0029 | 84.4307 | 83.7072 | 0.1449 | 195.4093 |
|
79 |
+
| 4.3956 | 0.9955 | 1600 | 4.2611 | 53.3257 | 19.9372 | 38.7516 | 49.5491 | 82.9683 | 84.3765 | 83.6629 | 0.1444 | 195.4093 |
|
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:e65a6b3a3eb930a402ae44cd67c0f2cdd44b1425a781709784dcdf509364d921
|
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 sha256:58e4ffcac53c28c14ae5d47c228396c1e98470ae139ac31369fc8f9db5c579fb
|
3 |
+
size 5112
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|