Training complete
Browse files- README.md +87 -0
- config.json +59 -0
- generation_config.json +14 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- runs/Jul05_11-35-16_nbzockupae/events.out.tfevents.1720179337.nbzockupae.81.0 +3 -0
- runs/Jul05_11-35-16_nbzockupae/events.out.tfevents.1720179587.nbzockupae.81.1 +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +64 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- summarization
|
4 |
+
- generated_from_trainer
|
5 |
+
model-index:
|
6 |
+
- name: led-risalah_data_v4
|
7 |
+
results: []
|
8 |
+
---
|
9 |
+
|
10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
11 |
+
should probably proofread and complete it, then remove this comment. -->
|
12 |
+
|
13 |
+
# led-risalah_data_v4
|
14 |
+
|
15 |
+
This model was trained from scratch on an unknown dataset.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 0.6965
|
18 |
+
- Rouge1 Precision: 0.7537
|
19 |
+
- Rouge1 Recall: 0.2044
|
20 |
+
- Rouge1 Fmeasure: 0.3201
|
21 |
+
|
22 |
+
## Model description
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Intended uses & limitations
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training and evaluation data
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training procedure
|
35 |
+
|
36 |
+
### Training hyperparameters
|
37 |
+
|
38 |
+
The following hyperparameters were used during training:
|
39 |
+
- learning_rate: 5e-05
|
40 |
+
- train_batch_size: 1
|
41 |
+
- eval_batch_size: 1
|
42 |
+
- seed: 42
|
43 |
+
- gradient_accumulation_steps: 8
|
44 |
+
- total_train_batch_size: 8
|
45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
+
- lr_scheduler_type: linear
|
47 |
+
- num_epochs: 30
|
48 |
+
- mixed_precision_training: Native AMP
|
49 |
+
|
50 |
+
### Training results
|
51 |
+
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 Fmeasure | Rouge1 Precision | Rouge1 Recall |
|
53 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------------:|:----------------:|:-------------:|
|
54 |
+
| 2.4649 | 0.91 | 8 | 1.9501 | 0.2231 | 0.5607 | 0.1407 |
|
55 |
+
| 1.7599 | 1.94 | 17 | 1.7553 | 0.2741 | 0.657 | 0.1746 |
|
56 |
+
| 1.4655 | 2.97 | 26 | 1.6912 | 0.2786 | 0.6685 | 0.1774 |
|
57 |
+
| 1.2734 | 4.0 | 35 | 1.7006 | 0.2589 | 0.651 | 0.162 |
|
58 |
+
| 1.2852 | 4.91 | 43 | 1.6481 | 0.2733 | 0.6657 | 0.1732 |
|
59 |
+
| 1.1964 | 5.94 | 52 | 1.6380 | 0.263 | 0.6567 | 0.1655 |
|
60 |
+
| 1.108 | 6.97 | 61 | 1.6441 | 0.2766 | 0.6757 | 0.1746 |
|
61 |
+
| 1.1023 | 8.91 | 72 | 1.1080 | 0.2842 | 0.6932 | 0.1794 |
|
62 |
+
| 1.2354 | 9.94 | 81 | 1.1105 | 0.2816 | 0.6858 | 0.1779 |
|
63 |
+
| 1.1152 | 10.97 | 90 | 1.1317 | 0.2872 | 0.71 | 0.1804 |
|
64 |
+
| 1.17 | 12.0 | 99 | 1.1206 | 0.2896 | 0.6942 | 0.1837 |
|
65 |
+
| 1.0691 | 12.91 | 107 | 1.1037 | 0.2941 | 0.7234 | 0.1851 |
|
66 |
+
| 0.9594 | 13.94 | 116 | 1.1145 | 0.2983 | 0.7299 | 0.1879 |
|
67 |
+
| 1.0332 | 14.97 | 125 | 1.1295 | 0.2959 | 0.7243 | 0.1863 |
|
68 |
+
| 0.9519 | 16.0 | 134 | 1.1271 | 0.2916 | 0.7114 | 0.1839 |
|
69 |
+
| 0.8779 | 16.91 | 142 | 1.1314 | 0.2971 | 0.7192 | 0.1878 |
|
70 |
+
| 0.944 | 18.91 | 152 | 0.8427 | 0.3212 | 0.7799 | 0.2036 |
|
71 |
+
| 0.9652 | 19.94 | 161 | 0.8398 | 0.3075 | 0.7396 | 0.1951 |
|
72 |
+
| 0.9622 | 20.97 | 170 | 0.8421 | 0.3255 | 0.7776 | 0.207 |
|
73 |
+
| 0.9645 | 22.0 | 179 | 0.8550 | 0.3045 | 0.7283 | 0.1934 |
|
74 |
+
| 0.8923 | 22.91 | 187 | 0.8556 | 0.3145 | 0.7585 | 0.1992 |
|
75 |
+
| 0.8635 | 23.94 | 196 | 0.8622 | 0.3086 | 0.7445 | 0.1957 |
|
76 |
+
| 0.827 | 24.97 | 205 | 0.8648 | 0.3047 | 0.7358 | 0.193 |
|
77 |
+
| 0.8529 | 26.0 | 214 | 0.8650 | 0.3129 | 0.7586 | 0.1981 |
|
78 |
+
| 0.7505 | 26.91 | 222 | 0.8719 | 0.3135 | 0.7591 | 0.1985 |
|
79 |
+
| 0.7491 | 27.94 | 231 | 0.8710 | 0.3078 | 0.7419 | 0.1951 |
|
80 |
+
|
81 |
+
|
82 |
+
### Framework versions
|
83 |
+
|
84 |
+
- Transformers 4.35.2
|
85 |
+
- Pytorch 2.1.1+cu121
|
86 |
+
- Datasets 2.14.5
|
87 |
+
- Tokenizers 0.15.1
|
config.json
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "./finetune/led-risalah/checkpoint-240",
|
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": 124,
|
50 |
+
"model_type": "led",
|
51 |
+
"no_repeat_ngram_size": 3,
|
52 |
+
"num_beams": 2,
|
53 |
+
"num_hidden_layers": 6,
|
54 |
+
"pad_token_id": 1,
|
55 |
+
"torch_dtype": "float32",
|
56 |
+
"transformers_version": "4.35.2",
|
57 |
+
"use_cache": false,
|
58 |
+
"vocab_size": 50265
|
59 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 0,
|
3 |
+
"decoder_start_token_id": 2,
|
4 |
+
"early_stopping": true,
|
5 |
+
"eos_token_id": 2,
|
6 |
+
"length_penalty": 2.0,
|
7 |
+
"max_length": 128,
|
8 |
+
"min_length": 40,
|
9 |
+
"no_repeat_ngram_size": 3,
|
10 |
+
"num_beams": 2,
|
11 |
+
"pad_token_id": 1,
|
12 |
+
"transformers_version": "4.35.2",
|
13 |
+
"use_cache": false
|
14 |
+
}
|
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:fe6b3ed7e4f18ba7f2da60ff2eda5a5d8a652f172a3909d07cd368019437e732
|
3 |
+
size 647614116
|
runs/Jul05_11-35-16_nbzockupae/events.out.tfevents.1720179337.nbzockupae.81.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4191abe0b7ad97eabc7c8feb3a65db2f67d900b1df2665d72f836d413916fd76
|
3 |
+
size 5382
|
runs/Jul05_11-35-16_nbzockupae/events.out.tfevents.1720179587.nbzockupae.81.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5dc45967c0dbd0db2ba5593dd15038572444a720ecb1ae941c1ccfa1cd8dd1e5
|
3 |
+
size 535
|
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": 128,
|
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:e1c51bc8eff0848d84edc3bd9689dd4ec4835b6ea722e4aea68bed68555968c1
|
3 |
+
size 4728
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|