Hasanur525
commited on
Commit
•
3e706f0
1
Parent(s):
9563ff3
End of training
Browse files- .gitattributes +1 -0
- README.md +86 -0
- config.json +34 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
- runs/Feb22_20-57-31_WIN-F8FVB99PGRI/events.out.tfevents.1708664252.WIN-F8FVB99PGRI.14272.0 +3 -0
- special_tokens_map.json +23 -0
- spiece.model +3 -0
- tokenizer.json +3 -0
- tokenizer_config.json +45 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: Hasanur525/deed_summarization_mt5_version_1
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- rouge
|
8 |
+
model-index:
|
9 |
+
- name: mt5-deed-sum
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# mt5-deed-sum
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [Hasanur525/deed_summarization_mt5_version_1](https://huggingface.co/Hasanur525/deed_summarization_mt5_version_1) on the None dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.4953
|
21 |
+
- Rouge1: 1.5754
|
22 |
+
- Rouge2: 1.087
|
23 |
+
- Rougel: 1.5005
|
24 |
+
- Rougelsum: 1.4211
|
25 |
+
- Gen Len: 310.6981
|
26 |
+
|
27 |
+
## Model description
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Intended uses & limitations
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training and evaluation data
|
36 |
+
|
37 |
+
More information needed
|
38 |
+
|
39 |
+
## Training procedure
|
40 |
+
|
41 |
+
### Training hyperparameters
|
42 |
+
|
43 |
+
The following hyperparameters were used during training:
|
44 |
+
- learning_rate: 2e-05
|
45 |
+
- train_batch_size: 2
|
46 |
+
- eval_batch_size: 2
|
47 |
+
- seed: 42
|
48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
+
- lr_scheduler_type: linear
|
50 |
+
- lr_scheduler_warmup_steps: 5000
|
51 |
+
- num_epochs: 22
|
52 |
+
|
53 |
+
### Training results
|
54 |
+
|
55 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|
56 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:--------:|
|
57 |
+
| 0.0915 | 1.0 | 375 | 0.5844 | 0.7311 | 0.4193 | 0.7311 | 0.7311 | 289.3396 |
|
58 |
+
| 0.9545 | 2.0 | 750 | 0.5858 | 0.6289 | 0.444 | 0.6289 | 0.6289 | 291.5912 |
|
59 |
+
| 0.8026 | 3.0 | 1125 | 0.5817 | 1.1119 | 0.6733 | 1.067 | 1.0428 | 295.0692 |
|
60 |
+
| 0.2525 | 4.0 | 1500 | 0.5698 | 0.7311 | 0.4193 | 0.7311 | 0.7311 | 299.7987 |
|
61 |
+
| 1.5794 | 5.0 | 1875 | 0.5685 | 0.8096 | 0.4733 | 0.7714 | 0.7549 | 286.0126 |
|
62 |
+
| 0.0558 | 6.0 | 2250 | 0.5701 | 0.5003 | 0.3431 | 0.5003 | 0.4785 | 301.6855 |
|
63 |
+
| 0.4973 | 7.0 | 2625 | 0.5521 | 1.1281 | 0.7349 | 0.9983 | 0.9983 | 295.0692 |
|
64 |
+
| 1.1935 | 8.0 | 3000 | 0.5661 | 1.3444 | 0.9964 | 1.2673 | 1.2213 | 324.3648 |
|
65 |
+
| 0.0752 | 9.0 | 3375 | 0.5531 | 1.4883 | 1.0199 | 1.4252 | 1.3979 | 301.0377 |
|
66 |
+
| 0.216 | 10.0 | 3750 | 0.5573 | 1.5516 | 1.0371 | 1.5047 | 1.4656 | 319.195 |
|
67 |
+
| 0.3619 | 11.0 | 4125 | 0.5571 | 1.2368 | 0.8055 | 1.2326 | 1.2146 | 294.4717 |
|
68 |
+
| 0.1881 | 12.0 | 4500 | 0.5293 | 1.2922 | 0.941 | 1.2149 | 1.2084 | 305.9057 |
|
69 |
+
| 0.2247 | 13.0 | 4875 | 0.5340 | 1.0581 | 0.594 | 0.9989 | 0.987 | 306.3774 |
|
70 |
+
| 0.0715 | 14.0 | 5250 | 0.5211 | 1.2905 | 0.8861 | 1.259 | 1.2143 | 321.6226 |
|
71 |
+
| 0.1851 | 15.0 | 5625 | 0.5231 | 1.4625 | 0.9737 | 1.3919 | 1.3637 | 318.4969 |
|
72 |
+
| 0.5285 | 16.0 | 6000 | 0.5154 | 1.1892 | 0.8552 | 1.1401 | 1.1061 | 313.2138 |
|
73 |
+
| 0.0482 | 17.0 | 6375 | 0.5032 | 1.1826 | 0.8687 | 1.1554 | 1.1554 | 327.1824 |
|
74 |
+
| 0.0733 | 18.0 | 6750 | 0.5193 | 1.6133 | 1.1373 | 1.5626 | 1.5085 | 317.8113 |
|
75 |
+
| 0.2814 | 19.0 | 7125 | 0.5007 | 1.5689 | 1.1133 | 1.5189 | 1.4606 | 307.7421 |
|
76 |
+
| 0.0672 | 20.0 | 7500 | 0.4959 | 1.5754 | 1.078 | 1.489 | 1.4166 | 316.6164 |
|
77 |
+
| 0.2456 | 21.0 | 7875 | 0.4966 | 1.5754 | 1.087 | 1.5005 | 1.4211 | 314.3396 |
|
78 |
+
| 0.0405 | 22.0 | 8250 | 0.4953 | 1.5754 | 1.087 | 1.5005 | 1.4211 | 310.6981 |
|
79 |
+
|
80 |
+
|
81 |
+
### Framework versions
|
82 |
+
|
83 |
+
- Transformers 4.37.2
|
84 |
+
- Pytorch 2.1.0.dev20230811+cu121
|
85 |
+
- Datasets 2.17.0
|
86 |
+
- Tokenizers 0.15.2
|
config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Hasanur525/deed_summarization_mt5_version_1",
|
3 |
+
"architectures": [
|
4 |
+
"MT5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"classifier_dropout": 0.0,
|
7 |
+
"d_ff": 2048,
|
8 |
+
"d_kv": 64,
|
9 |
+
"d_model": 768,
|
10 |
+
"decoder_start_token_id": 0,
|
11 |
+
"dense_act_fn": "gelu_new",
|
12 |
+
"dropout_rate": 0.1,
|
13 |
+
"eos_token_id": 1,
|
14 |
+
"feed_forward_proj": "gated-gelu",
|
15 |
+
"initializer_factor": 1.0,
|
16 |
+
"is_encoder_decoder": true,
|
17 |
+
"is_gated_act": true,
|
18 |
+
"layer_norm_epsilon": 1e-06,
|
19 |
+
"max_length": 500,
|
20 |
+
"model_type": "mt5",
|
21 |
+
"num_decoder_layers": 12,
|
22 |
+
"num_heads": 12,
|
23 |
+
"num_layers": 12,
|
24 |
+
"output_past": true,
|
25 |
+
"pad_token_id": 0,
|
26 |
+
"relative_attention_max_distance": 128,
|
27 |
+
"relative_attention_num_buckets": 32,
|
28 |
+
"tie_word_embeddings": false,
|
29 |
+
"tokenizer_class": "T5Tokenizer",
|
30 |
+
"torch_dtype": "float32",
|
31 |
+
"transformers_version": "4.37.2",
|
32 |
+
"use_cache": true,
|
33 |
+
"vocab_size": 250112
|
34 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"decoder_start_token_id": 0,
|
3 |
+
"eos_token_id": 1,
|
4 |
+
"max_length": 500,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.37.2"
|
7 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16ed1e58dd6000c5627c84abac6b5b288ef602a6ee24eda3d647d3efa26e5581
|
3 |
+
size 2329638768
|
runs/Feb22_20-57-31_WIN-F8FVB99PGRI/events.out.tfevents.1708664252.WIN-F8FVB99PGRI.14272.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b0b50b6165d3071b7cb0b0c4a32013d6bd026b80579ba32470514a0c198b1eb0
|
3 |
+
size 1311514
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token": {
|
3 |
+
"content": "</s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"pad_token": {
|
10 |
+
"content": "<pad>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"unk_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
|
3 |
+
size 4309802
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb3592f08c1c86d7ac1edb7e21f74420215806a3f90b02145a2f04d7bef52516
|
3 |
+
size 16315579
|
tokenizer_config.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<pad>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "</s>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "<unk>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
}
|
27 |
+
},
|
28 |
+
"additional_special_tokens": [],
|
29 |
+
"clean_up_tokenization_spaces": true,
|
30 |
+
"eos_token": "</s>",
|
31 |
+
"extra_ids": 0,
|
32 |
+
"legacy": true,
|
33 |
+
"max_length": 300,
|
34 |
+
"model_max_length": 1000000000000000019884624838656,
|
35 |
+
"pad_to_multiple_of": null,
|
36 |
+
"pad_token": "<pad>",
|
37 |
+
"pad_token_type_id": 0,
|
38 |
+
"padding_side": "right",
|
39 |
+
"sp_model_kwargs": {},
|
40 |
+
"stride": 0,
|
41 |
+
"tokenizer_class": "T5Tokenizer",
|
42 |
+
"truncation_side": "right",
|
43 |
+
"truncation_strategy": "longest_first",
|
44 |
+
"unk_token": "<unk>"
|
45 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:27f0764eefb4a4909ca06fda624647794f10720292983d75b67f6373fb13847d
|
3 |
+
size 4856
|