rizvi-rahil786
commited on
Commit
•
eb519b3
1
Parent(s):
1e17554
End of training
Browse files- README.md +67 -0
- config.json +64 -0
- generation_config.json +12 -0
- logs/events.out.tfevents.1703753517.1b2e4b41fe0c.1554.0 +3 -0
- logs/events.out.tfevents.1703764393.1b2e4b41fe0c.1554.1 +3 -0
- model.safetensors +3 -0
- prophetnet.tokenizer +0 -0
- special_tokens_map.json +6 -0
- tokenizer_config.json +49 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: microsoft/prophetnet-large-uncased
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- rouge
|
7 |
+
model-index:
|
8 |
+
- name: prophetnet-large-uncased-samsum
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# prophetnet-large-uncased-samsum
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [microsoft/prophetnet-large-uncased](https://huggingface.co/microsoft/prophetnet-large-uncased) on an unknown dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 1.8806
|
20 |
+
- Rouge1: 42.7998
|
21 |
+
- Rouge2: 20.6028
|
22 |
+
- Rougel: 32.7447
|
23 |
+
- Rougelsum: 38.6683
|
24 |
+
- Gen Len: 46.5763
|
25 |
+
|
26 |
+
## Model description
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Intended uses & limitations
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training and evaluation data
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Training procedure
|
39 |
+
|
40 |
+
### Training hyperparameters
|
41 |
+
|
42 |
+
The following hyperparameters were used during training:
|
43 |
+
- learning_rate: 5e-05
|
44 |
+
- train_batch_size: 8
|
45 |
+
- eval_batch_size: 8
|
46 |
+
- seed: 42
|
47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
+
- lr_scheduler_type: linear
|
49 |
+
- num_epochs: 5
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|
54 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
|
55 |
+
| 2.2102 | 1.0 | 1842 | 1.9800 | 46.2865 | 22.7077 | 36.6175 | 42.7446 | 37.8791 |
|
56 |
+
| 1.6648 | 2.0 | 3684 | 1.8943 | 43.8689 | 21.5646 | 34.0359 | 39.9618 | 44.8193 |
|
57 |
+
| 1.2354 | 3.0 | 5526 | 1.8806 | 42.7998 | 20.6028 | 32.7447 | 38.6683 | 46.5763 |
|
58 |
+
| 0.9176 | 4.0 | 7368 | 1.9474 | 43.5931 | 20.9008 | 33.236 | 39.1182 | 46.1087 |
|
59 |
+
| 0.6827 | 5.0 | 9210 | 2.0220 | 42.9591 | 20.2499 | 32.94 | 38.5586 | 46.9658 |
|
60 |
+
|
61 |
+
|
62 |
+
### Framework versions
|
63 |
+
|
64 |
+
- Transformers 4.36.2
|
65 |
+
- Pytorch 2.1.0+cu121
|
66 |
+
- Datasets 2.16.0
|
67 |
+
- Tokenizers 0.15.0
|
config.json
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/prophetnet-large-uncased",
|
3 |
+
"activation_dropout": 0.1,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"add_cross_attention": true,
|
6 |
+
"architectures": [
|
7 |
+
"ProphetNetForConditionalGeneration"
|
8 |
+
],
|
9 |
+
"attention_dropout": 0.1,
|
10 |
+
"bos_token_id": 102,
|
11 |
+
"decoder_ffn_dim": 4096,
|
12 |
+
"decoder_layerdrop": 0.0,
|
13 |
+
"decoder_max_position_embeddings": 514,
|
14 |
+
"decoder_start_token_id": 102,
|
15 |
+
"disable_ngram_loss": false,
|
16 |
+
"dropout": 0.1,
|
17 |
+
"early_stopping": true,
|
18 |
+
"encoder_ffn_dim": 4096,
|
19 |
+
"encoder_layerdrop": 0.0,
|
20 |
+
"encoder_max_position_embeddings": 513,
|
21 |
+
"eos_token_id": 102,
|
22 |
+
"eps": 0.0,
|
23 |
+
"hidden_size": 1024,
|
24 |
+
"id2label": {
|
25 |
+
"0": "LABEL_0",
|
26 |
+
"1": "LABEL_1",
|
27 |
+
"2": "LABEL_2"
|
28 |
+
},
|
29 |
+
"init_std": 0.02,
|
30 |
+
"is_encoder_decoder": true,
|
31 |
+
"label2id": {
|
32 |
+
"LABEL_0": 0,
|
33 |
+
"LABEL_1": 1,
|
34 |
+
"LABEL_2": 2
|
35 |
+
},
|
36 |
+
"length_penalty": 2.0,
|
37 |
+
"max_length": 142,
|
38 |
+
"max_position_embeddings": 512,
|
39 |
+
"model_type": "prophetnet",
|
40 |
+
"ngram": 2,
|
41 |
+
"no_repeat_ngram_size": 3,
|
42 |
+
"num_beams": 4,
|
43 |
+
"num_buckets": 32,
|
44 |
+
"num_decoder_attention_heads": 16,
|
45 |
+
"num_decoder_layers": 12,
|
46 |
+
"num_encoder_attention_heads": 16,
|
47 |
+
"num_encoder_layers": 12,
|
48 |
+
"output_past": false,
|
49 |
+
"pad_token_id": 0,
|
50 |
+
"prefix": " ",
|
51 |
+
"relative_max_distance": 128,
|
52 |
+
"task_specific_params": {
|
53 |
+
"summarization": {
|
54 |
+
"early_stopping": true,
|
55 |
+
"length_penalty": 2.0,
|
56 |
+
"no_repeat_ngram_size": 3,
|
57 |
+
"num_beams": 4
|
58 |
+
}
|
59 |
+
},
|
60 |
+
"torch_dtype": "float32",
|
61 |
+
"transformers_version": "4.36.2",
|
62 |
+
"use_cache": true,
|
63 |
+
"vocab_size": 30522
|
64 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 102,
|
3 |
+
"decoder_start_token_id": 102,
|
4 |
+
"early_stopping": true,
|
5 |
+
"eos_token_id": 102,
|
6 |
+
"length_penalty": 2.0,
|
7 |
+
"max_length": 142,
|
8 |
+
"no_repeat_ngram_size": 3,
|
9 |
+
"num_beams": 4,
|
10 |
+
"pad_token_id": 0,
|
11 |
+
"transformers_version": "4.36.2"
|
12 |
+
}
|
logs/events.out.tfevents.1703753517.1b2e4b41fe0c.1554.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d1f242ef736e299309f85a9378c9a834bb8992de9cb638f5bbd9cb5c768e4f5
|
3 |
+
size 11219
|
logs/events.out.tfevents.1703764393.1b2e4b41fe0c.1554.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ddbdbca2907906a2f707f3ba609c1ae3f5002431f4bd14153cb99851705cfbc
|
3 |
+
size 613
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a868ca89a716659b436ec68351c99f9f1c67a0942175fe2068466602e26f1c1
|
3 |
+
size 1565355112
|
prophetnet.tokenizer
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"mask_token": "[MASK]",
|
3 |
+
"pad_token": "[PAD]",
|
4 |
+
"sep_token": "[SEP]",
|
5 |
+
"unk_token": "[UNK]"
|
6 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"102": {
|
20 |
+
"content": "[SEP]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"103": {
|
28 |
+
"content": "[MASK]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
}
|
35 |
+
},
|
36 |
+
"clean_up_tokenization_spaces": true,
|
37 |
+
"do_basic_tokenize": true,
|
38 |
+
"do_lower_case": true,
|
39 |
+
"mask_token": "[MASK]",
|
40 |
+
"model_max_length": 512,
|
41 |
+
"never_split": null,
|
42 |
+
"pad_token": "[PAD]",
|
43 |
+
"sep_token": "[SEP]",
|
44 |
+
"strip_accents": null,
|
45 |
+
"tokenize_chinese_chars": true,
|
46 |
+
"tokenizer_class": "ProphetNetTokenizer",
|
47 |
+
"unk_token": "[UNK]",
|
48 |
+
"x_sep_token": "[X_SEP]"
|
49 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc176f96da6b56d2159f223342307336f3fb18d5dbda083a10f95e8589a08d4d
|
3 |
+
size 4856
|