Gayathri142214002
commited on
Commit
•
7072490
1
Parent(s):
31af7bb
Pegasus_paraphraser_Com_9
Browse files- README.md +54 -0
- config.json +55 -0
- generation_config.json +12 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: Gayathri142214002/Pegasus_paraphraser_Com_8
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: Pegasus_paraphraser_Com_9
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# Pegasus_paraphraser_Com_9
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [Gayathri142214002/Pegasus_paraphraser_Com_8](https://huggingface.co/Gayathri142214002/Pegasus_paraphraser_Com_8) on an unknown dataset.
|
17 |
+
|
18 |
+
## Model description
|
19 |
+
|
20 |
+
More information needed
|
21 |
+
|
22 |
+
## Intended uses & limitations
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Training and evaluation data
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training procedure
|
31 |
+
|
32 |
+
### Training hyperparameters
|
33 |
+
|
34 |
+
The following hyperparameters were used during training:
|
35 |
+
- learning_rate: 0.0001
|
36 |
+
- train_batch_size: 16
|
37 |
+
- eval_batch_size: 8
|
38 |
+
- seed: 42
|
39 |
+
- gradient_accumulation_steps: 8
|
40 |
+
- total_train_batch_size: 128
|
41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
+
- lr_scheduler_type: linear
|
43 |
+
- num_epochs: 4
|
44 |
+
|
45 |
+
### Training results
|
46 |
+
|
47 |
+
|
48 |
+
|
49 |
+
### Framework versions
|
50 |
+
|
51 |
+
- Transformers 4.36.2
|
52 |
+
- Pytorch 2.1.2+cu121
|
53 |
+
- Datasets 2.16.1
|
54 |
+
- Tokenizers 0.15.0
|
config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Gayathri142214002/Pegasus_paraphraser_Com_8",
|
3 |
+
"activation_dropout": 0.1,
|
4 |
+
"activation_function": "relu",
|
5 |
+
"add_bias_logits": false,
|
6 |
+
"add_final_layer_norm": true,
|
7 |
+
"architectures": [
|
8 |
+
"PegasusForConditionalGeneration"
|
9 |
+
],
|
10 |
+
"attention_dropout": 0.1,
|
11 |
+
"bos_token_id": 0,
|
12 |
+
"classif_dropout": 0.0,
|
13 |
+
"d_model": 1024,
|
14 |
+
"decoder_attention_heads": 16,
|
15 |
+
"decoder_ffn_dim": 4096,
|
16 |
+
"decoder_layerdrop": 0.0,
|
17 |
+
"decoder_layers": 16,
|
18 |
+
"decoder_start_token_id": 0,
|
19 |
+
"dropout": 0.1,
|
20 |
+
"encoder_attention_heads": 16,
|
21 |
+
"encoder_ffn_dim": 4096,
|
22 |
+
"encoder_layerdrop": 0.0,
|
23 |
+
"encoder_layers": 16,
|
24 |
+
"eos_token_id": 1,
|
25 |
+
"extra_pos_embeddings": 1,
|
26 |
+
"force_bos_token_to_be_generated": false,
|
27 |
+
"forced_eos_token_id": 1,
|
28 |
+
"id2label": {
|
29 |
+
"0": "LABEL_0",
|
30 |
+
"1": "LABEL_1",
|
31 |
+
"2": "LABEL_2"
|
32 |
+
},
|
33 |
+
"init_std": 0.02,
|
34 |
+
"is_encoder_decoder": true,
|
35 |
+
"label2id": {
|
36 |
+
"LABEL_0": 0,
|
37 |
+
"LABEL_1": 1,
|
38 |
+
"LABEL_2": 2
|
39 |
+
},
|
40 |
+
"length_penalty": 0.8,
|
41 |
+
"max_length": 60,
|
42 |
+
"max_position_embeddings": 60,
|
43 |
+
"model_type": "pegasus",
|
44 |
+
"normalize_before": true,
|
45 |
+
"normalize_embedding": false,
|
46 |
+
"num_beams": 8,
|
47 |
+
"num_hidden_layers": 16,
|
48 |
+
"pad_token_id": 0,
|
49 |
+
"scale_embedding": true,
|
50 |
+
"static_position_embeddings": true,
|
51 |
+
"torch_dtype": "float32",
|
52 |
+
"transformers_version": "4.36.2",
|
53 |
+
"use_cache": true,
|
54 |
+
"vocab_size": 96103
|
55 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"decoder_start_token_id": 0,
|
5 |
+
"eos_token_id": 1,
|
6 |
+
"forced_eos_token_id": 1,
|
7 |
+
"length_penalty": 0.8,
|
8 |
+
"max_length": 60,
|
9 |
+
"num_beams": 8,
|
10 |
+
"pad_token_id": 0,
|
11 |
+
"transformers_version": "4.36.2"
|
12 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e6c2fdcb984f9251ed8dd0abdadb4b6733f0da43c04495198ba00ff38394966d
|
3 |
+
size 2275755748
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bd18bcfaf6ad1b75dd3decc694646272b69c0c1d98cf0c152972f390c9b4f4fb
|
3 |
+
size 4792
|