DrishtiSharma
commited on
Commit
•
992f9a8
1
Parent(s):
8cf6d67
End of training
Browse files- README.md +72 -0
- adapter_config.json +32 -0
- adapter_model.safetensors +3 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +40 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
tags:
|
4 |
+
- trl
|
5 |
+
- sft
|
6 |
+
- generated_from_trainer
|
7 |
+
datasets:
|
8 |
+
- dialogstudio
|
9 |
+
base_model: NousResearch/Llama-2-7b-hf
|
10 |
+
model-index:
|
11 |
+
- name: llama2-7bb-tweet-summarization-gradnorm-0.3
|
12 |
+
results: []
|
13 |
+
---
|
14 |
+
|
15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
16 |
+
should probably proofread and complete it, then remove this comment. -->
|
17 |
+
|
18 |
+
# llama2-7bb-tweet-summarization-gradnorm-0.3
|
19 |
+
|
20 |
+
This model is a fine-tuned version of [NousResearch/Llama-2-7b-hf](https://huggingface.co/NousResearch/Llama-2-7b-hf) on the dialogstudio dataset.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 2.8160
|
23 |
+
- Rouge Scores: {'rouge1': 93.719779910895, 'rouge2': 78.0799701185797, 'rougeL': 64.91384075272471, 'rougeLsum': 93.71249369436103}
|
24 |
+
- Bleu Scores: [0.9468715981421053, 0.9340571158071639, 0.906767913949756, 0.8753561378232885]
|
25 |
+
- Gen Len: 463.0182
|
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: 0.0001
|
45 |
+
- train_batch_size: 4
|
46 |
+
- eval_batch_size: 8
|
47 |
+
- seed: 42
|
48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
+
- lr_scheduler_type: cosine
|
50 |
+
- num_epochs: 7
|
51 |
+
- mixed_precision_training: Native AMP
|
52 |
+
|
53 |
+
### Training results
|
54 |
+
|
55 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge Scores | Bleu Scores | Gen Len |
|
56 |
+
|:-------------:|:-----:|:----:|:---------------:|:-----------------------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------:|:--------:|
|
57 |
+
| 1.9246 | 1.0 | 220 | 1.8384 | {'rouge1': 92.78080137059182, 'rouge2': 78.71532643138437, 'rougeL': 68.0616149947273, 'rougeLsum': 92.78702835703021} | [0.9079275318266272, 0.8970741286020552, 0.8736002135507472, 0.8466150307526832] | 463.0182 |
|
58 |
+
| 1.6564 | 2.0 | 440 | 1.8335 | {'rouge1': 93.62527163754612, 'rouge2': 79.14899366889107, 'rougeL': 68.02122989340602, 'rougeLsum': 93.62676386700348} | [0.9282164809556785, 0.9171615801879893, 0.892709310950969, 0.8645188775345913] | 463.0182 |
|
59 |
+
| 1.3403 | 3.0 | 660 | 1.9481 | {'rouge1': 93.70688850262614, 'rouge2': 78.96026100012381, 'rougeL': 67.37638965440908, 'rougeLsum': 93.70399692691778} | [0.9342903619020663, 0.9225682522334384, 0.8972845918789121, 0.8681853449069523] | 463.0182 |
|
60 |
+
| 0.9984 | 4.0 | 880 | 2.1537 | {'rouge1': 93.77800041953847, 'rouge2': 78.72204799373465, 'rougeL': 66.56763131340682, 'rougeLsum': 93.77100407824561} | [0.9425931953005738, 0.9302863494509406, 0.9040669212466305, 0.8739193334758137] | 463.0182 |
|
61 |
+
| 0.7 | 5.0 | 1100 | 2.3692 | {'rouge1': 93.74639046979189, 'rouge2': 78.51569240275262, 'rougeL': 65.93032986525995, 'rougeLsum': 93.73745084400457} | [0.9440175755443134, 0.93171453625075, 0.9052208696375351, 0.8747208115562404] | 463.0182 |
|
62 |
+
| 0.4947 | 6.0 | 1320 | 2.6590 | {'rouge1': 93.75661844384149, 'rouge2': 78.18805763398609, 'rougeL': 65.29243896759789, 'rougeLsum': 93.75034348574664} | [0.9470358425741272, 0.9342995624545122, 0.9070823690393129, 0.8757451333358709] | 463.0182 |
|
63 |
+
| 0.3922 | 7.0 | 1540 | 2.8160 | {'rouge1': 93.719779910895, 'rouge2': 78.0799701185797, 'rougeL': 64.91384075272471, 'rougeLsum': 93.71249369436103} | [0.9468715981421053, 0.9340571158071639, 0.906767913949756, 0.8753561378232885] | 463.0182 |
|
64 |
+
|
65 |
+
|
66 |
+
### Framework versions
|
67 |
+
|
68 |
+
- PEFT 0.8.2.dev0
|
69 |
+
- Transformers 4.38.0.dev0
|
70 |
+
- Pytorch 2.1.0+cu121
|
71 |
+
- Datasets 2.16.2.dev0
|
72 |
+
- Tokenizers 0.15.1
|
adapter_config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "NousResearch/Llama-2-7b-hf",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"loftq_config": {},
|
12 |
+
"lora_alpha": 64,
|
13 |
+
"lora_dropout": 0.0,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": null,
|
17 |
+
"peft_type": "LORA",
|
18 |
+
"r": 64,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"up_proj",
|
23 |
+
"down_proj",
|
24 |
+
"k_proj",
|
25 |
+
"o_proj",
|
26 |
+
"q_proj",
|
27 |
+
"gate_proj",
|
28 |
+
"v_proj"
|
29 |
+
],
|
30 |
+
"task_type": "CAUSAL_LM",
|
31 |
+
"use_rslora": false
|
32 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:766ea809a7e879a6eb36793155d58c4d9491e147aaa63c3a80686d5dba91e121
|
3 |
+
size 639691872
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": true,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"bos_token": "<s>",
|
31 |
+
"clean_up_tokenization_spaces": false,
|
32 |
+
"eos_token": "</s>",
|
33 |
+
"legacy": false,
|
34 |
+
"model_max_length": 1000000000000000019884624838656,
|
35 |
+
"pad_token": "<unk>",
|
36 |
+
"sp_model_kwargs": {},
|
37 |
+
"tokenizer_class": "LlamaTokenizer",
|
38 |
+
"unk_token": "<unk>",
|
39 |
+
"use_default_system_prompt": false
|
40 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e25decb4c16d55906883d4c915c9d1e3eb6d4c62cd5ab44ce6b611fd24f9b2e1
|
3 |
+
size 4792
|