DrishtiSharma
commited on
Commit
•
f9d1d10
1
Parent(s):
1858276
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: llama2-7b-tweet-summarization
|
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 |
+
# llama2-7b-tweet-summarization
|
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: 2.8876
|
23 |
+
- Rouge Scores: {'rouge1': 71.60622394148149, 'rouge2': 59.01568798771897, 'rougeL': 48.52977346441143, 'rougeLsum': 71.51397796132038}
|
24 |
+
- Bleu Scores: [0.663980810175294, 0.6539436277190132, 0.6336458977384846, 0.6103966849577666]
|
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 |
+
| 1.9342 | 1.0 | 220 | 1.8650 | {'rouge1': 81.3543855201909, 'rouge2': 68.33628607515259, 'rougeL': 58.82060003710821, 'rougeLsum': 81.31170089312123} | [0.7475269615217999, 0.7320503944473035, 0.7092142839754116, 0.6841937810377433] | 463.0182 |
|
58 |
+
| 1.6847 | 2.0 | 440 | 1.8651 | {'rouge1': 82.24291097248478, 'rouge2': 69.08611946264551, 'rougeL': 59.03857240450188, 'rougeLsum': 82.21842705467084} | [0.7506228265880205, 0.7370025856405312, 0.7147650770848061, 0.6900216562765312] | 463.0182 |
|
59 |
+
| 1.3489 | 3.0 | 660 | 1.9777 | {'rouge1': 74.8813002669941, 'rouge2': 62.506440459770204, 'rougeL': 52.7220886983953, 'rougeLsum': 74.84300846787131} | [0.6692327330499573, 0.6584063380227538, 0.6386775472556582, 0.6163741473600254] | 463.0182 |
|
60 |
+
| 0.9474 | 4.0 | 880 | 2.1929 | {'rouge1': 78.71628333472167, 'rouge2': 65.58881455717321, 'rougeL': 55.06014924478776, 'rougeLsum': 78.69638389807935} | [0.7102475447746652, 0.6987491736376487, 0.6776051942379059, 0.6536770956211561] | 463.0182 |
|
61 |
+
| 0.6111 | 5.0 | 1100 | 2.4439 | {'rouge1': 78.27895756478365, 'rouge2': 64.90905260843559, 'rougeL': 54.06285449810264, 'rougeLsum': 78.22155552696411} | [0.7449392180339443, 0.7329638020466664, 0.7106292329793894, 0.6852866075200218] | 463.0182 |
|
62 |
+
| 0.3982 | 6.0 | 1320 | 2.7334 | {'rouge1': 70.6225818335813, 'rouge2': 58.36070884299628, 'rougeL': 48.1310974990119, 'rougeLsum': 70.48308395430783} | [0.6525378114736703, 0.6423715222547518, 0.6226082916386746, 0.6000829162052789] | 463.0182 |
|
63 |
+
| 0.3039 | 7.0 | 1540 | 2.8876 | {'rouge1': 71.60622394148149, 'rouge2': 59.01568798771897, 'rougeL': 48.52977346441143, 'rougeLsum': 71.51397796132038} | [0.663980810175294, 0.6539436277190132, 0.6336458977384846, 0.6103966849577666] | 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 |
+
"q_proj",
|
23 |
+
"down_proj",
|
24 |
+
"gate_proj",
|
25 |
+
"o_proj",
|
26 |
+
"v_proj",
|
27 |
+
"up_proj",
|
28 |
+
"k_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 sha256:430c21a4b9498698347f95f8282fcc8681d60a0ff00ff86cd642511dc7e40b13
|
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 sha256:6abd5fabc7d03f3e3accef0a9022077dd73a4226b8f971c8a0b07c8c7c4cbcce
|
3 |
+
size 4728
|