Rafaelrosendo1
commited on
Commit
•
2fbbe3c
1
Parent(s):
52202c5
Rafaelrosendo1/llama
Browse files- README.md +99 -0
- adapter_config.json +34 -0
- adapter_model.bin +3 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +5 -0
- special_tokens_map.json +6 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +40 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,99 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: llama2
|
3 |
+
base_model: meta-llama/Llama-2-7b-hf
|
4 |
+
tags:
|
5 |
+
- trl
|
6 |
+
- sft
|
7 |
+
- generated_from_trainer
|
8 |
+
model-index:
|
9 |
+
- name: llama-3-8b-local-definitivo
|
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 |
+
# llama-3-8b-local-definitivo
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the None dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 1.4658
|
21 |
+
|
22 |
+
## Model description
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Intended uses & limitations
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training and evaluation data
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training procedure
|
35 |
+
|
36 |
+
### Training hyperparameters
|
37 |
+
|
38 |
+
The following hyperparameters were used during training:
|
39 |
+
- learning_rate: 0.0002
|
40 |
+
- train_batch_size: 2
|
41 |
+
- eval_batch_size: 8
|
42 |
+
- seed: 42
|
43 |
+
- gradient_accumulation_steps: 2
|
44 |
+
- total_train_batch_size: 4
|
45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
+
- lr_scheduler_type: linear
|
47 |
+
- lr_scheduler_warmup_steps: 10
|
48 |
+
- num_epochs: 1
|
49 |
+
|
50 |
+
### Training results
|
51 |
+
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
54 |
+
| 1.893 | 0.03 | 25 | 1.7774 |
|
55 |
+
| 1.714 | 0.05 | 50 | 1.7412 |
|
56 |
+
| 1.7498 | 0.08 | 75 | 1.7188 |
|
57 |
+
| 1.6899 | 0.1 | 100 | 1.7036 |
|
58 |
+
| 1.7176 | 0.13 | 125 | 1.6906 |
|
59 |
+
| 1.7198 | 0.15 | 150 | 1.6782 |
|
60 |
+
| 1.7086 | 0.18 | 175 | 1.6694 |
|
61 |
+
| 1.7236 | 0.21 | 200 | 1.6559 |
|
62 |
+
| 1.7616 | 0.23 | 225 | 1.6457 |
|
63 |
+
| 1.6756 | 0.26 | 250 | 1.6341 |
|
64 |
+
| 1.7199 | 0.28 | 275 | 1.6236 |
|
65 |
+
| 1.7121 | 0.31 | 300 | 1.6175 |
|
66 |
+
| 1.7542 | 0.34 | 325 | 1.6071 |
|
67 |
+
| 1.6884 | 0.36 | 350 | 1.5967 |
|
68 |
+
| 1.6089 | 0.39 | 375 | 1.5892 |
|
69 |
+
| 1.6556 | 0.41 | 400 | 1.5821 |
|
70 |
+
| 1.5784 | 0.44 | 425 | 1.5745 |
|
71 |
+
| 1.6317 | 0.46 | 450 | 1.5636 |
|
72 |
+
| 1.6375 | 0.49 | 475 | 1.5571 |
|
73 |
+
| 1.6772 | 0.52 | 500 | 1.5498 |
|
74 |
+
| 1.5775 | 0.54 | 525 | 1.5408 |
|
75 |
+
| 1.6307 | 0.57 | 550 | 1.5335 |
|
76 |
+
| 1.6938 | 0.59 | 575 | 1.5304 |
|
77 |
+
| 1.5764 | 0.62 | 600 | 1.5211 |
|
78 |
+
| 1.5834 | 0.64 | 625 | 1.5164 |
|
79 |
+
| 1.5483 | 0.67 | 650 | 1.5090 |
|
80 |
+
| 1.5883 | 0.7 | 675 | 1.5013 |
|
81 |
+
| 1.6268 | 0.72 | 700 | 1.4993 |
|
82 |
+
| 1.5515 | 0.75 | 725 | 1.4919 |
|
83 |
+
| 1.665 | 0.77 | 750 | 1.4882 |
|
84 |
+
| 1.6557 | 0.8 | 775 | 1.4848 |
|
85 |
+
| 1.635 | 0.83 | 800 | 1.4829 |
|
86 |
+
| 1.6689 | 0.85 | 825 | 1.4782 |
|
87 |
+
| 1.6995 | 0.88 | 850 | 1.4742 |
|
88 |
+
| 1.6312 | 0.9 | 875 | 1.4714 |
|
89 |
+
| 1.6465 | 0.93 | 900 | 1.4689 |
|
90 |
+
| 1.51 | 0.95 | 925 | 1.4667 |
|
91 |
+
| 1.5953 | 0.98 | 950 | 1.4658 |
|
92 |
+
|
93 |
+
|
94 |
+
### Framework versions
|
95 |
+
|
96 |
+
- Transformers 4.34.0
|
97 |
+
- Pytorch 2.1.2+cu121
|
98 |
+
- Datasets 2.12.0
|
99 |
+
- Tokenizers 0.14.1
|
adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 32,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 16,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"q_proj",
|
24 |
+
"up_proj",
|
25 |
+
"v_proj",
|
26 |
+
"gate_proj",
|
27 |
+
"down_proj",
|
28 |
+
"k_proj",
|
29 |
+
"o_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d617ba54d6e56b0c8b5039a53088fb47ecf366386dea9383cb627c3fc055360
|
3 |
+
size 160069834
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0411a43ae1658296cc5d5e661745d2a53b5be55aa0380f188a7253ae21055d19
|
3 |
+
size 159967880
|
added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 2,
|
3 |
+
"<s>": 1,
|
4 |
+
"<unk>": 0
|
5 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"pad_token": "<unk>",
|
5 |
+
"unk_token": "<unk>"
|
6 |
+
}
|
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 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<unk>",
|
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": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
}
|
27 |
+
},
|
28 |
+
"additional_special_tokens": [],
|
29 |
+
"bos_token": "<s>",
|
30 |
+
"clean_up_tokenization_spaces": false,
|
31 |
+
"eos_token": "</s>",
|
32 |
+
"legacy": false,
|
33 |
+
"model_max_length": 1000000000000000019884624838656,
|
34 |
+
"pad_token": "<unk>",
|
35 |
+
"padding_side": "right",
|
36 |
+
"sp_model_kwargs": {},
|
37 |
+
"tokenizer_class": "LlamaTokenizer",
|
38 |
+
"unk_token": "<unk>",
|
39 |
+
"use_default_system_prompt": true
|
40 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6248506603f85d9811e1ea2245951537528766be6c3f96806aa05b38998cbd12
|
3 |
+
size 4536
|