trungtienluong
commited on
Commit
•
8133964
1
Parent(s):
054ee86
trungtienluong/test_5
Browse files
README.md
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: llama2
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
base_model: vilm/vinallama-7b-chat
|
7 |
+
model-index:
|
8 |
+
- name: experiments
|
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 |
+
# experiments
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [vilm/vinallama-7b-chat](https://huggingface.co/vilm/vinallama-7b-chat) on the None dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.4668
|
20 |
+
|
21 |
+
## Model description
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Intended uses & limitations
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training and evaluation data
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training procedure
|
34 |
+
|
35 |
+
### Training hyperparameters
|
36 |
+
|
37 |
+
The following hyperparameters were used during training:
|
38 |
+
- learning_rate: 5e-05
|
39 |
+
- train_batch_size: 8
|
40 |
+
- eval_batch_size: 8
|
41 |
+
- seed: 42
|
42 |
+
- gradient_accumulation_steps: 4
|
43 |
+
- total_train_batch_size: 32
|
44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: cosine
|
46 |
+
- lr_scheduler_warmup_ratio: 0.1
|
47 |
+
- num_epochs: 10
|
48 |
+
- mixed_precision_training: Native AMP
|
49 |
+
|
50 |
+
### Training results
|
51 |
+
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
54 |
+
| 0.3854 | 0.7 | 10 | 0.4145 |
|
55 |
+
| 0.3751 | 1.4 | 20 | 0.3999 |
|
56 |
+
| 0.3457 | 2.11 | 30 | 0.3857 |
|
57 |
+
| 0.324 | 2.81 | 40 | 0.3821 |
|
58 |
+
| 0.2329 | 3.51 | 50 | 0.3845 |
|
59 |
+
| 0.2332 | 4.21 | 60 | 0.3878 |
|
60 |
+
| 0.2211 | 4.91 | 70 | 0.3929 |
|
61 |
+
| 0.1682 | 5.61 | 80 | 0.4093 |
|
62 |
+
| 0.1503 | 6.32 | 90 | 0.4416 |
|
63 |
+
| 0.1439 | 7.02 | 100 | 0.4299 |
|
64 |
+
| 0.1299 | 7.72 | 110 | 0.4648 |
|
65 |
+
| 0.1074 | 8.42 | 120 | 0.4574 |
|
66 |
+
| 0.099 | 9.12 | 130 | 0.4655 |
|
67 |
+
| 0.1078 | 9.82 | 140 | 0.4668 |
|
68 |
+
|
69 |
+
|
70 |
+
### Framework versions
|
71 |
+
|
72 |
+
- PEFT 0.11.1
|
73 |
+
- Transformers 4.36.0
|
74 |
+
- Pytorch 2.3.0+cu121
|
75 |
+
- Datasets 2.19.2
|
76 |
+
- Tokenizers 0.15.2
|
adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "vilm/vinallama-7b-chat",
|
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 |
+
"o_proj",
|
24 |
+
"q_proj",
|
25 |
+
"k_proj",
|
26 |
+
"up_proj",
|
27 |
+
"gate_proj",
|
28 |
+
"down_proj",
|
29 |
+
"v_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f435648a844a4eac571206700f242922397c32fb5e0bed9d3f88e969035fd9e3
|
3 |
+
size 159967880
|
runs/Jun03_13-34-58_e4d730027502/events.out.tfevents.1717421701.e4d730027502.173.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c61a122639e0dbc4cf0ed5719f47bac004c41d69c6d8c08b5b1b74110aba4bb5
|
3 |
+
size 30479
|
runs/Jun03_13-34-58_e4d730027502/events.out.tfevents.1717426005.e4d730027502.173.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:071261fa252be94d23984425243d9bc636c4098127c51f8ee96e6c286f970fd1
|
3 |
+
size 359
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f46fe0d33d2c65d89c160b5a7434274673bb08ae1ad9610dae970b7e3047710
|
3 |
+
size 4664
|