llama8_on_korean_conv-base-ltm
Browse files- README.md +81 -0
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: other
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
base_model: beomi/Llama-3-Open-Ko-8B-Instruct-preview
|
7 |
+
model-index:
|
8 |
+
- name: llama8_on_korean_conv-base-ltm
|
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 |
+
# llama8_on_korean_conv-base-ltm
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [beomi/Llama-3-Open-Ko-8B-Instruct-preview](https://huggingface.co/beomi/Llama-3-Open-Ko-8B-Instruct-preview) on the None dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 1.1665
|
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: 1
|
40 |
+
- eval_batch_size: 1
|
41 |
+
- seed: 42
|
42 |
+
- gradient_accumulation_steps: 20
|
43 |
+
- total_train_batch_size: 20
|
44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: linear
|
46 |
+
- lr_scheduler_warmup_steps: 100
|
47 |
+
- training_steps: 2000
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
52 |
+
|:-------------:|:------:|:----:|:---------------:|
|
53 |
+
| 1.156 | 0.2563 | 100 | 1.1623 |
|
54 |
+
| 1.0573 | 0.5126 | 200 | 1.0621 |
|
55 |
+
| 0.9766 | 0.7688 | 300 | 1.0136 |
|
56 |
+
| 0.8888 | 1.0251 | 400 | 0.9799 |
|
57 |
+
| 0.7699 | 1.2814 | 500 | 0.9696 |
|
58 |
+
| 0.7575 | 1.5377 | 600 | 0.9534 |
|
59 |
+
| 0.7641 | 1.7940 | 700 | 0.9405 |
|
60 |
+
| 0.588 | 2.0502 | 800 | 0.9882 |
|
61 |
+
| 0.542 | 2.3065 | 900 | 0.9862 |
|
62 |
+
| 0.5494 | 2.5628 | 1000 | 0.9776 |
|
63 |
+
| 0.5314 | 2.8191 | 1100 | 0.9726 |
|
64 |
+
| 0.3521 | 3.0753 | 1200 | 1.0522 |
|
65 |
+
| 0.3379 | 3.3316 | 1300 | 1.0573 |
|
66 |
+
| 0.3875 | 3.5879 | 1400 | 1.0439 |
|
67 |
+
| 0.346 | 3.8442 | 1500 | 1.0578 |
|
68 |
+
| 0.2252 | 4.1005 | 1600 | 1.1292 |
|
69 |
+
| 0.2271 | 4.3567 | 1700 | 1.1488 |
|
70 |
+
| 0.2237 | 4.6130 | 1800 | 1.1526 |
|
71 |
+
| 0.2199 | 4.8693 | 1900 | 1.1563 |
|
72 |
+
| 0.1614 | 5.1256 | 2000 | 1.1665 |
|
73 |
+
|
74 |
+
|
75 |
+
### Framework versions
|
76 |
+
|
77 |
+
- PEFT 0.11.1
|
78 |
+
- Transformers 4.41.1
|
79 |
+
- Pytorch 2.3.0+cu121
|
80 |
+
- Datasets 2.19.1
|
81 |
+
- Tokenizers 0.19.1
|
adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "beomi/Llama-3-Open-Ko-8B-Instruct-preview",
|
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 |
+
"gate_proj",
|
24 |
+
"o_proj",
|
25 |
+
"q_proj",
|
26 |
+
"v_proj",
|
27 |
+
"k_proj",
|
28 |
+
"down_proj",
|
29 |
+
"up_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:e6b86c4b24b96ce02c9d73099da443b1131cd4183ee42d217e498e94ab7b535a
|
3 |
+
size 167832240
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce1430b14798b304275cfbd9868491942c1300a8b5a495c35627fac4c7b2ec1f
|
3 |
+
size 5176
|