lovellmnot
commited on
Commit
•
e7435ac
1
Parent(s):
928020c
End of training
Browse files- README.md +89 -0
- adapter_config.json +29 -0
- adapter_model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: meta-llama/Meta-Llama-3-8B-Instruct
|
3 |
+
library_name: peft
|
4 |
+
license: llama3
|
5 |
+
tags:
|
6 |
+
- generated_from_trainer
|
7 |
+
model-index:
|
8 |
+
- name: results
|
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 |
+
# results
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the None dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.0589
|
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: 8e-05
|
39 |
+
- train_batch_size: 1
|
40 |
+
- eval_batch_size: 1
|
41 |
+
- seed: 42
|
42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
+
- lr_scheduler_type: linear
|
44 |
+
- num_epochs: 30
|
45 |
+
- mixed_precision_training: Native AMP
|
46 |
+
|
47 |
+
### Training results
|
48 |
+
|
49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
50 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
51 |
+
| No log | 1.0 | 100 | 0.3525 |
|
52 |
+
| No log | 2.0 | 200 | 0.3112 |
|
53 |
+
| No log | 3.0 | 300 | 0.2998 |
|
54 |
+
| No log | 4.0 | 400 | 0.2830 |
|
55 |
+
| 0.6117 | 5.0 | 500 | 0.2682 |
|
56 |
+
| 0.6117 | 6.0 | 600 | 0.2514 |
|
57 |
+
| 0.6117 | 7.0 | 700 | 0.2319 |
|
58 |
+
| 0.6117 | 8.0 | 800 | 0.2051 |
|
59 |
+
| 0.6117 | 9.0 | 900 | 0.1846 |
|
60 |
+
| 0.2327 | 10.0 | 1000 | 0.1573 |
|
61 |
+
| 0.2327 | 11.0 | 1100 | 0.1433 |
|
62 |
+
| 0.2327 | 12.0 | 1200 | 0.1249 |
|
63 |
+
| 0.2327 | 13.0 | 1300 | 0.1147 |
|
64 |
+
| 0.2327 | 14.0 | 1400 | 0.1047 |
|
65 |
+
| 0.1381 | 15.0 | 1500 | 0.1016 |
|
66 |
+
| 0.1381 | 16.0 | 1600 | 0.0958 |
|
67 |
+
| 0.1381 | 17.0 | 1700 | 0.0903 |
|
68 |
+
| 0.1381 | 18.0 | 1800 | 0.0844 |
|
69 |
+
| 0.1381 | 19.0 | 1900 | 0.0821 |
|
70 |
+
| 0.0958 | 20.0 | 2000 | 0.0808 |
|
71 |
+
| 0.0958 | 21.0 | 2100 | 0.0743 |
|
72 |
+
| 0.0958 | 22.0 | 2200 | 0.0722 |
|
73 |
+
| 0.0958 | 23.0 | 2300 | 0.0690 |
|
74 |
+
| 0.0958 | 24.0 | 2400 | 0.0666 |
|
75 |
+
| 0.0758 | 25.0 | 2500 | 0.0642 |
|
76 |
+
| 0.0758 | 26.0 | 2600 | 0.0620 |
|
77 |
+
| 0.0758 | 27.0 | 2700 | 0.0609 |
|
78 |
+
| 0.0758 | 28.0 | 2800 | 0.0597 |
|
79 |
+
| 0.0758 | 29.0 | 2900 | 0.0590 |
|
80 |
+
| 0.0632 | 30.0 | 3000 | 0.0589 |
|
81 |
+
|
82 |
+
|
83 |
+
### Framework versions
|
84 |
+
|
85 |
+
- PEFT 0.12.0
|
86 |
+
- Transformers 4.44.0
|
87 |
+
- Pytorch 2.4.0
|
88 |
+
- Datasets 2.21.0
|
89 |
+
- Tokenizers 0.19.1
|
adapter_config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
|
5 |
+
"bias": "all",
|
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": 12,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"v_proj",
|
24 |
+
"q_proj"
|
25 |
+
],
|
26 |
+
"task_type": "CAUSAL_LM",
|
27 |
+
"use_dora": false,
|
28 |
+
"use_rslora": false
|
29 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ada0598278cab09464fd46c7111e46b842e6d59b76d2c53f4fc298852ec0b0c2
|
3 |
+
size 20464376
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b96ccadbb9f5b227282e74d30e7555b87e87bfea71450bcab41d13c98f943c92
|
3 |
+
size 5112
|