ccibeekeoc42
commited on
Commit
•
4175656
1
Parent(s):
938cda9
End of training
Browse files- README.md +78 -0
- adapter_model.safetensors +1 -1
README.md
ADDED
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
|
3 |
+
library_name: peft
|
4 |
+
license: llama3.1
|
5 |
+
tags:
|
6 |
+
- trl
|
7 |
+
- sft
|
8 |
+
- generated_from_trainer
|
9 |
+
model-index:
|
10 |
+
- name: Llama3.1-8b-instruct-SFT-2024-09-20_LoRAs_r64
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# Llama3.1-8b-instruct-SFT-2024-09-20_LoRAs_r64
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on an unknown dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 1.0712
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 1e-05
|
41 |
+
- train_batch_size: 6
|
42 |
+
- eval_batch_size: 1
|
43 |
+
- seed: 42
|
44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: constant
|
46 |
+
- num_epochs: 1.5
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
51 |
+
|:-------------:|:------:|:-----:|:---------------:|
|
52 |
+
| 1.5247 | 0.0793 | 1000 | 1.3914 |
|
53 |
+
| 1.341 | 0.1586 | 2000 | 1.3288 |
|
54 |
+
| 1.314 | 0.2380 | 3000 | 1.2961 |
|
55 |
+
| 1.261 | 0.3173 | 4000 | 1.2635 |
|
56 |
+
| 1.2397 | 0.3966 | 5000 | 1.2353 |
|
57 |
+
| 1.212 | 0.4759 | 6000 | 1.2240 |
|
58 |
+
| 1.2051 | 0.5552 | 7000 | 1.2019 |
|
59 |
+
| 1.1845 | 0.6346 | 8000 | 1.1861 |
|
60 |
+
| 1.157 | 0.7139 | 9000 | 1.1684 |
|
61 |
+
| 1.1418 | 0.7932 | 10000 | 1.1580 |
|
62 |
+
| 1.1374 | 0.8725 | 11000 | 1.1385 |
|
63 |
+
| 1.1187 | 0.9519 | 12000 | 1.1243 |
|
64 |
+
| 1.0841 | 1.0312 | 13000 | 1.1180 |
|
65 |
+
| 1.0365 | 1.1105 | 14000 | 1.1062 |
|
66 |
+
| 1.0266 | 1.1898 | 15000 | 1.0974 |
|
67 |
+
| 1.0216 | 1.2691 | 16000 | 1.0935 |
|
68 |
+
| 1.0217 | 1.3485 | 17000 | 1.0818 |
|
69 |
+
| 1.0048 | 1.4278 | 18000 | 1.0712 |
|
70 |
+
|
71 |
+
|
72 |
+
### Framework versions
|
73 |
+
|
74 |
+
- PEFT 0.12.0
|
75 |
+
- Transformers 4.44.2
|
76 |
+
- Pytorch 2.0.1+cu118
|
77 |
+
- Datasets 3.0.0
|
78 |
+
- Tokenizers 0.19.1
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2806378968
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c7f538b6d196d341a3f496b38309b68a29f5dab78de0aca3ada1cdc92a4f5f8b
|
3 |
size 2806378968
|