NanQiangHF
commited on
Commit
•
d8942f8
1
Parent(s):
12ff455
llama3_8b_bwgenerator_instruct
Browse files- README.md +14 -1
- adapter_model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -17,6 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
# Meta-Llama-3-8B-Instruct-Generator
|
18 |
|
19 |
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 an unknown dataset.
|
|
|
|
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -43,10 +45,21 @@ The following hyperparameters were used during training:
|
|
43 |
- total_train_batch_size: 256
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: linear
|
46 |
-
- num_epochs:
|
47 |
|
48 |
### Training results
|
49 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
50 |
|
51 |
|
52 |
### Framework versions
|
|
|
17 |
# Meta-Llama-3-8B-Instruct-Generator
|
18 |
|
19 |
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 an unknown dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.1433
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
45 |
- total_train_batch_size: 256
|
46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
- lr_scheduler_type: linear
|
48 |
+
- num_epochs: 3
|
49 |
|
50 |
### Training results
|
51 |
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
+
|:-------------:|:------:|:----:|:---------------:|
|
54 |
+
| 1.426 | 0.3287 | 20 | 0.4661 |
|
55 |
+
| 0.3689 | 0.6574 | 40 | 0.3151 |
|
56 |
+
| 0.2887 | 0.9861 | 60 | 0.2654 |
|
57 |
+
| 0.2441 | 1.3148 | 80 | 0.2161 |
|
58 |
+
| 0.1863 | 1.6436 | 100 | 0.1709 |
|
59 |
+
| 0.1656 | 1.9723 | 120 | 0.1576 |
|
60 |
+
| 0.1538 | 2.3010 | 140 | 0.1491 |
|
61 |
+
| 0.1475 | 2.6297 | 160 | 0.1444 |
|
62 |
+
| 0.1449 | 2.9584 | 180 | 0.1433 |
|
63 |
|
64 |
|
65 |
### Framework versions
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6832728
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b90ef7c8b961a355f7e52c0971c8c0da360dbf290b1a047c56ec8763f9df2f9
|
3 |
size 6832728
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5496
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:34d0b7ada03344befe42d1fd7554d24139bbd48a53a4c05f04bb2047367d065f
|
3 |
size 5496
|