Hugging Face's logo

NanQiangHF
/
llama3.1_8b_bwgenerator

PEFT
Safetensors
llama
trl
sft
Generated from Trainer
Model card Files Community
NanQiangHF commited on
Commit
09f1bb4
•
1 Parent(s): 5888ad9

llama3.1_8b_bwgenerator

Browse files
Files changed (3) hide show
  1. README.md +15 -13
  2. adapter_model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
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: 0.1856
22
 
23
  ## Model description
24
 
@@ -45,23 +45,25 @@ The following hyperparameters were used during training:
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
- | 1.8017 | 0.2585 | 10 | 0.8807 |
55
- | 0.5653 | 0.5170 | 20 | 0.3488 |
56
- | 0.3026 | 0.7754 | 30 | 0.2705 |
57
- | 0.255 | 1.0339 | 40 | 0.2418 |
58
- | 0.2307 | 1.2924 | 50 | 0.2223 |
59
- | 0.2157 | 1.5509 | 60 | 0.2099 |
60
- | 0.206 | 1.8094 | 70 | 0.2021 |
61
- | 0.1978 | 2.0679 | 80 | 0.1962 |
62
- | 0.1913 | 2.3263 | 90 | 0.1910 |
63
- | 0.1882 | 2.5848 | 100 | 0.1877 |
64
- | 0.1861 | 2.8433 | 110 | 0.1856 |
 
 
65
 
66
 
67
  ### Framework versions
 
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: 0.1193
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: 2
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:------:|:----:|:---------------:|
54
+ | 1.2338 | 0.1456 | 20 | 0.3871 |
55
+ | 0.3226 | 0.2911 | 40 | 0.2794 |
56
+ | 0.2612 | 0.4367 | 60 | 0.2409 |
57
+ | 0.2238 | 0.5822 | 80 | 0.2055 |
58
+ | 0.1848 | 0.7278 | 100 | 0.1625 |
59
+ | 0.1505 | 0.8733 | 120 | 0.1424 |
60
+ | 0.1382 | 1.0189 | 140 | 0.1347 |
61
+ | 0.1319 | 1.1644 | 160 | 0.1311 |
62
+ | 0.1281 | 1.3100 | 180 | 0.1265 |
63
+ | 0.1248 | 1.4555 | 200 | 0.1237 |
64
+ | 0.1228 | 1.6011 | 220 | 0.1221 |
65
+ | 0.1205 | 1.7466 | 240 | 0.1200 |
66
+ | 0.1201 | 1.8922 | 260 | 0.1193 |
67
 
68
 
69
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c838c4a2f8eba919eae620cb00e8e19ff58b8c3a5286160e3cc7b8b8526930c5
3
  size 6832728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f69449384f7f9777816d641acffe5fc1721bd9cb8f35df65a278fd43fe70fa8
3
  size 6832728
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d19cb981a2f30ca18fe5cd1d3364688db63eda07bd0aa8a226d9f92a0e824a1a
3
  size 5560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b369b6ad9bb7b80e5b5359a2eda8a6264f5ef7562c67f966d3aa7831507cce5c
3
  size 5560