Hugging Face's logo

ghegfield
/
Llama-2-7b-chat-hf-formula-peft

Generated from Trainer
Model card Files Community
ghegfield commited on
Commit
830008d
•
1 Parent(s): 57c6ed7

Llama-2-7b-chat-hf-formula-peft

Browse files
Files changed (3) hide show
  1. README.md +16 -9
  2. adapter_model.bin +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [NousResearch/Llama-2-7b-chat-hf](https://huggingface.co/NousResearch/Llama-2-7b-chat-hf) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 2.0978
18
 
19
  ## Model description
20
 
@@ -42,19 +42,26 @@ The following hyperparameters were used during training:
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: cosine
44
  - lr_scheduler_warmup_ratio: 0.03
45
- - num_epochs: 10
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
- | 4.0878 | 1.43 | 10 | 3.5298 |
52
- | 2.7514 | 2.86 | 20 | 2.5999 |
53
- | 1.854 | 4.29 | 30 | 2.2461 |
54
- | 1.4716 | 5.71 | 40 | 2.1421 |
55
- | 1.3602 | 7.14 | 50 | 2.1016 |
56
- | 1.2029 | 8.57 | 60 | 2.0985 |
57
- | 1.1427 | 10.0 | 70 | 2.0978 |
 
 
 
 
 
 
 
58
 
59
 
60
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [NousResearch/Llama-2-7b-chat-hf](https://huggingface.co/NousResearch/Llama-2-7b-chat-hf) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 2.1452
18
 
19
  ## Model description
20
 
 
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: cosine
44
  - lr_scheduler_warmup_ratio: 0.03
45
+ - num_epochs: 20
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
+ | 4.1878 | 1.43 | 10 | 3.6596 |
52
+ | 2.8437 | 2.86 | 20 | 2.6466 |
53
+ | 1.8635 | 4.29 | 30 | 2.2266 |
54
+ | 1.4052 | 5.71 | 40 | 2.1136 |
55
+ | 1.2186 | 7.14 | 50 | 2.0805 |
56
+ | 0.8835 | 8.57 | 60 | 2.0733 |
57
+ | 0.6991 | 10.0 | 70 | 2.0809 |
58
+ | 0.5608 | 11.43 | 80 | 2.0862 |
59
+ | 0.4188 | 12.86 | 90 | 2.1078 |
60
+ | 0.3897 | 14.29 | 100 | 2.1089 |
61
+ | 0.2748 | 15.71 | 110 | 2.1333 |
62
+ | 0.2582 | 17.14 | 120 | 2.1383 |
63
+ | 0.2394 | 18.57 | 130 | 2.1440 |
64
+ | 0.2392 | 20.0 | 140 | 2.1452 |
65
 
66
 
67
  ### Framework versions
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2214f28b30579be29788e2a080ea339e509923551bb2e714c9eb36e1a45ff897
3
  size 134264202
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d828a84c19864dcaa5c78bd55266c986295d7005af45e91353d3c6a03f1e0b75
3
  size 134264202
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:16e6728232aa17e18af041b60632a992d653c3308e50f2c33c2e4dad9af0d61c
3
  size 4536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7d68bafdce6f84a54d2e1e495ac9bc1d91336c46b4b2f89fdbafdc5853023f7
3
  size 4536