Tanabodee Limpaitoon commited on
Commit
7615e5c
1 Parent(s): 028ec0f

Model save

Browse files
README.md CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  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 the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 13.0106
20
 
21
  ## Model description
22
 
@@ -35,23 +35,25 @@ More information needed
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
- - learning_rate: 3e-05
39
  - train_batch_size: 8
40
  - eval_batch_size: 8
41
  - seed: 42
42
- - gradient_accumulation_steps: 32
43
- - total_train_batch_size: 256
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
- - lr_scheduler_type: cosine
46
- - num_epochs: 3
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss |
51
  |:-------------:|:------:|:----:|:---------------:|
52
- | No log | 0.9505 | 3 | 14.6404 |
53
- | No log | 1.9010 | 6 | 13.3242 |
54
- | No log | 2.8515 | 9 | 13.0106 |
 
 
55
 
56
 
57
  ### Framework versions
 
16
 
17
  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 the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 1.4442
20
 
21
  ## Model description
22
 
 
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
+ - learning_rate: 5e-05
39
  - train_batch_size: 8
40
  - eval_batch_size: 8
41
  - seed: 42
42
+ - gradient_accumulation_steps: 16
43
+ - total_train_batch_size: 128
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - num_epochs: 5
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss |
51
  |:-------------:|:------:|:----:|:---------------:|
52
+ | No log | 0.9505 | 6 | 10.0837 |
53
+ | No log | 1.9010 | 12 | 6.2223 |
54
+ | No log | 2.8515 | 18 | 3.3307 |
55
+ | No log | 3.9604 | 25 | 1.7251 |
56
+ | No log | 4.7525 | 30 | 1.4442 |
57
 
58
 
59
  ### Framework versions
runs/Sep22_14-39-34_e8b759157a8d/events.out.tfevents.1727015974.e8b759157a8d.5822.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a08722280c2251fab320955a74b098a0de05afb4148e7ae466c990a30234e772
3
- size 6694
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ba2f3803ac1810589ea377bc635b10ecabbe1e8437cdd23b68d518487783c1b
3
+ size 7308