Hugging Face's logo

garypak
/
llama3.2-1b-rumour-samples

Transformers
PyTorch
Generated from Trainer
Inference Endpoints
Model card Files Community
garypak commited on
Commit
ca50c68
•
1 Parent(s): 673ff54

End of training

Browse files
Files changed (3) hide show
  1. README.md +16 -17
  2. pytorch_model.bin +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 1.4458
22
- - Accuracy: 0.5545
23
 
24
  ## Model description
25
 
@@ -38,31 +38,30 @@ More information needed
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
- - learning_rate: 2e-05
42
- - train_batch_size: 8
43
  - eval_batch_size: 8
44
  - seed: 7788
45
- - gradient_accumulation_steps: 8
46
- - total_train_batch_size: 64
47
  - optimizer: Use adamw_hf with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
  - lr_scheduler_type: linear
49
- - num_epochs: 10
 
50
  - mixed_precision_training: Native AMP
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
55
  |:-------------:|:------:|:----:|:---------------:|:--------:|
56
- | 9.4603 | 1.0 | 38 | 3.4990 | 0.4103 |
57
- | 1.8476 | 2.0 | 76 | 2.0942 | 0.4135 |
58
- | 1.3344 | 3.0 | 114 | 1.7224 | 0.5032 |
59
- | 1.1373 | 4.0 | 152 | 1.6171 | 0.5080 |
60
- | 0.8903 | 5.0 | 190 | 1.5210 | 0.5080 |
61
- | 0.7372 | 6.0 | 228 | 1.4351 | 0.5481 |
62
- | 0.6233 | 7.0 | 266 | 1.4929 | 0.5481 |
63
- | 0.6974 | 8.0 | 304 | 1.4986 | 0.5369 |
64
- | 0.5388 | 9.0 | 342 | 1.4638 | 0.5529 |
65
- | 0.486 | 9.7492 | 370 | 1.4458 | 0.5545 |
66
 
67
 
68
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 2.0522
22
+ - Accuracy: 0.5321
23
 
24
  ## Model description
25
 
 
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
+ - learning_rate: 2.5e-05
42
+ - train_batch_size: 4
43
  - eval_batch_size: 8
44
  - seed: 7788
45
+ - gradient_accumulation_steps: 4
46
+ - total_train_batch_size: 16
47
  - optimizer: Use adamw_hf with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
  - lr_scheduler_type: linear
49
+ - lr_scheduler_warmup_ratio: 0.1
50
+ - num_epochs: 8
51
  - mixed_precision_training: Native AMP
52
 
53
  ### Training results
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
56
  |:-------------:|:------:|:----:|:---------------:|:--------:|
57
+ | 2.9563 | 0.9967 | 149 | 2.1771 | 0.3846 |
58
+ | 1.581 | 1.9967 | 298 | 1.9459 | 0.4952 |
59
+ | 1.0792 | 2.9967 | 447 | 1.6599 | 0.5513 |
60
+ | 0.7366 | 3.9967 | 596 | 2.2794 | 0.5144 |
61
+ | 0.4716 | 4.9967 | 745 | 1.9941 | 0.5513 |
62
+ | 0.2634 | 5.9967 | 894 | 2.0054 | 0.5641 |
63
+ | 0.1978 | 6.9967 | 1043 | 2.0889 | 0.5433 |
64
+ | 0.0945 | 7.9967 | 1192 | 2.0522 | 0.5321 |
 
 
65
 
66
 
67
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:350e62a1bc03b4fe2dc97466e56ad7a5aece6f13025c0511ef40bf0c1c8a575b
3
  size 2037172570
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4d7ff76ff66be9e7f9c927521b61318b4774ba93a72d820ed6c038e619b7434
3
  size 2037172570
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5cda533e64801a309df87fd5568854ba0b27310fd6c3dd91b18ee86b13268d5d
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59c7d5d97fe93ee184713e4047ee811ee9c74e3cf5561ae33a24866d6c7f7df0
3
  size 5304