Arihant Tripathi commited on
Commit
55f3076
·
verified ·
1 Parent(s): 6effbbc

qwen_new_mage_per_domain_balanced_1.5

Browse files
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 [Qwen/Qwen1.5-1.8B](https://huggingface.co/Qwen/Qwen1.5-1.8B) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.2937
22
- - Accuracy: 0.8863
23
 
24
  ## Model description
25
 
@@ -38,22 +38,28 @@ More information needed
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
- - learning_rate: 2e-05
42
  - train_batch_size: 32
43
  - eval_batch_size: 32
44
  - seed: 42
45
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
  - lr_scheduler_type: linear
47
- - num_epochs: 3
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:------:|:----:|:---------------:|:--------:|
53
- | 0.7355 | 0.0183 | 100 | 0.2731 | 0.8854 |
54
- | 0.3892 | 0.0366 | 200 | 0.4133 | 0.8156 |
55
- | 0.3087 | 0.0549 | 300 | 0.4579 | 0.8433 |
56
- | 0.2798 | 0.0732 | 400 | 0.2937 | 0.8863 |
 
 
 
 
 
 
57
 
58
 
59
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [Qwen/Qwen1.5-1.8B](https://huggingface.co/Qwen/Qwen1.5-1.8B) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.0842
22
+ - Accuracy: 0.9714
23
 
24
  ## Model description
25
 
 
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
+ - learning_rate: 5e-06
42
  - train_batch_size: 32
43
  - eval_batch_size: 32
44
  - seed: 42
45
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
  - lr_scheduler_type: linear
47
+ - num_epochs: 1
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:------:|:----:|:---------------:|:--------:|
53
+ | 0.1807 | 0.0915 | 500 | 0.3355 | 0.8881 |
54
+ | 0.1387 | 0.1831 | 1000 | 0.1860 | 0.9293 |
55
+ | 0.1443 | 0.2746 | 1500 | 0.1421 | 0.9418 |
56
+ | 0.1143 | 0.3662 | 2000 | 0.1273 | 0.9517 |
57
+ | 0.1103 | 0.4577 | 2500 | 0.1393 | 0.9490 |
58
+ | 0.1049 | 0.5492 | 3000 | 0.1159 | 0.9606 |
59
+ | 0.0809 | 0.6408 | 3500 | 0.1267 | 0.9526 |
60
+ | 0.0896 | 0.7323 | 4000 | 0.1104 | 0.9606 |
61
+ | 0.0758 | 0.8239 | 4500 | 0.1341 | 0.9633 |
62
+ | 0.0811 | 0.9154 | 5000 | 0.0842 | 0.9714 |
63
 
64
 
65
  ### Framework versions
evaluation_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eval_loss": 0.29367899894714355,
3
+ "eval_accuracy": 0.8863025962399284,
4
+ "eval_runtime": 35.1558,
5
+ "eval_samples_per_second": 31.773,
6
+ "eval_steps_per_second": 0.996,
7
+ "epoch": 0.07323324789454412
8
+ }
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3ce3d9b57e79624dab2def7a89cb835512538e32af92b8f75df25348a97d4b5a
3
  size 4955308912
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:738a95aaa357cdeec54c5282ac1cf2afd7cef77bee594ce14c614b3407e311ae
3
  size 4955308912
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:48a602a71f21cf6f632a54a988f5d83981bd4750d12ea7b50071a0e2241ff034
3
  size 1147395408
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dee692604a64516af4f8f5ed47fd6b0b29f07b26825d9462dcb85abb9a7b1a9a
3
  size 1147395408
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d9b60139369c744f986a4c30f484555e7e931535e218b54d38cac9893824e4e1
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76630ee7ca57d10ae6eb51557aa48d654231d33615c8c4c4854af4823bf72710
3
  size 5304