Hugging Face's logo

sophiargh
/
MNLP_M3_mcqa_model_v2

Text Generation
Transformers
Safetensors
qwen3
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
 Community
sophiargh commited on
Commit
2869276
·
verified ·
1 Parent(s): 63f4f63

Training in progress, step 5000

Browse files
Files changed (3) hide show
  1. README.md +14 -24
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -4,22 +4,19 @@ license: apache-2.0
4
  base_model: Qwen/Qwen3-0.6B-Base
5
  tags:
6
  - generated_from_trainer
7
- metrics:
8
- - accuracy
9
  model-index:
10
- - name: MNLP_M3_mcqa_model_2
11
  results: []
12
  ---
13
 
14
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
  should probably proofread and complete it, then remove this comment. -->
16
 
17
- # MNLP_M3_mcqa_model_2
18
 
19
- This model is a fine-tuned version of [Qwen/Qwen3-0.6B-Base](https://huggingface.co/Qwen/Qwen3-0.6B-Base) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.2953
22
- - Accuracy: 0.9001
23
 
24
  ## Model description
25
 
@@ -38,31 +35,24 @@ More information needed
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
- - learning_rate: 1e-05
42
- - train_batch_size: 2
43
- - eval_batch_size: 2
44
  - seed: 42
45
  - gradient_accumulation_steps: 4
46
- - total_train_batch_size: 8
47
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
  - lr_scheduler_type: cosine
49
- - lr_scheduler_warmup_ratio: 0.01
50
  - num_epochs: 4
51
 
52
  ### Training results
53
 
54
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
55
- |:-------------:|:------:|:-----:|:---------------:|:--------:|
56
- | 0.2687 | 0.2278 | 1000 | 0.2625 | 0.8896 |
57
- | 0.2575 | 0.4555 | 2000 | 0.2582 | 0.8926 |
58
- | 0.2475 | 0.6833 | 3000 | 0.2482 | 0.8975 |
59
- | 0.2497 | 0.9111 | 4000 | 0.2461 | 0.8968 |
60
- | 0.1928 | 1.1387 | 5000 | 0.2594 | 0.8999 |
61
- | 0.1868 | 1.3665 | 6000 | 0.2640 | 0.8997 |
62
- | 0.1974 | 1.5942 | 7000 | 0.2714 | 0.9001 |
63
- | 0.1935 | 1.8220 | 8000 | 0.2666 | 0.9006 |
64
- | 0.171 | 2.0497 | 9000 | 0.2907 | 0.8998 |
65
- | 0.1628 | 2.2774 | 10000 | 0.2953 | 0.9001 |
66
 
67
 
68
  ### Framework versions
 
4
  base_model: Qwen/Qwen3-0.6B-Base
5
  tags:
6
  - generated_from_trainer
 
 
7
  model-index:
8
+ - name: MNLP_M3_mcqa_model
9
  results: []
10
  ---
11
 
12
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
  should probably proofread and complete it, then remove this comment. -->
14
 
15
+ # MNLP_M3_mcqa_model
16
 
17
+ This model is a fine-tuned version of [Qwen/Qwen3-0.6B-Base](https://huggingface.co/Qwen/Qwen3-0.6B-Base) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.0028
 
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: 4
40
+ - eval_batch_size: 4
41
  - seed: 42
42
  - gradient_accumulation_steps: 4
43
+ - total_train_batch_size: 16
44
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
  - lr_scheduler_type: cosine
46
+ - lr_scheduler_warmup_ratio: 0.1
47
  - num_epochs: 4
48
 
49
  ### Training results
50
 
51
+ | Training Loss | Epoch | Step | Validation Loss |
52
+ |:-------------:|:-----:|:----:|:---------------:|
53
+ | 0.0019 | 1.0 | 2196 | 0.0018 |
54
+ | 0.0011 | 2.0 | 4392 | 0.0018 |
55
+ | 0.0003 | 3.0 | 6588 | 0.0028 |
 
 
 
 
 
 
 
56
 
57
 
58
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:54fd0f1e955c305c66c7781a270405271ae9a2f36b28c95dabe6a7bf6e1a9e75
3
  size 1192135096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8de2862e84ecf33c3d493b8e4001dbfbe454f101dda137b481388d60eb290120
3
  size 1192135096
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08165811af69b25e105edc482088f618cb57f80eb53879d985df3b3265b7e0a6
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b81453047a38e1b725777fd605757ed38025f96709bcf86ca902845d154f4bb6
3
  size 5304