Hugging Face's logo

archit11
/
qwen-ft

Text Generation
Transformers
TensorBoard
Safetensors
qwen2
Generated from Trainer
text-generation-inference
Model card Files
xet
Metrics Community
1

Improve language tag

#1
by lbourdois - opened
base: refs/heads/main
←
from: refs/pr/1
Discussion Files changed
+90
-76
Files changed (1) hide show
  1. README.md +90 -76
README.md CHANGED
@@ -1,76 +1,90 @@
1
- ---
2
- library_name: transformers
3
- license: apache-2.0
4
- base_model: Qwen/Qwen2.5-0.5B-Instruct
5
- tags:
6
- - generated_from_trainer
7
- model-index:
8
- - name: qwen-ft
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
- # qwen-ft
16
-
17
- This model is a fine-tuned version of [Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct) on an unknown dataset.
18
- It achieves the following results on the evaluation set:
19
- - Loss: 5.6514
20
-
21
- ## Model description
22
-
23
- More information needed
24
-
25
- ## Intended uses & limitations
26
-
27
- More information needed
28
-
29
- ## Training and evaluation data
30
-
31
- More information needed
32
-
33
- ## Training procedure
34
-
35
- ### Training hyperparameters
36
-
37
- The following hyperparameters were used during training:
38
- - learning_rate: 0.0002
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
- - lr_scheduler_type: cosine
46
- - lr_scheduler_warmup_steps: 5
47
- - training_steps: 800
48
-
49
- ### Training results
50
-
51
- | Training Loss | Epoch | Step | Validation Loss |
52
- |:-------------:|:------:|:----:|:---------------:|
53
- | 7.7492 | 0.0920 | 50 | 7.5711 |
54
- | 7.4321 | 0.1841 | 100 | 7.3186 |
55
- | 7.0377 | 0.2761 | 150 | 6.9218 |
56
- | 6.8861 | 0.3682 | 200 | 6.7542 |
57
- | 6.7161 | 0.4602 | 250 | 6.5817 |
58
- | 6.4542 | 0.5522 | 300 | 6.3050 |
59
- | 6.3839 | 0.6443 | 350 | 6.2909 |
60
- | 6.1342 | 0.7363 | 400 | 6.0133 |
61
- | 5.9798 | 0.8283 | 450 | 5.8894 |
62
- | 5.9043 | 0.9204 | 500 | 5.8061 |
63
- | 5.889 | 1.0124 | 550 | 5.7376 |
64
- | 5.7778 | 1.1045 | 600 | 5.6900 |
65
- | 5.8077 | 1.1965 | 650 | 5.6643 |
66
- | 5.7363 | 1.2885 | 700 | 5.6539 |
67
- | 5.7524 | 1.3806 | 750 | 5.6515 |
68
- | 5.7289 | 1.4726 | 800 | 5.6514 |
69
-
70
-
71
- ### Framework versions
72
-
73
- - Transformers 4.44.2
74
- - Pytorch 2.4.0
75
- - Datasets 3.0.0
76
- - Tokenizers 0.19.1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: Qwen/Qwen2.5-0.5B-Instruct
5
+ tags:
6
+ - generated_from_trainer
7
+ language:
8
+ - zho
9
+ - eng
10
+ - fra
11
+ - spa
12
+ - por
13
+ - deu
14
+ - ita
15
+ - rus
16
+ - jpn
17
+ - kor
18
+ - vie
19
+ - tha
20
+ - ara
21
+ model-index:
22
+ - name: qwen-ft
23
+ results: []
24
+ ---
25
+
26
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
27
+ should probably proofread and complete it, then remove this comment. -->
28
+
29
+ # qwen-ft
30
+
31
+ This model is a fine-tuned version of [Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct) on an unknown dataset.
32
+ It achieves the following results on the evaluation set:
33
+ - Loss: 5.6514
34
+
35
+ ## Model description
36
+
37
+ More information needed
38
+
39
+ ## Intended uses & limitations
40
+
41
+ More information needed
42
+
43
+ ## Training and evaluation data
44
+
45
+ More information needed
46
+
47
+ ## Training procedure
48
+
49
+ ### Training hyperparameters
50
+
51
+ The following hyperparameters were used during training:
52
+ - learning_rate: 0.0002
53
+ - train_batch_size: 4
54
+ - eval_batch_size: 4
55
+ - seed: 42
56
+ - gradient_accumulation_steps: 4
57
+ - total_train_batch_size: 16
58
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
+ - lr_scheduler_type: cosine
60
+ - lr_scheduler_warmup_steps: 5
61
+ - training_steps: 800
62
+
63
+ ### Training results
64
+
65
+ | Training Loss | Epoch | Step | Validation Loss |
66
+ |:-------------:|:------:|:----:|:---------------:|
67
+ | 7.7492 | 0.0920 | 50 | 7.5711 |
68
+ | 7.4321 | 0.1841 | 100 | 7.3186 |
69
+ | 7.0377 | 0.2761 | 150 | 6.9218 |
70
+ | 6.8861 | 0.3682 | 200 | 6.7542 |
71
+ | 6.7161 | 0.4602 | 250 | 6.5817 |
72
+ | 6.4542 | 0.5522 | 300 | 6.3050 |
73
+ | 6.3839 | 0.6443 | 350 | 6.2909 |
74
+ | 6.1342 | 0.7363 | 400 | 6.0133 |
75
+ | 5.9798 | 0.8283 | 450 | 5.8894 |
76
+ | 5.9043 | 0.9204 | 500 | 5.8061 |
77
+ | 5.889 | 1.0124 | 550 | 5.7376 |
78
+ | 5.7778 | 1.1045 | 600 | 5.6900 |
79
+ | 5.8077 | 1.1965 | 650 | 5.6643 |
80
+ | 5.7363 | 1.2885 | 700 | 5.6539 |
81
+ | 5.7524 | 1.3806 | 750 | 5.6515 |
82
+ | 5.7289 | 1.4726 | 800 | 5.6514 |
83
+
84
+
85
+ ### Framework versions
86
+
87
+ - Transformers 4.44.2
88
+ - Pytorch 2.4.0
89
+ - Datasets 3.0.0
90
+ - Tokenizers 0.19.1