Hugging Face's logo

rishavranaut
/
QWEN_without_time

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files
xet
Metrics Community
rishavranaut commited on
Commit
d24a821
·
verified ·
1 Parent(s): 5962927

rishavranaut/QWEN_without_time

Browse files
Files changed (1) hide show
  1. README.md +101 -0
README.md ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: peft
4
+ tags:
5
+ - generated_from_trainer
6
+ base_model: Qwen/Qwen2-7B
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: QWEN_without_time
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
+ # QWEN_without_time
18
+
19
+ This model is a fine-tuned version of [Qwen/Qwen2-7B](https://huggingface.co/Qwen/Qwen2-7B) on the None dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.3017
22
+ - Balanced Accuracy: 0.8957
23
+ - Accuracy: 0.8957
24
+ - Micro F1: 0.8957
25
+ - Macro F1: 0.8957
26
+ - Weighted F1: 0.8957
27
+ - Classification Report: precision recall f1-score support
28
+
29
+ 0 0.90 0.89 0.90 386
30
+ 1 0.89 0.90 0.90 381
31
+
32
+ accuracy 0.90 767
33
+ macro avg 0.90 0.90 0.90 767
34
+ weighted avg 0.90 0.90 0.90 767
35
+
36
+
37
+ ## Model description
38
+
39
+ More information needed
40
+
41
+ ## Intended uses & limitations
42
+
43
+ More information needed
44
+
45
+ ## Training and evaluation data
46
+
47
+ More information needed
48
+
49
+ ## Training procedure
50
+
51
+ ### Training hyperparameters
52
+
53
+ The following hyperparameters were used during training:
54
+ - learning_rate: 0.0001
55
+ - train_batch_size: 16
56
+ - eval_batch_size: 8
57
+ - seed: 42
58
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
+ - lr_scheduler_type: linear
60
+ - num_epochs: 3
61
+
62
+ ### Training results
63
+
64
+ | Training Loss | Epoch | Step | Validation Loss | Balanced Accuracy | Accuracy | Micro F1 | Macro F1 | Weighted F1 | Classification Report |
65
+ |:-------------:|:-----:|:----:|:---------------:|:-----------------:|:--------:|:--------:|:--------:|:-----------:|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|
66
+ | 0.5773 | 1.0 | 384 | 0.3372 | 0.8736 | 0.8735 | 0.8735 | 0.8735 | 0.8735 | precision recall f1-score support
67
+
68
+ 0 0.88 0.87 0.87 386
69
+ 1 0.87 0.88 0.87 381
70
+
71
+ accuracy 0.87 767
72
+ macro avg 0.87 0.87 0.87 767
73
+ weighted avg 0.87 0.87 0.87 767
74
+ |
75
+ | 0.3341 | 2.0 | 768 | 0.4140 | 0.8624 | 0.8631 | 0.8631 | 0.8612 | 0.8613 | precision recall f1-score support
76
+
77
+ 0 0.80 0.97 0.88 386
78
+ 1 0.97 0.75 0.84 381
79
+
80
+ accuracy 0.86 767
81
+ macro avg 0.88 0.86 0.86 767
82
+ weighted avg 0.88 0.86 0.86 767
83
+ |
84
+ | 0.2934 | 3.0 | 1152 | 0.3017 | 0.8957 | 0.8957 | 0.8957 | 0.8957 | 0.8957 | precision recall f1-score support
85
+
86
+ 0 0.90 0.89 0.90 386
87
+ 1 0.89 0.90 0.90 381
88
+
89
+ accuracy 0.90 767
90
+ macro avg 0.90 0.90 0.90 767
91
+ weighted avg 0.90 0.90 0.90 767
92
+ |
93
+
94
+
95
+ ### Framework versions
96
+
97
+ - PEFT 0.11.1
98
+ - Transformers 4.41.2
99
+ - Pytorch 2.3.0+cu121
100
+ - Datasets 2.19.1
101
+ - Tokenizers 0.19.1