Hugging Face's logo

chchen
/
Qwen2.5-7B-Instruct-PsyCourse-fold6

PEFT
Safetensors
llama-factory
Generated from Trainer
Model card Files
xet
Community
1

Improve language tag

#1
by lbourdois - opened
base: refs/heads/main
←
from: refs/pr/1
Discussion Files changed
+139
-125
Files changed (1) hide show
  1. README.md +139 -125
README.md CHANGED
@@ -1,126 +1,140 @@
1
- ---
2
- library_name: peft
3
- license: apache-2.0
4
- base_model: Qwen/Qwen2.5-7B-Instruct
5
- tags:
6
- - llama-factory
7
- - generated_from_trainer
8
- model-index:
9
- - name: Qwen2.5-7B-Instruct-PsyCourse-fold6
10
- results: []
11
- ---
12
-
13
- <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
- should probably proofread and complete it, then remove this comment. -->
15
-
16
- # Qwen2.5-7B-Instruct-PsyCourse-fold6
17
-
18
- This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on an unknown dataset.
19
- It achieves the following results on the evaluation set:
20
- - Loss: 0.0499
21
-
22
- ## Model description
23
-
24
- More information needed
25
-
26
- ## Intended uses & limitations
27
-
28
- More information needed
29
-
30
- ## Training and evaluation data
31
-
32
- More information needed
33
-
34
- ## Training procedure
35
-
36
- ### Training hyperparameters
37
-
38
- The following hyperparameters were used during training:
39
- - learning_rate: 0.0001
40
- - train_batch_size: 1
41
- - eval_batch_size: 1
42
- - seed: 42
43
- - gradient_accumulation_steps: 16
44
- - total_train_batch_size: 16
45
- - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
- - lr_scheduler_type: cosine
47
- - lr_scheduler_warmup_ratio: 0.1
48
- - num_epochs: 5.0
49
-
50
- ### Training results
51
-
52
- | Training Loss | Epoch | Step | Validation Loss |
53
- |:-------------:|:------:|:----:|:---------------:|
54
- | 0.8724 | 0.0770 | 50 | 0.6925 |
55
- | 0.1566 | 0.1539 | 100 | 0.1080 |
56
- | 0.0875 | 0.2309 | 150 | 0.0727 |
57
- | 0.0734 | 0.3078 | 200 | 0.0559 |
58
- | 0.0553 | 0.3848 | 250 | 0.0525 |
59
- | 0.0521 | 0.4617 | 300 | 0.0499 |
60
- | 0.0466 | 0.5387 | 350 | 0.0471 |
61
- | 0.0641 | 0.6156 | 400 | 0.0452 |
62
- | 0.0353 | 0.6926 | 450 | 0.0445 |
63
- | 0.0306 | 0.7695 | 500 | 0.0408 |
64
- | 0.048 | 0.8465 | 550 | 0.0382 |
65
- | 0.0373 | 0.9234 | 600 | 0.0377 |
66
- | 0.0306 | 1.0004 | 650 | 0.0359 |
67
- | 0.037 | 1.0773 | 700 | 0.0376 |
68
- | 0.0307 | 1.1543 | 750 | 0.0356 |
69
- | 0.03 | 1.2312 | 800 | 0.0348 |
70
- | 0.0342 | 1.3082 | 850 | 0.0349 |
71
- | 0.0199 | 1.3851 | 900 | 0.0341 |
72
- | 0.0405 | 1.4621 | 950 | 0.0354 |
73
- | 0.0329 | 1.5391 | 1000 | 0.0330 |
74
- | 0.0334 | 1.6160 | 1050 | 0.0333 |
75
- | 0.0325 | 1.6930 | 1100 | 0.0346 |
76
- | 0.0207 | 1.7699 | 1150 | 0.0327 |
77
- | 0.0216 | 1.8469 | 1200 | 0.0341 |
78
- | 0.03 | 1.9238 | 1250 | 0.0341 |
79
- | 0.023 | 2.0008 | 1300 | 0.0321 |
80
- | 0.0148 | 2.0777 | 1350 | 0.0336 |
81
- | 0.0283 | 2.1547 | 1400 | 0.0345 |
82
- | 0.0132 | 2.2316 | 1450 | 0.0357 |
83
- | 0.0199 | 2.3086 | 1500 | 0.0330 |
84
- | 0.0144 | 2.3855 | 1550 | 0.0360 |
85
- | 0.015 | 2.4625 | 1600 | 0.0338 |
86
- | 0.0206 | 2.5394 | 1650 | 0.0330 |
87
- | 0.0184 | 2.6164 | 1700 | 0.0333 |
88
- | 0.0256 | 2.6933 | 1750 | 0.0327 |
89
- | 0.0233 | 2.7703 | 1800 | 0.0344 |
90
- | 0.0229 | 2.8472 | 1850 | 0.0320 |
91
- | 0.0177 | 2.9242 | 1900 | 0.0335 |
92
- | 0.0295 | 3.0012 | 1950 | 0.0336 |
93
- | 0.011 | 3.0781 | 2000 | 0.0370 |
94
- | 0.009 | 3.1551 | 2050 | 0.0408 |
95
- | 0.0101 | 3.2320 | 2100 | 0.0405 |
96
- | 0.011 | 3.3090 | 2150 | 0.0401 |
97
- | 0.0127 | 3.3859 | 2200 | 0.0385 |
98
- | 0.0099 | 3.4629 | 2250 | 0.0380 |
99
- | 0.0109 | 3.5398 | 2300 | 0.0393 |
100
- | 0.0048 | 3.6168 | 2350 | 0.0399 |
101
- | 0.011 | 3.6937 | 2400 | 0.0397 |
102
- | 0.0066 | 3.7707 | 2450 | 0.0404 |
103
- | 0.0089 | 3.8476 | 2500 | 0.0418 |
104
- | 0.0129 | 3.9246 | 2550 | 0.0426 |
105
- | 0.0096 | 4.0015 | 2600 | 0.0414 |
106
- | 0.0015 | 4.0785 | 2650 | 0.0432 |
107
- | 0.0042 | 4.1554 | 2700 | 0.0452 |
108
- | 0.0024 | 4.2324 | 2750 | 0.0466 |
109
- | 0.0032 | 4.3093 | 2800 | 0.0475 |
110
- | 0.0024 | 4.3863 | 2850 | 0.0487 |
111
- | 0.0034 | 4.4633 | 2900 | 0.0491 |
112
- | 0.0016 | 4.5402 | 2950 | 0.0492 |
113
- | 0.0022 | 4.6172 | 3000 | 0.0494 |
114
- | 0.0066 | 4.6941 | 3050 | 0.0498 |
115
- | 0.0023 | 4.7711 | 3100 | 0.0499 |
116
- | 0.0053 | 4.8480 | 3150 | 0.0498 |
117
- | 0.002 | 4.9250 | 3200 | 0.0499 |
118
-
119
-
120
- ### Framework versions
121
-
122
- - PEFT 0.12.0
123
- - Transformers 4.46.1
124
- - Pytorch 2.5.1+cu124
125
- - Datasets 3.1.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
126
  - Tokenizers 0.20.3
 
1
+ ---
2
+ library_name: peft
3
+ license: apache-2.0
4
+ base_model: Qwen/Qwen2.5-7B-Instruct
5
+ tags:
6
+ - llama-factory
7
+ - generated_from_trainer
8
+ language:
9
+ - zho
10
+ - eng
11
+ - fra
12
+ - spa
13
+ - por
14
+ - deu
15
+ - ita
16
+ - rus
17
+ - jpn
18
+ - kor
19
+ - vie
20
+ - tha
21
+ - ara
22
+ model-index:
23
+ - name: Qwen2.5-7B-Instruct-PsyCourse-fold6
24
+ results: []
25
+ ---
26
+
27
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
28
+ should probably proofread and complete it, then remove this comment. -->
29
+
30
+ # Qwen2.5-7B-Instruct-PsyCourse-fold6
31
+
32
+ This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on an unknown dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.0499
35
+
36
+ ## Model description
37
+
38
+ More information needed
39
+
40
+ ## Intended uses & limitations
41
+
42
+ More information needed
43
+
44
+ ## Training and evaluation data
45
+
46
+ More information needed
47
+
48
+ ## Training procedure
49
+
50
+ ### Training hyperparameters
51
+
52
+ The following hyperparameters were used during training:
53
+ - learning_rate: 0.0001
54
+ - train_batch_size: 1
55
+ - eval_batch_size: 1
56
+ - seed: 42
57
+ - gradient_accumulation_steps: 16
58
+ - total_train_batch_size: 16
59
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
60
+ - lr_scheduler_type: cosine
61
+ - lr_scheduler_warmup_ratio: 0.1
62
+ - num_epochs: 5.0
63
+
64
+ ### Training results
65
+
66
+ | Training Loss | Epoch | Step | Validation Loss |
67
+ |:-------------:|:------:|:----:|:---------------:|
68
+ | 0.8724 | 0.0770 | 50 | 0.6925 |
69
+ | 0.1566 | 0.1539 | 100 | 0.1080 |
70
+ | 0.0875 | 0.2309 | 150 | 0.0727 |
71
+ | 0.0734 | 0.3078 | 200 | 0.0559 |
72
+ | 0.0553 | 0.3848 | 250 | 0.0525 |
73
+ | 0.0521 | 0.4617 | 300 | 0.0499 |
74
+ | 0.0466 | 0.5387 | 350 | 0.0471 |
75
+ | 0.0641 | 0.6156 | 400 | 0.0452 |
76
+ | 0.0353 | 0.6926 | 450 | 0.0445 |
77
+ | 0.0306 | 0.7695 | 500 | 0.0408 |
78
+ | 0.048 | 0.8465 | 550 | 0.0382 |
79
+ | 0.0373 | 0.9234 | 600 | 0.0377 |
80
+ | 0.0306 | 1.0004 | 650 | 0.0359 |
81
+ | 0.037 | 1.0773 | 700 | 0.0376 |
82
+ | 0.0307 | 1.1543 | 750 | 0.0356 |
83
+ | 0.03 | 1.2312 | 800 | 0.0348 |
84
+ | 0.0342 | 1.3082 | 850 | 0.0349 |
85
+ | 0.0199 | 1.3851 | 900 | 0.0341 |
86
+ | 0.0405 | 1.4621 | 950 | 0.0354 |
87
+ | 0.0329 | 1.5391 | 1000 | 0.0330 |
88
+ | 0.0334 | 1.6160 | 1050 | 0.0333 |
89
+ | 0.0325 | 1.6930 | 1100 | 0.0346 |
90
+ | 0.0207 | 1.7699 | 1150 | 0.0327 |
91
+ | 0.0216 | 1.8469 | 1200 | 0.0341 |
92
+ | 0.03 | 1.9238 | 1250 | 0.0341 |
93
+ | 0.023 | 2.0008 | 1300 | 0.0321 |
94
+ | 0.0148 | 2.0777 | 1350 | 0.0336 |
95
+ | 0.0283 | 2.1547 | 1400 | 0.0345 |
96
+ | 0.0132 | 2.2316 | 1450 | 0.0357 |
97
+ | 0.0199 | 2.3086 | 1500 | 0.0330 |
98
+ | 0.0144 | 2.3855 | 1550 | 0.0360 |
99
+ | 0.015 | 2.4625 | 1600 | 0.0338 |
100
+ | 0.0206 | 2.5394 | 1650 | 0.0330 |
101
+ | 0.0184 | 2.6164 | 1700 | 0.0333 |
102
+ | 0.0256 | 2.6933 | 1750 | 0.0327 |
103
+ | 0.0233 | 2.7703 | 1800 | 0.0344 |
104
+ | 0.0229 | 2.8472 | 1850 | 0.0320 |
105
+ | 0.0177 | 2.9242 | 1900 | 0.0335 |
106
+ | 0.0295 | 3.0012 | 1950 | 0.0336 |
107
+ | 0.011 | 3.0781 | 2000 | 0.0370 |
108
+ | 0.009 | 3.1551 | 2050 | 0.0408 |
109
+ | 0.0101 | 3.2320 | 2100 | 0.0405 |
110
+ | 0.011 | 3.3090 | 2150 | 0.0401 |
111
+ | 0.0127 | 3.3859 | 2200 | 0.0385 |
112
+ | 0.0099 | 3.4629 | 2250 | 0.0380 |
113
+ | 0.0109 | 3.5398 | 2300 | 0.0393 |
114
+ | 0.0048 | 3.6168 | 2350 | 0.0399 |
115
+ | 0.011 | 3.6937 | 2400 | 0.0397 |
116
+ | 0.0066 | 3.7707 | 2450 | 0.0404 |
117
+ | 0.0089 | 3.8476 | 2500 | 0.0418 |
118
+ | 0.0129 | 3.9246 | 2550 | 0.0426 |
119
+ | 0.0096 | 4.0015 | 2600 | 0.0414 |
120
+ | 0.0015 | 4.0785 | 2650 | 0.0432 |
121
+ | 0.0042 | 4.1554 | 2700 | 0.0452 |
122
+ | 0.0024 | 4.2324 | 2750 | 0.0466 |
123
+ | 0.0032 | 4.3093 | 2800 | 0.0475 |
124
+ | 0.0024 | 4.3863 | 2850 | 0.0487 |
125
+ | 0.0034 | 4.4633 | 2900 | 0.0491 |
126
+ | 0.0016 | 4.5402 | 2950 | 0.0492 |
127
+ | 0.0022 | 4.6172 | 3000 | 0.0494 |
128
+ | 0.0066 | 4.6941 | 3050 | 0.0498 |
129
+ | 0.0023 | 4.7711 | 3100 | 0.0499 |
130
+ | 0.0053 | 4.8480 | 3150 | 0.0498 |
131
+ | 0.002 | 4.9250 | 3200 | 0.0499 |
132
+
133
+
134
+ ### Framework versions
135
+
136
+ - PEFT 0.12.0
137
+ - Transformers 4.46.1
138
+ - Pytorch 2.5.1+cu124
139
+ - Datasets 3.1.0
140
  - Tokenizers 0.20.3