Hugging Face's logo

chchen
/
Qwen2.5-7B-Instruct-PsyCourse-fold4

PEFT
Safetensors
llama-factory
lora
Generated from Trainer
Model card Files
xet
Community
1
chchen lbourdois commited on
Commit
bd61648
·
verified ·
1 Parent(s): 819bc3d

Improve language tag (#1)

Browse files

- Improve language tag (a9b4f7bbe8aae99546b0de3aa2ff4adf0c693f7a)


Co-authored-by: Loïck BOURDOIS <[email protected]>

Files changed (1) hide show
  1. README.md +140 -126
README.md CHANGED
@@ -1,127 +1,141 @@
1
- ---
2
- library_name: peft
3
- license: apache-2.0
4
- base_model: Qwen/Qwen2.5-7B-Instruct
5
- tags:
6
- - llama-factory
7
- - lora
8
- - generated_from_trainer
9
- model-index:
10
- - name: Qwen2.5-7B-Instruct-PsyCourse-fold4
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
- # Qwen2.5-7B-Instruct-PsyCourse-fold4
18
-
19
- This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the course-train-fold1 dataset.
20
- It achieves the following results on the evaluation set:
21
- - Loss: 0.0318
22
-
23
- ## Model description
24
-
25
- More information needed
26
-
27
- ## Intended uses & limitations
28
-
29
- More information needed
30
-
31
- ## Training and evaluation data
32
-
33
- More information needed
34
-
35
- ## Training procedure
36
-
37
- ### Training hyperparameters
38
-
39
- The following hyperparameters were used during training:
40
- - learning_rate: 0.0001
41
- - train_batch_size: 1
42
- - eval_batch_size: 1
43
- - seed: 42
44
- - gradient_accumulation_steps: 16
45
- - total_train_batch_size: 16
46
- - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
- - lr_scheduler_type: cosine
48
- - lr_scheduler_warmup_ratio: 0.1
49
- - num_epochs: 5.0
50
-
51
- ### Training results
52
-
53
- | Training Loss | Epoch | Step | Validation Loss |
54
- |:-------------:|:------:|:----:|:---------------:|
55
- | 0.8709 | 0.0770 | 50 | 0.6925 |
56
- | 0.1563 | 0.1539 | 100 | 0.1080 |
57
- | 0.0875 | 0.2309 | 150 | 0.0731 |
58
- | 0.0732 | 0.3078 | 200 | 0.0556 |
59
- | 0.0549 | 0.3848 | 250 | 0.0527 |
60
- | 0.0517 | 0.4617 | 300 | 0.0496 |
61
- | 0.0464 | 0.5387 | 350 | 0.0474 |
62
- | 0.0635 | 0.6156 | 400 | 0.0451 |
63
- | 0.0357 | 0.6926 | 450 | 0.0442 |
64
- | 0.0298 | 0.7695 | 500 | 0.0401 |
65
- | 0.047 | 0.8465 | 550 | 0.0384 |
66
- | 0.0384 | 0.9234 | 600 | 0.0374 |
67
- | 0.0318 | 1.0004 | 650 | 0.0359 |
68
- | 0.0362 | 1.0773 | 700 | 0.0382 |
69
- | 0.0296 | 1.1543 | 750 | 0.0354 |
70
- | 0.0305 | 1.2312 | 800 | 0.0347 |
71
- | 0.0333 | 1.3082 | 850 | 0.0353 |
72
- | 0.0205 | 1.3851 | 900 | 0.0344 |
73
- | 0.041 | 1.4621 | 950 | 0.0346 |
74
- | 0.0321 | 1.5391 | 1000 | 0.0328 |
75
- | 0.0332 | 1.6160 | 1050 | 0.0335 |
76
- | 0.0326 | 1.6930 | 1100 | 0.0346 |
77
- | 0.0217 | 1.7699 | 1150 | 0.0334 |
78
- | 0.0212 | 1.8469 | 1200 | 0.0350 |
79
- | 0.0297 | 1.9238 | 1250 | 0.0341 |
80
- | 0.0217 | 2.0008 | 1300 | 0.0319 |
81
- | 0.0162 | 2.0777 | 1350 | 0.0337 |
82
- | 0.0313 | 2.1547 | 1400 | 0.0349 |
83
- | 0.0132 | 2.2316 | 1450 | 0.0357 |
84
- | 0.0184 | 2.3086 | 1500 | 0.0339 |
85
- | 0.0156 | 2.3855 | 1550 | 0.0355 |
86
- | 0.0137 | 2.4625 | 1600 | 0.0348 |
87
- | 0.0216 | 2.5394 | 1650 | 0.0335 |
88
- | 0.0195 | 2.6164 | 1700 | 0.0327 |
89
- | 0.0262 | 2.6933 | 1750 | 0.0321 |
90
- | 0.0252 | 2.7703 | 1800 | 0.0339 |
91
- | 0.0248 | 2.8472 | 1850 | 0.0318 |
92
- | 0.0173 | 2.9242 | 1900 | 0.0330 |
93
- | 0.0285 | 3.0012 | 1950 | 0.0333 |
94
- | 0.0112 | 3.0781 | 2000 | 0.0363 |
95
- | 0.0091 | 3.1551 | 2050 | 0.0396 |
96
- | 0.0086 | 3.2320 | 2100 | 0.0398 |
97
- | 0.0086 | 3.3090 | 2150 | 0.0412 |
98
- | 0.0156 | 3.3859 | 2200 | 0.0398 |
99
- | 0.0097 | 3.4629 | 2250 | 0.0387 |
100
- | 0.0103 | 3.5398 | 2300 | 0.0397 |
101
- | 0.0059 | 3.6168 | 2350 | 0.0408 |
102
- | 0.0122 | 3.6937 | 2400 | 0.0402 |
103
- | 0.0075 | 3.7707 | 2450 | 0.0408 |
104
- | 0.0104 | 3.8476 | 2500 | 0.0412 |
105
- | 0.0128 | 3.9246 | 2550 | 0.0417 |
106
- | 0.0094 | 4.0015 | 2600 | 0.0410 |
107
- | 0.0016 | 4.0785 | 2650 | 0.0424 |
108
- | 0.0045 | 4.1554 | 2700 | 0.0452 |
109
- | 0.0027 | 4.2324 | 2750 | 0.0460 |
110
- | 0.0027 | 4.3093 | 2800 | 0.0471 |
111
- | 0.0036 | 4.3863 | 2850 | 0.0483 |
112
- | 0.0034 | 4.4633 | 2900 | 0.0485 |
113
- | 0.0021 | 4.5402 | 2950 | 0.0485 |
114
- | 0.0025 | 4.6172 | 3000 | 0.0491 |
115
- | 0.0022 | 4.6941 | 3050 | 0.0492 |
116
- | 0.0038 | 4.7711 | 3100 | 0.0494 |
117
- | 0.0057 | 4.8480 | 3150 | 0.0494 |
118
- | 0.0028 | 4.9250 | 3200 | 0.0493 |
119
-
120
-
121
- ### Framework versions
122
-
123
- - PEFT 0.12.0
124
- - Transformers 4.46.1
125
- - Pytorch 2.5.1+cu124
126
- - Datasets 3.1.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
127
  - 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
+ - lora
8
+ - generated_from_trainer
9
+ language:
10
+ - zho
11
+ - eng
12
+ - fra
13
+ - spa
14
+ - por
15
+ - deu
16
+ - ita
17
+ - rus
18
+ - jpn
19
+ - kor
20
+ - vie
21
+ - tha
22
+ - ara
23
+ model-index:
24
+ - name: Qwen2.5-7B-Instruct-PsyCourse-fold4
25
+ results: []
26
+ ---
27
+
28
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
+ should probably proofread and complete it, then remove this comment. -->
30
+
31
+ # Qwen2.5-7B-Instruct-PsyCourse-fold4
32
+
33
+ This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the course-train-fold1 dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.0318
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: 1
56
+ - eval_batch_size: 1
57
+ - seed: 42
58
+ - gradient_accumulation_steps: 16
59
+ - total_train_batch_size: 16
60
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
61
+ - lr_scheduler_type: cosine
62
+ - lr_scheduler_warmup_ratio: 0.1
63
+ - num_epochs: 5.0
64
+
65
+ ### Training results
66
+
67
+ | Training Loss | Epoch | Step | Validation Loss |
68
+ |:-------------:|:------:|:----:|:---------------:|
69
+ | 0.8709 | 0.0770 | 50 | 0.6925 |
70
+ | 0.1563 | 0.1539 | 100 | 0.1080 |
71
+ | 0.0875 | 0.2309 | 150 | 0.0731 |
72
+ | 0.0732 | 0.3078 | 200 | 0.0556 |
73
+ | 0.0549 | 0.3848 | 250 | 0.0527 |
74
+ | 0.0517 | 0.4617 | 300 | 0.0496 |
75
+ | 0.0464 | 0.5387 | 350 | 0.0474 |
76
+ | 0.0635 | 0.6156 | 400 | 0.0451 |
77
+ | 0.0357 | 0.6926 | 450 | 0.0442 |
78
+ | 0.0298 | 0.7695 | 500 | 0.0401 |
79
+ | 0.047 | 0.8465 | 550 | 0.0384 |
80
+ | 0.0384 | 0.9234 | 600 | 0.0374 |
81
+ | 0.0318 | 1.0004 | 650 | 0.0359 |
82
+ | 0.0362 | 1.0773 | 700 | 0.0382 |
83
+ | 0.0296 | 1.1543 | 750 | 0.0354 |
84
+ | 0.0305 | 1.2312 | 800 | 0.0347 |
85
+ | 0.0333 | 1.3082 | 850 | 0.0353 |
86
+ | 0.0205 | 1.3851 | 900 | 0.0344 |
87
+ | 0.041 | 1.4621 | 950 | 0.0346 |
88
+ | 0.0321 | 1.5391 | 1000 | 0.0328 |
89
+ | 0.0332 | 1.6160 | 1050 | 0.0335 |
90
+ | 0.0326 | 1.6930 | 1100 | 0.0346 |
91
+ | 0.0217 | 1.7699 | 1150 | 0.0334 |
92
+ | 0.0212 | 1.8469 | 1200 | 0.0350 |
93
+ | 0.0297 | 1.9238 | 1250 | 0.0341 |
94
+ | 0.0217 | 2.0008 | 1300 | 0.0319 |
95
+ | 0.0162 | 2.0777 | 1350 | 0.0337 |
96
+ | 0.0313 | 2.1547 | 1400 | 0.0349 |
97
+ | 0.0132 | 2.2316 | 1450 | 0.0357 |
98
+ | 0.0184 | 2.3086 | 1500 | 0.0339 |
99
+ | 0.0156 | 2.3855 | 1550 | 0.0355 |
100
+ | 0.0137 | 2.4625 | 1600 | 0.0348 |
101
+ | 0.0216 | 2.5394 | 1650 | 0.0335 |
102
+ | 0.0195 | 2.6164 | 1700 | 0.0327 |
103
+ | 0.0262 | 2.6933 | 1750 | 0.0321 |
104
+ | 0.0252 | 2.7703 | 1800 | 0.0339 |
105
+ | 0.0248 | 2.8472 | 1850 | 0.0318 |
106
+ | 0.0173 | 2.9242 | 1900 | 0.0330 |
107
+ | 0.0285 | 3.0012 | 1950 | 0.0333 |
108
+ | 0.0112 | 3.0781 | 2000 | 0.0363 |
109
+ | 0.0091 | 3.1551 | 2050 | 0.0396 |
110
+ | 0.0086 | 3.2320 | 2100 | 0.0398 |
111
+ | 0.0086 | 3.3090 | 2150 | 0.0412 |
112
+ | 0.0156 | 3.3859 | 2200 | 0.0398 |
113
+ | 0.0097 | 3.4629 | 2250 | 0.0387 |
114
+ | 0.0103 | 3.5398 | 2300 | 0.0397 |
115
+ | 0.0059 | 3.6168 | 2350 | 0.0408 |
116
+ | 0.0122 | 3.6937 | 2400 | 0.0402 |
117
+ | 0.0075 | 3.7707 | 2450 | 0.0408 |
118
+ | 0.0104 | 3.8476 | 2500 | 0.0412 |
119
+ | 0.0128 | 3.9246 | 2550 | 0.0417 |
120
+ | 0.0094 | 4.0015 | 2600 | 0.0410 |
121
+ | 0.0016 | 4.0785 | 2650 | 0.0424 |
122
+ | 0.0045 | 4.1554 | 2700 | 0.0452 |
123
+ | 0.0027 | 4.2324 | 2750 | 0.0460 |
124
+ | 0.0027 | 4.3093 | 2800 | 0.0471 |
125
+ | 0.0036 | 4.3863 | 2850 | 0.0483 |
126
+ | 0.0034 | 4.4633 | 2900 | 0.0485 |
127
+ | 0.0021 | 4.5402 | 2950 | 0.0485 |
128
+ | 0.0025 | 4.6172 | 3000 | 0.0491 |
129
+ | 0.0022 | 4.6941 | 3050 | 0.0492 |
130
+ | 0.0038 | 4.7711 | 3100 | 0.0494 |
131
+ | 0.0057 | 4.8480 | 3150 | 0.0494 |
132
+ | 0.0028 | 4.9250 | 3200 | 0.0493 |
133
+
134
+
135
+ ### Framework versions
136
+
137
+ - PEFT 0.12.0
138
+ - Transformers 4.46.1
139
+ - Pytorch 2.5.1+cu124
140
+ - Datasets 3.1.0
141
  - Tokenizers 0.20.3