Hugging Face's logo

tyzhu
/
lmind_nq_train6000_eval6489_v1_docidx_v3_3e-5_lora2

Safetensors
Generated from Trainer
Model card Files Community
tyzhu commited on
Commit
6afaf7f
·
verified ·
1 Parent(s): 510f342

Model save

Browse files
Files changed (1) hide show
  1. README.md +117 -0
README.md ADDED
@@ -0,0 +1,117 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ base_model: Qwen/Qwen1.5-4B
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: lmind_nq_train6000_eval6489_v1_docidx_v3_3e-5_lora2
10
+ results: []
11
+ library_name: peft
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
+ # lmind_nq_train6000_eval6489_v1_docidx_v3_3e-5_lora2
18
+
19
+ This model is a fine-tuned version of [Qwen/Qwen1.5-4B](https://huggingface.co/Qwen/Qwen1.5-4B) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 6.3965
22
+ - Accuracy: 0.4106
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 3e-05
42
+ - train_batch_size: 1
43
+ - eval_batch_size: 2
44
+ - seed: 42
45
+ - distributed_type: multi-GPU
46
+ - num_devices: 4
47
+ - gradient_accumulation_steps: 8
48
+ - total_train_batch_size: 32
49
+ - total_eval_batch_size: 8
50
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
+ - lr_scheduler_type: constant
52
+ - lr_scheduler_warmup_ratio: 0.05
53
+ - num_epochs: 50.0
54
+
55
+ ### Training results
56
+
57
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
58
+ |:-------------:|:-------:|:-----:|:---------------:|:--------:|
59
+ | 1.9686 | 0.9985 | 341 | 3.6919 | 0.4374 |
60
+ | 1.9337 | 2.0 | 683 | 3.7485 | 0.4476 |
61
+ | 1.9033 | 2.9985 | 1024 | 3.8826 | 0.4496 |
62
+ | 1.857 | 4.0 | 1366 | 3.9701 | 0.4481 |
63
+ | 1.8042 | 4.9985 | 1707 | 4.1171 | 0.4473 |
64
+ | 1.7443 | 6.0 | 2049 | 4.1837 | 0.4470 |
65
+ | 1.7019 | 6.9985 | 2390 | 4.2604 | 0.4462 |
66
+ | 1.6305 | 8.0 | 2732 | 4.4065 | 0.4415 |
67
+ | 1.6056 | 8.9985 | 3073 | 4.4487 | 0.4398 |
68
+ | 1.5521 | 10.0 | 3415 | 4.5474 | 0.4389 |
69
+ | 1.4934 | 10.9985 | 3756 | 4.5898 | 0.4367 |
70
+ | 1.4287 | 12.0 | 4098 | 4.6911 | 0.4355 |
71
+ | 1.3846 | 12.9985 | 4439 | 4.7629 | 0.4355 |
72
+ | 1.3185 | 14.0 | 4781 | 4.7585 | 0.4328 |
73
+ | 1.2667 | 14.9985 | 5122 | 4.9389 | 0.4309 |
74
+ | 1.2144 | 16.0 | 5464 | 4.8987 | 0.4303 |
75
+ | 1.1708 | 16.9985 | 5805 | 5.0017 | 0.4297 |
76
+ | 1.1146 | 18.0 | 6147 | 4.9778 | 0.4307 |
77
+ | 1.0531 | 18.9985 | 6488 | 5.1216 | 0.4287 |
78
+ | 1.0158 | 20.0 | 6830 | 5.1210 | 0.4273 |
79
+ | 0.9555 | 20.9985 | 7171 | 5.1988 | 0.4293 |
80
+ | 0.9205 | 22.0 | 7513 | 5.2240 | 0.4270 |
81
+ | 0.8711 | 22.9985 | 7854 | 5.3467 | 0.4251 |
82
+ | 0.8082 | 24.0 | 8196 | 5.3555 | 0.4243 |
83
+ | 0.7854 | 24.9985 | 8537 | 5.4629 | 0.4241 |
84
+ | 0.7359 | 26.0 | 8879 | 5.4699 | 0.4231 |
85
+ | 0.7002 | 26.9985 | 9220 | 5.5053 | 0.4211 |
86
+ | 0.6684 | 28.0 | 9562 | 5.5584 | 0.4214 |
87
+ | 0.6236 | 28.9985 | 9903 | 5.6117 | 0.4196 |
88
+ | 0.5866 | 30.0 | 10245 | 5.5696 | 0.4196 |
89
+ | 0.5554 | 30.9985 | 10586 | 5.6579 | 0.4184 |
90
+ | 0.5291 | 32.0 | 10928 | 5.7396 | 0.4178 |
91
+ | 0.4968 | 32.9985 | 11269 | 5.8110 | 0.4181 |
92
+ | 0.4635 | 34.0 | 11611 | 5.8719 | 0.4167 |
93
+ | 0.4465 | 34.9985 | 11952 | 5.8658 | 0.4162 |
94
+ | 0.4184 | 36.0 | 12294 | 5.8887 | 0.4147 |
95
+ | 0.4002 | 36.9985 | 12635 | 5.9950 | 0.4165 |
96
+ | 0.3716 | 38.0 | 12977 | 5.9991 | 0.4155 |
97
+ | 0.3537 | 38.9985 | 13318 | 6.0723 | 0.4151 |
98
+ | 0.3361 | 40.0 | 13660 | 6.0777 | 0.4127 |
99
+ | 0.3199 | 40.9985 | 14001 | 6.1181 | 0.4150 |
100
+ | 0.303 | 42.0 | 14343 | 6.0911 | 0.4134 |
101
+ | 0.2797 | 42.9985 | 14684 | 6.1607 | 0.4145 |
102
+ | 0.2762 | 44.0 | 15026 | 6.1128 | 0.4126 |
103
+ | 0.2633 | 44.9985 | 15367 | 6.1446 | 0.4127 |
104
+ | 0.2508 | 46.0 | 15709 | 6.2330 | 0.4134 |
105
+ | 0.2397 | 46.9985 | 16050 | 6.2369 | 0.4125 |
106
+ | 0.2259 | 48.0 | 16392 | 6.2775 | 0.4142 |
107
+ | 0.2228 | 48.9985 | 16733 | 6.2132 | 0.4128 |
108
+ | 0.2098 | 49.9268 | 17050 | 6.3965 | 0.4106 |
109
+
110
+
111
+ ### Framework versions
112
+
113
+ - PEFT 0.5.0
114
+ - Transformers 4.41.1
115
+ - Pytorch 2.1.0+cu121
116
+ - Datasets 2.19.1
117
+ - Tokenizers 0.19.1