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
9a6c441
•
1 Parent(s): 16580bb

Model save

Browse files
Files changed (1) hide show
  1. README.md +63 -77
README.md CHANGED
@@ -1,26 +1,13 @@
1
  ---
2
- license: other
3
- base_model: Qwen/Qwen1.5-4B
4
  tags:
5
  - generated_from_trainer
6
- datasets:
7
- - tyzhu/lmind_nq_train6000_eval6489_v1_docidx_v3
8
  metrics:
9
  - accuracy
10
  model-index:
11
  - name: lmind_nq_train6000_eval6489_v1_docidx_v3_3e-5_lora2
12
- results:
13
- - task:
14
- name: Causal Language Modeling
15
- type: text-generation
16
- dataset:
17
- name: tyzhu/lmind_nq_train6000_eval6489_v1_docidx_v3
18
- type: tyzhu/lmind_nq_train6000_eval6489_v1_docidx_v3
19
- metrics:
20
- - name: Accuracy
21
- type: accuracy
22
- value: 0.4105641025641026
23
- library_name: peft
24
  ---
25
 
26
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -28,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
28
 
29
  # lmind_nq_train6000_eval6489_v1_docidx_v3_3e-5_lora2
30
 
31
- This model is a fine-tuned version of [Qwen/Qwen1.5-4B](https://huggingface.co/Qwen/Qwen1.5-4B) on the tyzhu/lmind_nq_train6000_eval6489_v1_docidx_v3 dataset.
32
  It achieves the following results on the evaluation set:
33
- - Loss: 6.3965
34
- - Accuracy: 0.4106
35
 
36
  ## Model description
37
 
@@ -51,12 +38,12 @@ More information needed
51
 
52
  The following hyperparameters were used during training:
53
  - learning_rate: 3e-05
54
- - train_batch_size: 1
55
  - eval_batch_size: 2
56
  - seed: 42
57
  - distributed_type: multi-GPU
58
  - num_devices: 4
59
- - gradient_accumulation_steps: 8
60
  - total_train_batch_size: 32
61
  - total_eval_batch_size: 8
62
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
@@ -66,64 +53,63 @@ The following hyperparameters were used during training:
66
 
67
  ### Training results
68
 
69
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
70
- |:-------------:|:-------:|:-----:|:---------------:|:--------:|
71
- | 1.9686 | 0.9985 | 341 | 3.6919 | 0.4374 |
72
- | 1.9337 | 2.0 | 683 | 3.7485 | 0.4476 |
73
- | 1.9033 | 2.9985 | 1024 | 3.8826 | 0.4496 |
74
- | 1.857 | 4.0 | 1366 | 3.9701 | 0.4481 |
75
- | 1.8042 | 4.9985 | 1707 | 4.1171 | 0.4473 |
76
- | 1.7443 | 6.0 | 2049 | 4.1837 | 0.4470 |
77
- | 1.7019 | 6.9985 | 2390 | 4.2604 | 0.4462 |
78
- | 1.6305 | 8.0 | 2732 | 4.4065 | 0.4415 |
79
- | 1.6056 | 8.9985 | 3073 | 4.4487 | 0.4398 |
80
- | 1.5521 | 10.0 | 3415 | 4.5474 | 0.4389 |
81
- | 1.4934 | 10.9985 | 3756 | 4.5898 | 0.4367 |
82
- | 1.4287 | 12.0 | 4098 | 4.6911 | 0.4355 |
83
- | 1.3846 | 12.9985 | 4439 | 4.7629 | 0.4355 |
84
- | 1.3185 | 14.0 | 4781 | 4.7585 | 0.4328 |
85
- | 1.2667 | 14.9985 | 5122 | 4.9389 | 0.4309 |
86
- | 1.2144 | 16.0 | 5464 | 4.8987 | 0.4303 |
87
- | 1.1708 | 16.9985 | 5805 | 5.0017 | 0.4297 |
88
- | 1.1146 | 18.0 | 6147 | 4.9778 | 0.4307 |
89
- | 1.0531 | 18.9985 | 6488 | 5.1216 | 0.4287 |
90
- | 1.0158 | 20.0 | 6830 | 5.1210 | 0.4273 |
91
- | 0.9555 | 20.9985 | 7171 | 5.1988 | 0.4293 |
92
- | 0.9205 | 22.0 | 7513 | 5.2240 | 0.4270 |
93
- | 0.8711 | 22.9985 | 7854 | 5.3467 | 0.4251 |
94
- | 0.8082 | 24.0 | 8196 | 5.3555 | 0.4243 |
95
- | 0.7854 | 24.9985 | 8537 | 5.4629 | 0.4241 |
96
- | 0.7359 | 26.0 | 8879 | 5.4699 | 0.4231 |
97
- | 0.7002 | 26.9985 | 9220 | 5.5053 | 0.4211 |
98
- | 0.6684 | 28.0 | 9562 | 5.5584 | 0.4214 |
99
- | 0.6236 | 28.9985 | 9903 | 5.6117 | 0.4196 |
100
- | 0.5866 | 30.0 | 10245 | 5.5696 | 0.4196 |
101
- | 0.5554 | 30.9985 | 10586 | 5.6579 | 0.4184 |
102
- | 0.5291 | 32.0 | 10928 | 5.7396 | 0.4178 |
103
- | 0.4968 | 32.9985 | 11269 | 5.8110 | 0.4181 |
104
- | 0.4635 | 34.0 | 11611 | 5.8719 | 0.4167 |
105
- | 0.4465 | 34.9985 | 11952 | 5.8658 | 0.4162 |
106
- | 0.4184 | 36.0 | 12294 | 5.8887 | 0.4147 |
107
- | 0.4002 | 36.9985 | 12635 | 5.9950 | 0.4165 |
108
- | 0.3716 | 38.0 | 12977 | 5.9991 | 0.4155 |
109
- | 0.3537 | 38.9985 | 13318 | 6.0723 | 0.4151 |
110
- | 0.3361 | 40.0 | 13660 | 6.0777 | 0.4127 |
111
- | 0.3199 | 40.9985 | 14001 | 6.1181 | 0.4150 |
112
- | 0.303 | 42.0 | 14343 | 6.0911 | 0.4134 |
113
- | 0.2797 | 42.9985 | 14684 | 6.1607 | 0.4145 |
114
- | 0.2762 | 44.0 | 15026 | 6.1128 | 0.4126 |
115
- | 0.2633 | 44.9985 | 15367 | 6.1446 | 0.4127 |
116
- | 0.2508 | 46.0 | 15709 | 6.2330 | 0.4134 |
117
- | 0.2397 | 46.9985 | 16050 | 6.2369 | 0.4125 |
118
- | 0.2259 | 48.0 | 16392 | 6.2775 | 0.4142 |
119
- | 0.2228 | 48.9985 | 16733 | 6.2132 | 0.4128 |
120
- | 0.2098 | 49.9268 | 17050 | 6.3965 | 0.4106 |
121
 
122
 
123
  ### Framework versions
124
 
125
- - PEFT 0.5.0
126
- - Transformers 4.41.1
127
  - Pytorch 2.1.0+cu121
128
- - Datasets 2.19.1
129
- - Tokenizers 0.19.1
 
1
  ---
2
+ license: llama2
3
+ base_model: meta-llama/Llama-2-7b-hf
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
  ---
12
 
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
15
 
16
  # lmind_nq_train6000_eval6489_v1_docidx_v3_3e-5_lora2
17
 
18
+ This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 4.9207
21
+ - Accuracy: 0.4310
22
 
23
  ## Model description
24
 
 
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 3e-05
41
+ - train_batch_size: 2
42
  - eval_batch_size: 2
43
  - seed: 42
44
  - distributed_type: multi-GPU
45
  - num_devices: 4
46
+ - gradient_accumulation_steps: 4
47
  - total_train_batch_size: 32
48
  - total_eval_batch_size: 8
49
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 
53
 
54
  ### Training results
55
 
56
+ | Training Loss | Epoch | Step | Accuracy | Validation Loss |
57
+ |:-------------:|:-----:|:-----:|:--------:|:---------------:|
58
+ | 1.4104 | 1.0 | 341 | 0.4537 | 3.3575 |
59
+ | 1.389 | 2.0 | 683 | 0.4544 | 3.4180 |
60
+ | 1.3414 | 3.0 | 1024 | 0.4548 | 3.5119 |
61
+ | 1.3002 | 4.0 | 1366 | 0.4554 | 3.5288 |
62
+ | 1.2574 | 5.0 | 1707 | 0.4539 | 3.6893 |
63
+ | 1.2258 | 6.0 | 2049 | 0.4562 | 3.7259 |
64
+ | 1.1844 | 7.0 | 2390 | 0.4559 | 3.7244 |
65
+ | 1.1363 | 8.0 | 2732 | 0.4544 | 3.8139 |
66
+ | 1.0903 | 9.0 | 3073 | 0.4524 | 3.9116 |
67
+ | 1.0538 | 10.0 | 3415 | 0.4516 | 3.9220 |
68
+ | 0.9971 | 11.0 | 3756 | 0.4514 | 3.9673 |
69
+ | 0.9699 | 12.0 | 4098 | 0.4508 | 4.0336 |
70
+ | 0.9235 | 13.0 | 4439 | 0.4493 | 4.0020 |
71
+ | 0.891 | 14.0 | 4781 | 0.4477 | 4.0716 |
72
+ | 0.845 | 15.0 | 5122 | 0.4477 | 4.0992 |
73
+ | 0.8009 | 16.0 | 5464 | 0.4464 | 4.0933 |
74
+ | 0.782 | 17.0 | 5805 | 0.4467 | 4.1283 |
75
+ | 0.7294 | 18.0 | 6147 | 0.4456 | 4.1643 |
76
+ | 0.6792 | 19.0 | 6488 | 0.4449 | 4.1859 |
77
+ | 0.6672 | 20.0 | 6830 | 0.4437 | 4.2010 |
78
+ | 0.6258 | 21.0 | 7171 | 0.4429 | 4.2300 |
79
+ | 0.599 | 22.0 | 7513 | 0.4419 | 4.2532 |
80
+ | 0.5625 | 23.0 | 7854 | 0.4430 | 4.2937 |
81
+ | 0.5267 | 24.0 | 8196 | 0.4415 | 4.2548 |
82
+ | 0.5004 | 25.0 | 8537 | 0.4404 | 4.3325 |
83
+ | 0.4681 | 26.0 | 8879 | 0.4396 | 4.3162 |
84
+ | 0.4453 | 27.0 | 9220 | 0.4388 | 4.3771 |
85
+ | 0.4161 | 28.0 | 9562 | 0.4386 | 4.4060 |
86
+ | 0.3994 | 29.0 | 9903 | 0.4377 | 4.4688 |
87
+ | 0.3695 | 30.0 | 10245 | 0.4377 | 4.4645 |
88
+ | 0.3505 | 31.0 | 10586 | 0.4378 | 4.4624 |
89
+ | 0.3342 | 32.0 | 10928 | 0.4365 | 4.4630 |
90
+ | 0.3075 | 33.0 | 11269 | 0.4342 | 4.5444 |
91
+ | 0.2949 | 34.0 | 11611 | 0.4344 | 4.5481 |
92
+ | 0.2705 | 35.0 | 11952 | 0.4357 | 4.5614 |
93
+ | 0.2554 | 36.0 | 12294 | 0.4339 | 4.5910 |
94
+ | 0.2428 | 37.0 | 12635 | 0.4332 | 4.6458 |
95
+ | 0.2277 | 38.0 | 12977 | 0.4327 | 4.6553 |
96
+ | 0.2172 | 39.0 | 13318 | 0.4328 | 4.7071 |
97
+ | 0.2016 | 40.0 | 13660 | 0.4331 | 4.7180 |
98
+ | 0.1965 | 41.0 | 14001 | 0.4323 | 4.7568 |
99
+ | 0.1851 | 42.0 | 14343 | 0.4321 | 4.7562 |
100
+ | 0.1739 | 43.0 | 14684 | 0.4317 | 4.7874 |
101
+ | 0.1719 | 44.0 | 15004 | 4.8029 | 0.4323 |
102
+ | 0.1626 | 45.0 | 15346 | 4.7820 | 0.4318 |
103
+ | 0.1535 | 46.0 | 15687 | 4.8637 | 0.4315 |
104
+ | 0.1524 | 47.0 | 16029 | 4.8990 | 0.4315 |
105
+ | 0.1419 | 48.0 | 16370 | 4.8602 | 0.4309 |
106
+ | 0.1405 | 49.0 | 16712 | 4.8813 | 0.4301 |
107
+ | 0.134 | 49.99 | 17050 | 4.9207 | 0.4310 |
108
 
109
 
110
  ### Framework versions
111
 
112
+ - Transformers 4.34.0
 
113
  - Pytorch 2.1.0+cu121
114
+ - Datasets 2.18.0
115
+ - Tokenizers 0.14.1