Hugging Face's logo

tyzhu
/
lmind_nq_train6000_eval6489_v1_docidx_v3_1e-4_lora2

Safetensors
Generated from Trainer
Model card Files Community
tyzhu commited on
Commit
81d3d43
•
1 Parent(s): e5f2c23

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_1e-4_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: 0.4188205128205128
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_1e-4_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: 6.7424
34
- - Accuracy: 0.4188
35
 
36
  ## Model description
37
 
@@ -51,12 +38,12 @@ More information needed
51
 
52
  The following hyperparameters were used during training:
53
  - learning_rate: 0.0001
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
- | 1.9571 | 0.9985 | 341 | 3.9512 | 0.4538 |
72
- | 1.8819 | 2.0 | 683 | 4.1128 | 0.4483 |
73
- | 1.7702 | 2.9985 | 1024 | 4.3277 | 0.4461 |
74
- | 1.6163 | 4.0 | 1366 | 4.5849 | 0.4424 |
75
- | 1.4427 | 4.9985 | 1707 | 4.8503 | 0.4386 |
76
- | 1.2498 | 6.0 | 2049 | 5.0926 | 0.4349 |
77
- | 1.0655 | 6.9985 | 2390 | 5.2708 | 0.4326 |
78
- | 0.8733 | 8.0 | 2732 | 5.4024 | 0.4317 |
79
- | 0.7219 | 8.9985 | 3073 | 5.5348 | 0.4294 |
80
- | 0.5932 | 10.0 | 3415 | 5.7690 | 0.4261 |
81
- | 0.4719 | 10.9985 | 3756 | 5.8943 | 0.4254 |
82
- | 0.3838 | 12.0 | 4098 | 6.0191 | 0.4247 |
83
- | 0.329 | 12.9985 | 4439 | 6.1044 | 0.4246 |
84
- | 0.2742 | 14.0 | 4781 | 6.1465 | 0.4216 |
85
- | 0.2432 | 14.9985 | 5122 | 6.3254 | 0.4227 |
86
- | 0.2158 | 16.0 | 5464 | 6.4410 | 0.4228 |
87
- | 0.2013 | 16.9985 | 5805 | 6.3924 | 0.4215 |
88
- | 0.1851 | 18.0 | 6147 | 6.5217 | 0.4201 |
89
- | 0.1721 | 18.9985 | 6488 | 6.5573 | 0.4209 |
90
- | 0.1676 | 20.0 | 6830 | 6.5661 | 0.4214 |
91
- | 0.1579 | 20.9985 | 7171 | 6.5663 | 0.4213 |
92
- | 0.1575 | 22.0 | 7513 | 6.6259 | 0.4202 |
93
- | 0.15 | 22.9985 | 7854 | 6.5955 | 0.4214 |
94
- | 0.1427 | 24.0 | 8196 | 6.6297 | 0.4216 |
95
- | 0.145 | 24.9985 | 8537 | 6.5757 | 0.4227 |
96
- | 0.1393 | 26.0 | 8879 | 6.5675 | 0.4213 |
97
- | 0.1405 | 26.9985 | 9220 | 6.6650 | 0.4213 |
98
- | 0.1365 | 28.0 | 9562 | 6.6427 | 0.4210 |
99
- | 0.1372 | 28.9985 | 9903 | 6.5481 | 0.4209 |
100
- | 0.134 | 30.0 | 10245 | 6.6617 | 0.4199 |
101
- | 0.1287 | 30.9985 | 10586 | 6.6241 | 0.4207 |
102
- | 0.1305 | 32.0 | 10928 | 6.6094 | 0.4199 |
103
- | 0.1274 | 32.9985 | 11269 | 6.6823 | 0.4165 |
104
- | 0.1296 | 34.0 | 11611 | 6.6210 | 0.4195 |
105
- | 0.1271 | 34.9985 | 11952 | 6.7042 | 0.4185 |
106
- | 0.1239 | 36.0 | 12294 | 6.6016 | 0.4204 |
107
- | 0.1263 | 36.9985 | 12635 | 6.5736 | 0.4195 |
108
- | 0.1234 | 38.0 | 12977 | 6.6094 | 0.4169 |
109
- | 0.1236 | 38.9985 | 13318 | 6.6395 | 0.4151 |
110
- | 0.1211 | 40.0 | 13660 | 6.6604 | 0.4132 |
111
- | 0.1235 | 40.9985 | 14001 | 6.7098 | 0.4172 |
112
- | 0.1206 | 42.0 | 14343 | 6.6072 | 0.4172 |
113
- | 0.1165 | 42.9985 | 14684 | 6.7641 | 0.4178 |
114
- | 0.1207 | 44.0 | 15026 | 6.6669 | 0.4187 |
115
- | 0.1168 | 44.9985 | 15367 | 6.7258 | 0.4185 |
116
- | 0.1194 | 46.0 | 15709 | 6.7819 | 0.4187 |
117
- | 0.1179 | 46.9985 | 16050 | 6.7337 | 0.4189 |
118
- | 0.1158 | 48.0 | 16392 | 6.7115 | 0.4196 |
119
- | 0.1197 | 48.9985 | 16733 | 6.7568 | 0.4179 |
120
- | 0.1163 | 49.9268 | 17050 | 6.7424 | 0.4188 |
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_1e-4_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_1e-4_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: 5.3535
21
+ - Accuracy: 0.4374
22
 
23
  ## Model description
24
 
 
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 0.0001
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
+ | 1.3892 | 1.0 | 341 | 0.4544 | 3.4056 |
59
+ | 1.3499 | 2.0 | 683 | 0.4577 | 3.4531 |
60
+ | 1.2427 | 3.0 | 1024 | 0.4584 | 3.6711 |
61
+ | 1.1231 | 4.0 | 1366 | 0.4570 | 3.8000 |
62
+ | 0.995 | 5.0 | 1707 | 0.4552 | 3.9532 |
63
+ | 0.8693 | 6.0 | 2049 | 0.4526 | 4.0766 |
64
+ | 0.7302 | 7.0 | 2390 | 0.4501 | 4.1717 |
65
+ | 0.6033 | 8.0 | 2732 | 0.448 | 4.2778 |
66
+ | 0.4825 | 9.0 | 3073 | 0.4462 | 4.3415 |
67
+ | 0.387 | 10.0 | 3415 | 0.4463 | 4.4131 |
68
+ | 0.2933 | 11.0 | 3756 | 0.4434 | 4.4906 |
69
+ | 0.2344 | 12.0 | 4098 | 0.4425 | 4.6517 |
70
+ | 0.1919 | 13.0 | 4439 | 0.4408 | 4.7515 |
71
+ | 0.1581 | 14.0 | 4781 | 0.4421 | 4.7323 |
72
+ | 0.1429 | 15.0 | 5122 | 0.4407 | 4.8101 |
73
+ | 0.1279 | 16.0 | 5464 | 0.4406 | 4.8482 |
74
+ | 0.1231 | 17.0 | 5805 | 0.4411 | 4.9735 |
75
+ | 0.1145 | 18.0 | 6147 | 0.4415 | 5.0121 |
76
+ | 0.1087 | 19.0 | 6488 | 0.4394 | 4.9836 |
77
+ | 0.1084 | 20.0 | 6830 | 0.4388 | 5.1171 |
78
+ | 0.1069 | 21.0 | 7171 | 0.4405 | 5.0120 |
79
+ | 0.1075 | 22.0 | 7513 | 0.44 | 5.2343 |
80
+ | 0.1024 | 23.0 | 7854 | 0.4409 | 5.1501 |
81
+ | 0.0981 | 24.0 | 8196 | 0.4403 | 5.0801 |
82
+ | 0.097 | 25.0 | 8537 | 0.4416 | 5.1037 |
83
+ | 0.0963 | 26.0 | 8879 | 0.4398 | 5.2064 |
84
+ | 0.0983 | 27.0 | 9220 | 0.4414 | 5.0664 |
85
+ | 0.0969 | 28.0 | 9562 | 0.4410 | 5.2559 |
86
+ | 0.0966 | 29.0 | 9903 | 0.4404 | 5.1960 |
87
+ | 0.0954 | 30.0 | 10245 | 0.4396 | 5.2238 |
88
+ | 0.0931 | 31.0 | 10586 | 0.4402 | 5.2195 |
89
+ | 0.0923 | 32.0 | 10928 | 0.4407 | 5.2871 |
90
+ | 0.0911 | 33.0 | 11269 | 0.4392 | 5.3201 |
91
+ | 0.0934 | 34.0 | 11611 | 0.4387 | 5.3628 |
92
+ | 0.091 | 35.0 | 11952 | 0.4390 | 5.3197 |
93
+ | 0.0902 | 36.0 | 12294 | 0.4391 | 5.1868 |
94
+ | 0.0916 | 37.0 | 12635 | 0.4424 | 5.1227 |
95
+ | 0.0905 | 38.0 | 12977 | 0.4367 | 5.2214 |
96
+ | 0.0907 | 39.0 | 13318 | 0.4412 | 5.2412 |
97
+ | 0.0883 | 40.0 | 13660 | 0.4395 | 5.3015 |
98
+ | 0.0892 | 41.0 | 14001 | 0.4392 | 5.2816 |
99
+ | 0.0881 | 42.0 | 14343 | 0.4351 | 5.3583 |
100
+ | 0.0881 | 43.0 | 14684 | 0.4365 | 5.2678 |
101
+ | 0.0898 | 44.0 | 15026 | 0.4372 | 5.3854 |
102
+ | 0.0874 | 45.0 | 15345 | 5.3568 | 0.4392 |
103
+ | 0.088 | 46.0 | 15687 | 5.3908 | 0.4358 |
104
+ | 0.0885 | 47.0 | 16028 | 5.2685 | 0.4366 |
105
+ | 0.0872 | 48.0 | 16370 | 5.3500 | 0.44 |
106
+ | 0.0869 | 49.0 | 16711 | 5.3612 | 0.4372 |
107
+ | 0.0864 | 49.99 | 17050 | 5.3535 | 0.4374 |
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