Hugging Face's logo

tyzhu
/
lmind_nq_train6000_eval6489_v1_qa_3e-5_lora2

Safetensors
Generated from Trainer
Eval Results
Model card Files Community
tyzhu commited on
Commit
d29c349
•
1 Parent(s): 259126e

Model save

Browse files
Files changed (2) hide show
  1. README.md +55 -67
  2. training_args.bin +1 -1
README.md CHANGED
@@ -3,23 +3,11 @@ license: llama2
3
  base_model: meta-llama/Llama-2-7b-hf
4
  tags:
5
  - generated_from_trainer
6
- datasets:
7
- - tyzhu/lmind_nq_train6000_eval6489_v1_qa
8
  metrics:
9
  - accuracy
10
  model-index:
11
  - name: lmind_nq_train6000_eval6489_v1_qa_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_qa
18
- type: tyzhu/lmind_nq_train6000_eval6489_v1_qa
19
- metrics:
20
- - name: Accuracy
21
- type: accuracy
22
- value: 0.5965641025641025
23
  ---
24
 
25
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -27,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
27
 
28
  # lmind_nq_train6000_eval6489_v1_qa_3e-5_lora2
29
 
30
- This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the tyzhu/lmind_nq_train6000_eval6489_v1_qa dataset.
31
  It achieves the following results on the evaluation set:
32
- - Loss: 2.4443
33
  - Accuracy: 0.5966
 
34
 
35
  ## Model description
36
 
@@ -65,58 +53,58 @@ The following hyperparameters were used during training:
65
 
66
  ### Training results
67
 
68
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
- |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | 2.0369 | 1.0 | 187 | 1.2953 | 0.6128 |
71
- | 1.2821 | 2.0 | 375 | 1.2741 | 0.6146 |
72
- | 1.1987 | 3.0 | 562 | 1.2715 | 0.6162 |
73
- | 1.066 | 4.0 | 750 | 1.3011 | 0.6151 |
74
- | 0.9381 | 5.0 | 937 | 1.3728 | 0.6126 |
75
- | 0.8238 | 6.0 | 1125 | 1.4599 | 0.6091 |
76
- | 0.7289 | 7.0 | 1312 | 1.5455 | 0.6064 |
77
- | 0.6559 | 8.0 | 1500 | 1.6359 | 0.6026 |
78
- | 0.5733 | 9.0 | 1687 | 1.7149 | 0.6006 |
79
- | 0.5336 | 10.0 | 1875 | 1.8006 | 0.5989 |
80
- | 0.5116 | 11.0 | 2062 | 1.8851 | 0.5982 |
81
- | 0.4934 | 12.0 | 2250 | 1.9262 | 0.5982 |
82
- | 0.4823 | 13.0 | 2437 | 1.9413 | 0.5974 |
83
- | 0.47 | 14.0 | 2625 | 2.0121 | 0.5967 |
84
- | 0.4661 | 15.0 | 2812 | 2.0250 | 0.5968 |
85
- | 0.462 | 16.0 | 3000 | 1.9805 | 0.5990 |
86
- | 0.4357 | 17.0 | 3187 | 2.0656 | 0.5976 |
87
- | 0.4348 | 18.0 | 3375 | 2.0308 | 0.5979 |
88
- | 0.4331 | 19.0 | 3562 | 2.0629 | 0.5990 |
89
- | 0.4341 | 20.0 | 3750 | 2.0815 | 0.5983 |
90
- | 0.434 | 21.0 | 3937 | 2.1253 | 0.5968 |
91
- | 0.4335 | 22.0 | 4125 | 2.1789 | 0.5971 |
92
- | 0.4346 | 23.0 | 4312 | 2.1455 | 0.5952 |
93
- | 0.4326 | 24.0 | 4500 | 2.1990 | 0.5971 |
94
- | 0.4139 | 25.0 | 4687 | 2.1890 | 0.5976 |
95
- | 0.4139 | 26.0 | 4875 | 2.1939 | 0.5968 |
96
- | 0.4162 | 27.0 | 5062 | 2.2190 | 0.5965 |
97
- | 0.4177 | 28.0 | 5250 | 2.2781 | 0.5955 |
98
- | 0.4173 | 29.0 | 5437 | 2.2681 | 0.5976 |
99
- | 0.4187 | 30.0 | 5625 | 2.2996 | 0.5959 |
100
- | 0.4199 | 31.0 | 5812 | 2.2395 | 0.5981 |
101
- | 0.4213 | 32.0 | 6000 | 2.2991 | 0.5957 |
102
- | 0.4015 | 33.0 | 6187 | 2.3223 | 0.5952 |
103
- | 0.4058 | 34.0 | 6375 | 2.3266 | 0.5957 |
104
- | 0.4056 | 35.0 | 6562 | 2.3779 | 0.5946 |
105
- | 0.4078 | 36.0 | 6750 | 2.3453 | 0.5951 |
106
- | 0.4097 | 37.0 | 6937 | 2.3379 | 0.5965 |
107
- | 0.4105 | 38.0 | 7125 | 2.3624 | 0.5969 |
108
- | 0.4116 | 39.0 | 7312 | 2.3846 | 0.5962 |
109
- | 0.4121 | 40.0 | 7500 | 2.3748 | 0.5945 |
110
- | 0.3973 | 41.0 | 7687 | 2.3797 | 0.5956 |
111
- | 0.3985 | 42.0 | 7875 | 2.3599 | 0.5967 |
112
- | 0.4014 | 43.0 | 8062 | 2.3475 | 0.5971 |
113
- | 0.4032 | 44.0 | 8250 | 2.3937 | 0.5987 |
114
- | 0.4028 | 45.0 | 8437 | 2.3863 | 0.5967 |
115
- | 0.4027 | 46.0 | 8625 | 2.4195 | 0.5956 |
116
- | 0.4046 | 47.0 | 8812 | 2.3832 | 0.5970 |
117
- | 0.4067 | 48.0 | 9000 | 2.3805 | 0.5973 |
118
- | 0.3923 | 49.0 | 9187 | 2.4460 | 0.5957 |
119
- | 0.3949 | 49.87 | 9350 | 2.4443 | 0.5966 |
120
 
121
 
122
  ### Framework versions
 
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_qa_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_qa_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
  - Accuracy: 0.5966
21
+ - Loss: 2.4443
22
 
23
  ## Model description
24
 
 
53
 
54
  ### Training results
55
 
56
+ | Training Loss | Epoch | Step | Accuracy | Validation Loss |
57
+ |:-------------:|:-----:|:----:|:--------:|:---------------:|
58
+ | 2.0369 | 1.0 | 187 | 0.6128 | 1.2953 |
59
+ | 1.2821 | 2.0 | 375 | 0.6146 | 1.2741 |
60
+ | 1.1987 | 3.0 | 562 | 0.6162 | 1.2715 |
61
+ | 1.066 | 4.0 | 750 | 0.6151 | 1.3011 |
62
+ | 0.9381 | 5.0 | 937 | 0.6126 | 1.3728 |
63
+ | 0.8238 | 6.0 | 1125 | 0.6091 | 1.4599 |
64
+ | 0.7289 | 7.0 | 1312 | 0.6064 | 1.5455 |
65
+ | 0.6559 | 8.0 | 1500 | 0.6026 | 1.6359 |
66
+ | 0.5733 | 9.0 | 1687 | 0.6006 | 1.7149 |
67
+ | 0.5336 | 10.0 | 1875 | 0.5989 | 1.8006 |
68
+ | 0.5116 | 11.0 | 2062 | 0.5982 | 1.8851 |
69
+ | 0.4934 | 12.0 | 2250 | 0.5982 | 1.9262 |
70
+ | 0.4823 | 13.0 | 2437 | 0.5974 | 1.9413 |
71
+ | 0.47 | 14.0 | 2625 | 0.5967 | 2.0121 |
72
+ | 0.4661 | 15.0 | 2812 | 0.5968 | 2.0250 |
73
+ | 0.462 | 16.0 | 3000 | 0.5990 | 1.9805 |
74
+ | 0.4357 | 17.0 | 3187 | 0.5976 | 2.0656 |
75
+ | 0.4348 | 18.0 | 3375 | 0.5979 | 2.0308 |
76
+ | 0.4331 | 19.0 | 3562 | 0.5990 | 2.0629 |
77
+ | 0.4341 | 20.0 | 3750 | 0.5983 | 2.0815 |
78
+ | 0.434 | 21.0 | 3937 | 0.5968 | 2.1253 |
79
+ | 0.4335 | 22.0 | 4125 | 0.5971 | 2.1789 |
80
+ | 0.4346 | 23.0 | 4312 | 0.5952 | 2.1455 |
81
+ | 0.4326 | 24.0 | 4500 | 0.5971 | 2.1990 |
82
+ | 0.4139 | 25.0 | 4687 | 0.5976 | 2.1890 |
83
+ | 0.4139 | 26.0 | 4875 | 0.5968 | 2.1939 |
84
+ | 0.4162 | 27.0 | 5062 | 0.5965 | 2.2190 |
85
+ | 0.4177 | 28.0 | 5250 | 0.5955 | 2.2781 |
86
+ | 0.4173 | 29.0 | 5437 | 0.5976 | 2.2681 |
87
+ | 0.4187 | 30.0 | 5625 | 0.5959 | 2.2996 |
88
+ | 0.4199 | 31.0 | 5812 | 0.5981 | 2.2395 |
89
+ | 0.4213 | 32.0 | 6000 | 0.5957 | 2.2991 |
90
+ | 0.4015 | 33.0 | 6187 | 0.5952 | 2.3223 |
91
+ | 0.4058 | 34.0 | 6375 | 0.5957 | 2.3266 |
92
+ | 0.4056 | 35.0 | 6562 | 0.5946 | 2.3779 |
93
+ | 0.4078 | 36.0 | 6750 | 0.5951 | 2.3453 |
94
+ | 0.4097 | 37.0 | 6937 | 0.5965 | 2.3379 |
95
+ | 0.4105 | 38.0 | 7125 | 0.5969 | 2.3624 |
96
+ | 0.4116 | 39.0 | 7312 | 0.5962 | 2.3846 |
97
+ | 0.4121 | 40.0 | 7500 | 0.5945 | 2.3748 |
98
+ | 0.3973 | 41.0 | 7687 | 0.5956 | 2.3797 |
99
+ | 0.3985 | 42.0 | 7875 | 0.5967 | 2.3599 |
100
+ | 0.4014 | 43.0 | 8062 | 0.5971 | 2.3475 |
101
+ | 0.4032 | 44.0 | 8250 | 0.5987 | 2.3937 |
102
+ | 0.4028 | 45.0 | 8437 | 0.5967 | 2.3863 |
103
+ | 0.4027 | 46.0 | 8625 | 0.5956 | 2.4195 |
104
+ | 0.4046 | 47.0 | 8812 | 0.5970 | 2.3832 |
105
+ | 0.4067 | 48.0 | 9000 | 0.5973 | 2.3805 |
106
+ | 0.3923 | 49.0 | 9187 | 0.5957 | 2.4460 |
107
+ | 0.3949 | 49.87 | 9350 | 0.5966 | 2.4443 |
108
 
109
 
110
  ### Framework versions
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52c53f755ad4d3669bc1e92a0dd04ac5e6ef02b39406da28fac147ebfc373982
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f85c63378605fb27f5bb068faed83b13c598aedf9c901a41a832daf86a42b472
3
  size 4728