Hugging Face's logo

tyzhu
/
lmind_nq_train6000_eval6489_v1_qa_5e-4_lora2

Safetensors
Generated from Trainer
Eval Results
Model card Files Community
tyzhu commited on
Commit
d4a09eb
·
verified ·
1 Parent(s): 764c9f4

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_5e-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_qa
18
- type: tyzhu/lmind_nq_train6000_eval6489_v1_qa
19
- metrics:
20
- - name: Accuracy
21
- type: accuracy
22
- value: 0.3654871794871795
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_5e-4_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: 5.5751
33
  - Accuracy: 0.3655
 
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
- | 1.43 | 1.0 | 187 | 1.2683 | 0.6162 |
71
- | 1.0285 | 2.0 | 375 | 1.3220 | 0.6129 |
72
- | 0.7318 | 3.0 | 562 | 1.4645 | 0.6076 |
73
- | 0.5898 | 4.0 | 750 | 1.5454 | 0.6050 |
74
- | 0.5309 | 5.0 | 937 | 1.6439 | 0.6026 |
75
- | 0.4985 | 6.0 | 1125 | 1.7220 | 0.6034 |
76
- | 0.5091 | 7.0 | 1312 | 1.8008 | 0.6008 |
77
- | 0.4796 | 8.0 | 1500 | 1.7782 | 0.6001 |
78
- | 0.4453 | 9.0 | 1687 | 1.8255 | 0.5985 |
79
- | 0.448 | 10.0 | 1875 | 1.7979 | 0.5931 |
80
- | 0.4522 | 11.0 | 2062 | 1.8272 | 0.5959 |
81
- | 0.4552 | 12.0 | 2250 | 1.8670 | 0.5946 |
82
- | 0.4551 | 13.0 | 2437 | 1.8706 | 0.5950 |
83
- | 0.4559 | 14.0 | 2625 | 1.8731 | 0.5925 |
84
- | 0.4581 | 15.0 | 2812 | 1.8531 | 0.5932 |
85
- | 0.4535 | 16.0 | 3000 | 1.9492 | 0.5923 |
86
- | 0.4308 | 17.0 | 3187 | 1.8944 | 0.5915 |
87
- | 0.4312 | 18.0 | 3375 | 1.9315 | 0.5904 |
88
- | 0.4372 | 19.0 | 3562 | 1.9201 | 0.5899 |
89
- | 0.4359 | 20.0 | 3750 | 1.9753 | 0.5895 |
90
- | 0.4363 | 21.0 | 3937 | 1.9932 | 0.5877 |
91
- | 0.4404 | 22.0 | 4125 | 2.0326 | 0.5866 |
92
- | 0.4436 | 23.0 | 4312 | 2.0008 | 0.5848 |
93
- | 0.4438 | 24.0 | 4500 | 2.0186 | 0.5877 |
94
- | 0.4233 | 25.0 | 4687 | 2.0452 | 0.5863 |
95
- | 0.4237 | 26.0 | 4875 | 2.0520 | 0.5843 |
96
- | 0.4289 | 27.0 | 5062 | 2.0817 | 0.5828 |
97
- | 0.4325 | 28.0 | 5250 | 2.0512 | 0.5833 |
98
- | 0.4329 | 29.0 | 5437 | 2.0906 | 0.5828 |
99
- | 0.4314 | 30.0 | 5625 | 2.0403 | 0.5824 |
100
- | 0.431 | 31.0 | 5812 | 2.1194 | 0.5824 |
101
- | 0.4318 | 32.0 | 6000 | 2.0985 | 0.5829 |
102
- | 0.414 | 33.0 | 6187 | 2.1533 | 0.5805 |
103
- | 0.4214 | 34.0 | 6375 | 2.1918 | 0.5779 |
104
- | 0.4264 | 35.0 | 6562 | 2.1835 | 0.5774 |
105
- | 0.4361 | 36.0 | 6750 | 2.1864 | 0.5771 |
106
- | 0.4369 | 37.0 | 6937 | 2.1546 | 0.5761 |
107
- | 0.4362 | 38.0 | 7125 | 2.1423 | 0.5752 |
108
- | 0.4322 | 39.0 | 7312 | 2.1938 | 0.5778 |
109
- | 0.4359 | 40.0 | 7500 | 2.2000 | 0.5752 |
110
- | 0.4153 | 41.0 | 7687 | 2.2344 | 0.5751 |
111
- | 0.4195 | 42.0 | 7875 | 2.2526 | 0.5747 |
112
- | 0.9164 | 43.0 | 8062 | 2.1985 | 0.5717 |
113
- | 0.4295 | 44.0 | 8250 | 2.2145 | 0.5718 |
114
- | 0.4298 | 45.0 | 8437 | 2.2211 | 0.5714 |
115
- | 0.4446 | 46.0 | 8625 | 2.2656 | 0.5703 |
116
- | 2.0935 | 47.0 | 8812 | 2.6962 | 0.5081 |
117
- | 3.096 | 48.0 | 9000 | 3.2961 | 0.4494 |
118
- | 2.9615 | 49.0 | 9187 | 4.3483 | 0.4241 |
119
- | 4.5736 | 49.87 | 9350 | 5.5751 | 0.3655 |
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_5e-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_qa_5e-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
  - Accuracy: 0.3655
21
+ - Loss: 5.5751
22
 
23
  ## Model description
24
 
 
53
 
54
  ### Training results
55
 
56
+ | Training Loss | Epoch | Step | Accuracy | Validation Loss |
57
+ |:-------------:|:-----:|:----:|:--------:|:---------------:|
58
+ | 1.43 | 1.0 | 187 | 0.6162 | 1.2683 |
59
+ | 1.0285 | 2.0 | 375 | 0.6129 | 1.3220 |
60
+ | 0.7318 | 3.0 | 562 | 0.6076 | 1.4645 |
61
+ | 0.5898 | 4.0 | 750 | 0.6050 | 1.5454 |
62
+ | 0.5309 | 5.0 | 937 | 0.6026 | 1.6439 |
63
+ | 0.4985 | 6.0 | 1125 | 0.6034 | 1.7220 |
64
+ | 0.5091 | 7.0 | 1312 | 0.6008 | 1.8008 |
65
+ | 0.4796 | 8.0 | 1500 | 0.6001 | 1.7782 |
66
+ | 0.4453 | 9.0 | 1687 | 0.5985 | 1.8255 |
67
+ | 0.448 | 10.0 | 1875 | 0.5931 | 1.7979 |
68
+ | 0.4522 | 11.0 | 2062 | 0.5959 | 1.8272 |
69
+ | 0.4552 | 12.0 | 2250 | 0.5946 | 1.8670 |
70
+ | 0.4551 | 13.0 | 2437 | 0.5950 | 1.8706 |
71
+ | 0.4559 | 14.0 | 2625 | 0.5925 | 1.8731 |
72
+ | 0.4581 | 15.0 | 2812 | 0.5932 | 1.8531 |
73
+ | 0.4535 | 16.0 | 3000 | 0.5923 | 1.9492 |
74
+ | 0.4308 | 17.0 | 3187 | 0.5915 | 1.8944 |
75
+ | 0.4312 | 18.0 | 3375 | 0.5904 | 1.9315 |
76
+ | 0.4372 | 19.0 | 3562 | 0.5899 | 1.9201 |
77
+ | 0.4359 | 20.0 | 3750 | 0.5895 | 1.9753 |
78
+ | 0.4363 | 21.0 | 3937 | 0.5877 | 1.9932 |
79
+ | 0.4404 | 22.0 | 4125 | 0.5866 | 2.0326 |
80
+ | 0.4436 | 23.0 | 4312 | 0.5848 | 2.0008 |
81
+ | 0.4438 | 24.0 | 4500 | 0.5877 | 2.0186 |
82
+ | 0.4233 | 25.0 | 4687 | 0.5863 | 2.0452 |
83
+ | 0.4237 | 26.0 | 4875 | 0.5843 | 2.0520 |
84
+ | 0.4289 | 27.0 | 5062 | 0.5828 | 2.0817 |
85
+ | 0.4325 | 28.0 | 5250 | 0.5833 | 2.0512 |
86
+ | 0.4329 | 29.0 | 5437 | 0.5828 | 2.0906 |
87
+ | 0.4314 | 30.0 | 5625 | 0.5824 | 2.0403 |
88
+ | 0.431 | 31.0 | 5812 | 0.5824 | 2.1194 |
89
+ | 0.4318 | 32.0 | 6000 | 0.5829 | 2.0985 |
90
+ | 0.414 | 33.0 | 6187 | 0.5805 | 2.1533 |
91
+ | 0.4214 | 34.0 | 6375 | 0.5779 | 2.1918 |
92
+ | 0.4264 | 35.0 | 6562 | 0.5774 | 2.1835 |
93
+ | 0.4361 | 36.0 | 6750 | 0.5771 | 2.1864 |
94
+ | 0.4369 | 37.0 | 6937 | 0.5761 | 2.1546 |
95
+ | 0.4362 | 38.0 | 7125 | 0.5752 | 2.1423 |
96
+ | 0.4322 | 39.0 | 7312 | 0.5778 | 2.1938 |
97
+ | 0.4359 | 40.0 | 7500 | 0.5752 | 2.2000 |
98
+ | 0.4153 | 41.0 | 7687 | 0.5751 | 2.2344 |
99
+ | 0.4195 | 42.0 | 7875 | 0.5747 | 2.2526 |
100
+ | 0.9164 | 43.0 | 8062 | 0.5717 | 2.1985 |
101
+ | 0.4295 | 44.0 | 8250 | 0.5718 | 2.2145 |
102
+ | 0.4298 | 45.0 | 8437 | 0.5714 | 2.2211 |
103
+ | 0.4446 | 46.0 | 8625 | 0.5703 | 2.2656 |
104
+ | 2.0935 | 47.0 | 8812 | 0.5081 | 2.6962 |
105
+ | 3.096 | 48.0 | 9000 | 0.4494 | 3.2961 |
106
+ | 2.9615 | 49.0 | 9187 | 0.4241 | 4.3483 |
107
+ | 4.5736 | 49.87 | 9350 | 0.3655 | 5.5751 |
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:aeaafcc180d545c4c7bc83b3ef040967ab10c6394ea7a4c1dc01fb190e8fc740
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9881d03eac47eae77c66d5b3efa5f2f1ada7d872deaef1bc8433a5f4f678f08e
3
  size 4728