Hugging Face's logo

tyzhu
/
lmind_hotpot_train8000_eval7405_v1_qa_3e-5_lora2

Safetensors
Generated from Trainer
Eval Results
Model card Files Community
tyzhu commited on
Commit
d05fc77
·
verified ·
1 Parent(s): 9b369f4

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_hotpot_train8000_eval7405_v1_qa
8
  metrics:
9
  - accuracy
10
  model-index:
11
  - name: lmind_hotpot_train8000_eval7405_v1_qa_3e-5_lora2
12
- results:
13
- - task:
14
- name: Causal Language Modeling
15
- type: text-generation
16
- dataset:
17
- name: tyzhu/lmind_hotpot_train8000_eval7405_v1_qa
18
- type: tyzhu/lmind_hotpot_train8000_eval7405_v1_qa
19
- metrics:
20
- - name: Accuracy
21
- type: accuracy
22
- value: 0.5822278481012658
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_hotpot_train8000_eval7405_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_hotpot_train8000_eval7405_v1_qa dataset.
31
  It achieves the following results on the evaluation set:
32
- - Loss: 3.7015
33
  - Accuracy: 0.5822
 
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
- | 1.8255 | 1.0 | 250 | 1.8392 | 0.6054 |
71
- | 1.7368 | 2.0 | 500 | 1.8111 | 0.6078 |
72
- | 1.6689 | 3.0 | 750 | 1.8103 | 0.6075 |
73
- | 1.5555 | 4.0 | 1000 | 1.8414 | 0.6067 |
74
- | 1.4559 | 5.0 | 1250 | 1.8992 | 0.6038 |
75
- | 1.3514 | 6.0 | 1500 | 1.9584 | 0.6018 |
76
- | 1.2491 | 7.0 | 1750 | 2.0300 | 0.6000 |
77
- | 1.1749 | 8.0 | 2000 | 2.1051 | 0.5982 |
78
- | 1.0769 | 9.0 | 2250 | 2.1948 | 0.5954 |
79
- | 1.0134 | 10.0 | 2500 | 2.2515 | 0.5943 |
80
- | 0.9209 | 11.0 | 2750 | 2.3421 | 0.5921 |
81
- | 0.8636 | 12.0 | 3000 | 2.4443 | 0.5905 |
82
- | 0.7866 | 13.0 | 3250 | 2.5574 | 0.588 |
83
- | 0.7448 | 14.0 | 3500 | 2.5800 | 0.5867 |
84
- | 0.6709 | 15.0 | 3750 | 2.6912 | 0.5846 |
85
- | 0.6439 | 16.0 | 4000 | 2.7546 | 0.5853 |
86
- | 0.5869 | 17.0 | 4250 | 2.7997 | 0.5831 |
87
- | 0.5596 | 18.0 | 4500 | 2.8435 | 0.5833 |
88
- | 0.5205 | 19.0 | 4750 | 2.9510 | 0.5833 |
89
- | 0.5045 | 20.0 | 5000 | 2.9797 | 0.5824 |
90
- | 0.47 | 21.0 | 5250 | 3.0530 | 0.5832 |
91
- | 0.455 | 22.0 | 5500 | 3.0804 | 0.5821 |
92
- | 0.4332 | 23.0 | 5750 | 3.1938 | 0.5813 |
93
- | 0.4171 | 24.0 | 6000 | 3.1836 | 0.5816 |
94
- | 0.4049 | 25.0 | 6250 | 3.1950 | 0.5817 |
95
- | 0.3975 | 26.0 | 6500 | 3.2749 | 0.5801 |
96
- | 0.3798 | 27.0 | 6750 | 3.3141 | 0.5808 |
97
- | 0.3774 | 28.0 | 7000 | 3.3085 | 0.5815 |
98
- | 0.3636 | 29.0 | 7250 | 3.3525 | 0.5813 |
99
- | 0.362 | 30.0 | 7500 | 3.4330 | 0.5809 |
100
- | 0.3486 | 31.0 | 7750 | 3.4240 | 0.5805 |
101
- | 0.3471 | 32.0 | 8000 | 3.4737 | 0.5806 |
102
- | 0.335 | 33.0 | 8250 | 3.4706 | 0.5825 |
103
- | 0.3367 | 34.0 | 8500 | 3.4640 | 0.5829 |
104
- | 0.3276 | 35.0 | 8750 | 3.5442 | 0.5806 |
105
- | 0.3298 | 36.0 | 9000 | 3.6080 | 0.58 |
106
- | 0.3226 | 37.0 | 9250 | 3.5853 | 0.5818 |
107
- | 0.3229 | 38.0 | 9500 | 3.5513 | 0.5826 |
108
- | 0.3163 | 39.0 | 9750 | 3.5633 | 0.5812 |
109
- | 0.3181 | 40.0 | 10000 | 3.6170 | 0.5816 |
110
- | 0.3105 | 41.0 | 10250 | 3.5726 | 0.5821 |
111
- | 0.3113 | 42.0 | 10500 | 3.6571 | 0.5811 |
112
- | 0.3083 | 43.0 | 10750 | 3.6066 | 0.5824 |
113
- | 0.3082 | 44.0 | 11000 | 3.6072 | 0.582 |
114
- | 0.3032 | 45.0 | 11250 | 3.6758 | 0.5822 |
115
- | 0.3041 | 46.0 | 11500 | 3.7283 | 0.5827 |
116
- | 0.3016 | 47.0 | 11750 | 3.7187 | 0.5813 |
117
- | 0.3017 | 48.0 | 12000 | 3.6693 | 0.5803 |
118
- | 0.294 | 49.0 | 12250 | 3.7501 | 0.5812 |
119
- | 0.2981 | 50.0 | 12500 | 3.7015 | 0.5822 |
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_hotpot_train8000_eval7405_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_hotpot_train8000_eval7405_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: 0.5822
21
+ - Loss: 3.7015
22
 
23
  ## Model description
24
 
 
53
 
54
  ### Training results
55
 
56
+ | Training Loss | Epoch | Step | Accuracy | Validation Loss |
57
+ |:-------------:|:-----:|:-----:|:--------:|:---------------:|
58
+ | 1.8255 | 1.0 | 250 | 0.6054 | 1.8392 |
59
+ | 1.7368 | 2.0 | 500 | 0.6078 | 1.8111 |
60
+ | 1.6689 | 3.0 | 750 | 0.6075 | 1.8103 |
61
+ | 1.5555 | 4.0 | 1000 | 0.6067 | 1.8414 |
62
+ | 1.4559 | 5.0 | 1250 | 0.6038 | 1.8992 |
63
+ | 1.3514 | 6.0 | 1500 | 0.6018 | 1.9584 |
64
+ | 1.2491 | 7.0 | 1750 | 0.6000 | 2.0300 |
65
+ | 1.1749 | 8.0 | 2000 | 0.5982 | 2.1051 |
66
+ | 1.0769 | 9.0 | 2250 | 0.5954 | 2.1948 |
67
+ | 1.0134 | 10.0 | 2500 | 0.5943 | 2.2515 |
68
+ | 0.9209 | 11.0 | 2750 | 0.5921 | 2.3421 |
69
+ | 0.8636 | 12.0 | 3000 | 0.5905 | 2.4443 |
70
+ | 0.7866 | 13.0 | 3250 | 0.588 | 2.5574 |
71
+ | 0.7448 | 14.0 | 3500 | 0.5867 | 2.5800 |
72
+ | 0.6709 | 15.0 | 3750 | 0.5846 | 2.6912 |
73
+ | 0.6439 | 16.0 | 4000 | 0.5853 | 2.7546 |
74
+ | 0.5869 | 17.0 | 4250 | 0.5831 | 2.7997 |
75
+ | 0.5596 | 18.0 | 4500 | 0.5833 | 2.8435 |
76
+ | 0.5205 | 19.0 | 4750 | 0.5833 | 2.9510 |
77
+ | 0.5045 | 20.0 | 5000 | 0.5824 | 2.9797 |
78
+ | 0.47 | 21.0 | 5250 | 0.5832 | 3.0530 |
79
+ | 0.455 | 22.0 | 5500 | 0.5821 | 3.0804 |
80
+ | 0.4332 | 23.0 | 5750 | 0.5813 | 3.1938 |
81
+ | 0.4171 | 24.0 | 6000 | 0.5816 | 3.1836 |
82
+ | 0.4049 | 25.0 | 6250 | 0.5817 | 3.1950 |
83
+ | 0.3975 | 26.0 | 6500 | 0.5801 | 3.2749 |
84
+ | 0.3798 | 27.0 | 6750 | 0.5808 | 3.3141 |
85
+ | 0.3774 | 28.0 | 7000 | 0.5815 | 3.3085 |
86
+ | 0.3636 | 29.0 | 7250 | 0.5813 | 3.3525 |
87
+ | 0.362 | 30.0 | 7500 | 0.5809 | 3.4330 |
88
+ | 0.3486 | 31.0 | 7750 | 0.5805 | 3.4240 |
89
+ | 0.3471 | 32.0 | 8000 | 0.5806 | 3.4737 |
90
+ | 0.335 | 33.0 | 8250 | 0.5825 | 3.4706 |
91
+ | 0.3367 | 34.0 | 8500 | 0.5829 | 3.4640 |
92
+ | 0.3276 | 35.0 | 8750 | 0.5806 | 3.5442 |
93
+ | 0.3298 | 36.0 | 9000 | 0.58 | 3.6080 |
94
+ | 0.3226 | 37.0 | 9250 | 0.5818 | 3.5853 |
95
+ | 0.3229 | 38.0 | 9500 | 0.5826 | 3.5513 |
96
+ | 0.3163 | 39.0 | 9750 | 0.5812 | 3.5633 |
97
+ | 0.3181 | 40.0 | 10000 | 0.5816 | 3.6170 |
98
+ | 0.3105 | 41.0 | 10250 | 0.5821 | 3.5726 |
99
+ | 0.3113 | 42.0 | 10500 | 0.5811 | 3.6571 |
100
+ | 0.3083 | 43.0 | 10750 | 0.5824 | 3.6066 |
101
+ | 0.3082 | 44.0 | 11000 | 0.582 | 3.6072 |
102
+ | 0.3032 | 45.0 | 11250 | 0.5822 | 3.6758 |
103
+ | 0.3041 | 46.0 | 11500 | 0.5827 | 3.7283 |
104
+ | 0.3016 | 47.0 | 11750 | 0.5813 | 3.7187 |
105
+ | 0.3017 | 48.0 | 12000 | 0.5803 | 3.6693 |
106
+ | 0.294 | 49.0 | 12250 | 0.5812 | 3.7501 |
107
+ | 0.2981 | 50.0 | 12500 | 0.5822 | 3.7015 |
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:b708b99b821bdf687ebed6196095d1415f662e1088452054a7df6a8e9ebd3c3f
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae1d2a0a609fe5fd776d7a15047d12c62ea7239d841ad071a1a5c42201452e8a
3
  size 4728