Hugging Face's logo

tyzhu
/
lmind_nq_train6000_eval6489_v1_reciteonly_qa_v3_lora2

PEFT
Safetensors
Generated from Trainer
Eval Results
Model card Files Community
tyzhu commited on
Commit
d3cec89
•
1 Parent(s): e919bd6

Model save

Browse files
Files changed (1) hide show
  1. README.md +22 -22
README.md CHANGED
@@ -15,8 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model was trained from scratch on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 2.4922
19
- - Accuracy: 0.6471
20
 
21
  ## Model description
22
 
@@ -53,26 +53,26 @@ The following hyperparameters were used during training:
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
55
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
56
- | 1.2282 | 1.0 | 187 | 1.1749 | 0.6707 |
57
- | 1.1429 | 2.0 | 375 | 1.1714 | 0.6710 |
58
- | 1.0415 | 3.0 | 562 | 1.1815 | 0.6707 |
59
- | 0.9188 | 4.0 | 750 | 1.2171 | 0.6683 |
60
- | 0.8039 | 5.0 | 937 | 1.2718 | 0.6662 |
61
- | 0.6782 | 6.0 | 1125 | 1.3539 | 0.6622 |
62
- | 0.5567 | 7.0 | 1312 | 1.4447 | 0.6598 |
63
- | 0.4472 | 8.0 | 1500 | 1.5391 | 0.6570 |
64
- | 0.341 | 9.0 | 1687 | 1.6785 | 0.6536 |
65
- | 0.2626 | 10.0 | 1875 | 1.8042 | 0.6515 |
66
- | 0.2015 | 11.0 | 2062 | 1.9496 | 0.6488 |
67
- | 0.1589 | 12.0 | 2250 | 2.0568 | 0.6477 |
68
- | 0.1274 | 13.0 | 2437 | 2.1358 | 0.6477 |
69
- | 0.1074 | 14.0 | 2625 | 2.2125 | 0.6475 |
70
- | 0.097 | 15.0 | 2812 | 2.3376 | 0.6469 |
71
- | 0.0901 | 16.0 | 3000 | 2.3907 | 0.6466 |
72
- | 0.0816 | 17.0 | 3187 | 2.4377 | 0.6460 |
73
- | 0.0796 | 18.0 | 3375 | 2.4466 | 0.6461 |
74
- | 0.0786 | 19.0 | 3562 | 2.4673 | 0.6454 |
75
- | 0.0784 | 19.95 | 3740 | 2.4922 | 0.6471 |
76
 
77
 
78
  ### Framework versions
 
15
 
16
  This model was trained from scratch on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 2.4374
19
+ - Accuracy: 0.6510
20
 
21
  ## Model description
22
 
 
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
55
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
56
+ | 1.168 | 1.0 | 187 | 1.1156 | 0.6787 |
57
+ | 1.0838 | 2.0 | 375 | 1.1152 | 0.6790 |
58
+ | 0.9936 | 3.0 | 562 | 1.1289 | 0.6781 |
59
+ | 0.8717 | 4.0 | 750 | 1.1731 | 0.6742 |
60
+ | 0.7555 | 5.0 | 937 | 1.2357 | 0.6711 |
61
+ | 0.6292 | 6.0 | 1125 | 1.3174 | 0.6674 |
62
+ | 0.5073 | 7.0 | 1312 | 1.4164 | 0.6638 |
63
+ | 0.4021 | 8.0 | 1500 | 1.4974 | 0.6621 |
64
+ | 0.3017 | 9.0 | 1687 | 1.6756 | 0.6576 |
65
+ | 0.2292 | 10.0 | 1875 | 1.8038 | 0.6548 |
66
+ | 0.1766 | 11.0 | 2062 | 1.9233 | 0.6539 |
67
+ | 0.1406 | 12.0 | 2250 | 2.0465 | 0.6519 |
68
+ | 0.1146 | 13.0 | 2437 | 2.1205 | 0.6518 |
69
+ | 0.0988 | 14.0 | 2625 | 2.1974 | 0.6523 |
70
+ | 0.0915 | 15.0 | 2812 | 2.2592 | 0.6519 |
71
+ | 0.0859 | 16.0 | 3000 | 2.3234 | 0.6515 |
72
+ | 0.0785 | 17.0 | 3187 | 2.3664 | 0.6515 |
73
+ | 0.0761 | 18.0 | 3375 | 2.3999 | 0.6507 |
74
+ | 0.0767 | 19.0 | 3562 | 2.4329 | 0.6517 |
75
+ | 0.0756 | 19.95 | 3740 | 2.4374 | 0.6510 |
76
 
77
 
78
  ### Framework versions