Hugging Face's logo

Litzy619
/
V0305P7

Safetensors
Generated from Trainer
Model card Files
xet
 Community
Litzy619 commited on
Commit
c9b869a
·
verified ·
1 Parent(s): 80a7173

End of training

Browse files
Files changed (4) hide show
  1. README.md +36 -36
  2. adapter_model.bin +1 -1
  3. model.safetensors +1 -1
  4. training_args.bin +1 -1
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [yahma/llama-7b-hf](https://huggingface.co/yahma/llama-7b-hf) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.0694
19
 
20
  ## Model description
21
 
@@ -50,41 +50,41 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:----:|:---------------:|
53
- | 1.8807 | 0.09 | 10 | 0.8284 |
54
- | 0.3213 | 0.17 | 20 | 0.1560 |
55
- | 0.1577 | 0.26 | 30 | 0.1545 |
56
- | 0.1515 | 0.34 | 40 | 0.1486 |
57
- | 0.1501 | 0.43 | 50 | 0.1467 |
58
- | 0.1522 | 0.51 | 60 | 0.1312 |
59
- | 0.1363 | 0.6 | 70 | 0.1154 |
60
- | 0.1262 | 0.68 | 80 | 0.1048 |
61
- | 0.1101 | 0.77 | 90 | 0.0930 |
62
- | 0.113 | 0.85 | 100 | 0.0956 |
63
- | 0.1098 | 0.94 | 110 | 0.0949 |
64
- | 0.1039 | 1.02 | 120 | 0.0960 |
65
- | 0.0944 | 1.11 | 130 | 0.0948 |
66
- | 0.0913 | 1.19 | 140 | 0.0880 |
67
- | 0.0893 | 1.28 | 150 | 0.0819 |
68
- | 0.0892 | 1.37 | 160 | 0.0843 |
69
- | 0.0884 | 1.45 | 170 | 0.0862 |
70
- | 0.0802 | 1.54 | 180 | 0.0876 |
71
- | 0.0839 | 1.62 | 190 | 0.0811 |
72
- | 0.088 | 1.71 | 200 | 0.0798 |
73
- | 0.0856 | 1.79 | 210 | 0.0782 |
74
- | 0.082 | 1.88 | 220 | 0.0750 |
75
- | 0.0797 | 1.96 | 230 | 0.0768 |
76
- | 0.0694 | 2.05 | 240 | 0.0761 |
77
- | 0.0591 | 2.13 | 250 | 0.0787 |
78
- | 0.0546 | 2.22 | 260 | 0.0747 |
79
- | 0.0544 | 2.3 | 270 | 0.0775 |
80
- | 0.0596 | 2.39 | 280 | 0.0723 |
81
- | 0.0587 | 2.47 | 290 | 0.0666 |
82
- | 0.059 | 2.56 | 300 | 0.0668 |
83
- | 0.06 | 2.65 | 310 | 0.0691 |
84
- | 0.0513 | 2.73 | 320 | 0.0699 |
85
- | 0.0565 | 2.82 | 330 | 0.0692 |
86
- | 0.0538 | 2.9 | 340 | 0.0695 |
87
- | 0.0539 | 2.99 | 350 | 0.0694 |
88
 
89
 
90
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [yahma/llama-7b-hf](https://huggingface.co/yahma/llama-7b-hf) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.0720
19
 
20
  ## Model description
21
 
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:----:|:---------------:|
53
+ | 1.6031 | 0.09 | 10 | 0.2267 |
54
+ | 0.172 | 0.17 | 20 | 0.1521 |
55
+ | 0.1569 | 0.26 | 30 | 0.1541 |
56
+ | 0.1515 | 0.34 | 40 | 0.1571 |
57
+ | 0.1519 | 0.43 | 50 | 0.1508 |
58
+ | 0.1565 | 0.51 | 60 | 0.1499 |
59
+ | 0.1515 | 0.6 | 70 | 0.1501 |
60
+ | 0.152 | 0.68 | 80 | 0.1409 |
61
+ | 0.1413 | 0.77 | 90 | 0.1359 |
62
+ | 0.1303 | 0.85 | 100 | 0.1025 |
63
+ | 0.1181 | 0.94 | 110 | 0.0935 |
64
+ | 0.1178 | 1.02 | 120 | 0.0946 |
65
+ | 0.1043 | 1.11 | 130 | 0.0963 |
66
+ | 0.0955 | 1.19 | 140 | 0.0936 |
67
+ | 0.0948 | 1.28 | 150 | 0.0856 |
68
+ | 0.095 | 1.37 | 160 | 0.0802 |
69
+ | 0.0941 | 1.45 | 170 | 0.0779 |
70
+ | 0.0863 | 1.54 | 180 | 0.0821 |
71
+ | 0.0868 | 1.62 | 190 | 0.0802 |
72
+ | 0.0904 | 1.71 | 200 | 0.0768 |
73
+ | 0.0893 | 1.79 | 210 | 0.0783 |
74
+ | 0.0851 | 1.88 | 220 | 0.0732 |
75
+ | 0.079 | 1.96 | 230 | 0.0763 |
76
+ | 0.0666 | 2.05 | 240 | 0.0793 |
77
+ | 0.0498 | 2.13 | 250 | 0.0794 |
78
+ | 0.05 | 2.22 | 260 | 0.0777 |
79
+ | 0.0479 | 2.3 | 270 | 0.0795 |
80
+ | 0.0543 | 2.39 | 280 | 0.0723 |
81
+ | 0.0544 | 2.47 | 290 | 0.0702 |
82
+ | 0.0534 | 2.56 | 300 | 0.0703 |
83
+ | 0.0544 | 2.65 | 310 | 0.0704 |
84
+ | 0.048 | 2.73 | 320 | 0.0737 |
85
+ | 0.0499 | 2.82 | 330 | 0.0736 |
86
+ | 0.0525 | 2.9 | 340 | 0.0718 |
87
+ | 0.0502 | 2.99 | 350 | 0.0720 |
88
 
89
 
90
  ### Framework versions
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:92332fcfbcf07ba26ad9561f051433d7920c6ec2cc12bd6afaa504b43a65c997
3
  size 277233383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fbcccb522cc1958e41058bcf2a86cf36634da262dcabd3f414be6ea3d2d9fa6
3
  size 277233383
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a614a845b72518ce43f5bb3d1df1a126026a3b6f3389af6d948044572033ef53
3
  size 13753862632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb69d63e434835f49684ab67396af55ac9ef4afd38cffc0f62e3da8d884962de
3
  size 13753862632
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4c6792d33fdbf567c80f939e9397797df52195d2759f14b75f567a94c59e2b51
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9eedabbc531cf90124d023e06802e32d25bcf17aa18b61582fb2128c566acfb
3
  size 5240