Hugging Face's logo

Litzy619
/
V0305P5

Safetensors
Generated from Trainer
Model card Files Community
Litzy619 commited on
Commit
71b0515
·
verified ·
1 Parent(s): a28e972

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: 0.0736
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
- | 1.7001 | 0.09 | 10 | 0.5244 |
54
- | 0.2134 | 0.17 | 20 | 0.1572 |
55
- | 0.1574 | 0.26 | 30 | 0.1549 |
56
- | 0.1522 | 0.34 | 40 | 0.1488 |
57
- | 0.1501 | 0.43 | 50 | 0.1488 |
58
- | 0.1553 | 0.51 | 60 | 0.1484 |
59
- | 0.1482 | 0.6 | 70 | 0.1376 |
60
- | 0.144 | 0.68 | 80 | 0.1298 |
61
- | 0.131 | 0.77 | 90 | 0.1147 |
62
- | 0.1268 | 0.85 | 100 | 0.1112 |
63
- | 0.1196 | 0.94 | 110 | 0.0988 |
64
- | 0.115 | 1.02 | 120 | 0.1008 |
65
- | 0.1083 | 1.11 | 130 | 0.0982 |
66
- | 0.102 | 1.19 | 140 | 0.0943 |
67
- | 0.0984 | 1.28 | 150 | 0.0875 |
68
- | 0.0964 | 1.37 | 160 | 0.0853 |
69
- | 0.0953 | 1.45 | 170 | 0.0855 |
70
- | 0.0888 | 1.54 | 180 | 0.0825 |
71
- | 0.089 | 1.62 | 190 | 0.0839 |
72
- | 0.0955 | 1.71 | 200 | 0.0811 |
73
- | 0.094 | 1.79 | 210 | 0.0784 |
74
- | 0.0901 | 1.88 | 220 | 0.0729 |
75
- | 0.0856 | 1.96 | 230 | 0.0771 |
76
- | 0.0717 | 2.05 | 240 | 0.0744 |
77
- | 0.0648 | 2.13 | 250 | 0.0730 |
78
- | 0.061 | 2.22 | 260 | 0.0720 |
79
- | 0.0589 | 2.3 | 270 | 0.0759 |
80
- | 0.0664 | 2.39 | 280 | 0.0702 |
81
- | 0.0676 | 2.47 | 290 | 0.0693 |
82
- | 0.0636 | 2.56 | 300 | 0.0699 |
83
- | 0.0667 | 2.65 | 310 | 0.0711 |
84
- | 0.0585 | 2.73 | 320 | 0.0726 |
85
- | 0.0619 | 2.82 | 330 | 0.0732 |
86
- | 0.0613 | 2.9 | 340 | 0.0735 |
87
- | 0.0611 | 2.99 | 350 | 0.0736 |
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: 0.0750
19
 
20
  ## Model description
21
 
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:----:|:---------------:|
53
+ | 1.3878 | 0.09 | 10 | 0.1658 |
54
+ | 0.2801 | 0.17 | 20 | 0.1531 |
55
+ | 0.1578 | 0.26 | 30 | 0.1529 |
56
+ | 0.1521 | 0.34 | 40 | 0.1514 |
57
+ | 0.1515 | 0.43 | 50 | 0.1508 |
58
+ | 0.1567 | 0.51 | 60 | 0.1507 |
59
+ | 0.1517 | 0.6 | 70 | 0.1491 |
60
+ | 0.1531 | 0.68 | 80 | 0.1480 |
61
+ | 0.149 | 0.77 | 90 | 0.1474 |
62
+ | 0.153 | 0.85 | 100 | 0.1521 |
63
+ | 0.1511 | 0.94 | 110 | 0.1264 |
64
+ | 0.14 | 1.02 | 120 | 0.1210 |
65
+ | 0.1316 | 1.11 | 130 | 0.1209 |
66
+ | 0.1198 | 1.19 | 140 | 0.1015 |
67
+ | 0.1105 | 1.28 | 150 | 0.0888 |
68
+ | 0.1067 | 1.37 | 160 | 0.0930 |
69
+ | 0.1043 | 1.45 | 170 | 0.0852 |
70
+ | 0.0962 | 1.54 | 180 | 0.0887 |
71
+ | 0.0968 | 1.62 | 190 | 0.0805 |
72
+ | 0.0957 | 1.71 | 200 | 0.0824 |
73
+ | 0.0939 | 1.79 | 210 | 0.0819 |
74
+ | 0.0918 | 1.88 | 220 | 0.0803 |
75
+ | 0.0865 | 1.96 | 230 | 0.0818 |
76
+ | 0.0734 | 2.05 | 240 | 0.0791 |
77
+ | 0.0591 | 2.13 | 250 | 0.0743 |
78
+ | 0.0614 | 2.22 | 260 | 0.0709 |
79
+ | 0.0544 | 2.3 | 270 | 0.0836 |
80
+ | 0.0611 | 2.39 | 280 | 0.0747 |
81
+ | 0.064 | 2.47 | 290 | 0.0711 |
82
+ | 0.0582 | 2.56 | 300 | 0.0721 |
83
+ | 0.0646 | 2.65 | 310 | 0.0752 |
84
+ | 0.0551 | 2.73 | 320 | 0.0761 |
85
+ | 0.0571 | 2.82 | 330 | 0.0753 |
86
+ | 0.0562 | 2.9 | 340 | 0.0750 |
87
+ | 0.0537 | 2.99 | 350 | 0.0750 |
88
 
89
 
90
  ### Framework versions
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5bfb33b157a490feaae41c874bfc47dac6521afa164be9fe0f62fa9e22b1b521
3
  size 277233383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78e96cef13efa9f218d041e670836a900dc05f3a7fcbb4c3e316dcdacb207bf3
3
  size 277233383
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4cda54a716596a32925231682cc89dc7529545fa5645bc782cb3181fcbed044
3
  size 13753862632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f83e0c6e005244a44aeb3e7ff9c9fc99f1ed24d4d68791a5451a32645116a6b7
3
  size 13753862632
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:62921a43cee5de27960055b37e38a64aaa84f2753e1d805a7a96c0e907f5b0a8
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc2ed757218e1c65809ac3546e1c2cc07be32d712d44e8282390881a5b697c96
3
  size 5240