Hugging Face's logo

santis2
/
gpt2-alpaca-instruction-fine-tuning-qlora

Generated from Trainer
Model card Files Community
santis2 commited on
Commit
638fc26
•
1 Parent(s): c5d1933

End of training

Browse files
Files changed (3) hide show
  1. README.md +10 -51
  2. adapter_model.bin +1 -1
  3. 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 [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 1.8887
19
 
20
  ## Model description
21
 
@@ -47,56 +47,15 @@ The following hyperparameters were used during training:
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
- | No log | 0.02 | 50 | 2.4375 |
51
- | No log | 0.04 | 100 | 2.375 |
52
- | No log | 0.06 | 150 | 2.2637 |
53
- | No log | 0.08 | 200 | 2.1855 |
54
- | No log | 0.1 | 250 | 2.1094 |
55
- | No log | 0.12 | 300 | 2.0840 |
56
- | No log | 0.14 | 350 | 2.0977 |
57
- | No log | 0.16 | 400 | 2.0488 |
58
- | No log | 0.18 | 450 | 2.0332 |
59
- | No log | 0.2 | 500 | 2.0312 |
60
- | No log | 0.22 | 550 | 2.0352 |
61
- | No log | 0.24 | 600 | 2.0430 |
62
- | No log | 0.26 | 650 | 2.0117 |
63
- | No log | 0.28 | 700 | 2.0117 |
64
- | No log | 0.3 | 750 | 2.0059 |
65
- | No log | 0.32 | 800 | 1.9961 |
66
- | No log | 0.34 | 850 | 1.9551 |
67
- | No log | 0.36 | 900 | 1.9463 |
68
- | No log | 0.38 | 950 | 1.9854 |
69
- | 2.4218 | 0.4 | 1000 | 1.9883 |
70
- | 2.4218 | 0.42 | 1050 | 1.9766 |
71
- | 2.4218 | 0.44 | 1100 | 1.9424 |
72
- | 2.4218 | 0.46 | 1150 | 1.9727 |
73
- | 2.4218 | 0.48 | 1200 | 1.9473 |
74
- | 2.4218 | 0.5 | 1250 | 1.9580 |
75
- | 2.4218 | 0.52 | 1300 | 1.9404 |
76
- | 2.4218 | 0.54 | 1350 | 1.9287 |
77
- | 2.4218 | 0.56 | 1400 | 1.9473 |
78
- | 2.4218 | 0.58 | 1450 | 1.9209 |
79
- | 2.4218 | 0.6 | 1500 | 1.9219 |
80
- | 2.4218 | 0.62 | 1550 | 1.9336 |
81
- | 2.4218 | 0.64 | 1600 | 1.9287 |
82
- | 2.4218 | 0.66 | 1650 | 1.9082 |
83
- | 2.4218 | 0.68 | 1700 | 1.9219 |
84
- | 2.4218 | 0.7 | 1750 | 1.8994 |
85
- | 2.4218 | 0.72 | 1800 | 1.9092 |
86
- | 2.4218 | 0.74 | 1850 | 1.8877 |
87
- | 2.4218 | 0.76 | 1900 | 1.8994 |
88
- | 2.4218 | 0.78 | 1950 | 1.8955 |
89
- | 2.1818 | 0.8 | 2000 | 1.8896 |
90
- | 2.1818 | 0.82 | 2050 | 1.8867 |
91
- | 2.1818 | 0.84 | 2100 | 1.8857 |
92
- | 2.1818 | 0.86 | 2150 | 1.8916 |
93
- | 2.1818 | 0.88 | 2200 | 1.8857 |
94
- | 2.1818 | 0.9 | 2250 | 1.8916 |
95
- | 2.1818 | 0.92 | 2300 | 1.8926 |
96
- | 2.1818 | 0.94 | 2350 | 1.8896 |
97
- | 2.1818 | 0.96 | 2400 | 1.8887 |
98
- | 2.1818 | 0.98 | 2450 | 1.8887 |
99
- | 2.1818 | 1.0 | 2500 | 1.8887 |
100
 
101
 
102
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 1.8330
19
 
20
  ## Model description
21
 
 
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
+ | 2.1183 | 0.11 | 1000 | 1.8975 |
51
+ | 2.1329 | 0.22 | 2000 | 1.8818 |
52
+ | 2.1179 | 0.33 | 3000 | 1.8770 |
53
+ | 2.0949 | 0.44 | 4000 | 1.8662 |
54
+ | 2.0871 | 0.55 | 5000 | 1.8477 |
55
+ | 2.0668 | 0.66 | 6000 | 1.8447 |
56
+ | 2.0636 | 0.77 | 7000 | 1.8379 |
57
+ | 2.0442 | 0.88 | 8000 | 1.8311 |
58
+ | 2.0597 | 0.99 | 9000 | 1.8330 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
59
 
60
 
61
  ### Framework versions
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a334ec3053209cb845bc81932233132acb549926c87aba853e23d489a32a5f96
3
  size 836233
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cbe638ccfc25554463f8ac4c665f3267bf10aefe6df0dc17a38e73bc03d9ff5
3
  size 836233
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ecbb1db31f94682b6fda336e4801e4a6aec03c7ca75aaa69f601e42568bfafb
3
  size 4091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46bb18173bd05ac7b9b26a6fb744bead9d87fa2db621a70ac19078ef47a47d40
3
  size 4091