Hugging Face's logo

jysssacc
/
mt0-base_adalora_lr5e-05_bs4_epoch20_wd0.01

PEFT
Safetensors
Generated from Trainer
Model card Files Community
jysssacc commited on
Commit
dd30de1
•
1 Parent(s): e0c38fa

End of training

Browse files
Files changed (2) hide show
  1. README.md +21 -21
  2. adapter_model.safetensors +1 -1
README.md CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [bigscience/mt0-base](https://huggingface.co/bigscience/mt0-base) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.0096
20
 
21
  ## Model description
22
 
@@ -48,26 +48,26 @@ The following hyperparameters were used during training:
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
- | 1.6161 | 1.0 | 157 | 1.3091 |
52
- | 1.4515 | 2.0 | 314 | 1.1106 |
53
- | 1.2816 | 3.0 | 471 | 0.6214 |
54
- | 0.4086 | 4.0 | 628 | 0.1344 |
55
- | 0.2076 | 5.0 | 785 | 0.0700 |
56
- | 0.1125 | 6.0 | 942 | 0.0485 |
57
- | 0.0986 | 7.0 | 1099 | 0.0364 |
58
- | 0.0796 | 8.0 | 1256 | 0.0287 |
59
- | 0.063 | 9.0 | 1413 | 0.0239 |
60
- | 0.0636 | 10.0 | 1570 | 0.0207 |
61
- | 0.052 | 11.0 | 1727 | 0.0177 |
62
- | 0.0496 | 12.0 | 1884 | 0.0156 |
63
- | 0.0406 | 13.0 | 2041 | 0.0140 |
64
- | 0.0412 | 14.0 | 2198 | 0.0128 |
65
- | 0.0407 | 15.0 | 2355 | 0.0117 |
66
- | 0.0396 | 16.0 | 2512 | 0.0109 |
67
- | 0.0357 | 17.0 | 2669 | 0.0104 |
68
- | 0.0399 | 18.0 | 2826 | 0.0100 |
69
- | 0.0377 | 19.0 | 2983 | 0.0097 |
70
- | 0.0357 | 20.0 | 3140 | 0.0096 |
71
 
72
 
73
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [bigscience/mt0-base](https://huggingface.co/bigscience/mt0-base) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.0093
20
 
21
  ## Model description
22
 
 
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
+ | 1.6158 | 1.0 | 157 | 1.3090 |
52
+ | 1.4517 | 2.0 | 314 | 1.1107 |
53
+ | 1.2826 | 3.0 | 471 | 0.6223 |
54
+ | 0.4138 | 4.0 | 628 | 0.1360 |
55
+ | 0.2104 | 5.0 | 785 | 0.0696 |
56
+ | 0.113 | 6.0 | 942 | 0.0494 |
57
+ | 0.1002 | 7.0 | 1099 | 0.0399 |
58
+ | 0.0839 | 8.0 | 1256 | 0.0330 |
59
+ | 0.0671 | 9.0 | 1413 | 0.0278 |
60
+ | 0.0676 | 10.0 | 1570 | 0.0237 |
61
+ | 0.0552 | 11.0 | 1727 | 0.0201 |
62
+ | 0.0518 | 12.0 | 1884 | 0.0172 |
63
+ | 0.0427 | 13.0 | 2041 | 0.0148 |
64
+ | 0.0422 | 14.0 | 2198 | 0.0130 |
65
+ | 0.0418 | 15.0 | 2355 | 0.0116 |
66
+ | 0.0398 | 16.0 | 2512 | 0.0106 |
67
+ | 0.0359 | 17.0 | 2669 | 0.0099 |
68
+ | 0.0394 | 18.0 | 2826 | 0.0096 |
69
+ | 0.0382 | 19.0 | 2983 | 0.0093 |
70
+ | 0.0354 | 20.0 | 3140 | 0.0093 |
71
 
72
 
73
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ccf6800ba812f5221f21a4e7373d1666a7e5c038df32de97548a08b99919453
3
  size 20446184
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f35ac44412fa92ed5b1e265491c85d019e5a0d7b5c4f735ebe43d6b48e6d2f17
3
  size 20446184