Hugging Face's logo

jysssacc
/
mt0-base_PrefixTuning_lr5e-05_bs4_epoch20_wd0.01

PEFT
Safetensors
Generated from Trainer
Model card Files Community
jysssacc commited on
Commit
ee353cc
•
1 Parent(s): fb7e966

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: 0.2019
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
- | 0.8363 | 1.0 | 157 | 0.4449 |
52
- | 0.8084 | 2.0 | 314 | 0.4286 |
53
- | 0.7857 | 3.0 | 471 | 0.4025 |
54
- | 0.7468 | 4.0 | 628 | 0.3726 |
55
- | 0.6856 | 5.0 | 785 | 0.3463 |
56
- | 0.6662 | 6.0 | 942 | 0.3231 |
57
- | 0.6387 | 7.0 | 1099 | 0.3029 |
58
- | 0.6215 | 8.0 | 1256 | 0.2853 |
59
- | 0.5762 | 9.0 | 1413 | 0.2699 |
60
- | 0.5556 | 10.0 | 1570 | 0.2569 |
61
- | 0.5157 | 11.0 | 1727 | 0.2455 |
62
- | 0.5168 | 12.0 | 1884 | 0.2358 |
63
- | 0.4804 | 13.0 | 2041 | 0.2273 |
64
- | 0.492 | 14.0 | 2198 | 0.2203 |
65
- | 0.4759 | 15.0 | 2355 | 0.2145 |
66
- | 0.4642 | 16.0 | 2512 | 0.2099 |
67
- | 0.4606 | 17.0 | 2669 | 0.2064 |
68
- | 0.4485 | 18.0 | 2826 | 0.2039 |
69
- | 0.4529 | 19.0 | 2983 | 0.2024 |
70
- | 0.4427 | 20.0 | 3140 | 0.2019 |
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: 0.2067
20
 
21
  ## Model description
22
 
 
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
+ | 0.8049 | 1.0 | 157 | 0.4431 |
52
+ | 0.7867 | 2.0 | 314 | 0.4271 |
53
+ | 0.7594 | 3.0 | 471 | 0.4017 |
54
+ | 0.7285 | 4.0 | 628 | 0.3724 |
55
+ | 0.6645 | 5.0 | 785 | 0.3470 |
56
+ | 0.6434 | 6.0 | 942 | 0.3244 |
57
+ | 0.6189 | 7.0 | 1099 | 0.3047 |
58
+ | 0.6048 | 8.0 | 1256 | 0.2879 |
59
+ | 0.5618 | 9.0 | 1413 | 0.2731 |
60
+ | 0.536 | 10.0 | 1570 | 0.2602 |
61
+ | 0.5033 | 11.0 | 1727 | 0.2494 |
62
+ | 0.5052 | 12.0 | 1884 | 0.2398 |
63
+ | 0.4647 | 13.0 | 2041 | 0.2316 |
64
+ | 0.479 | 14.0 | 2198 | 0.2248 |
65
+ | 0.4629 | 15.0 | 2355 | 0.2191 |
66
+ | 0.4541 | 16.0 | 2512 | 0.2146 |
67
+ | 0.4484 | 17.0 | 2669 | 0.2111 |
68
+ | 0.4415 | 18.0 | 2826 | 0.2087 |
69
+ | 0.4447 | 19.0 | 2983 | 0.2072 |
70
+ | 0.4343 | 20.0 | 3140 | 0.2067 |
71
 
72
 
73
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:47ed88ee6b4b96b5757fca23d8a6bbe014b1ea457ba53c5d2c754e183c7782b2
3
  size 737408
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb581f0d6b6474764830f1276a29c7de12d6b29ef7e2d704bfeee25c1813ac11
3
  size 737408