Hugging Face's logo

elliottfitzgerald
/
opt-125m-finetuned-mnli-mm

PEFT
TensorBoard
Safetensors
opt
Generated from Trainer
Model card Files Metrics Community
elliottfitzgerald commited on
Commit
f4b0135
•
1 Parent(s): 8e37fe4

End of training

Browse files
Files changed (3) hide show
  1. README.md +16 -14
  2. adapter_model.safetensors +1 -1
  3. runs/May01_02-42-53_ddcf5e5af957/events.out.tfevents.1714531519.ddcf5e5af957.12632.3 +3 -0
README.md CHANGED
@@ -1,8 +1,9 @@
1
  ---
2
  license: other
3
- base_model: facebook/opt-125m
4
  tags:
5
  - generated_from_trainer
 
6
  metrics:
7
  - accuracy
8
  model-index:
@@ -17,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [facebook/opt-125m](https://huggingface.co/facebook/opt-125m) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.9714
21
- - Accuracy: 0.5174
22
 
23
  ## Model description
24
 
@@ -49,21 +50,22 @@ The following hyperparameters were used during training:
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
- | No log | 1.0 | 1 | 1.0253 | 0.5172 |
53
- | No log | 2.0 | 2 | 0.9714 | 0.5174 |
54
- | No log | 3.0 | 3 | 0.8388 | 0.5168 |
55
- | No log | 4.0 | 4 | 0.7774 | 0.5144 |
56
- | No log | 5.0 | 5 | 0.7668 | 0.5104 |
57
- | No log | 6.0 | 6 | 0.7845 | 0.5108 |
58
- | No log | 7.0 | 7 | 0.8156 | 0.5138 |
59
- | No log | 8.0 | 8 | 0.8515 | 0.5128 |
60
- | No log | 9.0 | 9 | 0.8807 | 0.5138 |
61
- | No log | 10.0 | 10 | 0.8944 | 0.5153 |
62
 
63
 
64
  ### Framework versions
65
 
 
66
  - Transformers 4.40.1
67
  - Pytorch 2.2.1+cu121
68
  - Datasets 2.19.0
69
- - Tokenizers 0.19.1
 
1
  ---
2
  license: other
3
+ library_name: peft
4
  tags:
5
  - generated_from_trainer
6
+ base_model: facebook/opt-125m
7
  metrics:
8
  - accuracy
9
  model-index:
 
18
 
19
  This model is a fine-tuned version of [facebook/opt-125m](https://huggingface.co/facebook/opt-125m) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.7569
22
+ - Accuracy: 0.4937
23
 
24
  ## Model description
25
 
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
+ | No log | 1.0 | 1 | 0.7338 | 0.4701 |
54
+ | No log | 2.0 | 2 | 0.7326 | 0.4701 |
55
+ | No log | 3.0 | 3 | 0.7318 | 0.4705 |
56
+ | No log | 4.0 | 4 | 0.7311 | 0.4722 |
57
+ | No log | 5.0 | 5 | 0.7306 | 0.4738 |
58
+ | No log | 6.0 | 6 | 0.7303 | 0.4761 |
59
+ | No log | 7.0 | 7 | 0.7300 | 0.4770 |
60
+ | No log | 8.0 | 8 | 0.7297 | 0.4786 |
61
+ | No log | 9.0 | 9 | 0.7296 | 0.4796 |
62
+ | No log | 10.0 | 10 | 0.7295 | 0.4798 |
63
 
64
 
65
  ### Framework versions
66
 
67
+ - PEFT 0.10.0
68
  - Transformers 4.40.1
69
  - Pytorch 2.2.1+cu121
70
  - Datasets 2.19.0
71
+ - Tokenizers 0.19.1
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b6d875a0d70a413e4c6d32fbb457da6b35a1d582c78533c7f44d8a9bd4c27980
3
  size 67792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82997232dafe3083ea8896eb8ded07f2b670c78e485b2df7b3f696770f0eab34
3
  size 67792
runs/May01_02-42-53_ddcf5e5af957/events.out.tfevents.1714531519.ddcf5e5af957.12632.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74c8c01cdee72acca4e4946f2051bfb8521d6ae900152f25108b30d7c1a5f069
3
+ size 405