Tristan Thrush
commited on
Commit
•
dfa3edb
1
Parent(s):
b6f52b7
update model card README.md
Browse files
README.md
CHANGED
@@ -2,6 +2,8 @@
|
|
2 |
license: mit
|
3 |
tags:
|
4 |
- generated_from_trainer
|
|
|
|
|
5 |
model-index:
|
6 |
- name: gpt2-summarization_reward_model
|
7 |
results: []
|
@@ -13,6 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
# gpt2-summarization_reward_model
|
14 |
|
15 |
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the None dataset.
|
|
|
|
|
|
|
16 |
|
17 |
## Model description
|
18 |
|
@@ -32,26 +37,31 @@ More information needed
|
|
32 |
|
33 |
The following hyperparameters were used during training:
|
34 |
- learning_rate: 2e-05
|
35 |
-
- train_batch_size:
|
36 |
-
- eval_batch_size:
|
37 |
- seed: 42
|
38 |
- distributed_type: multi-GPU
|
39 |
-
-
|
40 |
- total_train_batch_size: 64
|
|
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: linear
|
43 |
-
- num_epochs:
|
44 |
|
45 |
### Training results
|
46 |
|
47 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
48 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
49 |
-
|
|
|
|
|
|
|
|
|
|
50 |
|
51 |
|
52 |
### Framework versions
|
53 |
|
54 |
-
- Transformers 4.
|
55 |
- Pytorch 1.13.1+cu117
|
56 |
- Datasets 2.8.0
|
57 |
- Tokenizers 0.13.2
|
|
|
2 |
license: mit
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- accuracy
|
7 |
model-index:
|
8 |
- name: gpt2-summarization_reward_model
|
9 |
results: []
|
|
|
15 |
# gpt2-summarization_reward_model
|
16 |
|
17 |
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the None dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.7473
|
20 |
+
- Accuracy: 0.6006
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
- learning_rate: 2e-05
|
40 |
+
- train_batch_size: 4
|
41 |
+
- eval_batch_size: 4
|
42 |
- seed: 42
|
43 |
- distributed_type: multi-GPU
|
44 |
+
- num_devices: 16
|
45 |
- total_train_batch_size: 64
|
46 |
+
- total_eval_batch_size: 64
|
47 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
- lr_scheduler_type: linear
|
49 |
+
- num_epochs: 5
|
50 |
|
51 |
### Training results
|
52 |
|
53 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
54 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
55 |
+
| 0.6421 | 1.0 | 1451 | 0.6815 | 0.6036 |
|
56 |
+
| 0.5893 | 2.0 | 2902 | 0.6764 | 0.6048 |
|
57 |
+
| 0.5488 | 3.0 | 4353 | 0.7074 | 0.6012 |
|
58 |
+
| 0.5187 | 4.0 | 5804 | 0.7254 | 0.6009 |
|
59 |
+
| 0.5034 | 5.0 | 7255 | 0.7473 | 0.6006 |
|
60 |
|
61 |
|
62 |
### Framework versions
|
63 |
|
64 |
+
- Transformers 4.26.0
|
65 |
- Pytorch 1.13.1+cu117
|
66 |
- Datasets 2.8.0
|
67 |
- Tokenizers 0.13.2
|