Luca-Engel
commited on
Commit
•
ef8f9c6
1
Parent(s):
dda4e5d
do test run on scitas with base gpt mode
Browse files- README.md +21 -16
- model.safetensors +1 -1
README.md
CHANGED
@@ -17,15 +17,15 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the None dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss:
|
21 |
-
- Rewards/chosen:
|
22 |
-
- Rewards/rejected:
|
23 |
-
- Rewards/accuracies: 0.
|
24 |
-
- Rewards/margins: 0.
|
25 |
-
- Logps/rejected: -
|
26 |
-
- Logps/chosen: -
|
27 |
-
- Logits/rejected: -
|
28 |
-
- Logits/chosen: -
|
29 |
|
30 |
## Model description
|
31 |
|
@@ -45,26 +45,31 @@ More information needed
|
|
45 |
|
46 |
The following hyperparameters were used during training:
|
47 |
- learning_rate: 5e-05
|
48 |
-
- train_batch_size:
|
49 |
-
- eval_batch_size:
|
50 |
- seed: 42
|
|
|
|
|
51 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
52 |
- lr_scheduler_type: linear
|
53 |
- lr_scheduler_warmup_ratio: 0.1
|
54 |
-
- num_epochs:
|
55 |
|
56 |
### Training results
|
57 |
|
58 |
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|
59 |
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
|
60 |
-
|
|
61 |
-
| 0.
|
62 |
-
| 0.
|
|
|
|
|
|
|
63 |
|
64 |
|
65 |
### Framework versions
|
66 |
|
67 |
- Transformers 4.40.2
|
68 |
-
- Pytorch 2.
|
69 |
- Datasets 2.19.1
|
70 |
- Tokenizers 0.19.1
|
|
|
17 |
|
18 |
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the None dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.9044
|
21 |
+
- Rewards/chosen: 0.7444
|
22 |
+
- Rewards/rejected: 0.2592
|
23 |
+
- Rewards/accuracies: 0.5817
|
24 |
+
- Rewards/margins: 0.4852
|
25 |
+
- Logps/rejected: -429.5133
|
26 |
+
- Logps/chosen: -506.8889
|
27 |
+
- Logits/rejected: -50.2012
|
28 |
+
- Logits/chosen: -45.4443
|
29 |
|
30 |
## Model description
|
31 |
|
|
|
45 |
|
46 |
The following hyperparameters were used during training:
|
47 |
- learning_rate: 5e-05
|
48 |
+
- train_batch_size: 8
|
49 |
+
- eval_batch_size: 8
|
50 |
- seed: 42
|
51 |
+
- gradient_accumulation_steps: 2
|
52 |
+
- total_train_batch_size: 16
|
53 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
54 |
- lr_scheduler_type: linear
|
55 |
- lr_scheduler_warmup_ratio: 0.1
|
56 |
+
- num_epochs: 6
|
57 |
|
58 |
### Training results
|
59 |
|
60 |
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|
61 |
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
|
62 |
+
| 0.8683 | 1.0 | 1337 | 0.9044 | 0.7444 | 0.2592 | 0.5817 | 0.4852 | -429.5133 | -506.8889 | -50.2012 | -45.4443 |
|
63 |
+
| 0.4795 | 2.0 | 2674 | 0.9425 | 0.1993 | -0.4639 | 0.5959 | 0.6632 | -436.7442 | -512.3394 | -54.4344 | -49.5827 |
|
64 |
+
| 0.1485 | 3.0 | 4011 | 1.1159 | -2.0134 | -2.6798 | 0.5775 | 0.6664 | -458.9030 | -534.4666 | -70.3363 | -65.4014 |
|
65 |
+
| 0.0378 | 4.0 | 5348 | 1.3151 | -3.6174 | -4.7588 | 0.5927 | 1.1415 | -479.6934 | -550.5060 | -70.8835 | -65.6636 |
|
66 |
+
| 0.0127 | 5.0 | 6685 | 1.4381 | -4.8640 | -6.0585 | 0.5822 | 1.1945 | -492.6903 | -562.9730 | -70.3612 | -64.6966 |
|
67 |
+
| 0.0006 | 6.0 | 8022 | 1.5074 | -5.3161 | -6.4742 | 0.5837 | 1.1581 | -496.8472 | -567.4940 | -70.7820 | -64.9708 |
|
68 |
|
69 |
|
70 |
### Framework versions
|
71 |
|
72 |
- Transformers 4.40.2
|
73 |
+
- Pytorch 2.1.0+cu118
|
74 |
- Datasets 2.19.1
|
75 |
- Tokenizers 0.19.1
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 497774208
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4845218046a89bea86f750ff165e97f41596402f2b795bd78146d7ec38d055ee
|
3 |
size 497774208
|