End of training
Browse files- README.md +17 -10
- 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/bloom-1b1](https://huggingface.co/bigscience/bloom-1b1) on the None dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss: 4.
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -35,27 +35,34 @@ More information needed
|
|
35 |
### Training hyperparameters
|
36 |
|
37 |
The following hyperparameters were used during training:
|
38 |
-
- learning_rate:
|
39 |
- train_batch_size: 8
|
40 |
- eval_batch_size: 8
|
41 |
- seed: 42
|
42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
- lr_scheduler_type: linear
|
44 |
-
- num_epochs:
|
45 |
|
46 |
### Training results
|
47 |
|
48 |
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
|:-------------:|:-----:|:----:|:---------------:|
|
50 |
-
| 5.
|
51 |
-
|
|
52 |
-
| 4.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
53 |
|
54 |
|
55 |
### Framework versions
|
56 |
|
57 |
- PEFT 0.9.0
|
58 |
-
- Transformers 4.
|
59 |
-
- Pytorch 2.1
|
60 |
-
- Datasets 2.
|
61 |
-
- Tokenizers 0.15.
|
|
|
16 |
|
17 |
This model is a fine-tuned version of [bigscience/bloom-1b1](https://huggingface.co/bigscience/bloom-1b1) on the None dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 4.3832
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
35 |
### Training hyperparameters
|
36 |
|
37 |
The following hyperparameters were used during training:
|
38 |
+
- learning_rate: 0.0002
|
39 |
- train_batch_size: 8
|
40 |
- eval_batch_size: 8
|
41 |
- seed: 42
|
42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
- lr_scheduler_type: linear
|
44 |
+
- num_epochs: 10
|
45 |
|
46 |
### Training results
|
47 |
|
48 |
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
|:-------------:|:-----:|:----:|:---------------:|
|
50 |
+
| 5.0298 | 1.0 | 829 | 4.7124 |
|
51 |
+
| 4.681 | 2.0 | 1658 | 4.5977 |
|
52 |
+
| 4.6154 | 3.0 | 2487 | 4.5345 |
|
53 |
+
| 4.5244 | 4.0 | 3316 | 4.4902 |
|
54 |
+
| 4.4751 | 5.0 | 4145 | 4.4582 |
|
55 |
+
| 4.4559 | 6.0 | 4974 | 4.4347 |
|
56 |
+
| 4.4124 | 7.0 | 5803 | 4.4158 |
|
57 |
+
| 4.3982 | 8.0 | 6632 | 4.4015 |
|
58 |
+
| 4.3716 | 9.0 | 7461 | 4.3889 |
|
59 |
+
| 4.341 | 10.0 | 8290 | 4.3832 |
|
60 |
|
61 |
|
62 |
### Framework versions
|
63 |
|
64 |
- PEFT 0.9.0
|
65 |
+
- Transformers 4.36.2
|
66 |
+
- Pytorch 2.2.1+cu121
|
67 |
+
- Datasets 2.15.0
|
68 |
+
- Tokenizers 0.15.0
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 9444296
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fdd7563eda7b4c56689a8d510a1ac76ae40e3820c88463a88d650e4197b61651
|
3 |
size 9444296
|