Commit
•
3a1fdbc
1
Parent(s):
c1d0cd7
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: lmd-8bars-2048-epochs10
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# lmd-8bars-2048-epochs10
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the None dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 1.0086
|
| 18 |
+
|
| 19 |
+
## Model description
|
| 20 |
+
|
| 21 |
+
More information needed
|
| 22 |
+
|
| 23 |
+
## Intended uses & limitations
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Training and evaluation data
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training procedure
|
| 32 |
+
|
| 33 |
+
### Training hyperparameters
|
| 34 |
+
|
| 35 |
+
The following hyperparameters were used during training:
|
| 36 |
+
- learning_rate: 0.0005
|
| 37 |
+
- train_batch_size: 8
|
| 38 |
+
- eval_batch_size: 4
|
| 39 |
+
- seed: 1
|
| 40 |
+
- gradient_accumulation_steps: 2
|
| 41 |
+
- total_train_batch_size: 16
|
| 42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
+
- lr_scheduler_type: cosine
|
| 44 |
+
- lr_scheduler_warmup_ratio: 0.01
|
| 45 |
+
- num_epochs: 10
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
| 51 |
+
| 2.4182 | 0.5 | 4994 | 1.4933 |
|
| 52 |
+
| 1.4626 | 1.0 | 9988 | 1.3082 |
|
| 53 |
+
| 1.3176 | 1.5 | 14982 | 1.2276 |
|
| 54 |
+
| 1.2604 | 2.0 | 19976 | 1.1815 |
|
| 55 |
+
| 1.2101 | 2.5 | 24970 | 1.1499 |
|
| 56 |
+
| 1.1804 | 3.0 | 29964 | 1.1260 |
|
| 57 |
+
| 1.1517 | 3.5 | 34958 | 1.1043 |
|
| 58 |
+
| 1.1349 | 4.0 | 39952 | 1.0887 |
|
| 59 |
+
| 1.1133 | 4.5 | 44946 | 1.0762 |
|
| 60 |
+
| 1.0995 | 5.0 | 49940 | 1.0618 |
|
| 61 |
+
| 1.0824 | 5.5 | 54934 | 1.0507 |
|
| 62 |
+
| 1.0713 | 6.0 | 59928 | 1.0423 |
|
| 63 |
+
| 1.0552 | 6.5 | 64922 | 1.0328 |
|
| 64 |
+
| 1.0505 | 7.0 | 69916 | 1.0279 |
|
| 65 |
+
| 1.0365 | 7.5 | 74910 | 1.0217 |
|
| 66 |
+
| 1.0307 | 8.0 | 79904 | 1.0153 |
|
| 67 |
+
| 1.022 | 8.5 | 84898 | 1.0107 |
|
| 68 |
+
| 1.0189 | 9.0 | 89892 | 1.0090 |
|
| 69 |
+
| 1.0129 | 9.5 | 94886 | 1.0084 |
|
| 70 |
+
| 1.0139 | 10.0 | 99880 | 1.0086 |
|
| 71 |
+
|
| 72 |
+
|
| 73 |
+
### Framework versions
|
| 74 |
+
|
| 75 |
+
- Transformers 4.30.2
|
| 76 |
+
- Pytorch 2.0.1+cu118
|
| 77 |
+
- Datasets 2.13.1
|
| 78 |
+
- Tokenizers 0.13.3
|