Delete README.md
Browse files
README.md
DELETED
|
@@ -1,82 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
base_model: vilm/VinaLLaMA-2.7B-800b
|
| 3 |
-
tags:
|
| 4 |
-
- generated_from_trainer
|
| 5 |
-
model-index:
|
| 6 |
-
- name: out-vinallama-fft-2.7b
|
| 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 |
-
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
|
| 14 |
-
# out-vinallama-fft-2.7b
|
| 15 |
-
|
| 16 |
-
This model is a fine-tuned version of [vilm/VinaLLaMA-2.7B-800b](https://huggingface.co/vilm/VinaLLaMA-2.7B-800b) on the None dataset.
|
| 17 |
-
It achieves the following results on the evaluation set:
|
| 18 |
-
- Loss: 1.1028
|
| 19 |
-
|
| 20 |
-
## Model description
|
| 21 |
-
|
| 22 |
-
More information needed
|
| 23 |
-
|
| 24 |
-
## Intended uses & limitations
|
| 25 |
-
|
| 26 |
-
More information needed
|
| 27 |
-
|
| 28 |
-
## Training and evaluation data
|
| 29 |
-
|
| 30 |
-
More information needed
|
| 31 |
-
|
| 32 |
-
## Training procedure
|
| 33 |
-
|
| 34 |
-
### Training hyperparameters
|
| 35 |
-
|
| 36 |
-
The following hyperparameters were used during training:
|
| 37 |
-
- learning_rate: 2e-05
|
| 38 |
-
- train_batch_size: 4
|
| 39 |
-
- eval_batch_size: 4
|
| 40 |
-
- seed: 42
|
| 41 |
-
- distributed_type: multi-GPU
|
| 42 |
-
- num_devices: 4
|
| 43 |
-
- gradient_accumulation_steps: 4
|
| 44 |
-
- total_train_batch_size: 64
|
| 45 |
-
- total_eval_batch_size: 16
|
| 46 |
-
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
-
- lr_scheduler_type: cosine
|
| 48 |
-
- lr_scheduler_warmup_steps: 100
|
| 49 |
-
- num_epochs: 4
|
| 50 |
-
|
| 51 |
-
### Training results
|
| 52 |
-
|
| 53 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
| 54 |
-
|:-------------:|:-----:|:----:|:---------------:|
|
| 55 |
-
| 2.1202 | 0.0 | 1 | 2.0400 |
|
| 56 |
-
| 1.3783 | 0.2 | 205 | 1.3514 |
|
| 57 |
-
| 1.2539 | 0.4 | 410 | 1.2604 |
|
| 58 |
-
| 1.2168 | 0.6 | 615 | 1.2119 |
|
| 59 |
-
| 1.1739 | 0.8 | 820 | 1.1790 |
|
| 60 |
-
| 1.1273 | 1.0 | 1025 | 1.1548 |
|
| 61 |
-
| 1.0544 | 1.18 | 1230 | 1.1435 |
|
| 62 |
-
| 1.032 | 1.38 | 1435 | 1.1296 |
|
| 63 |
-
| 1.0114 | 1.58 | 1640 | 1.1182 |
|
| 64 |
-
| 1.0188 | 1.78 | 1845 | 1.1079 |
|
| 65 |
-
| 0.9877 | 1.98 | 2050 | 1.0994 |
|
| 66 |
-
| 0.9981 | 2.16 | 2255 | 1.1081 |
|
| 67 |
-
| 0.9505 | 2.36 | 2460 | 1.1030 |
|
| 68 |
-
| 0.9936 | 2.57 | 2665 | 1.0984 |
|
| 69 |
-
| 0.9076 | 2.77 | 2870 | 1.0924 |
|
| 70 |
-
| 0.8569 | 2.97 | 3075 | 1.0888 |
|
| 71 |
-
| 0.8902 | 3.15 | 3280 | 1.1067 |
|
| 72 |
-
| 0.8285 | 3.35 | 3485 | 1.1041 |
|
| 73 |
-
| 0.8617 | 3.55 | 3690 | 1.1036 |
|
| 74 |
-
| 0.8393 | 3.75 | 3895 | 1.1028 |
|
| 75 |
-
|
| 76 |
-
|
| 77 |
-
### Framework versions
|
| 78 |
-
|
| 79 |
-
- Transformers 4.34.1
|
| 80 |
-
- Pytorch 2.0.1+cu118
|
| 81 |
-
- Datasets 2.14.6
|
| 82 |
-
- Tokenizers 0.14.1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|