End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
license: other
|
| 4 |
+
base_model: NousResearch/Meta-Llama-3-8B-Alternate-Tokenizer
|
| 5 |
+
tags:
|
| 6 |
+
- axolotl
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
model-index:
|
| 9 |
+
- name: 17ddfec3-de9b-4a13-aab4-36976da7fb83
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
|
| 17 |
+
<br>
|
| 18 |
+
|
| 19 |
+
# 17ddfec3-de9b-4a13-aab4-36976da7fb83
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [NousResearch/Meta-Llama-3-8B-Alternate-Tokenizer](https://huggingface.co/NousResearch/Meta-Llama-3-8B-Alternate-Tokenizer) on the None dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 1.1896
|
| 24 |
+
|
| 25 |
+
## Model description
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training and evaluation data
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training procedure
|
| 38 |
+
|
| 39 |
+
### Training hyperparameters
|
| 40 |
+
|
| 41 |
+
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 0.000204
|
| 43 |
+
- train_batch_size: 4
|
| 44 |
+
- eval_batch_size: 4
|
| 45 |
+
- seed: 42
|
| 46 |
+
- gradient_accumulation_steps: 2
|
| 47 |
+
- total_train_batch_size: 8
|
| 48 |
+
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 49 |
+
- lr_scheduler_type: cosine
|
| 50 |
+
- lr_scheduler_warmup_steps: 50
|
| 51 |
+
- training_steps: 500
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 56 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 57 |
+
| No log | 0.0001 | 1 | 2.1742 |
|
| 58 |
+
| 2.0712 | 0.0026 | 50 | 1.7819 |
|
| 59 |
+
| 1.8743 | 0.0052 | 100 | 1.7514 |
|
| 60 |
+
| 1.8739 | 0.0079 | 150 | 1.8120 |
|
| 61 |
+
| 2.1821 | 0.0105 | 200 | 1.6885 |
|
| 62 |
+
| 1.7126 | 0.0131 | 250 | 1.4994 |
|
| 63 |
+
| 1.8793 | 0.0157 | 300 | 1.4284 |
|
| 64 |
+
| 1.8794 | 0.0183 | 350 | 1.3096 |
|
| 65 |
+
| 1.6114 | 0.0210 | 400 | 1.2151 |
|
| 66 |
+
| 1.8403 | 0.0236 | 450 | 1.1930 |
|
| 67 |
+
| 1.8475 | 0.0262 | 500 | 1.1896 |
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
### Framework versions
|
| 71 |
+
|
| 72 |
+
- PEFT 0.13.2
|
| 73 |
+
- Transformers 4.46.0
|
| 74 |
+
- Pytorch 2.5.0+cu124
|
| 75 |
+
- Datasets 3.0.1
|
| 76 |
+
- Tokenizers 0.20.1
|