End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: katuni4ka/tiny-random-qwen1.5-moe
|
| 4 |
+
tags:
|
| 5 |
+
- axolotl
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: 5663e6cc-de8d-4ea7-87d4-be498fce4d0e
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
[<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)
|
| 16 |
+
<br>
|
| 17 |
+
|
| 18 |
+
# 5663e6cc-de8d-4ea7-87d4-be498fce4d0e
|
| 19 |
+
|
| 20 |
+
This model is a fine-tuned version of [katuni4ka/tiny-random-qwen1.5-moe](https://huggingface.co/katuni4ka/tiny-random-qwen1.5-moe) on the None dataset.
|
| 21 |
+
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 11.7402
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 0.000206
|
| 42 |
+
- train_batch_size: 4
|
| 43 |
+
- eval_batch_size: 4
|
| 44 |
+
- seed: 60
|
| 45 |
+
- gradient_accumulation_steps: 8
|
| 46 |
+
- total_train_batch_size: 32
|
| 47 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 48 |
+
- lr_scheduler_type: cosine
|
| 49 |
+
- lr_scheduler_warmup_steps: 100
|
| 50 |
+
- training_steps: 9000
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 55 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 56 |
+
| No log | 0.0003 | 1 | 11.9364 |
|
| 57 |
+
| 11.7934 | 0.1516 | 500 | 11.7890 |
|
| 58 |
+
| 11.7818 | 0.3033 | 1000 | 11.7749 |
|
| 59 |
+
| 11.7769 | 0.4549 | 1500 | 11.7676 |
|
| 60 |
+
| 11.772 | 0.6066 | 2000 | 11.7620 |
|
| 61 |
+
| 11.7681 | 0.7582 | 2500 | 11.7579 |
|
| 62 |
+
| 11.76 | 0.9098 | 3000 | 11.7542 |
|
| 63 |
+
| 11.7532 | 1.0615 | 3500 | 11.7502 |
|
| 64 |
+
| 11.774 | 1.2131 | 4000 | 11.7484 |
|
| 65 |
+
| 11.7583 | 1.3648 | 4500 | 11.7457 |
|
| 66 |
+
| 11.7423 | 1.5164 | 5000 | 11.7446 |
|
| 67 |
+
| 11.7536 | 1.6681 | 5500 | 11.7429 |
|
| 68 |
+
| 11.7444 | 1.8197 | 6000 | 11.7420 |
|
| 69 |
+
| 11.753 | 1.9713 | 6500 | 11.7410 |
|
| 70 |
+
| 11.7538 | 2.1230 | 7000 | 11.7406 |
|
| 71 |
+
| 11.7483 | 2.2746 | 7500 | 11.7404 |
|
| 72 |
+
| 11.7539 | 2.4263 | 8000 | 11.7401 |
|
| 73 |
+
| 11.7568 | 2.5779 | 8500 | 11.7402 |
|
| 74 |
+
| 11.7279 | 2.7295 | 9000 | 11.7402 |
|
| 75 |
+
|
| 76 |
+
|
| 77 |
+
### Framework versions
|
| 78 |
+
|
| 79 |
+
- PEFT 0.13.2
|
| 80 |
+
- Transformers 4.46.0
|
| 81 |
+
- Pytorch 2.5.0+cu124
|
| 82 |
+
- Datasets 3.0.1
|
| 83 |
+
- Tokenizers 0.20.1
|