End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,113 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
license: mit
|
| 4 |
+
base_model: fxmarty/really-tiny-falcon-testing
|
| 5 |
+
tags:
|
| 6 |
+
- axolotl
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
model-index:
|
| 9 |
+
- name: cb25be4a-1449-40a2-8109-b264b1323006
|
| 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 |
+
# cb25be4a-1449-40a2-8109-b264b1323006
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [fxmarty/really-tiny-falcon-testing](https://huggingface.co/fxmarty/really-tiny-falcon-testing) on the None dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 10.9429
|
| 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: 0.000216
|
| 43 |
+
- train_batch_size: 4
|
| 44 |
+
- eval_batch_size: 4
|
| 45 |
+
- seed: 160
|
| 46 |
+
- gradient_accumulation_steps: 8
|
| 47 |
+
- total_train_batch_size: 32
|
| 48 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 100
|
| 51 |
+
- training_steps: 25000
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 56 |
+
|:-------------:|:------:|:-----:|:---------------:|
|
| 57 |
+
| No log | 0.0001 | 1 | 11.0842 |
|
| 58 |
+
| 87.9232 | 0.0563 | 500 | 10.9857 |
|
| 59 |
+
| 87.8442 | 0.1127 | 1000 | 10.9758 |
|
| 60 |
+
| 87.8066 | 0.1690 | 1500 | 10.9695 |
|
| 61 |
+
| 87.7834 | 0.2254 | 2000 | 10.9653 |
|
| 62 |
+
| 87.7611 | 0.2817 | 2500 | 10.9617 |
|
| 63 |
+
| 87.7402 | 0.3381 | 3000 | 10.9590 |
|
| 64 |
+
| 87.7235 | 0.3944 | 3500 | 10.9564 |
|
| 65 |
+
| 87.7075 | 0.4508 | 4000 | 10.9547 |
|
| 66 |
+
| 87.7165 | 0.5071 | 4500 | 10.9536 |
|
| 67 |
+
| 87.7037 | 0.5635 | 5000 | 10.9525 |
|
| 68 |
+
| 87.7007 | 0.6198 | 5500 | 10.9517 |
|
| 69 |
+
| 87.6844 | 0.6762 | 6000 | 10.9507 |
|
| 70 |
+
| 87.6852 | 0.7325 | 6500 | 10.9500 |
|
| 71 |
+
| 87.6855 | 0.7889 | 7000 | 10.9495 |
|
| 72 |
+
| 87.6894 | 0.8452 | 7500 | 10.9487 |
|
| 73 |
+
| 87.6775 | 0.9015 | 8000 | 10.9483 |
|
| 74 |
+
| 87.6793 | 0.9579 | 8500 | 10.9477 |
|
| 75 |
+
| 87.662 | 1.0143 | 9000 | 10.9471 |
|
| 76 |
+
| 87.6669 | 1.0706 | 9500 | 10.9467 |
|
| 77 |
+
| 87.6676 | 1.1270 | 10000 | 10.9459 |
|
| 78 |
+
| 87.6588 | 1.1833 | 10500 | 10.9458 |
|
| 79 |
+
| 87.6601 | 1.2397 | 11000 | 10.9454 |
|
| 80 |
+
| 87.658 | 1.2960 | 11500 | 10.9452 |
|
| 81 |
+
| 87.6455 | 1.3524 | 12000 | 10.9451 |
|
| 82 |
+
| 87.647 | 1.4087 | 12500 | 10.9447 |
|
| 83 |
+
| 87.6441 | 1.4650 | 13000 | 10.9446 |
|
| 84 |
+
| 87.641 | 1.5214 | 13500 | 10.9444 |
|
| 85 |
+
| 87.6401 | 1.5777 | 14000 | 10.9442 |
|
| 86 |
+
| 87.6508 | 1.6341 | 14500 | 10.9442 |
|
| 87 |
+
| 87.6442 | 1.6904 | 15000 | 10.9440 |
|
| 88 |
+
| 87.6442 | 1.7468 | 15500 | 10.9439 |
|
| 89 |
+
| 87.653 | 1.8031 | 16000 | 10.9437 |
|
| 90 |
+
| 87.6379 | 1.8595 | 16500 | 10.9437 |
|
| 91 |
+
| 87.6483 | 1.9158 | 17000 | 10.9435 |
|
| 92 |
+
| 87.6465 | 1.9722 | 17500 | 10.9435 |
|
| 93 |
+
| 87.6348 | 2.0285 | 18000 | 10.9433 |
|
| 94 |
+
| 87.6466 | 2.0849 | 18500 | 10.9433 |
|
| 95 |
+
| 87.6434 | 2.1412 | 19000 | 10.9433 |
|
| 96 |
+
| 87.6441 | 2.1976 | 19500 | 10.9430 |
|
| 97 |
+
| 87.6309 | 2.2539 | 20000 | 10.9430 |
|
| 98 |
+
| 87.6324 | 2.3103 | 20500 | 10.9430 |
|
| 99 |
+
| 87.64 | 2.3666 | 21000 | 10.9430 |
|
| 100 |
+
| 87.6376 | 2.4230 | 21500 | 10.9429 |
|
| 101 |
+
| 87.6364 | 2.4793 | 22000 | 10.9429 |
|
| 102 |
+
| 87.645 | 2.5357 | 22500 | 10.9429 |
|
| 103 |
+
| 87.6321 | 2.5920 | 23000 | 10.9429 |
|
| 104 |
+
| 87.6373 | 2.6484 | 23500 | 10.9429 |
|
| 105 |
+
|
| 106 |
+
|
| 107 |
+
### Framework versions
|
| 108 |
+
|
| 109 |
+
- PEFT 0.13.2
|
| 110 |
+
- Transformers 4.46.0
|
| 111 |
+
- Pytorch 2.5.0+cu124
|
| 112 |
+
- Datasets 3.0.1
|
| 113 |
+
- Tokenizers 0.20.1
|