82 lines
2.9 KiB
Markdown
82 lines
2.9 KiB
Markdown
---
|
|
library_name: transformers
|
|
license: llama3.2
|
|
base_model: meta-llama/Llama-3.2-1B-Instruct
|
|
tags:
|
|
- peft-factory
|
|
- freeze
|
|
- llama-factory
|
|
- generated_from_trainer
|
|
model-index:
|
|
- name: train_record_42_1779354540
|
|
results: []
|
|
---
|
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
should probably proofread and complete it, then remove this comment. -->
|
|
|
|
# train_record_42_1779354540
|
|
|
|
This model is a fine-tuned version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) on the record dataset.
|
|
It achieves the following results on the evaluation set:
|
|
- Loss: 0.3537
|
|
- Num Input Tokens Seen: 49166912
|
|
|
|
## Model description
|
|
|
|
More information needed
|
|
|
|
## Intended uses & limitations
|
|
|
|
More information needed
|
|
|
|
## Training and evaluation data
|
|
|
|
More information needed
|
|
|
|
## Training procedure
|
|
|
|
### Training hyperparameters
|
|
|
|
The following hyperparameters were used during training:
|
|
- learning_rate: 2e-06
|
|
- train_batch_size: 8
|
|
- eval_batch_size: 8
|
|
- seed: 42
|
|
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
|
- lr_scheduler_type: cosine
|
|
- lr_scheduler_warmup_ratio: 0.1
|
|
- num_epochs: 1
|
|
|
|
### Training results
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Input Tokens Seen |
|
|
|:-------------:|:------:|:-----:|:---------------:|:-----------------:|
|
|
| 0.764 | 0.0501 | 782 | 0.6362 | 2474432 |
|
|
| 0.6569 | 0.1001 | 1564 | 0.5395 | 4931328 |
|
|
| 0.5165 | 0.1502 | 2346 | 0.5076 | 7397056 |
|
|
| 0.5774 | 0.2002 | 3128 | 0.4884 | 9832064 |
|
|
| 0.4226 | 0.2503 | 3910 | 0.4644 | 12304064 |
|
|
| 0.3784 | 0.3004 | 4692 | 0.4629 | 14775488 |
|
|
| 0.579 | 0.3504 | 5474 | 0.4391 | 17259840 |
|
|
| 0.3547 | 0.4005 | 6256 | 0.4233 | 19707456 |
|
|
| 0.3794 | 0.4505 | 7038 | 0.4316 | 22178432 |
|
|
| 0.3939 | 0.5006 | 7820 | 0.4134 | 24646208 |
|
|
| 0.3382 | 0.5507 | 8602 | 0.3985 | 27101056 |
|
|
| 0.4 | 0.6007 | 9384 | 0.3917 | 29544576 |
|
|
| 0.3188 | 0.6508 | 10166 | 0.3784 | 32010176 |
|
|
| 0.4233 | 0.7009 | 10948 | 0.3722 | 34475136 |
|
|
| 0.2995 | 0.7509 | 11730 | 0.3648 | 36931648 |
|
|
| 0.3367 | 0.8010 | 12512 | 0.3636 | 39382144 |
|
|
| 0.272 | 0.8510 | 13294 | 0.3571 | 41847872 |
|
|
| 0.3451 | 0.9011 | 14076 | 0.3544 | 44318848 |
|
|
| 0.2502 | 0.9512 | 14858 | 0.3537 | 46767552 |
|
|
|
|
|
|
### Framework versions
|
|
|
|
- Transformers 4.51.3
|
|
- Pytorch 2.10.0+cu128
|
|
- Datasets 4.0.0
|
|
- Tokenizers 0.21.4
|