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
|
|
- full
|
|
- llama-factory
|
|
- generated_from_trainer
|
|
model-index:
|
|
- name: train_record_42_1779207275
|
|
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_1779207275
|
|
|
|
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: 0.3958
|
|
- Num Input Tokens Seen: 245808128
|
|
|
|
## 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: 5
|
|
|
|
### Training results
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Input Tokens Seen |
|
|
|:-------------:|:------:|:-----:|:---------------:|:-----------------:|
|
|
| 0.5223 | 0.2500 | 3906 | 0.4993 | 12292032 |
|
|
| 0.4299 | 0.5001 | 7812 | 0.4629 | 24620672 |
|
|
| 0.5401 | 0.7501 | 11718 | 0.4265 | 36894016 |
|
|
| 0.3044 | 1.0002 | 15624 | 0.4150 | 49176512 |
|
|
| 0.3211 | 1.2502 | 19530 | 0.4428 | 61465280 |
|
|
| 0.2995 | 1.5003 | 23436 | 0.4194 | 73739776 |
|
|
| 0.3781 | 1.7503 | 27342 | 0.4182 | 86015936 |
|
|
| 0.2566 | 2.0004 | 31248 | 0.3958 | 98341056 |
|
|
| 0.2249 | 2.2504 | 35154 | 0.4533 | 110649216 |
|
|
| 0.1628 | 2.5005 | 39060 | 0.4516 | 122910592 |
|
|
| 0.2075 | 2.7505 | 42966 | 0.4763 | 135222656 |
|
|
| 0.1128 | 3.0006 | 46872 | 0.4709 | 147516736 |
|
|
| 0.0907 | 3.2506 | 50778 | 0.5112 | 159826368 |
|
|
| 0.1686 | 3.5007 | 54684 | 0.5226 | 172084032 |
|
|
| 0.1204 | 3.7507 | 58590 | 0.4965 | 184402752 |
|
|
| 0.1592 | 4.0008 | 62496 | 0.5179 | 196687936 |
|
|
| 0.0903 | 4.2508 | 66402 | 0.6059 | 209017024 |
|
|
| 0.1712 | 4.5009 | 70308 | 0.5779 | 221278272 |
|
|
| 0.1391 | 4.7509 | 74214 | 0.5740 | 233564288 |
|
|
|
|
|
|
### Framework versions
|
|
|
|
- Transformers 4.51.3
|
|
- Pytorch 2.10.0+cu128
|
|
- Datasets 4.0.0
|
|
- Tokenizers 0.21.4
|