Files
ModelHub XC 75a10cef13 初始化项目,由ModelHub XC社区提供模型
Model: rbelanec/train_record_42_1779207275
Source: Original Platform
2026-06-04 17:07:25 +08:00

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