82 lines
2.8 KiB
Markdown
82 lines
2.8 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_sst2_42_1779354537
|
|
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_sst2_42_1779354537
|
|
|
|
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 sst2 dataset.
|
|
It achieves the following results on the evaluation set:
|
|
- Loss: 0.0908
|
|
- Num Input Tokens Seen: 3725120
|
|
|
|
## 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 |
|
|
|:-------------:|:------:|:----:|:---------------:|:-----------------:|
|
|
| 0.0584 | 0.0500 | 379 | 0.1753 | 187072 |
|
|
| 0.1154 | 0.1000 | 758 | 0.1295 | 373504 |
|
|
| 0.0745 | 0.1501 | 1137 | 0.1949 | 557824 |
|
|
| 0.1712 | 0.2001 | 1516 | 0.1069 | 743424 |
|
|
| 0.2865 | 0.2501 | 1895 | 0.1277 | 930944 |
|
|
| 0.1225 | 0.3001 | 2274 | 0.1098 | 1116800 |
|
|
| 0.1152 | 0.3501 | 2653 | 0.1235 | 1303872 |
|
|
| 0.1615 | 0.4002 | 3032 | 0.1323 | 1490688 |
|
|
| 0.0698 | 0.4502 | 3411 | 0.1182 | 1678208 |
|
|
| 0.3465 | 0.5002 | 3790 | 0.1325 | 1864128 |
|
|
| 0.1538 | 0.5502 | 4169 | 0.0976 | 2047552 |
|
|
| 0.1911 | 0.6002 | 4548 | 0.1150 | 2232448 |
|
|
| 0.1499 | 0.6503 | 4927 | 0.0984 | 2420096 |
|
|
| 0.2014 | 0.7003 | 5306 | 0.0908 | 2605504 |
|
|
| 0.0014 | 0.7503 | 5685 | 0.0957 | 2790656 |
|
|
| 0.1294 | 0.8003 | 6064 | 0.0955 | 2979456 |
|
|
| 0.1202 | 0.8503 | 6443 | 0.0970 | 3167488 |
|
|
| 0.0013 | 0.9004 | 6822 | 0.0957 | 3355520 |
|
|
| 0.05 | 0.9504 | 7201 | 0.0956 | 3541632 |
|
|
|
|
|
|
### Framework versions
|
|
|
|
- Transformers 4.51.3
|
|
- Pytorch 2.10.0+cu128
|
|
- Datasets 4.0.0
|
|
- Tokenizers 0.21.4
|