Files
emotion-reasoning-1b/README.md
ModelHub XC ae9afd9c2a 初始化项目,由ModelHub XC社区提供模型
Model: syvai/emotion-reasoning-1b
Source: Original Platform
2026-05-26 15:10:17 +08:00

121 lines
2.8 KiB
Markdown

---
library_name: transformers
license: llama3.2
base_model: meta-llama/Llama-3.2-1B-Instruct
tags:
- axolotl
- generated_from_trainer
datasets:
- syvai/emotion-reasoning
model-index:
- name: emotion-reasoning-1b
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. -->
[<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)
<details><summary>See axolotl config</summary>
axolotl version: `0.10.0.dev0`
```yaml
base_model: meta-llama/Llama-3.2-1B-Instruct
# Automatically upload checkpoint and final model to HF
hub_model_id: syvai/emotion-reasoning-1b
datasets:
- path: syvai/emotion-reasoning
type: chat_template
dataset_prepared_path: last_run_prepared
val_set_size: 0.02
output_dir: ./outputs/out
sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true
wandb_project: reasoning-emotions
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 8
micro_batch_size: 2
num_epochs: 1
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 2e-5
bf16: auto
tf32: false
gradient_checkpointing: true
gradient_checkpointing_kwargs:
use_reentrant: false
resume_from_checkpoint:
logging_steps: 1
flash_attention: true
warmup_steps: 10
evals_per_epoch: 2
saves_per_epoch: 1
weight_decay: 0.0
special_tokens:
pad_token: <|end_of_text|>
```
</details><br>
# emotion-reasoning-1b
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 syvai/emotion-reasoning dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4510
## 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-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 1.0
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 2.4357 | 0.0047 | 1 | 2.4860 |
| 1.4295 | 0.5009 | 106 | 1.4510 |
### Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.1
- Tokenizers 0.21.1