metadata
base_model: cotarc0/COT2output-1B
library_name: peft
license: llama3.2
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: 007bbfb7_1B_ttt
results: []
007bbfb7_1B_ttt
This model is a fine-tuned version of cotarc0/COT2output-1B on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0437
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: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.0704 | 1.0 | 3 | 0.0594 |
| 0.0379 | 2.0 | 6 | 0.0469 |
| 0.0248 | 3.0 | 9 | 0.0437 |
Framework versions
- PEFT 0.13.2
- Transformers 4.45.0.dev0
- Pytorch 2.4.0+cu121
- Datasets 3.5.0
- Tokenizers 0.19.1