metadata
base_model: mistralai/Mistral-7B-Instruct-v0.3
datasets:
- GaetanMichelet/chat-60_ft_task-1
library_name: peft
license: apache-2.0
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
model-index:
- name: Mistral-7B_task-1_60-samples_config-2_full
results: []
Mistral-7B_task-1_60-samples_config-2_full
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.3 on the GaetanMichelet/chat-60_ft_task-1 dataset. It achieves the following results on the evaluation set:
- Loss: 0.9316
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: 0.0001
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 16
- total_train_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: 50
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
2.1677 | 0.6957 | 2 | 1.9772 |
2.0588 | 1.7391 | 5 | 1.7098 |
1.6144 | 2.7826 | 8 | 1.4226 |
1.3861 | 3.8261 | 11 | 1.1334 |
1.0181 | 4.8696 | 14 | 0.9961 |
0.9301 | 5.9130 | 17 | 0.9633 |
0.8066 | 6.9565 | 20 | 0.9348 |
0.7473 | 8.0 | 23 | 0.9316 |
0.6909 | 8.6957 | 25 | 0.9585 |
0.5525 | 9.7391 | 28 | 0.9743 |
0.49 | 10.7826 | 31 | 1.0671 |
0.3604 | 11.8261 | 34 | 1.1000 |
0.3096 | 12.8696 | 37 | 1.2756 |
0.2231 | 13.9130 | 40 | 1.3029 |
0.1846 | 14.9565 | 43 | 1.4381 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.0
- Pytorch 2.1.2+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1