metadata
license: apache-2.0
base_model: mistralai/Mistral-7B-Instruct-v0.2
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: Summary4500_M2_300steps_1e8rate_SFT
results: []
Summary4500_M2_300steps_1e8rate_SFT
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.1418
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: 1e-08
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- training_steps: 300
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.1335 | 0.0112 | 50 | 2.1446 |
| 2.1332 | 0.0224 | 100 | 2.1433 |
| 2.131 | 0.0336 | 150 | 2.1422 |
| 2.1309 | 0.0448 | 200 | 2.1409 |
| 2.1305 | 0.0559 | 250 | 2.1418 |
| 2.1304 | 0.0671 | 300 | 2.1418 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.0.0+cu117
- Datasets 2.20.0
- Tokenizers 0.19.1