metadata
library_name: transformers
license: apache-2.0
base_model: mistralai/Mistral-7B-Instruct-v0.2
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: IE_M2_650steps_1e8rate_SFT
results: []
IE_M2_650steps_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: 1.9102
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: 2
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- training_steps: 650
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.8842 | 0.4 | 50 | 1.9129 |
| 1.9556 | 0.8 | 100 | 1.9129 |
| 2.0185 | 1.2 | 150 | 1.9121 |
| 1.9349 | 1.6 | 200 | 1.9112 |
| 1.975 | 2.0 | 250 | 1.9107 |
| 2.0088 | 2.4 | 300 | 1.9104 |
| 2.0245 | 2.8 | 350 | 1.9106 |
| 1.911 | 3.2 | 400 | 1.9101 |
| 2.0222 | 3.6 | 450 | 1.9105 |
| 1.9025 | 4.0 | 500 | 1.9104 |
| 2.0573 | 4.4 | 550 | 1.9102 |
| 1.9739 | 4.8 | 600 | 1.9102 |
| 2.001 | 5.2 | 650 | 1.9102 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.0.0+cu117
- Datasets 3.0.0
- Tokenizers 0.19.1