metadata
base_model: HachiML/Mists-7B-v01-simple-projector-trained
license: apache-2.0
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: Mists-7B-v01-simpleQA
results: []
Mists-7B-v01-simpleQA
This model is a fine-tuned version of HachiML/Mists-7B-v01-simple-projector-trained on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0972
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: 128
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 1
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.1811 | 0.0888 | 50 | 5.1410 |
1.2662 | 0.1776 | 100 | 4.0209 |
0.5676 | 0.2664 | 150 | 3.6247 |
0.6122 | 0.3552 | 200 | 2.5723 |
0.3855 | 0.4440 | 250 | 1.8618 |
0.5471 | 0.5329 | 300 | 1.5969 |
0.5238 | 0.6217 | 350 | 0.9045 |
0.3799 | 0.7105 | 400 | 0.5475 |
0.2406 | 0.7993 | 450 | 0.1614 |
0.1381 | 0.8881 | 500 | 0.1055 |
0.0992 | 0.9769 | 550 | 0.0972 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.0.1
- Datasets 2.20.0
- Tokenizers 0.19.1