metadata
license: apache-2.0
base_model: mistralai/Mistral-7B-Instruct-v0.1
tags:
- generated_from_trainer
model-index:
- name: SequentialLearner
results: []
SequentialLearner
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.1 on an 100K Sequential Dataset with Meta Hierachal Learning It achieves the following results on the evaluation set:
- Loss: 0.7433
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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.5
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.97 | 25 | 0.7822 |
| No log | 1.98 | 51 | 0.6128 |
| No log | 2.99 | 77 | 0.6115 |
| No log | 4.0 | 103 | 0.6793 |
| No log | 4.85 | 125 | 0.7433 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0