metadata
base_model: cosmin/falcon-7b-sharded-bf16
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: falcon-7b-sharded
results: []
falcon-7b-sharded
This model is a fine-tuned version of cosmin/falcon-7b-sharded-bf16 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.3060
- F1: 0.0027
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: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 500
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 3.0776 | 1.0 | 55 | 2.8379 | 0.0027 |
| 2.3055 | 1.99 | 110 | 2.5165 | 0.0220 |
| 2.3104 | 2.99 | 165 | 2.4452 | 0.0027 |
| 2.1221 | 4.0 | 221 | 2.3845 | 0.0027 |
| 2.2114 | 5.0 | 276 | 2.3660 | 0.0151 |
| 2.0432 | 5.99 | 331 | 2.3325 | 0.0124 |
| 2.0811 | 6.99 | 386 | 2.3185 | 0.0027 |
| 2.0372 | 8.0 | 442 | 2.3066 | 0.0027 |
| 2.019 | 9.0 | 497 | 2.3058 | 0.0027 |
| 2.0906 | 9.05 | 500 | 2.3060 | 0.0027 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1