metadata
license: apache-2.0
tags:
- generated_from_trainer
base_model: JackFram/llama-68m
model-index:
- name: llama-68m-oasst_top1_2023-08-25
results: []
llama-68m-oasst_top1_2023-08-25
This model is a fine-tuned version of JackFram/llama-68m on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.1780
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.5174 | 0.9922 | 95 | 3.3601 |
| 3.2821 | 1.9948 | 191 | 3.2136 |
| 3.2174 | 2.9765 | 285 | 3.1780 |
Framework versions
- Transformers 4.42.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1