350_STEPS_TEST_SFT
This model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3260
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: 1
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- training_steps: 350
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.4448 | 0.1 | 50 | 0.5649 |
| 0.5998 | 0.2 | 100 | 0.6260 |
| 0.5585 | 0.29 | 150 | 0.5314 |
| 0.3909 | 0.39 | 200 | 0.3844 |
| 0.3704 | 0.49 | 250 | 0.3523 |
| 0.3376 | 0.59 | 300 | 0.3305 |
| 0.3266 | 0.68 | 350 | 0.3260 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.0.0+cu117
- Datasets 2.17.0
- Tokenizers 0.15.2
- Downloads last month
- 4
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for tsavage68/chat_350STEPS_1e5_SFT
Base model
meta-llama/Llama-2-7b-chat-hf