18c5fa0c-fe09-46ec-ba5d-7f2ede9adea9
This model is a fine-tuned version of migtissera/Tess-v2.5-Phi-3-medium-128k-14B on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.3083
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: 0.000208
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 50
- training_steps: 394
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.0025 | 1 | 7.0019 |
| 8.4818 | 0.1269 | 50 | 6.9127 |
| 8.8266 | 0.2538 | 100 | 4.1633 |
| 8.6808 | 0.3807 | 150 | 4.3894 |
| 7.9309 | 0.5076 | 200 | 3.6368 |
| 7.147 | 0.6345 | 250 | 3.0470 |
| 7.1612 | 0.7614 | 300 | 2.3794 |
| 7.3849 | 0.8883 | 350 | 2.3083 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1
- Downloads last month
- 0
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
HF Inference API was unable to determine this model’s pipeline type.
Model tree for lesso/18c5fa0c-fe09-46ec-ba5d-7f2ede9adea9
Base model
microsoft/Phi-3-medium-128k-instruct