v1_600_STEPS_1e7_SFT_SFT
This model is a fine-tuned version of mosaicml/mpt-7b-instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6305
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: 1e-07
- train_batch_size: 2
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- training_steps: 600
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.8395 | 0.05 | 50 | 1.8528 |
| 1.8225 | 0.1 | 100 | 1.8184 |
| 1.7699 | 0.15 | 150 | 1.7650 |
| 1.7281 | 0.2 | 200 | 1.7192 |
| 1.6882 | 0.24 | 250 | 1.6831 |
| 1.6643 | 0.29 | 300 | 1.6589 |
| 1.641 | 0.34 | 350 | 1.6433 |
| 1.6306 | 0.39 | 400 | 1.6349 |
| 1.6145 | 0.44 | 450 | 1.6309 |
| 1.6315 | 0.49 | 500 | 1.6304 |
| 1.6192 | 0.54 | 550 | 1.6305 |
| 1.6226 | 0.59 | 600 | 1.6305 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.0.0+cu117
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 3
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/mpt_600_STEPS_1e7_SFT_SFT
Base model
mosaicml/mpt-7b-instruct