mistral_extended_darulm_20_05_24_part1-2_32000_bpe_part1-2_lr1e4_bs256
This model is a fine-tuned version of RefalMachine/mistral_extended_darulm_20_05_24_part1-2_32000_bpe_mean_init_03_07_24 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.0916
- Accuracy: 0.5569
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: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 64
- total_train_batch_size: 256
- total_eval_batch_size: 256
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 1.0
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
2.4222 | 0.09 | 2000 | 2.2032 | 0.5413 |
2.3728 | 0.17 | 4000 | 2.1733 | 0.5444 |
2.3632 | 0.26 | 6000 | 2.1551 | 0.5472 |
2.3496 | 0.34 | 8000 | 2.1404 | 0.5490 |
2.3335 | 0.43 | 10000 | 2.1259 | 0.5512 |
2.3195 | 0.51 | 12000 | 2.1136 | 0.5532 |
2.2879 | 0.6 | 14000 | 2.1031 | 0.5550 |
2.2873 | 0.69 | 16000 | 2.0966 | 0.5560 |
2.2828 | 0.77 | 18000 | 2.0930 | 0.5566 |
2.288 | 0.86 | 20000 | 2.0918 | 0.5568 |
2.2916 | 0.94 | 22000 | 2.0917 | 0.5569 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0a0+6ddf5cf85e.nv24.04
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 2
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.