mistral_extended_darulm_20_05_24_part1-2_32000_bpe_part1_lr5e5_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: 2.1293
- Accuracy: 0.5523
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: 5e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 32
- total_train_batch_size: 128
- total_eval_batch_size: 128
- 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 |
---|---|---|---|---|
2.4766 | 0.09 | 2000 | 2.2273 | 0.5390 |
2.4272 | 0.18 | 4000 | 2.1898 | 0.5437 |
2.3999 | 0.27 | 6000 | 2.1705 | 0.5460 |
2.3854 | 0.36 | 8000 | 2.1576 | 0.5475 |
2.3496 | 0.45 | 10000 | 2.1462 | 0.5496 |
2.333 | 0.54 | 12000 | 2.1386 | 0.5508 |
2.3897 | 0.63 | 14000 | 2.1334 | 0.5516 |
2.3475 | 0.73 | 16000 | 2.1305 | 0.5520 |
2.3543 | 0.82 | 18000 | 2.1295 | 0.5522 |
2.3509 | 0.91 | 20000 | 2.1293 | 0.5524 |
2.3257 | 1.0 | 22000 | 2.1293 | 0.5523 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0a0+6ddf5cf85e.nv24.04
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 4
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.