mistral_darulm_20_05_24_part1-2_32000_bpe_part1_lr1e4_bs256
This model is a fine-tuned version of RefalMachine/mistral_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: 2.0608
- Accuracy: 0.5629
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: 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 |
---|---|---|---|---|
2.4 | 0.09 | 2000 | 2.1902 | 0.5446 |
2.4193 | 0.18 | 4000 | 2.1591 | 0.5483 |
2.3273 | 0.26 | 6000 | 2.1383 | 0.5510 |
2.3505 | 0.35 | 8000 | 2.1187 | 0.5540 |
2.3378 | 0.44 | 10000 | 2.1016 | 0.5565 |
2.3075 | 0.53 | 12000 | 2.0866 | 0.5586 |
2.2635 | 0.62 | 14000 | 2.0736 | 0.5607 |
2.2902 | 0.71 | 16000 | 2.0658 | 0.5621 |
2.2709 | 0.79 | 18000 | 2.0619 | 0.5628 |
2.2601 | 0.88 | 20000 | 2.0609 | 0.5629 |
2.2622 | 0.97 | 22000 | 2.0608 | 0.5631 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0a0+6ddf5cf85e.nv24.04
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 3
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.