llama3_darulm_20_05_24_part1-2_128000_bpe_part1_lr5e5_bs256
This model is a fine-tuned version of RefalMachine/llama3_darulm_20_05_24_part1-2_128000_bpe_mean_init_03_07_24 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.6344
- Accuracy: 0.4925
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 |
---|---|---|---|---|
3.088 | 0.1 | 2000 | 2.8078 | 0.4755 |
2.9724 | 0.2 | 4000 | 2.7032 | 0.4851 |
2.9099 | 0.3 | 6000 | 2.6654 | 0.4888 |
2.8772 | 0.4 | 8000 | 2.6489 | 0.4908 |
2.8782 | 0.51 | 10000 | 2.6404 | 0.4919 |
2.8857 | 0.61 | 12000 | 2.6365 | 0.4922 |
2.8539 | 0.71 | 14000 | 2.6349 | 0.4925 |
2.8931 | 0.81 | 16000 | 2.6344 | 0.4925 |
2.8953 | 0.91 | 18000 | 2.6344 | 0.4926 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0a0+6ddf5cf85e.nv24.04
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 1
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.