llama3_darulm_20_05_24_part1-2_128000_bpe_part1_lr1e4_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: 2.4358
- Accuracy: 0.5110
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 |
---|---|---|---|---|
2.8374 | 0.1 | 2000 | 2.5858 | 0.4936 |
2.7597 | 0.2 | 4000 | 2.5110 | 0.5012 |
2.7019 | 0.3 | 6000 | 2.4783 | 0.5051 |
2.6726 | 0.4 | 8000 | 2.4600 | 0.5075 |
2.6652 | 0.51 | 10000 | 2.4475 | 0.5090 |
2.6681 | 0.61 | 12000 | 2.4403 | 0.5102 |
2.6389 | 0.71 | 14000 | 2.4372 | 0.5108 |
2.6703 | 0.81 | 16000 | 2.4361 | 0.5109 |
2.6699 | 0.91 | 18000 | 2.4359 | 0.5109 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0a0+6ddf5cf85e.nv24.04
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 6
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.
Model tree for RefalMachine/llama3_darulm_20_05_24_part1-2_128000_bpe_part1_lr1e4_bs256
Finetuned
this model