eurollm-1.7b-instruct-aurora-open-2511-posttrain
This model is a fine-tuned version of /nfs/datastore0/pawelc/models/hf/eurollm-1.7b-instruct-aurora-open-2511-pretrain/iter_0143051 on the aurora_sft_ndla_train dataset. It achieves the following results on the evaluation set:
- Loss: 1.5664
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
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.2076 | 0.6015 | 20000 | 1.7133 |
| 0.9407 | 1.2029 | 40000 | 1.6131 |
| 1.3593 | 1.8044 | 60000 | 1.5805 |
| 1.2963 | 2.4059 | 80000 | 1.5697 |
| 1.3385 | 3.0073 | 100000 | 1.5666 |
| 1.787 | 3.6088 | 120000 | 1.5663 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.6.0+cu124
- Datasets 4.0.0
- Tokenizers 0.22.1
- Downloads last month
- 261