73 lines
1.9 KiB
Markdown
73 lines
1.9 KiB
Markdown
|
---
|
||
|
|
library_name: transformers
|
||
|
|
tags:
|
||
|
|
- generated_from_trainer
|
||
|
|
model-index:
|
||
|
|
- name: slm-125m-tutor
|
||
|
|
results: []
|
||
|
|
---
|
||
|
|
|
||
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
||
|
|
should probably proofread and complete it, then remove this comment. -->
|
||
|
|
|
||
|
|
# slm-125m-tutor
|
||
|
|
|
||
|
|
This model was trained from scratch on an unknown dataset.
|
||
|
|
It achieves the following results on the evaluation set:
|
||
|
|
- Loss: 1.0573
|
||
|
|
|
||
|
|
## 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: 3e-05
|
||
|
|
- train_batch_size: 16
|
||
|
|
- eval_batch_size: 16
|
||
|
|
- seed: 42
|
||
|
|
- distributed_type: multi-GPU
|
||
|
|
- num_devices: 2
|
||
|
|
- gradient_accumulation_steps: 2
|
||
|
|
- total_train_batch_size: 64
|
||
|
|
- total_eval_batch_size: 32
|
||
|
|
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
||
|
|
- lr_scheduler_type: cosine
|
||
|
|
- lr_scheduler_warmup_steps: 0.03
|
||
|
|
- num_epochs: 3
|
||
|
|
- mixed_precision_training: Native AMP
|
||
|
|
|
||
|
|
### Training results
|
||
|
|
|
||
|
|
| Training Loss | Epoch | Step | Validation Loss |
|
||
|
|
|:-------------:|:------:|:----:|:---------------:|
|
||
|
|
| 1.3378 | 0.2863 | 500 | 1.2903 |
|
||
|
|
| 1.2281 | 0.5726 | 1000 | 1.1914 |
|
||
|
|
| 1.1361 | 0.8589 | 1500 | 1.1385 |
|
||
|
|
| 0.9816 | 1.1449 | 2000 | 1.1079 |
|
||
|
|
| 0.9342 | 1.4311 | 2500 | 1.0880 |
|
||
|
|
| 0.9271 | 1.7174 | 3000 | 1.0697 |
|
||
|
|
| 0.9189 | 2.0034 | 3500 | 1.0578 |
|
||
|
|
| 0.7955 | 2.2897 | 4000 | 1.0619 |
|
||
|
|
| 0.8140 | 2.5760 | 4500 | 1.0589 |
|
||
|
|
| 0.8316 | 2.8623 | 5000 | 1.0573 |
|
||
|
|
|
||
|
|
|
||
|
|
### Framework versions
|
||
|
|
|
||
|
|
- Transformers 5.0.0
|
||
|
|
- Pytorch 2.10.0+cu128
|
||
|
|
- Datasets 4.8.3
|
||
|
|
- Tokenizers 0.22.2
|