metadata
library_name: transformers
license: apache-2.0
base_model: BEE-spoke-data/tFINE-900m-e16-d32-flan
tags:
- generated_from_trainer
model-index:
- name: tFINE-900m-e16-d32-flan-infinity-instruct-7m-T2T_en-1024
results: []
tFINE-900m-e16-d32-flan-infinity-instruct-7m-T2T_en-1024
This model is a fine-tuned version of BEE-spoke-data/tFINE-900m-e16-d32-flan on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.3589
- Num Input Tokens Seen: 785148304
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: 17868
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- total_eval_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 1.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Input Tokens Seen |
|---|---|---|---|---|
| 1.6487 | 0.0969 | 2000 | 1.7665 | 78885660 |
| 1.4957 | 0.1938 | 4000 | 1.6085 | 157778628 |
| 1.4224 | 0.2907 | 6000 | 1.5239 | 236103764 |
| 1.3764 | 0.3877 | 8000 | 1.4715 | 314442716 |
| 1.3553 | 0.4846 | 10000 | 1.4268 | 392909044 |
| 1.3308 | 0.5815 | 12000 | 1.4009 | 471314876 |
| 1.2622 | 0.6784 | 14000 | 1.3831 | 550234352 |
| 1.2585 | 0.7753 | 16000 | 1.3684 | 628560668 |
| 1.2477 | 0.8722 | 18000 | 1.3608 | 707047904 |
| 1.216 | 0.9691 | 20000 | 1.3589 | 785148304 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1