metadata
library_name: transformers
language:
- en
license: apache-2.0
base_model: google/flan-t5-xl
tags:
- generated_from_trainer
model-index:
- name: flan-t5-xl-summary-map-reduce-1024
results: []
flan-t5-xl-summary-map-reduce-1024
This model is a fine-tuned version of google/flan-t5-xl on the pszemraj/summary-map-reduce dataset. It achieves the following results on the evaluation set:
- Loss: 0.6039
- Num Input Tokens Seen: 7138765
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: 8e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 17868
- gradient_accumulation_steps: 32
- total_train_batch_size: 64
- optimizer: Use OptimizerNames.PAGED_ADAMW with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 2.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Input Tokens Seen |
|---|---|---|---|---|
| 0.8172 | 0.3851 | 100 | 0.6644 | 1364870 |
| 0.7664 | 0.7702 | 200 | 0.6271 | 2744502 |
| 0.6584 | 1.1552 | 300 | 0.6146 | 4137699 |
| 0.6348 | 1.5403 | 400 | 0.6049 | 5518719 |
| 0.6372 | 1.9254 | 500 | 0.6038 | 6895203 |
Framework versions
- Transformers 4.46.0.dev0
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.2