|
--- |
|
license: apache-2.0 |
|
base_model: google/flan-t5-base |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- xlsum |
|
model-index: |
|
- name: flan-t5-base-xlsum |
|
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. --> |
|
|
|
# flan-t5-base-xlsum |
|
|
|
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the xlsum dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3988 |
|
|
|
## 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: 6 |
|
- eval_batch_size: 12 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 200 |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
| 17.0416 | 0.09 | 200 | 0.4680 | |
|
| 0.495 | 0.18 | 400 | 0.4080 | |
|
| 0.4721 | 0.28 | 600 | 0.4051 | |
|
| 0.4677 | 0.37 | 800 | 0.4048 | |
|
| 0.4691 | 0.46 | 1000 | 0.4035 | |
|
| 0.4667 | 0.55 | 1200 | 0.4025 | |
|
| 0.464 | 0.65 | 1400 | 0.4015 | |
|
| 0.4575 | 0.74 | 1600 | 0.4004 | |
|
| 0.4598 | 0.83 | 1800 | 0.4003 | |
|
| 0.4602 | 0.92 | 2000 | 0.4004 | |
|
| 0.4556 | 1.02 | 2200 | 0.3992 | |
|
| 0.4335 | 1.11 | 2400 | 0.3992 | |
|
| 0.4347 | 1.2 | 2600 | 0.3992 | |
|
| 0.4421 | 1.29 | 2800 | 0.3999 | |
|
| 0.4318 | 1.39 | 3000 | 0.3988 | |
|
| 0.4425 | 1.48 | 3200 | 0.3981 | |
|
| 0.4428 | 1.57 | 3400 | 0.3988 | |
|
| 0.4345 | 1.66 | 3600 | 0.3980 | |
|
| 0.4266 | 1.76 | 3800 | 0.3979 | |
|
| 0.4245 | 1.85 | 4000 | 0.3982 | |
|
| 0.4215 | 1.94 | 4200 | 0.3967 | |
|
| 0.4285 | 2.03 | 4400 | 0.3977 | |
|
| 0.4082 | 2.13 | 4600 | 0.3981 | |
|
| 0.4049 | 2.22 | 4800 | 0.3980 | |
|
| 0.4139 | 2.31 | 5000 | 0.3975 | |
|
| 0.4008 | 2.4 | 5200 | 0.3983 | |
|
| 0.4073 | 2.5 | 5400 | 0.3980 | |
|
| 0.4214 | 2.59 | 5600 | 0.3979 | |
|
| 0.411 | 2.68 | 5800 | 0.3983 | |
|
| 0.4173 | 2.77 | 6000 | 0.3971 | |
|
| 0.4098 | 2.87 | 6200 | 0.3970 | |
|
| 0.4267 | 2.96 | 6400 | 0.3968 | |
|
| 0.3958 | 3.05 | 6600 | 0.3976 | |
|
| 0.3959 | 3.14 | 6800 | 0.3984 | |
|
| 0.4049 | 3.24 | 7000 | 0.3978 | |
|
| 0.3993 | 3.33 | 7200 | 0.3980 | |
|
| 0.3971 | 3.42 | 7400 | 0.3983 | |
|
| 0.4032 | 3.51 | 7600 | 0.3987 | |
|
| 0.391 | 3.61 | 7800 | 0.3987 | |
|
| 0.3988 | 3.7 | 8000 | 0.3990 | |
|
| 0.3912 | 3.79 | 8200 | 0.3984 | |
|
| 0.3958 | 3.88 | 8400 | 0.3982 | |
|
| 0.396 | 3.98 | 8600 | 0.3979 | |
|
| 0.3926 | 4.07 | 8800 | 0.3988 | |
|
| 0.3913 | 4.16 | 9000 | 0.3988 | |
|
| 0.3915 | 4.25 | 9200 | 0.3985 | |
|
| 0.3885 | 4.35 | 9400 | 0.3988 | |
|
| 0.3824 | 4.44 | 9600 | 0.3991 | |
|
| 0.3884 | 4.53 | 9800 | 0.3989 | |
|
| 0.3816 | 4.62 | 10000 | 0.3989 | |
|
| 0.4028 | 4.72 | 10200 | 0.3986 | |
|
| 0.3881 | 4.81 | 10400 | 0.3988 | |
|
| 0.3809 | 4.9 | 10600 | 0.3988 | |
|
| 0.3873 | 4.99 | 10800 | 0.3988 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.31.0 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.13.1 |
|
- Tokenizers 0.13.3 |
|
|
