metadata
license: apache-2.0
base_model: allenai/longformer-base-4096
tags:
- generated_from_trainer
model-index:
- name: longformer_new_tokens_doscientosmil
results: []
longformer_new_tokens_doscientosmil
This model is a fine-tuned version of allenai/longformer-base-4096 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.4513
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: 2e-05
- train_batch_size: 2
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 120
- total_train_batch_size: 240
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1500
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.4058 | 0.16 | 121 | 3.3450 |
| 3.4909 | 0.32 | 242 | 3.0219 |
| 3.136 | 0.48 | 363 | 2.8524 |
| 2.9192 | 0.65 | 484 | 2.7127 |
| 2.8107 | 0.81 | 605 | 2.5899 |
| 2.6765 | 0.97 | 726 | 2.4513 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1