|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: full2-lstm-2 |
|
|
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. --> |
|
|
|
|
|
# full2-lstm-2 |
|
|
|
|
|
This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 3.9738 |
|
|
|
|
|
## 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: 32 |
|
|
- eval_batch_size: 32 |
|
|
- seed: 2 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- training_steps: 3052726 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
|
| 4.7958 | 0.03 | 76320 | 4.7656 | |
|
|
| 4.5105 | 1.03 | 152640 | 4.4827 | |
|
|
| 4.3654 | 0.03 | 228960 | 4.3482 | |
|
|
| 4.2801 | 1.03 | 305280 | 4.2650 | |
|
|
| 4.2161 | 0.03 | 381600 | 4.2080 | |
|
|
| 4.1711 | 1.03 | 457920 | 4.1662 | |
|
|
| 4.1373 | 0.03 | 534240 | 4.1357 | |
|
|
| 4.106 | 1.03 | 610560 | 4.1113 | |
|
|
| 4.0755 | 0.03 | 686880 | 4.0909 | |
|
|
| 4.0519 | 1.03 | 763200 | 4.0743 | |
|
|
| 4.0312 | 0.03 | 839520 | 4.0611 | |
|
|
| 4.0136 | 1.03 | 915840 | 4.0505 | |
|
|
| 4.0004 | 0.03 | 992160 | 4.0414 | |
|
|
| 3.9837 | 1.03 | 1068480 | 4.0328 | |
|
|
| 3.9692 | 0.03 | 1144800 | 4.0253 | |
|
|
| 3.9547 | 1.03 | 1221120 | 4.0192 | |
|
|
| 3.9407 | 0.03 | 1297440 | 4.0140 | |
|
|
| 3.9307 | 1.03 | 1373760 | 4.0091 | |
|
|
| 3.9213 | 0.03 | 1450080 | 4.0055 | |
|
|
| 3.9184 | 1.03 | 1526400 | 4.0017 | |
|
|
| 3.9134 | 0.03 | 1602720 | 3.9992 | |
|
|
| 3.9108 | 1.03 | 1679040 | 3.9962 | |
|
|
| 3.9086 | 0.03 | 1755360 | 3.9935 | |
|
|
| 3.9036 | 1.03 | 1831680 | 3.9910 | |
|
|
| 3.8942 | 0.03 | 1908000 | 3.9890 | |
|
|
| 3.8892 | 1.03 | 1984320 | 3.9867 | |
|
|
| 3.8825 | 0.03 | 2060640 | 3.9852 | |
|
|
| 3.8768 | 1.03 | 2136960 | 3.9835 | |
|
|
| 3.8758 | 0.03 | 2213280 | 3.9815 | |
|
|
| 3.8693 | 1.03 | 2289600 | 3.9807 | |
|
|
| 3.8621 | 0.03 | 2365920 | 3.9796 | |
|
|
| 3.8589 | 0.03 | 2442240 | 3.9788 | |
|
|
| 3.8513 | 0.03 | 2518560 | 3.9778 | |
|
|
| 3.8487 | 1.03 | 2594880 | 3.9770 | |
|
|
| 3.8424 | 0.03 | 2671200 | 3.9763 | |
|
|
| 3.8467 | 1.03 | 2747520 | 3.9756 | |
|
|
| 3.8475 | 0.03 | 2823840 | 3.9750 | |
|
|
| 3.8449 | 1.03 | 2900160 | 3.9745 | |
|
|
| 3.8521 | 0.03 | 2976480 | 3.9741 | |
|
|
| 3.8498 | 0.02 | 3052726 | 3.9738 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.3 |
|
|
- Pytorch 2.0.1 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
