|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: full2-lstm-3 |
|
|
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-3 |
|
|
|
|
|
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: 3.9703 |
|
|
|
|
|
## 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: 3 |
|
|
- 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 | |
|
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
|
| 4.7949 | 0.03 | 76320 | 4.7623 | |
|
|
| 4.5075 | 1.03 | 152640 | 4.4794 | |
|
|
| 4.3602 | 0.03 | 228960 | 4.3429 | |
|
|
| 4.2766 | 1.03 | 305280 | 4.2588 | |
|
|
| 4.2113 | 0.03 | 381600 | 4.2022 | |
|
|
| 4.1648 | 1.03 | 457920 | 4.1606 | |
|
|
| 4.1336 | 0.03 | 534240 | 4.1292 | |
|
|
| 4.1008 | 1.03 | 610560 | 4.1050 | |
|
|
| 4.0722 | 0.03 | 686880 | 4.0849 | |
|
|
| 4.0491 | 1.03 | 763200 | 4.0689 | |
|
|
| 4.0263 | 0.03 | 839520 | 4.0557 | |
|
|
| 4.0088 | 1.03 | 915840 | 4.0452 | |
|
|
| 3.9954 | 0.03 | 992160 | 4.0355 | |
|
|
| 3.9784 | 1.03 | 1068480 | 4.0274 | |
|
|
| 3.9641 | 0.03 | 1144800 | 4.0212 | |
|
|
| 3.9491 | 1.03 | 1221120 | 4.0152 | |
|
|
| 3.9347 | 0.03 | 1297440 | 4.0090 | |
|
|
| 3.9257 | 1.03 | 1373760 | 4.0047 | |
|
|
| 3.9144 | 0.03 | 1450080 | 4.0009 | |
|
|
| 3.9137 | 1.03 | 1526400 | 3.9975 | |
|
|
| 3.9061 | 0.03 | 1602720 | 3.9940 | |
|
|
| 3.9037 | 1.03 | 1679040 | 3.9917 | |
|
|
| 3.9045 | 0.03 | 1755360 | 3.9893 | |
|
|
| 3.8999 | 1.03 | 1831680 | 3.9873 | |
|
|
| 3.8897 | 0.03 | 1908000 | 3.9854 | |
|
|
| 3.8842 | 1.03 | 1984320 | 3.9832 | |
|
|
| 3.8789 | 0.03 | 2060640 | 3.9805 | |
|
|
| 3.8724 | 1.03 | 2136960 | 3.9793 | |
|
|
| 3.8717 | 0.03 | 2213280 | 3.9778 | |
|
|
| 3.8658 | 1.03 | 2289600 | 3.9768 | |
|
|
| 3.8594 | 0.03 | 2365920 | 3.9757 | |
|
|
| 3.8523 | 1.03 | 2442240 | 3.9751 | |
|
|
| 3.8455 | 0.03 | 2518560 | 3.9739 | |
|
|
| 3.8431 | 0.03 | 2594880 | 3.9734 | |
|
|
| 3.8368 | 0.03 | 2671200 | 3.9728 | |
|
|
| 3.8431 | 1.03 | 2747520 | 3.9721 | |
|
|
| 3.8423 | 0.03 | 2823840 | 3.9716 | |
|
|
| 3.8432 | 0.03 | 2900160 | 3.9712 | |
|
|
| 3.8477 | 1.03 | 2976480 | 3.9706 | |
|
|
| 3.8461 | 0.02 | 3052726 | 3.9703 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.3 |
|
|
- Pytorch 2.0.1 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
