|
--- |
|
license: apache-2.0 |
|
base_model: distilbert-base-uncased |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: empathy_model_apr3 |
|
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. --> |
|
|
|
# empathy_model_apr3 |
|
|
|
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0044 |
|
- Mse: 0.0044 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 3 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Mse | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:| |
|
| 0.0072 | 0.05 | 50 | 0.0045 | 0.0045 | |
|
| 0.0086 | 0.11 | 100 | 0.0109 | 0.0109 | |
|
| 0.0063 | 0.16 | 150 | 0.0045 | 0.0045 | |
|
| 0.0054 | 0.22 | 200 | 0.0051 | 0.0051 | |
|
| 0.0081 | 0.27 | 250 | 0.0060 | 0.0060 | |
|
| 0.0076 | 0.32 | 300 | 0.0046 | 0.0046 | |
|
| 0.0067 | 0.38 | 350 | 0.0047 | 0.0047 | |
|
| 0.0071 | 0.43 | 400 | 0.0045 | 0.0045 | |
|
| 0.006 | 0.48 | 450 | 0.0054 | 0.0054 | |
|
| 0.0064 | 0.54 | 500 | 0.0046 | 0.0046 | |
|
| 0.0069 | 0.59 | 550 | 0.0063 | 0.0063 | |
|
| 0.0044 | 0.65 | 600 | 0.0076 | 0.0076 | |
|
| 0.0069 | 0.7 | 650 | 0.0044 | 0.0044 | |
|
| 0.0041 | 0.75 | 700 | 0.0043 | 0.0043 | |
|
| 0.007 | 0.81 | 750 | 0.0044 | 0.0044 | |
|
| 0.0049 | 0.86 | 800 | 0.0045 | 0.0045 | |
|
| 0.0058 | 0.92 | 850 | 0.0055 | 0.0055 | |
|
| 0.0061 | 0.97 | 900 | 0.0045 | 0.0045 | |
|
| 0.004 | 1.02 | 950 | 0.0044 | 0.0044 | |
|
| 0.0064 | 1.08 | 1000 | 0.0049 | 0.0049 | |
|
| 0.0055 | 1.13 | 1050 | 0.0050 | 0.0050 | |
|
| 0.0052 | 1.19 | 1100 | 0.0043 | 0.0043 | |
|
| 0.0054 | 1.24 | 1150 | 0.0043 | 0.0043 | |
|
| 0.0066 | 1.29 | 1200 | 0.0048 | 0.0048 | |
|
| 0.0065 | 1.35 | 1250 | 0.0043 | 0.0043 | |
|
| 0.0056 | 1.4 | 1300 | 0.0045 | 0.0045 | |
|
| 0.0054 | 1.45 | 1350 | 0.0043 | 0.0043 | |
|
| 0.0067 | 1.51 | 1400 | 0.0044 | 0.0044 | |
|
| 0.0067 | 1.56 | 1450 | 0.0042 | 0.0042 | |
|
| 0.0044 | 1.62 | 1500 | 0.0043 | 0.0043 | |
|
| 0.0062 | 1.67 | 1550 | 0.0043 | 0.0043 | |
|
| 0.0057 | 1.72 | 1600 | 0.0043 | 0.0043 | |
|
| 0.0049 | 1.78 | 1650 | 0.0042 | 0.0042 | |
|
| 0.0059 | 1.83 | 1700 | 0.0045 | 0.0045 | |
|
| 0.0066 | 1.89 | 1750 | 0.0045 | 0.0045 | |
|
| 0.0045 | 1.94 | 1800 | 0.0051 | 0.0051 | |
|
| 0.0056 | 1.99 | 1850 | 0.0042 | 0.0042 | |
|
| 0.0042 | 2.05 | 1900 | 0.0045 | 0.0045 | |
|
| 0.0058 | 2.1 | 1950 | 0.0045 | 0.0045 | |
|
| 0.0045 | 2.16 | 2000 | 0.0045 | 0.0045 | |
|
| 0.0058 | 2.21 | 2050 | 0.0043 | 0.0043 | |
|
| 0.0055 | 2.26 | 2100 | 0.0049 | 0.0049 | |
|
| 0.0054 | 2.32 | 2150 | 0.0043 | 0.0043 | |
|
| 0.0046 | 2.37 | 2200 | 0.0044 | 0.0044 | |
|
| 0.0051 | 2.42 | 2250 | 0.0044 | 0.0044 | |
|
| 0.0057 | 2.48 | 2300 | 0.0044 | 0.0044 | |
|
| 0.0047 | 2.53 | 2350 | 0.0047 | 0.0047 | |
|
| 0.0054 | 2.59 | 2400 | 0.0044 | 0.0044 | |
|
| 0.0052 | 2.64 | 2450 | 0.0044 | 0.0044 | |
|
| 0.0043 | 2.69 | 2500 | 0.0046 | 0.0046 | |
|
| 0.0056 | 2.75 | 2550 | 0.0044 | 0.0044 | |
|
| 0.0039 | 2.8 | 2600 | 0.0043 | 0.0043 | |
|
| 0.0049 | 2.86 | 2650 | 0.0047 | 0.0047 | |
|
| 0.0042 | 2.91 | 2700 | 0.0046 | 0.0046 | |
|
| 0.0051 | 2.96 | 2750 | 0.0044 | 0.0044 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.3 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|