Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: mit
|
| 4 |
+
base_model: microsoft/DialoGPT-small
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
model-index:
|
| 10 |
+
- name: dialochess-v3
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# dialochess-v3
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [microsoft/DialoGPT-small](https://huggingface.co/microsoft/DialoGPT-small) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.8843
|
| 22 |
+
- Accuracy: 0.0002
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 5e-05
|
| 42 |
+
- train_batch_size: 8
|
| 43 |
+
- eval_batch_size: 8
|
| 44 |
+
- seed: 42
|
| 45 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 46 |
+
- lr_scheduler_type: cosine
|
| 47 |
+
- num_epochs: 3
|
| 48 |
+
- mixed_precision_training: Native AMP
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 53 |
+
|:-------------:|:------:|:----:|:---------------:|:--------:|
|
| 54 |
+
| 1.3128 | 0.1616 | 200 | 1.1914 | 0.0002 |
|
| 55 |
+
| 1.1935 | 0.3231 | 400 | 1.0974 | 0.0002 |
|
| 56 |
+
| 1.1181 | 0.4847 | 600 | 1.0419 | 0.0 |
|
| 57 |
+
| 1.0778 | 0.6462 | 800 | 1.0080 | 0.0 |
|
| 58 |
+
| 1.0426 | 0.8078 | 1000 | 0.9828 | 0.0002 |
|
| 59 |
+
| 1.0185 | 0.9693 | 1200 | 0.9612 | 0.0002 |
|
| 60 |
+
| 1.0075 | 1.1309 | 1400 | 0.9458 | 0.0001 |
|
| 61 |
+
| 0.9765 | 1.2924 | 1600 | 0.9348 | 0.0002 |
|
| 62 |
+
| 0.9806 | 1.4540 | 1800 | 0.9248 | 0.0001 |
|
| 63 |
+
| 0.9542 | 1.6155 | 2000 | 0.9132 | 0.0002 |
|
| 64 |
+
| 0.9684 | 1.7771 | 2200 | 0.9059 | 0.0002 |
|
| 65 |
+
| 0.9525 | 1.9386 | 2400 | 0.9015 | 0.0002 |
|
| 66 |
+
| 0.9396 | 2.1002 | 2600 | 0.8960 | 0.0002 |
|
| 67 |
+
| 0.9342 | 2.2617 | 2800 | 0.8896 | 0.0002 |
|
| 68 |
+
| 0.9327 | 2.4233 | 3000 | 0.8874 | 0.0002 |
|
| 69 |
+
| 0.9344 | 2.5848 | 3200 | 0.8848 | 0.0002 |
|
| 70 |
+
| 0.9272 | 2.7464 | 3400 | 0.8848 | 0.0002 |
|
| 71 |
+
| 0.9288 | 2.9079 | 3600 | 0.8843 | 0.0002 |
|
| 72 |
+
|
| 73 |
+
|
| 74 |
+
### Framework versions
|
| 75 |
+
|
| 76 |
+
- Transformers 4.57.2
|
| 77 |
+
- Pytorch 2.9.0+cu126
|
| 78 |
+
- Datasets 4.0.0
|
| 79 |
+
- Tokenizers 0.22.1
|