update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
model-index:
|
| 5 |
+
- name: DS-Chatbox-gpt2-vietnamese-V3
|
| 6 |
+
results: []
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 10 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 11 |
+
|
| 12 |
+
# DS-Chatbox-gpt2-vietnamese-V3
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [NlpHUST/gpt2-vietnamese](https://huggingface.co/NlpHUST/gpt2-vietnamese) on the None dataset.
|
| 15 |
+
It achieves the following results on the evaluation set:
|
| 16 |
+
- Loss: 2.2578
|
| 17 |
+
|
| 18 |
+
## Model description
|
| 19 |
+
|
| 20 |
+
More information needed
|
| 21 |
+
|
| 22 |
+
## Intended uses & limitations
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Training and evaluation data
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training procedure
|
| 31 |
+
|
| 32 |
+
### Training hyperparameters
|
| 33 |
+
|
| 34 |
+
The following hyperparameters were used during training:
|
| 35 |
+
- learning_rate: 0.0015
|
| 36 |
+
- train_batch_size: 8
|
| 37 |
+
- eval_batch_size: 8
|
| 38 |
+
- seed: 42
|
| 39 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 40 |
+
- lr_scheduler_type: cosine
|
| 41 |
+
- lr_scheduler_warmup_steps: 1000
|
| 42 |
+
- num_epochs: 2
|
| 43 |
+
|
| 44 |
+
### Training results
|
| 45 |
+
|
| 46 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 47 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
| 48 |
+
| 3.1989 | 0.06 | 1000 | 3.0855 |
|
| 49 |
+
| 2.9934 | 0.12 | 2000 | 2.9327 |
|
| 50 |
+
| 2.8951 | 0.18 | 3000 | 2.8807 |
|
| 51 |
+
| 2.8375 | 0.23 | 4000 | 2.8522 |
|
| 52 |
+
| 2.8234 | 0.29 | 5000 | 2.8395 |
|
| 53 |
+
| 2.8097 | 0.35 | 6000 | 2.8198 |
|
| 54 |
+
| 2.804 | 0.41 | 7000 | 2.8119 |
|
| 55 |
+
| 2.8038 | 0.47 | 8000 | 2.8194 |
|
| 56 |
+
| 2.8005 | 0.53 | 9000 | 2.8135 |
|
| 57 |
+
| 2.7875 | 0.59 | 10000 | 2.8138 |
|
| 58 |
+
| 2.7649 | 0.64 | 11000 | 2.8101 |
|
| 59 |
+
| 2.7662 | 0.7 | 12000 | 2.7934 |
|
| 60 |
+
| 2.7563 | 0.76 | 13000 | 2.7802 |
|
| 61 |
+
| 2.7366 | 0.82 | 14000 | 2.7552 |
|
| 62 |
+
| 2.707 | 0.88 | 15000 | 2.7383 |
|
| 63 |
+
| 2.6932 | 0.94 | 16000 | 2.7115 |
|
| 64 |
+
| 2.6671 | 1.0 | 17000 | 2.6839 |
|
| 65 |
+
| 2.5019 | 1.05 | 18000 | 2.6664 |
|
| 66 |
+
| 2.4742 | 1.11 | 19000 | 2.6425 |
|
| 67 |
+
| 2.4658 | 1.17 | 20000 | 2.5986 |
|
| 68 |
+
| 2.4333 | 1.23 | 21000 | 2.5585 |
|
| 69 |
+
| 2.4084 | 1.29 | 22000 | 2.5246 |
|
| 70 |
+
| 2.3733 | 1.35 | 23000 | 2.4904 |
|
| 71 |
+
| 2.3384 | 1.41 | 24000 | 2.4525 |
|
| 72 |
+
| 2.2983 | 1.46 | 25000 | 2.4152 |
|
| 73 |
+
| 2.2626 | 1.52 | 26000 | 2.3866 |
|
| 74 |
+
| 2.2241 | 1.58 | 27000 | 2.3538 |
|
| 75 |
+
| 2.2054 | 1.64 | 28000 | 2.3278 |
|
| 76 |
+
| 2.1699 | 1.7 | 29000 | 2.3026 |
|
| 77 |
+
| 2.1467 | 1.76 | 30000 | 2.2826 |
|
| 78 |
+
| 2.1362 | 1.82 | 31000 | 2.2706 |
|
| 79 |
+
| 2.1312 | 1.87 | 32000 | 2.2625 |
|
| 80 |
+
| 2.1158 | 1.93 | 33000 | 2.2587 |
|
| 81 |
+
| 2.1291 | 1.99 | 34000 | 2.2578 |
|
| 82 |
+
|
| 83 |
+
|
| 84 |
+
### Framework versions
|
| 85 |
+
|
| 86 |
+
- Transformers 4.30.1
|
| 87 |
+
- Pytorch 2.0.0
|
| 88 |
+
- Datasets 2.1.0
|
| 89 |
+
- Tokenizers 0.13.3
|