Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: lighteternal/gpt2-finetuned-greek
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: gpt2_custom_c_q_and_a_v3
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# gpt2_custom_c_q_and_a_v3
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [lighteternal/gpt2-finetuned-greek](https://huggingface.co/lighteternal/gpt2-finetuned-greek) on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.0066
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 5e-05
|
| 38 |
+
- train_batch_size: 16
|
| 39 |
+
- eval_batch_size: 8
|
| 40 |
+
- seed: 42
|
| 41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
+
- lr_scheduler_type: linear
|
| 43 |
+
- lr_scheduler_warmup_steps: 100
|
| 44 |
+
- num_epochs: 200
|
| 45 |
+
|
| 46 |
+
### Training results
|
| 47 |
+
|
| 48 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 49 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 50 |
+
| 2.3925 | 8.33 | 100 | 0.7608 |
|
| 51 |
+
| 0.4388 | 16.67 | 200 | 0.1300 |
|
| 52 |
+
| 0.1291 | 25.0 | 300 | 0.0496 |
|
| 53 |
+
| 0.0634 | 33.33 | 400 | 0.0244 |
|
| 54 |
+
| 0.0402 | 41.67 | 500 | 0.0164 |
|
| 55 |
+
| 0.0281 | 50.0 | 600 | 0.0115 |
|
| 56 |
+
| 0.0214 | 58.33 | 700 | 0.0091 |
|
| 57 |
+
| 0.0178 | 66.67 | 800 | 0.0086 |
|
| 58 |
+
| 0.0151 | 75.0 | 900 | 0.0079 |
|
| 59 |
+
| 0.0137 | 83.33 | 1000 | 0.0076 |
|
| 60 |
+
| 0.0122 | 91.67 | 1100 | 0.0075 |
|
| 61 |
+
| 0.0122 | 100.0 | 1200 | 0.0073 |
|
| 62 |
+
| 0.0111 | 108.33 | 1300 | 0.0072 |
|
| 63 |
+
| 0.011 | 116.67 | 1400 | 0.0070 |
|
| 64 |
+
| 0.0101 | 125.0 | 1500 | 0.0069 |
|
| 65 |
+
| 0.0107 | 133.33 | 1600 | 0.0072 |
|
| 66 |
+
| 0.0097 | 141.67 | 1700 | 0.0069 |
|
| 67 |
+
| 0.0094 | 150.0 | 1800 | 0.0069 |
|
| 68 |
+
| 0.0095 | 158.33 | 1900 | 0.0068 |
|
| 69 |
+
| 0.0094 | 166.67 | 2000 | 0.0067 |
|
| 70 |
+
| 0.0088 | 175.0 | 2100 | 0.0066 |
|
| 71 |
+
| 0.0088 | 183.33 | 2200 | 0.0067 |
|
| 72 |
+
| 0.0087 | 191.67 | 2300 | 0.0066 |
|
| 73 |
+
| 0.0088 | 200.0 | 2400 | 0.0066 |
|
| 74 |
+
|
| 75 |
+
|
| 76 |
+
### Framework versions
|
| 77 |
+
|
| 78 |
+
- Transformers 4.32.1
|
| 79 |
+
- Pytorch 2.0.1+cu118
|
| 80 |
+
- Tokenizers 0.13.3
|