End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-nc-nd-4.0
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
base_model: kakaobrain/kogpt
|
| 7 |
+
model-index:
|
| 8 |
+
- name: pretrain_wo-cot_w-asd_gpt
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# pretrain_wo-cot_w-asd_gpt
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [kakaobrain/kogpt](https://huggingface.co/kakaobrain/kogpt) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 5.2695
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 3e-05
|
| 39 |
+
- train_batch_size: 1
|
| 40 |
+
- eval_batch_size: 1
|
| 41 |
+
- seed: 42
|
| 42 |
+
- gradient_accumulation_steps: 8
|
| 43 |
+
- total_train_batch_size: 8
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- num_epochs: 3
|
| 47 |
+
- mixed_precision_training: Native AMP
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 53 |
+
| 9.3854 | 0.1290 | 1 | 10.0019 |
|
| 54 |
+
| 9.2319 | 0.2581 | 2 | 9.7577 |
|
| 55 |
+
| 8.9195 | 0.3871 | 3 | 9.4655 |
|
| 56 |
+
| 8.7866 | 0.5161 | 4 | 9.1438 |
|
| 57 |
+
| 8.4714 | 0.6452 | 5 | 9.1438 |
|
| 58 |
+
| 8.548 | 0.7742 | 6 | 8.8258 |
|
| 59 |
+
| 8.1645 | 0.9032 | 7 | 8.5218 |
|
| 60 |
+
| 7.9288 | 1.0323 | 8 | 8.1624 |
|
| 61 |
+
| 7.4999 | 1.1613 | 9 | 7.8294 |
|
| 62 |
+
| 7.0631 | 1.2903 | 10 | 7.5127 |
|
| 63 |
+
| 6.9252 | 1.4194 | 11 | 7.1942 |
|
| 64 |
+
| 6.7075 | 1.5484 | 12 | 6.8620 |
|
| 65 |
+
| 6.4293 | 1.6774 | 13 | 6.5825 |
|
| 66 |
+
| 6.1982 | 1.8065 | 14 | 6.2854 |
|
| 67 |
+
| 5.9671 | 1.9355 | 15 | 6.0680 |
|
| 68 |
+
| 5.5963 | 2.0645 | 16 | 5.8336 |
|
| 69 |
+
| 5.4335 | 2.1935 | 17 | 5.6719 |
|
| 70 |
+
| 5.3723 | 2.3226 | 18 | 5.5392 |
|
| 71 |
+
| 5.3661 | 2.4516 | 19 | 5.4076 |
|
| 72 |
+
| 5.0969 | 2.5806 | 20 | 5.3410 |
|
| 73 |
+
| 5.0227 | 2.7097 | 21 | 5.2695 |
|
| 74 |
+
|
| 75 |
+
|
| 76 |
+
### Framework versions
|
| 77 |
+
|
| 78 |
+
- PEFT 0.11.1
|
| 79 |
+
- Transformers 4.41.1
|
| 80 |
+
- Pytorch 2.3.0+cu121
|
| 81 |
+
- Datasets 2.19.1
|
| 82 |
+
- Tokenizers 0.19.1
|