cc-100_0-2 Done
Browse files
README.md
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
license: apache-2.0
|
| 4 |
-
base_model:
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
model-index:
|
|
@@ -14,7 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
# KoModernBERT
|
| 16 |
|
| 17 |
-
This model is a fine-tuned version of [
|
|
|
|
|
|
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
@@ -33,24 +35,39 @@ More information needed
|
|
| 33 |
### Training hyperparameters
|
| 34 |
|
| 35 |
The following hyperparameters were used during training:
|
| 36 |
-
- learning_rate:
|
| 37 |
- train_batch_size: 8
|
| 38 |
- eval_batch_size: 8
|
| 39 |
- seed: 42
|
| 40 |
-
-
|
| 41 |
-
-
|
|
|
|
|
|
|
|
|
|
| 42 |
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 43 |
- lr_scheduler_type: linear
|
| 44 |
-
-
|
| 45 |
-
- num_epochs: 1
|
| 46 |
|
| 47 |
### Training results
|
| 48 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 49 |
|
| 50 |
|
| 51 |
### Framework versions
|
| 52 |
|
| 53 |
-
- Transformers 4.48.
|
| 54 |
-
- Pytorch 2.5.1+
|
| 55 |
-
- Datasets 3.
|
| 56 |
- Tokenizers 0.21.0
|
|
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
license: apache-2.0
|
| 4 |
+
base_model: CocoRoF/KoModernBERT
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
model-index:
|
|
|
|
| 14 |
|
| 15 |
# KoModernBERT
|
| 16 |
|
| 17 |
+
This model is a fine-tuned version of [CocoRoF/KoModernBERT](https://huggingface.co/CocoRoF/KoModernBERT) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 2.3473
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 35 |
### Training hyperparameters
|
| 36 |
|
| 37 |
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 1e-05
|
| 39 |
- train_batch_size: 8
|
| 40 |
- eval_batch_size: 8
|
| 41 |
- seed: 42
|
| 42 |
+
- distributed_type: multi-GPU
|
| 43 |
+
- num_devices: 8
|
| 44 |
+
- gradient_accumulation_steps: 8
|
| 45 |
+
- total_train_batch_size: 512
|
| 46 |
+
- total_eval_batch_size: 64
|
| 47 |
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 48 |
- lr_scheduler_type: linear
|
| 49 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 50 |
+
- num_epochs: 1.0
|
| 51 |
|
| 52 |
### Training results
|
| 53 |
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 55 |
+
|:-------------:|:------:|:-----:|:---------------:|
|
| 56 |
+
| 26.6178 | 0.0928 | 5000 | 3.3099 |
|
| 57 |
+
| 23.887 | 0.1856 | 10000 | 2.9665 |
|
| 58 |
+
| 22.3186 | 0.2784 | 15000 | 2.7910 |
|
| 59 |
+
| 21.6275 | 0.3711 | 20000 | 2.6757 |
|
| 60 |
+
| 20.7564 | 0.4639 | 25000 | 2.5967 |
|
| 61 |
+
| 20.0201 | 0.5567 | 30000 | 2.5263 |
|
| 62 |
+
| 19.7037 | 0.6495 | 35000 | 2.4709 |
|
| 63 |
+
| 19.2119 | 0.7423 | 40000 | 2.4196 |
|
| 64 |
+
| 19.053 | 0.8351 | 45000 | 2.3825 |
|
| 65 |
+
| 18.7262 | 0.9279 | 50000 | 2.3473 |
|
| 66 |
|
| 67 |
|
| 68 |
### Framework versions
|
| 69 |
|
| 70 |
+
- Transformers 4.48.1
|
| 71 |
+
- Pytorch 2.5.1+cu124
|
| 72 |
+
- Datasets 3.2.0
|
| 73 |
- Tokenizers 0.21.0
|