update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
model-index:
|
| 5 |
+
- name: enlm-roberta-final
|
| 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 |
+
# enlm-roberta-final
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [manirai91/enlm-roberta](https://huggingface.co/manirai91/enlm-roberta) on an unknown dataset.
|
| 15 |
+
It achieves the following results on the evaluation set:
|
| 16 |
+
- Loss: 1.4187
|
| 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: 6e-06
|
| 36 |
+
- train_batch_size: 16
|
| 37 |
+
- eval_batch_size: 16
|
| 38 |
+
- seed: 42
|
| 39 |
+
- distributed_type: multi-GPU
|
| 40 |
+
- num_devices: 4
|
| 41 |
+
- gradient_accumulation_steps: 128
|
| 42 |
+
- total_train_batch_size: 8192
|
| 43 |
+
- total_eval_batch_size: 64
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-06
|
| 45 |
+
- lr_scheduler_type: polynomial
|
| 46 |
+
- num_epochs: 10
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 51 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 52 |
+
| 1.5245 | 0.34 | 160 | 1.4187 |
|
| 53 |
+
| 1.5245 | 0.69 | 320 | 1.4183 |
|
| 54 |
+
| 1.5259 | 1.03 | 480 | 1.4177 |
|
| 55 |
+
| 1.5265 | 1.37 | 640 | 1.4185 |
|
| 56 |
+
| 1.5245 | 1.72 | 800 | 1.4190 |
|
| 57 |
+
| 1.5241 | 2.06 | 960 | 1.4172 |
|
| 58 |
+
| 1.5227 | 2.4 | 1120 | 1.4165 |
|
| 59 |
+
| 1.5226 | 2.75 | 1280 | 1.4152 |
|
| 60 |
+
| 1.522 | 3.09 | 1440 | 1.4190 |
|
| 61 |
+
| 1.5243 | 3.43 | 1600 | 1.4177 |
|
| 62 |
+
| 1.5213 | 3.78 | 1760 | 1.4134 |
|
| 63 |
+
| 1.524 | 4.12 | 1920 | 1.4140 |
|
| 64 |
+
| 1.5223 | 4.46 | 2080 | 1.4173 |
|
| 65 |
+
| 1.5236 | 4.81 | 2240 | 1.4121 |
|
| 66 |
+
| 1.5239 | 5.15 | 2400 | 1.4186 |
|
| 67 |
+
| 1.5203 | 5.49 | 2560 | 1.4154 |
|
| 68 |
+
| 1.522 | 5.84 | 2720 | 1.4162 |
|
| 69 |
+
| 1.5209 | 6.18 | 2880 | 1.4154 |
|
| 70 |
+
| 1.5196 | 6.52 | 3040 | 1.4153 |
|
| 71 |
+
| 1.5209 | 6.87 | 3200 | 1.4122 |
|
| 72 |
+
| 1.5202 | 7.21 | 3360 | 1.4146 |
|
| 73 |
+
| 1.5192 | 7.55 | 3520 | 1.4141 |
|
| 74 |
+
| 1.5215 | 7.9 | 3680 | 1.4123 |
|
| 75 |
+
| 1.5228 | 8.24 | 3840 | 1.4147 |
|
| 76 |
+
| 1.5222 | 8.58 | 4000 | 1.4144 |
|
| 77 |
+
| 1.5201 | 8.93 | 4160 | 1.4173 |
|
| 78 |
+
| 1.523 | 9.27 | 4320 | 1.4171 |
|
| 79 |
+
| 1.5212 | 9.61 | 4480 | 1.4149 |
|
| 80 |
+
| 1.522 | 9.96 | 4640 | 1.4187 |
|
| 81 |
+
|
| 82 |
+
|
| 83 |
+
### Framework versions
|
| 84 |
+
|
| 85 |
+
- Transformers 4.20.1
|
| 86 |
+
- Pytorch 1.11.0
|
| 87 |
+
- Datasets 2.3.2
|
| 88 |
+
- Tokenizers 0.12.1
|