update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,103 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
datasets:
|
| 5 |
+
- odinsynth_sequence_dataset
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
model-index:
|
| 9 |
+
- name: odinsynth_encoder_decoder_native_hf_test_2
|
| 10 |
+
results:
|
| 11 |
+
- task:
|
| 12 |
+
name: Sequence-to-sequence Language Modeling
|
| 13 |
+
type: text2text-generation
|
| 14 |
+
dataset:
|
| 15 |
+
name: odinsynth_sequence_dataset
|
| 16 |
+
type: odinsynth_sequence_dataset
|
| 17 |
+
config: synthetic_surface
|
| 18 |
+
split: validation
|
| 19 |
+
args: synthetic_surface
|
| 20 |
+
metrics:
|
| 21 |
+
- name: Accuracy
|
| 22 |
+
type: accuracy
|
| 23 |
+
value: 0.934322390845116
|
| 24 |
+
---
|
| 25 |
+
|
| 26 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 27 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 28 |
+
|
| 29 |
+
# odinsynth_encoder_decoder_native_hf_test_2
|
| 30 |
+
|
| 31 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on the odinsynth_sequence_dataset dataset.
|
| 32 |
+
It achieves the following results on the evaluation set:
|
| 33 |
+
- Loss: 0.0771
|
| 34 |
+
- Accuracy: 0.9343
|
| 35 |
+
|
| 36 |
+
## Model description
|
| 37 |
+
|
| 38 |
+
More information needed
|
| 39 |
+
|
| 40 |
+
## Intended uses & limitations
|
| 41 |
+
|
| 42 |
+
More information needed
|
| 43 |
+
|
| 44 |
+
## Training and evaluation data
|
| 45 |
+
|
| 46 |
+
More information needed
|
| 47 |
+
|
| 48 |
+
## Training procedure
|
| 49 |
+
|
| 50 |
+
### Training hyperparameters
|
| 51 |
+
|
| 52 |
+
The following hyperparameters were used during training:
|
| 53 |
+
- learning_rate: 5e-05
|
| 54 |
+
- train_batch_size: 3
|
| 55 |
+
- eval_batch_size: 3
|
| 56 |
+
- seed: 42
|
| 57 |
+
- gradient_accumulation_steps: 200
|
| 58 |
+
- total_train_batch_size: 600
|
| 59 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 60 |
+
- lr_scheduler_type: linear
|
| 61 |
+
- num_epochs: 20.0
|
| 62 |
+
|
| 63 |
+
### Training results
|
| 64 |
+
|
| 65 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 66 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 67 |
+
| 0.1612 | 0.67 | 60 | 0.1145 | 0.9376 |
|
| 68 |
+
| 0.0666 | 1.34 | 120 | 0.0628 | 0.9356 |
|
| 69 |
+
| 0.0599 | 2.01 | 180 | 0.0611 | 0.9355 |
|
| 70 |
+
| 0.0563 | 2.68 | 240 | 0.0631 | 0.9352 |
|
| 71 |
+
| 0.0512 | 3.35 | 300 | 0.0630 | 0.9347 |
|
| 72 |
+
| 0.0472 | 4.02 | 360 | 0.0638 | 0.9338 |
|
| 73 |
+
| 0.0438 | 4.69 | 420 | 0.0655 | 0.9339 |
|
| 74 |
+
| 0.0405 | 5.36 | 480 | 0.0660 | 0.9345 |
|
| 75 |
+
| 0.0378 | 6.03 | 540 | 0.0666 | 0.9342 |
|
| 76 |
+
| 0.0344 | 6.69 | 600 | 0.0669 | 0.9343 |
|
| 77 |
+
| 0.0323 | 7.36 | 660 | 0.0678 | 0.9344 |
|
| 78 |
+
| 0.0307 | 8.03 | 720 | 0.0694 | 0.9343 |
|
| 79 |
+
| 0.0294 | 8.7 | 780 | 0.0706 | 0.9345 |
|
| 80 |
+
| 0.0286 | 9.37 | 840 | 0.0725 | 0.9342 |
|
| 81 |
+
| 0.0275 | 10.04 | 900 | 0.0727 | 0.9343 |
|
| 82 |
+
| 0.0282 | 10.71 | 960 | 0.0732 | 0.9342 |
|
| 83 |
+
| 0.0264 | 11.38 | 1020 | 0.0735 | 0.9343 |
|
| 84 |
+
| 0.026 | 12.05 | 1080 | 0.0750 | 0.9342 |
|
| 85 |
+
| 0.0254 | 12.72 | 1140 | 0.0753 | 0.9343 |
|
| 86 |
+
| 0.0244 | 13.39 | 1200 | 0.0746 | 0.9344 |
|
| 87 |
+
| 0.0242 | 14.06 | 1260 | 0.0752 | 0.9343 |
|
| 88 |
+
| 0.024 | 14.73 | 1320 | 0.0758 | 0.9342 |
|
| 89 |
+
| 0.0239 | 15.4 | 1380 | 0.0764 | 0.9343 |
|
| 90 |
+
| 0.0234 | 16.07 | 1440 | 0.0763 | 0.9343 |
|
| 91 |
+
| 0.0231 | 16.74 | 1500 | 0.0764 | 0.9343 |
|
| 92 |
+
| 0.0226 | 17.41 | 1560 | 0.0770 | 0.9343 |
|
| 93 |
+
| 0.023 | 18.08 | 1620 | 0.0770 | 0.9343 |
|
| 94 |
+
| 0.0227 | 18.74 | 1680 | 0.0771 | 0.9343 |
|
| 95 |
+
| 0.0221 | 19.41 | 1740 | 0.0771 | 0.9343 |
|
| 96 |
+
|
| 97 |
+
|
| 98 |
+
### Framework versions
|
| 99 |
+
|
| 100 |
+
- Transformers 4.27.4
|
| 101 |
+
- Pytorch 2.0.0
|
| 102 |
+
- Datasets 2.11.0
|
| 103 |
+
- Tokenizers 0.11.0
|