update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
metrics:
|
| 5 |
+
- accuracy
|
| 6 |
+
model-index:
|
| 7 |
+
- name: model_v1_complete_training_wt_init_48_small
|
| 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 |
+
# model_v1_complete_training_wt_init_48_small
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 2.5728
|
| 19 |
+
- Accuracy: 0.5268
|
| 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: 1e-05
|
| 39 |
+
- train_batch_size: 48
|
| 40 |
+
- eval_batch_size: 48
|
| 41 |
+
- seed: 10
|
| 42 |
+
- distributed_type: multi-GPU
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- lr_scheduler_warmup_steps: 10000
|
| 46 |
+
- num_epochs: 5
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 51 |
+
|:-------------:|:-----:|:------:|:---------------:|:--------:|
|
| 52 |
+
| 3.7567 | 0.25 | 30000 | 3.5433 | 0.4111 |
|
| 53 |
+
| 3.3711 | 0.49 | 60000 | 3.1762 | 0.4519 |
|
| 54 |
+
| 3.1874 | 0.74 | 90000 | 3.0125 | 0.4709 |
|
| 55 |
+
| 3.0895 | 0.98 | 120000 | 2.9136 | 0.4832 |
|
| 56 |
+
| 3.0097 | 1.23 | 150000 | 2.8447 | 0.4919 |
|
| 57 |
+
| 2.9567 | 1.47 | 180000 | 2.7906 | 0.4985 |
|
| 58 |
+
| 2.9172 | 1.72 | 210000 | 2.7519 | 0.5034 |
|
| 59 |
+
| 2.8781 | 1.97 | 240000 | 2.7183 | 0.5079 |
|
| 60 |
+
| 2.8467 | 2.21 | 270000 | 2.6916 | 0.5113 |
|
| 61 |
+
| 2.8156 | 2.46 | 300000 | 2.6691 | 0.5142 |
|
| 62 |
+
| 2.7975 | 2.7 | 330000 | 2.6503 | 0.5168 |
|
| 63 |
+
| 2.7806 | 2.95 | 360000 | 2.6341 | 0.5189 |
|
| 64 |
+
| 2.7637 | 3.2 | 390000 | 2.6222 | 0.5204 |
|
| 65 |
+
| 2.7629 | 3.44 | 420000 | 2.6085 | 0.5223 |
|
| 66 |
+
| 2.7457 | 3.69 | 450000 | 2.5993 | 0.5235 |
|
| 67 |
+
| 2.7393 | 3.93 | 480000 | 2.5901 | 0.5247 |
|
| 68 |
+
| 2.7285 | 4.18 | 510000 | 2.5829 | 0.5256 |
|
| 69 |
+
| 2.7204 | 4.42 | 540000 | 2.5792 | 0.5260 |
|
| 70 |
+
| 2.7213 | 4.67 | 570000 | 2.5758 | 0.5266 |
|
| 71 |
+
| 2.716 | 4.92 | 600000 | 2.5728 | 0.5268 |
|
| 72 |
+
|
| 73 |
+
|
| 74 |
+
### Framework versions
|
| 75 |
+
|
| 76 |
+
- Transformers 4.30.2
|
| 77 |
+
- Pytorch 1.14.0a0+410ce96
|
| 78 |
+
- Datasets 2.13.0
|
| 79 |
+
- Tokenizers 0.13.3
|