update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
metrics:
|
| 5 |
+
- accuracy
|
| 6 |
+
model-index:
|
| 7 |
+
- name: roberta-tiny-8l-10M
|
| 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 |
+
# roberta-tiny-8l-10M
|
| 15 |
+
|
| 16 |
+
This model was trained from scratch on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 7.3437
|
| 19 |
+
- Accuracy: 0.0512
|
| 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: 0.0004
|
| 39 |
+
- train_batch_size: 16
|
| 40 |
+
- eval_batch_size: 32
|
| 41 |
+
- seed: 42
|
| 42 |
+
- gradient_accumulation_steps: 32
|
| 43 |
+
- total_train_batch_size: 512
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: cosine
|
| 46 |
+
- lr_scheduler_warmup_steps: 50
|
| 47 |
+
- num_epochs: 100.0
|
| 48 |
+
- mixed_precision_training: Native AMP
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 53 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 54 |
+
| 7.8102 | 1.04 | 50 | 7.3747 | 0.0514 |
|
| 55 |
+
| 7.805 | 2.08 | 100 | 7.3699 | 0.0517 |
|
| 56 |
+
| 7.7907 | 3.12 | 150 | 7.3595 | 0.0517 |
|
| 57 |
+
| 7.7838 | 4.16 | 200 | 7.3617 | 0.0514 |
|
| 58 |
+
| 7.7706 | 5.21 | 250 | 7.3586 | 0.0514 |
|
| 59 |
+
| 7.2933 | 6.25 | 300 | 7.3566 | 0.0513 |
|
| 60 |
+
| 7.2932 | 7.29 | 350 | 7.3527 | 0.0516 |
|
| 61 |
+
| 7.2986 | 8.33 | 400 | 7.3561 | 0.0516 |
|
| 62 |
+
| 7.289 | 9.37 | 450 | 7.3495 | 0.0515 |
|
| 63 |
+
| 7.2879 | 10.41 | 500 | 7.3455 | 0.0514 |
|
| 64 |
+
| 7.276 | 11.45 | 550 | 7.3477 | 0.0513 |
|
| 65 |
+
| 7.3072 | 12.49 | 600 | 7.3446 | 0.0516 |
|
| 66 |
+
| 7.2978 | 13.53 | 650 | 7.3463 | 0.0514 |
|
| 67 |
+
| 7.2857 | 14.58 | 700 | 7.3426 | 0.0515 |
|
| 68 |
+
| 7.2868 | 15.62 | 750 | 7.3438 | 0.0515 |
|
| 69 |
+
| 7.2973 | 16.66 | 800 | 7.3442 | 0.0517 |
|
| 70 |
+
| 7.2988 | 17.7 | 850 | 7.3437 | 0.0512 |
|
| 71 |
+
|
| 72 |
+
|
| 73 |
+
### Framework versions
|
| 74 |
+
|
| 75 |
+
- Transformers 4.24.0
|
| 76 |
+
- Pytorch 1.11.0+cu113
|
| 77 |
+
- Datasets 2.6.1
|
| 78 |
+
- Tokenizers 0.12.1
|