update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: small-mlm-imdb
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# small-mlm-imdb
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [google/bert_uncased_L-4_H-512_A-8](https://huggingface.co/google/bert_uncased_L-4_H-512_A-8) on the None dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 2.3673
|
| 18 |
+
|
| 19 |
+
## Model description
|
| 20 |
+
|
| 21 |
+
More information needed
|
| 22 |
+
|
| 23 |
+
## Intended uses & limitations
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Training and evaluation data
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training procedure
|
| 32 |
+
|
| 33 |
+
### Training hyperparameters
|
| 34 |
+
|
| 35 |
+
The following hyperparameters were used during training:
|
| 36 |
+
- learning_rate: 3e-05
|
| 37 |
+
- train_batch_size: 32
|
| 38 |
+
- eval_batch_size: 32
|
| 39 |
+
- seed: 42
|
| 40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
+
- lr_scheduler_type: constant
|
| 42 |
+
- num_epochs: 200
|
| 43 |
+
|
| 44 |
+
### Training results
|
| 45 |
+
|
| 46 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 47 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
| 48 |
+
| 2.7542 | 0.16 | 500 | 2.5445 |
|
| 49 |
+
| 2.6734 | 0.32 | 1000 | 2.5191 |
|
| 50 |
+
| 2.6552 | 0.48 | 1500 | 2.4976 |
|
| 51 |
+
| 2.6481 | 0.64 | 2000 | 2.4866 |
|
| 52 |
+
| 2.6291 | 0.8 | 2500 | 2.4599 |
|
| 53 |
+
| 2.6134 | 0.96 | 3000 | 2.4585 |
|
| 54 |
+
| 2.5627 | 1.12 | 3500 | 2.4476 |
|
| 55 |
+
| 2.5564 | 1.28 | 4000 | 2.4340 |
|
| 56 |
+
| 2.5493 | 1.44 | 4500 | 2.4354 |
|
| 57 |
+
| 2.5435 | 1.6 | 5000 | 2.4307 |
|
| 58 |
+
| 2.5352 | 1.76 | 5500 | 2.4224 |
|
| 59 |
+
| 2.5445 | 1.92 | 6000 | 2.4167 |
|
| 60 |
+
| 2.5191 | 2.08 | 6500 | 2.4175 |
|
| 61 |
+
| 2.5143 | 2.24 | 7000 | 2.4149 |
|
| 62 |
+
| 2.5059 | 2.4 | 7500 | 2.4117 |
|
| 63 |
+
| 2.4865 | 2.56 | 8000 | 2.4063 |
|
| 64 |
+
| 2.5113 | 2.72 | 8500 | 2.3976 |
|
| 65 |
+
| 2.5115 | 2.88 | 9000 | 2.3959 |
|
| 66 |
+
| 2.485 | 3.04 | 9500 | 2.3917 |
|
| 67 |
+
| 2.4652 | 3.2 | 10000 | 2.3908 |
|
| 68 |
+
| 2.4569 | 3.36 | 10500 | 2.3877 |
|
| 69 |
+
| 2.4706 | 3.52 | 11000 | 2.3836 |
|
| 70 |
+
| 2.4375 | 3.68 | 11500 | 2.3870 |
|
| 71 |
+
| 2.4556 | 3.84 | 12000 | 2.3819 |
|
| 72 |
+
| 2.4487 | 4.0 | 12500 | 2.3842 |
|
| 73 |
+
| 2.4233 | 4.16 | 13000 | 2.3731 |
|
| 74 |
+
| 2.4238 | 4.32 | 13500 | 2.3801 |
|
| 75 |
+
| 2.4051 | 4.48 | 14000 | 2.3809 |
|
| 76 |
+
| 2.432 | 4.64 | 14500 | 2.3641 |
|
| 77 |
+
| 2.428 | 4.8 | 15000 | 2.3686 |
|
| 78 |
+
| 2.4248 | 4.96 | 15500 | 2.3741 |
|
| 79 |
+
| 2.4109 | 5.12 | 16000 | 2.3673 |
|
| 80 |
+
|
| 81 |
+
|
| 82 |
+
### Framework versions
|
| 83 |
+
|
| 84 |
+
- Transformers 4.25.1
|
| 85 |
+
- Pytorch 1.12.1
|
| 86 |
+
- Datasets 2.7.1
|
| 87 |
+
- Tokenizers 0.13.2
|