Commit
•
4950d10
1
Parent(s):
bcce059
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: agpl-3.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: icebert-texas-squad-is
|
| 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 |
+
# icebert-texas-squad-is
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [vesteinn/IceBERT](https://huggingface.co/vesteinn/IceBERT) on an unknown dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 1.8908
|
| 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: 2e-05
|
| 37 |
+
- train_batch_size: 8
|
| 38 |
+
- eval_batch_size: 8
|
| 39 |
+
- seed: 42
|
| 40 |
+
- gradient_accumulation_steps: 4
|
| 41 |
+
- total_train_batch_size: 32
|
| 42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
+
- lr_scheduler_type: linear
|
| 44 |
+
- num_epochs: 3
|
| 45 |
+
|
| 46 |
+
### Training results
|
| 47 |
+
|
| 48 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 49 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
| 50 |
+
| 2.5353 | 0.12 | 500 | 2.2356 |
|
| 51 |
+
| 2.364 | 0.24 | 1000 | 2.0607 |
|
| 52 |
+
| 2.2243 | 0.36 | 1500 | 2.0617 |
|
| 53 |
+
| 2.1403 | 0.49 | 2000 | 1.9934 |
|
| 54 |
+
| 2.1491 | 0.61 | 2500 | 2.0515 |
|
| 55 |
+
| 2.0604 | 0.73 | 3000 | 1.9602 |
|
| 56 |
+
| 2.0232 | 0.85 | 3500 | 1.8954 |
|
| 57 |
+
| 2.0905 | 0.97 | 4000 | 1.9474 |
|
| 58 |
+
| 1.9229 | 1.09 | 4500 | 1.9814 |
|
| 59 |
+
| 1.9162 | 1.22 | 5000 | 1.9053 |
|
| 60 |
+
| 1.8937 | 1.34 | 5500 | 1.9501 |
|
| 61 |
+
| 1.9085 | 1.46 | 6000 | 1.8882 |
|
| 62 |
+
| 1.8671 | 1.58 | 6500 | 1.8996 |
|
| 63 |
+
| 1.8997 | 1.7 | 7000 | 1.8340 |
|
| 64 |
+
| 1.8546 | 1.82 | 7500 | 1.8883 |
|
| 65 |
+
| 1.8935 | 1.95 | 8000 | 1.8567 |
|
| 66 |
+
| 1.7031 | 2.07 | 8500 | 1.9206 |
|
| 67 |
+
| 1.7699 | 2.19 | 9000 | 1.8790 |
|
| 68 |
+
| 1.7016 | 2.31 | 9500 | 1.8670 |
|
| 69 |
+
| 1.7744 | 2.43 | 10000 | 1.8951 |
|
| 70 |
+
| 1.7518 | 2.55 | 10500 | 1.9550 |
|
| 71 |
+
| 1.7503 | 2.68 | 11000 | 1.9120 |
|
| 72 |
+
| 1.7818 | 2.8 | 11500 | 1.8820 |
|
| 73 |
+
| 1.6955 | 2.92 | 12000 | 1.8908 |
|
| 74 |
+
|
| 75 |
+
|
| 76 |
+
### Framework versions
|
| 77 |
+
|
| 78 |
+
- Transformers 4.12.2
|
| 79 |
+
- Pytorch 1.8.1+cu101
|
| 80 |
+
- Datasets 1.12.1
|
| 81 |
+
- Tokenizers 0.10.3
|