Commit
•
0a1d383
1
Parent(s):
193c56f
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: mnli_MULTI
|
| 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 |
+
# mnli_MULTI
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [WillHeld/roberta-base-mnli](https://huggingface.co/WillHeld/roberta-base-mnli) on the None dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 0.5379
|
| 18 |
+
- Acc: 0.8407
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 2e-05
|
| 38 |
+
- train_batch_size: 32
|
| 39 |
+
- eval_batch_size: 32
|
| 40 |
+
- seed: 42
|
| 41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
+
- lr_scheduler_type: linear
|
| 43 |
+
- num_epochs: 3
|
| 44 |
+
|
| 45 |
+
### Training results
|
| 46 |
+
|
| 47 |
+
| Training Loss | Epoch | Step | Validation Loss | Acc |
|
| 48 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|
|
| 49 |
+
| 0.4798 | 0.17 | 2000 | 0.4797 | 0.8220 |
|
| 50 |
+
| 0.4483 | 0.33 | 4000 | 0.4576 | 0.8257 |
|
| 51 |
+
| 0.4282 | 0.5 | 6000 | 0.4628 | 0.8298 |
|
| 52 |
+
| 0.4333 | 0.67 | 8000 | 0.4426 | 0.8311 |
|
| 53 |
+
| 0.4251 | 0.83 | 10000 | 0.4449 | 0.8333 |
|
| 54 |
+
| 0.4154 | 1.0 | 12000 | 0.4518 | 0.8376 |
|
| 55 |
+
| 0.3064 | 1.17 | 14000 | 0.4845 | 0.8350 |
|
| 56 |
+
| 0.3072 | 1.33 | 16000 | 0.4803 | 0.8383 |
|
| 57 |
+
| 0.3144 | 1.5 | 18000 | 0.4824 | 0.8322 |
|
| 58 |
+
| 0.3025 | 1.66 | 20000 | 0.4634 | 0.8391 |
|
| 59 |
+
| 0.3063 | 1.83 | 22000 | 0.4625 | 0.8419 |
|
| 60 |
+
| 0.304 | 2.0 | 24000 | 0.4637 | 0.8401 |
|
| 61 |
+
| 0.2232 | 2.16 | 26000 | 0.5330 | 0.8434 |
|
| 62 |
+
| 0.2215 | 2.33 | 28000 | 0.5338 | 0.8374 |
|
| 63 |
+
| 0.2181 | 2.5 | 30000 | 0.5366 | 0.8393 |
|
| 64 |
+
| 0.216 | 2.66 | 32000 | 0.5333 | 0.8425 |
|
| 65 |
+
| 0.2118 | 2.83 | 34000 | 0.5293 | 0.8414 |
|
| 66 |
+
| 0.2128 | 3.0 | 36000 | 0.5379 | 0.8407 |
|
| 67 |
+
|
| 68 |
+
|
| 69 |
+
### Framework versions
|
| 70 |
+
|
| 71 |
+
- Transformers 4.24.0
|
| 72 |
+
- Pytorch 1.13.0+cu117
|
| 73 |
+
- Datasets 2.7.1
|
| 74 |
+
- Tokenizers 0.12.1
|