Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: microsoft/deberta-v3-large
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
model-index:
|
| 9 |
+
- name: checkpoints_28_9_microsoft_deberta_V5
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# checkpoints_28_9_microsoft_deberta_V5
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on the None dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.6408
|
| 21 |
+
- Map@3: 0.8542
|
| 22 |
+
- Accuracy: 0.76
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 1e-05
|
| 42 |
+
- train_batch_size: 4
|
| 43 |
+
- eval_batch_size: 4
|
| 44 |
+
- seed: 42
|
| 45 |
+
- gradient_accumulation_steps: 32
|
| 46 |
+
- total_train_batch_size: 128
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: cosine
|
| 49 |
+
- lr_scheduler_warmup_ratio: 0.2
|
| 50 |
+
- num_epochs: 1
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Map@3 | Accuracy |
|
| 55 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:--------:|
|
| 56 |
+
| 1.6111 | 0.05 | 25 | 1.6092 | 0.5092 | 0.325 |
|
| 57 |
+
| 1.6139 | 0.11 | 50 | 1.6085 | 0.7 | 0.575 |
|
| 58 |
+
| 1.6096 | 0.16 | 75 | 1.5867 | 0.7583 | 0.645 |
|
| 59 |
+
| 1.2905 | 0.21 | 100 | 1.1496 | 0.7767 | 0.66 |
|
| 60 |
+
| 1.0263 | 0.27 | 125 | 0.8628 | 0.8067 | 0.705 |
|
| 61 |
+
| 0.9475 | 0.32 | 150 | 0.7252 | 0.8458 | 0.75 |
|
| 62 |
+
| 0.841 | 0.37 | 175 | 0.7018 | 0.8492 | 0.76 |
|
| 63 |
+
| 0.8301 | 0.43 | 200 | 0.7137 | 0.8492 | 0.755 |
|
| 64 |
+
| 0.823 | 0.48 | 225 | 0.6633 | 0.8525 | 0.755 |
|
| 65 |
+
| 0.8263 | 0.53 | 250 | 0.6751 | 0.8608 | 0.765 |
|
| 66 |
+
| 0.7962 | 0.59 | 275 | 0.6704 | 0.8542 | 0.755 |
|
| 67 |
+
| 0.8013 | 0.64 | 300 | 0.6583 | 0.8525 | 0.755 |
|
| 68 |
+
| 0.789 | 0.69 | 325 | 0.6497 | 0.8533 | 0.76 |
|
| 69 |
+
| 0.7979 | 0.75 | 350 | 0.6512 | 0.8525 | 0.755 |
|
| 70 |
+
| 0.7751 | 0.8 | 375 | 0.6445 | 0.8583 | 0.765 |
|
| 71 |
+
| 0.7993 | 0.85 | 400 | 0.6424 | 0.8558 | 0.765 |
|
| 72 |
+
| 0.7685 | 0.91 | 425 | 0.6408 | 0.8542 | 0.76 |
|
| 73 |
+
| 0.7807 | 0.96 | 450 | 0.6408 | 0.8542 | 0.76 |
|
| 74 |
+
|
| 75 |
+
|
| 76 |
+
### Framework versions
|
| 77 |
+
|
| 78 |
+
- Transformers 4.32.1
|
| 79 |
+
- Pytorch 2.0.0
|
| 80 |
+
- Datasets 2.9.0
|
| 81 |
+
- Tokenizers 0.13.3
|