update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,92 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: rubert-tiny2-srl
|
| 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 |
+
# rubert-tiny2-srl
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [cointegrated/rubert-tiny2](https://huggingface.co/cointegrated/rubert-tiny2) on an unknown dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- eval_loss: 0.4175
|
| 18 |
+
- eval_Benefactive_precision: 0.0
|
| 19 |
+
- eval_Benefactive_recall: 0.0
|
| 20 |
+
- eval_Benefactive_f1: 0.0
|
| 21 |
+
- eval_Benefactive_number: 5
|
| 22 |
+
- eval_Causator_precision: 0.0
|
| 23 |
+
- eval_Causator_recall: 0.0
|
| 24 |
+
- eval_Causator_f1: 0.0
|
| 25 |
+
- eval_Causator_number: 26
|
| 26 |
+
- eval_Cause_precision: 0.0
|
| 27 |
+
- eval_Cause_recall: 0.0
|
| 28 |
+
- eval_Cause_f1: 0.0
|
| 29 |
+
- eval_Cause_number: 21
|
| 30 |
+
- eval_ContrSubject_precision: 0.0
|
| 31 |
+
- eval_ContrSubject_recall: 0.0
|
| 32 |
+
- eval_ContrSubject_f1: 0.0
|
| 33 |
+
- eval_ContrSubject_number: 19
|
| 34 |
+
- eval_Deliberative_precision: 0.0
|
| 35 |
+
- eval_Deliberative_recall: 0.0
|
| 36 |
+
- eval_Deliberative_f1: 0.0
|
| 37 |
+
- eval_Deliberative_number: 10
|
| 38 |
+
- eval_Experiencer_precision: 0.5512
|
| 39 |
+
- eval_Experiencer_recall: 0.4321
|
| 40 |
+
- eval_Experiencer_f1: 0.4844
|
| 41 |
+
- eval_Experiencer_number: 162
|
| 42 |
+
- eval_Object_precision: 0.6905
|
| 43 |
+
- eval_Object_recall: 0.0963
|
| 44 |
+
- eval_Object_f1: 0.1691
|
| 45 |
+
- eval_Object_number: 301
|
| 46 |
+
- eval_Predicate_precision: 0.9360
|
| 47 |
+
- eval_Predicate_recall: 0.9737
|
| 48 |
+
- eval_Predicate_f1: 0.9545
|
| 49 |
+
- eval_Predicate_number: 571
|
| 50 |
+
- eval_overall_precision: 0.8585
|
| 51 |
+
- eval_overall_recall: 0.5874
|
| 52 |
+
- eval_overall_f1: 0.6976
|
| 53 |
+
- eval_overall_accuracy: 0.8855
|
| 54 |
+
- eval_runtime: 1.6021
|
| 55 |
+
- eval_samples_per_second: 355.786
|
| 56 |
+
- eval_steps_per_second: 355.786
|
| 57 |
+
- epoch: 1.0
|
| 58 |
+
- step: 4864
|
| 59 |
+
|
| 60 |
+
## Model description
|
| 61 |
+
|
| 62 |
+
More information needed
|
| 63 |
+
|
| 64 |
+
## Intended uses & limitations
|
| 65 |
+
|
| 66 |
+
More information needed
|
| 67 |
+
|
| 68 |
+
## Training and evaluation data
|
| 69 |
+
|
| 70 |
+
More information needed
|
| 71 |
+
|
| 72 |
+
## Training procedure
|
| 73 |
+
|
| 74 |
+
### Training hyperparameters
|
| 75 |
+
|
| 76 |
+
The following hyperparameters were used during training:
|
| 77 |
+
- learning_rate: 1.1643470912014148e-05
|
| 78 |
+
- train_batch_size: 1
|
| 79 |
+
- eval_batch_size: 1
|
| 80 |
+
- seed: 163748
|
| 81 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 82 |
+
- lr_scheduler_type: linear
|
| 83 |
+
- lr_scheduler_warmup_ratio: 0.28
|
| 84 |
+
- num_epochs: 5
|
| 85 |
+
- mixed_precision_training: Native AMP
|
| 86 |
+
|
| 87 |
+
### Framework versions
|
| 88 |
+
|
| 89 |
+
- Transformers 4.28.1
|
| 90 |
+
- Pytorch 2.0.0+cu117
|
| 91 |
+
- Datasets 2.11.0
|
| 92 |
+
- Tokenizers 0.13.3
|