update model card README.md

README.md

@@ -0,0 +1,72 @@
+---
+license: mit
+tags:
+- generated_from_trainer
+datasets:
+- glue
+metrics:
+- accuracy
+- f1
+model-index:
+- name: roberta-base-finetuned-mrpc
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# roberta-base-finetuned-mrpc
+
+This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the glue dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3411
+- Accuracy: 0.865
+- F1: 0.9046
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: IPU
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 64
+- total_eval_batch_size: 20
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+- training precision: Mixed Precision
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
+| 0.4522        | 1.0   | 57   | 0.4265          | 0.8075   | 0.8666 |
+| 0.2951        | 2.0   | 114  | 0.3313          | 0.8625   | 0.9009 |
+| 0.3248        | 3.0   | 171  | 0.3604          | 0.855    | 0.9000 |
+| 0.1417        | 4.0   | 228  | 0.3411          | 0.865    | 0.9046 |
+| 0.1147        | 5.0   | 285  | 0.3359          | 0.865    | 0.9018 |
+
+
+### Framework versions
+
+- Transformers 4.20.1
+- Pytorch 1.10.0+cpu
+- Datasets 2.3.2
+- Tokenizers 0.12.1