update model card README.md

README.md

@@ -1,5 +1,5 @@
 ---
-license: apache-2.0
+license: mit
 tags:
 - generated_from_trainer
 metrics:
@@ -17,13 +17,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # medlid-identify
 
-This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the None dataset.
+This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1241
-- Precision: 0.3760
-- Recall: 0.4362
-- F1: 0.4038
-- Accuracy: 0.9601
+- Loss: 0.1248
+- Precision: 0.4410
+- Recall: 0.4209
+- F1: 0.4307
+- Accuracy: 0.9541
 
 ## Model description
 
@@ -54,10 +54,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.1426        | 1.0   | 835  | 0.1035          | 0.2819    | 0.2529 | 0.2666 | 0.9603   |
-| 0.0852        | 2.0   | 1670 | 0.0975          | 0.3845    | 0.3259 | 0.3528 | 0.9636   |
-| 0.061         | 3.0   | 2505 | 0.1099          | 0.3832    | 0.4585 | 0.4175 | 0.9607   |
-| 0.0465        | 4.0   | 3340 | 0.1241          | 0.3760    | 0.4362 | 0.4038 | 0.9601   |
+| No log        | 1.0   | 381  | 0.1297          | 0.3898    | 0.3032 | 0.3411 | 0.9525   |
+| 0.1774        | 2.0   | 762  | 0.1191          | 0.4485    | 0.3489 | 0.3925 | 0.9551   |
+| 0.1177        | 3.0   | 1143 | 0.1216          | 0.4341    | 0.4209 | 0.4274 | 0.9544   |
+| 0.0974        | 4.0   | 1524 | 0.1248          | 0.4410    | 0.4209 | 0.4307 | 0.9541   |
 
 
 ### Framework versions