Pushing ruRoberta-large_ner model to Hugging Face Hub

README.md

@@ -19,11 +19,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [ai-forever/ruRoberta-large](https://huggingface.co/ai-forever/ruRoberta-large) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1151
-- Precision: 0.8182
-- Recall: 0.9
-- F1: 0.8571
-- Accuracy: 0.9671
+- Loss: 0.0824
+- Precision: 0.7879
+- Recall: 0.8667
+- F1: 0.8254
+- Accuracy: 0.9667
 
 ## Model description
 
@@ -54,9 +54,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 15   | 0.2455          | 0.5385    | 0.7    | 0.6087 | 0.9211   |
-| No log        | 2.0   | 30   | 0.1663          | 0.7429    | 0.8667 | 0.8    | 0.9342   |
-| No log        | 3.0   | 45   | 0.1151          | 0.8182    | 0.9    | 0.8571 | 0.9671   |
+| No log        | 1.0   | 15   | 0.2732          | 0.5833    | 0.7    | 0.6364 | 0.88     |
+| No log        | 2.0   | 30   | 0.1424          | 0.7059    | 0.8    | 0.7500 | 0.94     |
+| No log        | 3.0   | 45   | 0.0824          | 0.7879    | 0.8667 | 0.8254 | 0.9667   |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1129ba12dabceb53c3416e18174eb15c5b70be53b3e57d604e38a2e19ad85480
+oid sha256:e384d8b727c528e147ec75ad9cc6f3b9337171418558d884ba62996fcd23cd81
 size 1417396454