End of training

README.md

@@ -15,22 +15,34 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 5.5425
-- eval_Accuracy: 0.1
-- eval_F1_macro: 0.05
-- eval_F1_class_0: 0.4
-- eval_F1_class_1: 0.0
-- eval_F1_class_2: 0.0
+- eval_loss: 2.0155
+- eval_Accuracy: 0.4159
+- eval_F1_macro: 0.1352
+- eval_F1_class_0: 0.8025
+- eval_F1_class_1: 0.2857
+- eval_F1_class_2: 0.5222
 - eval_F1_class_3: 0.0
-- eval_F1_class_4: 0.0
+- eval_F1_class_4: 0.0593
 - eval_F1_class_5: 0.0
-- eval_F1_class_6: 0.0
+- eval_F1_class_6: 0.0194
 - eval_F1_class_7: 0.0
-- eval_runtime: 0.1585
-- eval_samples_per_second: 63.088
-- eval_steps_per_second: 12.618
-- epoch: 0.14
-- step: 1000
+- eval_F1_class_8: 0.0
+- eval_F1_class_9: 0.8555
+- eval_F1_class_10: 0.0
+- eval_F1_class_11: 0.0
+- eval_F1_class_12: 0.1262
+- eval_F1_class_13: 0.0
+- eval_F1_class_14: 0.0
+- eval_F1_class_15: 0.0323
+- eval_F1_class_16: 0.0
+- eval_F1_class_17: 0.0
+- eval_F1_class_18: 0.0
+- eval_F1_class_19: 0.0
+- eval_runtime: 16.4701
+- eval_samples_per_second: 68.609
+- eval_steps_per_second: 8.622
+- epoch: 0.23
+- step: 1500
 
 ## Model description
 
@@ -55,7 +67,7 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 2
+- num_epochs: 3
 
 ### Framework versions
 

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9d12063d8151aeaef325ddd596358c1463c6be50245f3f727f5eddad26612ea
+oid sha256:84181eb84690c54f9779a9c04c3f109198fbb1bd1cd8e0b78f3fdbb45f30014d
 size 267910893