End of training

README.md

@@ -15,12 +15,7 @@ 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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.5726
-- eval_accuracy: 0.7585
-- eval_runtime: 32.8845
-- eval_samples_per_second: 60.819
-- eval_steps_per_second: 7.602
-- step: 0
+- Loss: 0.8887
 
 ## Model description
 
@@ -47,6 +42,18 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - num_epochs: 3
 
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.7323        | 0.5   | 500  | 0.6324          |
+| 0.6503        | 1.0   | 1000 | 0.6049          |
+| 0.511         | 1.5   | 1500 | 0.6623          |
+| 0.4746        | 2.0   | 2000 | 0.6099          |
+| 0.3001        | 2.5   | 2500 | 0.8699          |
+| 0.3052        | 3.0   | 3000 | 0.8887          |
+
+
 ### Framework versions
 
 - Transformers 4.35.0

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3a9ac663717e176a93ed6ae0ec54f1444665e31b886359bd2f509bf16aa9c5e
+oid sha256:d8cbdd811b403580d1693ab28e313a86c9cf633215f7dd3e45c69b34838f57a5
 size 267835644

runs/Nov13_10-32-47_4e183528b7c7/events.out.tfevents.1699871597.4e183528b7c7.491.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d02130a9a25d57196faf8a08efb5baeb5144758b519d3d8142c03d1acb7cf0d2
-size 6425
+oid sha256:47cdeba0847cd480445bfe0cb5f9768db9bc9cb5dec8a04c7e10d893a46e7712
+size 7207