ft-distilroberta-base-with-askscience

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.9974
+- Loss: 2.0739
 
 ## Model description
 
@@ -40,17 +40,15 @@ 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: 5
+- num_epochs: 2
+- mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 281  | 2.0834          |
-| 2.2583        | 2.0   | 562  | 2.0319          |
-| 2.2583        | 3.0   | 843  | 2.0342          |
-| 2.153         | 4.0   | 1124 | 2.0170          |
-| 2.153         | 5.0   | 1405 | 2.0002          |
+| No log        | 1.0   | 336  | 2.0490          |
+| 2.2504        | 2.0   | 672  | 2.0507          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:442a61f4985b4404ac88b7b6931354b1c1bb44633a78167525b709368bbad43f
+oid sha256:a6319a6c91799d74a7550a92f378cd9294e222c7963a06c64aad9b7b170051d6
 size 328693404

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec33708f324cb5a574eff41cf81e560edf53989ce8ecdaad48d2af147c98aafe
+oid sha256:7b019b9f3e2e7fe1e7e752550bb6c743bc579c883d9f3323b96ebe239ffb11f7
 size 4219