SciBERT-SocietalAI-Finetuned

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [allenai/scibert_scivocab_uncased](https://huggingface.co/allenai/scibert_scivocab_uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5248
-- Accuracy: 0.8913
+- Loss: 0.4315
+- Accuracy: 0.8986
 
 ## Model description
 
@@ -43,15 +43,14 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 2
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.294         | 1.0   | 138  | 0.3993          | 0.8732   |
-| 0.2816        | 2.0   | 276  | 0.3760          | 0.8986   |
-| 0.1214        | 3.0   | 414  | 0.5248          | 0.8913   |
+| 0.2976        | 1.0   | 138  | 0.3139          | 0.8877   |
+| 0.2736        | 2.0   | 276  | 0.4315          | 0.8986   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbea7d0cf3bb37fb6fcb334da7014d3a1a926b7564a1d47a449ab7bf52e6b156
+oid sha256:0afec5b9f4f81ac7e4615ae485c51779371fc78066738792b5189d98b1201289
 size 439703544

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abea55f4840e258bbb3506cfc31ec36d376222a164f6f4ed2e85c207cd44e4ec
+oid sha256:15e97843e3922ace0120fe5fe07e5a9a2ec549e8bb597db9bea258aabe05cd64
 size 5240