End of training

README.md

@@ -3,6 +3,8 @@ license: mit
 base_model: openai-community/roberta-base-openai-detector
 tags:
 - generated_from_trainer
+metrics:
+- accuracy
 model-index:
 - name: train_debug
   results: []
@@ -14,6 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
 # train_debug
 
 This model is a fine-tuned version of [openai-community/roberta-base-openai-detector](https://huggingface.co/openai-community/roberta-base-openai-detector) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0400
+- Accuracy: 0.995
+- Roc Auc: 0.9996
 
 ## Model description
 
@@ -40,6 +46,14 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - num_epochs: 2
 
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy | Roc Auc |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|:-------:|
+| 0.065         | 1.0   | 6250  | 0.0451          | 0.994    | 0.9989  |
+| 0.0223        | 2.0   | 12500 | 0.0400          | 0.995    | 0.9996  |
+
+
 ### Framework versions
 
 - Transformers 4.36.0

config.json

@@ -28,6 +28,7 @@
   "output_past": true,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
   "torch_dtype": "float32",
   "transformers_version": "4.36.0",
   "type_vocab_size": 1,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6430586d4db241308ae480d82475f3ca2a5a0c563ee4d375c0485ca6ebeb9bb6
+oid sha256:e240e630227ca033d08e7f5052431a70ce78e213b7972da74f0bfe6a981bf367
 size 498612824

runs/Jan20_02-30-22_5363b5ff727f/events.out.tfevents.1705717826.5363b5ff727f.26.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:568d841569e2f2861bb97be6de4004fcca07e614fa992399221e714b202f9f00
+size 9545

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d209a6edb532104bf131c8f92bccb377ef093f3154a568108ff2afa52b4cd91c
+oid sha256:9667ab544b855eff62830fc1858c8a611a1ac033fbadaf656e033e2ad09ef18a
 size 4283