MadnessSTAR123/my-ynat-model/roberta-base-klue-ynat-classification

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [klue/roberta-base](https://huggingface.co/klue/roberta-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4680
-- Accuracy: 0.846
+- Loss: 0.4441
+- Accuracy: 0.859
 
 ## Model description
 
@@ -44,13 +44,12 @@ The following hyperparameters were used during training:
 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - num_epochs: 1
-- mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.5195        | 1.0   | 1250 | 0.5312          | 0.842    |
+| 0.5318        | 1.0   | 1250 | 0.5333          | 0.845    |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8272f14a8aeefc3355bfdaa5357dd1b63a660b2df5983a1aa8f7688dac89b4a
+oid sha256:b252aba2e5f657a0b6fc580e3f57a325fde5d531f718f6fd44ce2a1b27f31fba
 size 442518100

tokenizer_config.json

@@ -0,0 +1,18 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "is_local": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dc56808e7d296219e3bb60a83384527682b5a6d2d519892548605ed60f7c77b
+oid sha256:e528b2761e1cf589035fce7136709c970cf74388f1476117c93781735977eec2
 size 5137