m0vie

README.md

@@ -4,7 +4,7 @@ license: apache-2.0
 base_model: beomi/kcbert-base
 tags:
 - CYH
-- 10class
+- 10_class
 - multi_labels
 - generated_from_trainer
 model-index:
@@ -19,8 +19,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [beomi/kcbert-base](https://huggingface.co/beomi/kcbert-base) on the unsmile_data dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1294
-- Lrap: 0.8817
+- Loss: 0.1549
+- Lrap: 0.8752
 
 ## Model description
 
@@ -43,7 +43,7 @@ The following hyperparameters were used during training:
 - train_batch_size: 64
 - eval_batch_size: 64
 - seed: 42
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- 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: 5
 
@@ -51,16 +51,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Lrap   |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| No log        | 1.0   | 235  | 0.1446          | 0.8602 |
-| No log        | 2.0   | 470  | 0.1274          | 0.8745 |
-| 0.1692        | 3.0   | 705  | 0.1231          | 0.8783 |
-| 0.1692        | 4.0   | 940  | 0.1278          | 0.8831 |
-| 0.0766        | 5.0   | 1175 | 0.1294          | 0.8817 |
+| No log        | 1.0   | 235  | 0.1340          | 0.8753 |
+| No log        | 2.0   | 470  | 0.1364          | 0.8814 |
+| 0.0526        | 3.0   | 705  | 0.1462          | 0.8791 |
+| 0.0526        | 4.0   | 940  | 0.1544          | 0.8754 |
+| 0.0265        | 5.0   | 1175 | 0.1549          | 0.8752 |
 
 
 ### Framework versions
 
-- Transformers 4.44.2
-- Pytorch 2.4.1+cu121
-- Datasets 3.0.1
-- Tokenizers 0.19.1
+- Transformers 4.48.3
+- Pytorch 2.5.1+cu124
+- Datasets 3.3.0
+- Tokenizers 0.21.0

config.json

@@ -49,7 +49,7 @@
   "position_embedding_type": "absolute",
   "problem_type": "multi_label_classification",
   "torch_dtype": "float32",
-  "transformers_version": "4.44.2",
+  "transformers_version": "4.48.3",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 30000

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16fb1b4789011a11770735f86a735ec83af559dcaf25484d82a7a554c12dcdcb
+oid sha256:65fa1581637838c20db0728185d632a2d5cd23a22566fa0fae8d5877bd44305f
 size 435728400

runs/Feb17_06-22-00_12730a3fb4bc/events.out.tfevents.1739773339.12730a3fb4bc.297.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0ce0128e994d1bc00766f5246631fc0638f3918bb0fc443af745ffbfc2612ef
+size 30997

tokenizer_config.json

@@ -45,6 +45,7 @@
   "cls_token": "[CLS]",
   "do_basic_tokenize": true,
   "do_lower_case": false,
+  "extra_special_tokens": {},
   "mask_token": "[MASK]",
   "model_max_length": 300,
   "never_split": null,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86e7753d36151191d543c8315a607ea9cb31cc7a65490631e5e97bb6ac06f417
-size 5176
+oid sha256:8f7f4c54663e23e6a60697164f855198c2f0a905671c59e7e7d424ed2fdf2438
+size 5368