End of training

README.md

@@ -61,22 +61,6 @@ The following hyperparameters were used during training:
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:-----------------:|:--------:|:---------------:|:------------:|:---------------:|:------------:|
 | 0.3655        | 1.69  | 200  | 0.4396          | 0.8166   | 0.8171   | 0.8185            | 0.8171   | 0.8163          | 0.8185       | 0.8171          | 0.8171       |
 
-### eval result
-|Datasets|asadfgglie/nli-zh-tw-all/test|asadfgglie/BanBan_2024-10-17-facial_expressions-nli/test|eval_dataset|test_dataset|
-| :---: | :---: | :---: | :---: | :---: |
-|eval_loss|0.507|0.871|0.535|0.546|
-|eval_f1_macro|0.81|0.575|0.783|0.788|
-|eval_f1_micro|0.811|0.58|0.785|0.789|
-|eval_accuracy_balanced|0.811|0.584|0.783|0.788|
-|eval_accuracy|0.811|0.58|0.785|0.789|
-|eval_precision_macro|0.81|0.59|0.783|0.788|
-|eval_recall_macro|0.811|0.584|0.783|0.788|
-|eval_precision_micro|0.811|0.58|0.785|0.789|
-|eval_recall_micro|0.811|0.58|0.785|0.789|
-|eval_runtime|50.625|0.613|11.113|44.111|
-|eval_samples_per_second|167.901|1544.075|169.975|171.319|
-|eval_steps_per_second|2.627|24.483|2.699|2.698|
-|Size of dataset|8500|946|1889|7557|
 
 ### Framework versions
 

config.json

@@ -30,7 +30,7 @@
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
-  "torch_dtype": "float32",
+  "torch_dtype": "float16",
   "transformers_version": "4.33.3",
   "type_vocab_size": 1,
   "use_cache": true,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bce1ed232c1a3b5d465b5132f09604e7cb360ca1a488e36ac70abd1a65707f9a
-size 2239705966
+oid sha256:ba1d9c8c3417523893b2716e4a6f2ebcc6fe89ee30a02e3f4a4f81ac137ca915
+size 1119921006