Model save

README.md

@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7838
-- Accuracy: 0.7574
+- Loss: 0.6733
+- Accuracy: 0.7685
 
 ## Model description
 
@@ -45,17 +45,45 @@ The following hyperparameters were used during training:
 - 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
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 4
+- num_epochs: 32
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.9521        | 1.0   | 666  | 1.2573          | 0.6477   |
-| 1.2266        | 2.0   | 1332 | 0.8911          | 0.7470   |
-| 0.9458        | 3.0   | 1998 | 0.8049          | 0.7547   |
-| 0.796         | 4.0   | 2664 | 0.7838          | 0.7574   |
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 2.1739        | 1.0   | 666   | 2.0326          | 0.2935   |
+| 1.9721        | 2.0   | 1332  | 1.3851          | 0.6387   |
+| 1.5155        | 3.0   | 1998  | 0.8932          | 0.7512   |
+| 0.8468        | 4.0   | 2664  | 0.7398          | 0.7696   |
+| 0.7476        | 5.0   | 3330  | 0.6910          | 0.7739   |
+| 0.6958        | 6.0   | 3996  | 0.6723          | 0.7773   |
+| 0.628         | 7.0   | 4662  | 0.6542          | 0.7823   |
+| 0.6108        | 8.0   | 5328  | 0.6435          | 0.7812   |
+| 0.5897        | 9.0   | 5994  | 0.6433          | 0.7795   |
+| 0.5641        | 10.0  | 6660  | 0.6367          | 0.7808   |
+| 0.5473        | 11.0  | 7326  | 0.6393          | 0.7827   |
+| 0.5367        | 12.0  | 7992  | 0.6329          | 0.7803   |
+| 0.5164        | 13.0  | 8658  | 0.6391          | 0.7769   |
+| 0.5133        | 14.0  | 9324  | 0.6371          | 0.7797   |
+| 0.5006        | 15.0  | 9990  | 0.6371          | 0.7767   |
+| 0.4928        | 16.0  | 10656 | 0.6410          | 0.7784   |
+| 0.4898        | 17.0  | 11322 | 0.6473          | 0.7792   |
+| 0.4661        | 18.0  | 11988 | 0.6443          | 0.7743   |
+| 0.463         | 19.0  | 12654 | 0.6516          | 0.7745   |
+| 0.456         | 20.0  | 13320 | 0.6573          | 0.7754   |
+| 0.4643        | 21.0  | 13986 | 0.6613          | 0.7750   |
+| 0.4471        | 22.0  | 14652 | 0.6608          | 0.7722   |
+| 0.4525        | 23.0  | 15318 | 0.6601          | 0.7718   |
+| 0.4395        | 24.0  | 15984 | 0.6645          | 0.7703   |
+| 0.4396        | 25.0  | 16650 | 0.6647          | 0.7690   |
+| 0.4371        | 26.0  | 17316 | 0.6682          | 0.7709   |
+| 0.4234        | 27.0  | 17982 | 0.6669          | 0.7707   |
+| 0.4282        | 28.0  | 18648 | 0.6706          | 0.7700   |
+| 0.4181        | 29.0  | 19314 | 0.6705          | 0.7690   |
+| 0.4275        | 30.0  | 19980 | 0.6727          | 0.7694   |
+| 0.4218        | 31.0  | 20646 | 0.6731          | 0.7685   |
+| 0.423         | 32.0  | 21312 | 0.6733          | 0.7685   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd507911dadb86afc813877dfa3c080c3c072abeb99526b35d9d40b7eb0e54be
+oid sha256:46a2b4b2ec9f77c7a55a6cfff5bfde4eeeff3c70f33cf7c35c7a098f06ab2b01
 size 267854100