Model save

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4183
+- Loss: 0.4475
 
 ## Model description
 
@@ -41,21 +41,23 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- num_epochs: 3
+- num_epochs: 5
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.6532        | 1.0   | 586  | 0.5639          |
-| 0.4884        | 2.0   | 1172 | 0.4635          |
-| 0.3384        | 3.0   | 1758 | 0.4183          |
+| 0.6389        | 1.0   | 579  | 0.5691          |
+| 0.4856        | 2.0   | 1158 | 0.4436          |
+| 0.3324        | 3.0   | 1737 | 0.3934          |
+| 0.2259        | 4.0   | 2316 | 0.4446          |
+| 0.1627        | 5.0   | 2895 | 0.4475          |
 
 
 ### Framework versions
 
-- Transformers 4.35.2
-- Pytorch 2.1.0+cu118
+- Transformers 4.36.1
+- Pytorch 2.1.0+cu121
 - Datasets 2.15.0
 - Tokenizers 0.15.0

logs/events.out.tfevents.1702777880.c71d5f26e561.230.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a58671c4e67dfa750c1ff59c9d1b3f86ca98aaf0502cf80763e3298729e803e
-size 5738
+oid sha256:869954bee405faf916be8efb249e413c3f0056b4eb7e0617f5f90f331e5e4a8c
+size 6948

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 269,
+    "max_length": 272,
     "strategy": "LongestFirst",
     "stride": 0
   },