mhr2004/plm-nsp-10000

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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3057
+- Loss: 0.3458
 
 ## Model description
 
@@ -35,8 +35,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 1024
-- eval_batch_size: 1024
+- train_batch_size: 128
+- eval_batch_size: 128
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -46,12 +46,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.5659        | 1.0   | 20   | 0.3155          |
-| 0.2655        | 2.0   | 40   | 0.2214          |
-| 0.1577        | 3.0   | 60   | 0.2089          |
-| 0.102         | 4.0   | 80   | 0.2469          |
-| 0.0706        | 5.0   | 100  | 0.2625          |
-| 0.052         | 6.0   | 120  | 0.3057          |
+| 0.3481        | 1.0   | 157  | 0.2161          |
+| 0.1366        | 2.0   | 314  | 0.2019          |
+| 0.0759        | 3.0   | 471  | 0.2479          |
+| 0.0535        | 4.0   | 628  | 0.3482          |
+| 0.0443        | 5.0   | 785  | 0.3458          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cad6daba5fdae30a16788e8a4a72fe75024c9f848c3ff1cae2fc28e657d51b5
+oid sha256:4b7a31bce40b5039e5e4582b1c47f746e4766349c9ee01fa74d9b72cf7d7e8fc
 size 498612824

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60ebb6b2c9c7ebadde7cd41f4b992d7b858903a865d74c1ffb9cb75f471abc2f
+oid sha256:e29c957cd88b53f0bd9712e84d8dd1fc2311d20bf8b9476bc045ff21efdab3be
 size 4920