End of training

README.md

@@ -1,5 +1,6 @@
 ---
-base_model: huawei-noah/TinyBERT_General_4L_312D
+license: mit
+base_model: roberta-base
 tags:
 - generated_from_trainer
 metrics:
@@ -14,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # NLP_Capstone
 
-This model is a fine-tuned version of [huawei-noah/TinyBERT_General_4L_312D](https://huggingface.co/huawei-noah/TinyBERT_General_4L_312D) on an unknown dataset.
+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: 0.3046
-- Accuracy: 0.8807
+- Loss: 0.2569
+- Accuracy: 0.9311
 
 ## Model description
 
@@ -37,8 +38,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 32
-- eval_batch_size: 32
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -46,18 +47,18 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.4323        | 1.0   | 623  | 0.3441          | 0.8573   |
-| 0.3047        | 2.0   | 1246 | 0.3249          | 0.8699   |
-| 0.2598        | 3.0   | 1869 | 0.3046          | 0.8807   |
-| 0.2298        | 4.0   | 2492 | 0.3078          | 0.8828   |
-| 0.2086        | 5.0   | 3115 | 0.3129          | 0.8824   |
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 0.2645        | 1.0   | 2491  | 0.2569          | 0.9311   |
+| 0.19          | 2.0   | 4982  | 0.3083          | 0.9301   |
+| 0.1172        | 3.0   | 7473  | 0.3950          | 0.9307   |
+| 0.0654        | 4.0   | 9964  | 0.4016          | 0.9390   |
+| 0.0208        | 5.0   | 12455 | 0.4682          | 0.9376   |
 
 
 ### Framework versions
 
-- Transformers 4.34.1
+- Transformers 4.35.0
 - Pytorch 2.1.0+cu118
 - Datasets 2.14.6
 - Tokenizers 0.14.1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7300275e9eabf455d20e5b4438bfffc5108b5e26ea9110968716721f9cdda27
+oid sha256:18752dde6d10b26ec086389e9909621fafa5b325e7894fc21ff09b6d9d372dec
 size 498612824

runs/Nov02_22-18-36_8737697ea2eb/events.out.tfevents.1698963580.8737697ea2eb.401.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ceddc86a0d2decf9b6cf2c5ff0bf46bba6d49a7cccdeb9e2b779d3cfe5e687b
-size 8474
+oid sha256:aa90fa315c5ffe1556265c8b5d3123916dbb3fe61aa33d5e399dc6535db9d414
+size 9936

runs/Nov02_22-18-36_8737697ea2eb/events.out.tfevents.1698974520.8737697ea2eb.401.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b74c8e583e0cb85071f32bec0f5954c28bc8a51d0fbd71b6b0a7fb5fcfdc3d02
+size 411