Training complete

README.md

@@ -0,0 +1,52 @@
+---
+license: mit
+base_model: FacebookAI/roberta-base
+tags:
+- generated_from_trainer
+model-index:
+- name: roberta_base_TextClass_IMDB_adamw_torch
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# roberta_base_TextClass_IMDB_adamw_torch
+
+This model is a fine-tuned version of [FacebookAI/roberta-base](https://huggingface.co/FacebookAI/roberta-base) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- 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
+- num_epochs: 5
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.34.1
+- Pytorch 2.3.0+cu118
+- Datasets 2.19.0
+- Tokenizers 0.14.1

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a39f27cfa76db7aa395cadfd4a9ddfcaae4a04be0df78df28b7d56a241f15602
+oid sha256:09a720747bd5e5e2b853b34ab8485c9c6cf1e1b2a2b589d83272fa9789206540
 size 498658094

test_metrics.json

@@ -0,0 +1,3 @@
+{
+    "test_accuracy": 0.94928
+}

train_losses.csv

@@ -0,0 +1,33 @@
+loss,epoch
+0.3832,0.16
+0.3023,0.32
+0.2967,0.48
+0.2778,0.64
+0.2507,0.8
+0.2765,0.96
+0.179,1.12
+0.2017,1.28
+0.1742,1.44
+0.1759,1.6
+0.1791,1.76
+0.1834,1.92
+0.1214,2.08
+0.0941,2.24
+0.11,2.4
+0.0935,2.56
+0.0875,2.72
+0.1161,2.88
+0.0906,3.04
+0.0518,3.2
+0.0546,3.36
+0.0566,3.52
+0.0454,3.68
+0.0533,3.84
+0.0367,4.0
+0.0294,4.16
+0.0331,4.32
+0.0221,4.48
+0.0318,4.64
+0.0361,4.8
+0.0262,4.96
+0.1304085351715088,5.0