End of training

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4645
-- F1: 0.9171
+- Loss: 0.7747
+- F1: 0.8920
 
 ## Model description
 
@@ -38,8 +38,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 32
-- eval_batch_size: 16
+- train_batch_size: 64
+- eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -49,14 +49,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 3.5614        | 1.0   | 313  | 1.4645          | 0.7468 |
-| 0.8361        | 2.0   | 626  | 0.6110          | 0.9055 |
-| 0.4892        | 3.0   | 939  | 0.4645          | 0.9171 |
+| No log        | 1.0   | 157  | 1.9070          | 0.6876 |
+| 2.8337        | 2.0   | 314  | 0.9826          | 0.8615 |
+| 1.054         | 3.0   | 471  | 0.7747          | 0.8920 |
 
 
 ### Framework versions
 
 - Transformers 4.36.0
-- Pytorch 2.2.1+cu121
-- Datasets 2.18.0
+- Pytorch 2.0.1+cu118
+- Datasets 2.20.0
 - Tokenizers 0.15.2

logs/events.out.tfevents.1721054605.llm-dpo-workbench-0.278.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d425e095ebfc96d4f5db6e2472e585cb8805c52f3cb911979b18727009e6ab7
-size 10473
+oid sha256:636cd4a45eede3d594c20d5f3f63acc871c6b00026a0a3902d90f090c3765aa1
+size 11301

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c882408fe0457f059e7ebc3d61848a1d785fbea9736254f4274e61713b3e4437
+oid sha256:d3ba795cc48c1f6cc0ae0a8f0bd4b76fdf5328615c07d611a454dcba2755a550
 size 438189348