my-great-gpt2-review-model

README.md

@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 5.0966
-- Model Preparation Time: 0.0013
+- Loss: 2.1378
+- Model Preparation Time: 0.0022
 
 ## Model description
 
@@ -36,19 +36,19 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.009991
+- learning_rate: 0.005211
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 0.8
+- num_epochs: 1
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss | Model Preparation Time |
-|:-------------:|:------:|:----:|:---------------:|:----------------------:|
-| 5.1163        | 0.8000 | 8118 | 5.0966          | 0.0013                 |
+| Training Loss | Epoch | Step  | Validation Loss | Model Preparation Time |
+|:-------------:|:-----:|:-----:|:---------------:|:----------------------:|
+| 2.227         | 1.0   | 10308 | 2.1378          | 0.0022                 |
 
 
 ### Framework versions

runs/Aug13_18-46-52_9e51d5e8b7ca/events.out.tfevents.1755111062.9e51d5e8b7ca.428.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:993754fb675d6cb99b6fa00a6b557210d937cd0ea3ff6b6dda9faa9d141d0961
-size 9817
+oid sha256:b6900a0cfdff64d901b8b22a248ffa1cd09cef978909e9eef7619cedc5dff050
+size 10508

runs/Aug13_18-46-52_9e51d5e8b7ca/events.out.tfevents.1755113675.9e51d5e8b7ca.428.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d859212685c3be1bc67153a3ff3960cd5aad97e5e426367f465841ba2dc0acf9
+size 425