Model save

README.md

@@ -1,17 +1,17 @@
----
-license: mit
-library_name: peft
-tags:
-- generated_from_trainer
-base_model: openai-community/gpt2
-datasets:
-- emotion
-metrics:
-- accuracy
-model-index:
-- name: emotion-gpt2-lora
-  results: []
----
+---
+license: mit
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: openai-community/gpt2
+datasets:
+- emotion
+metrics:
+- accuracy
+model-index:
+- name: emotion-gpt2-lora
+  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. -->
@@ -20,8 +20,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on the emotion dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1514
-- Accuracy: 0.928
+- Loss: 0.1374
+- Accuracy: 0.9395
 
 ## Model description
 
@@ -41,8 +41,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0005
-- train_batch_size: 64
-- eval_batch_size: 64
+- train_batch_size: 32
+- eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -52,16 +52,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 250  | 0.3008          | 0.897    |
-| 0.6384        | 2.0   | 500  | 0.1992          | 0.9265   |
-| 0.6384        | 3.0   | 750  | 0.1801          | 0.9245   |
-| 0.1923        | 4.0   | 1000 | 0.1514          | 0.928    |
+| 0.9231        | 1.0   | 500  | 0.2423          | 0.9145   |
+| 0.2458        | 2.0   | 1000 | 0.1677          | 0.9335   |
+| 0.1833        | 3.0   | 1500 | 0.1530          | 0.938    |
+| 0.1537        | 4.0   | 2000 | 0.1374          | 0.9395   |
 
 
 ### Framework versions
 
 - PEFT 0.10.0
-- Transformers 4.40.2
+- Transformers 4.40.1
 - Pytorch 2.3.0
-- Datasets 2.19.1
+- Datasets 2.19.0
 - Tokenizers 0.19.1