End of training

README.md

@@ -1,72 +1,69 @@
 ---
-language: en
-tags:
-- sentiment-analysis
-- transformers
-- pytorch
+library_name: transformers
+language:
+- en
 license: apache-2.0
-datasets: 
-- custom-dataset
+base_model: distilbert-base-uncased
+tags:
+- generated_from_trainer
 metrics:
 - accuracy
-model_name: distilbert-base-uncased-finetuned-sentiment
+model-index:
+- name: distilbert-base-uncased-finetuned-sentiment
+  results: []
 ---
 
-# DistilBERT Base Uncased Fine-tuned for Sentiment Analysis
+<!-- 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. -->
 
-## Model Description
+# distilbert-base-uncased-finetuned-sentiment
 
-This model is a fine-tuned version of `distilbert-base-uncased` on a sentiment analysis dataset. It is trained to classify text into positive and negative sentiment categories.
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the imdb-dataset-of-50k-movie-reviews dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2166
+- Accuracy: 0.9263
 
-## Training Details
+## Model description
 
-The model was fine-tuned on a sentiment analysis dataset using the Hugging Face `transformers` library. The training parameters are as follows:
+More information needed
 
-- **Learning Rate**: 2e-5
-- **Batch Size**: 32
-- **Number of Epochs**: 4
-- **Optimizer**: AdamW
-- **Scheduler**: Linear with warmup
-- **Device**: Nvidia T4 GPU
+## Intended uses & limitations
 
-## Training and Validation Metrics
+More information needed
 
-| Step | Training Loss | Validation Loss | Accuracy |
-|------|---------------|-----------------|----------|
-| 400  | 0.389300      | 0.181316        | 93.25%   |
-| 800  | 0.161900      | 0.166204        | 94.13%   |
-| 1200 | 0.114600      | 0.200135        | 94.30%   |
-| 1600 | 0.076300      | 0.211609        | 94.40%   |
-| 2000 | 0.041600      | 0.225439        | 94.45%   |
+## Training and evaluation data
 
-Final training metrics:
+More information needed
 
-- **Global Step**: 2000
-- **Training Loss**: 0.156715
-- **Training Runtime**: 1257.5696 seconds
-- **Training Samples per Second**: 50.892
-- **Training Steps per Second**: 1.59
-- **Total FLOPS**: 8477913513984000.0
-- **Epochs**: 4.0
+## Training procedure
 
-## Model Performance
+### Training hyperparameters
 
-The model achieves an accuracy of approximately 94.45% on the validation set.
+The following hyperparameters were used during training:
+- learning_rate: 2.5e-05
+- 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
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 5
+- mixed_precision_training: Native AMP
 
-## Usage
+### Training results
 
-To use this model for sentiment analysis, you can load it using the `transformers` library:
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.3029        | 1.0   | 1250 | 0.2369          | 0.9085   |
+| 0.1607        | 2.0   | 2500 | 0.2166          | 0.9263   |
+| 0.0924        | 3.0   | 3750 | 0.2867          | 0.9208   |
+| 0.0521        | 4.0   | 5000 | 0.3193          | 0.9235   |
+| 0.0312        | 5.0   | 6250 | 0.3764          | 0.9227   |
 
-```python
-from transformers import DistilBertTokenizerFast, DistilBertForSequenceClassification
 
-model_name = 'luluw/distilbert-base-uncased-finetuned-sentiment'
-tokenizer = DistilBertTokenizerFast.from_pretrained(model_name)
-model = DistilBertForSequenceClassification.from_pretrained(model_name)
+### Framework versions
 
-# Example usage
-text = "I love this product!"
-inputs = tokenizer(text, return_tensors='pt')
-outputs = model(**inputs)
-predictions = torch.argmax(outputs.logits, dim=-1)
-```
+- Transformers 4.44.2
+- Pytorch 2.5.0+cu121
+- Datasets 3.1.0
+- Tokenizers 0.19.1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8b0b94d570d9e72562ec6a67e1f9e661b8fd37d61713328cbaee868d2d894c1
+oid sha256:1206849e3c05739b6e3bf22cc7eaeb36a30aa7d253db0b5fda5700924cdcfc6f
 size 267832560

runs/Nov10_17-03-26_f6031cd483a5/events.out.tfevents.1731258420.f6031cd483a5.323.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67c95f1e6f50faa95c018d9c8a825ee37aa3eb6cd5634cbeb4647663335f8335
-size 7672
+oid sha256:2df890952a7d0da62e644e9e049b65069e27e68594739f8232bcaa4f14f07765
+size 8026

runs/Nov10_17-03-26_f6031cd483a5/events.out.tfevents.1731261865.f6031cd483a5.323.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2db3174734ef3f66770fe0084eff460f5a4a913807a6dda62c6696ea68bdb73
+size 411