CoolFace
Modelpublic

batman555/layer_1_classifier_google

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face
0likes14downloads
README.md68 linesDownload Raw Back to root
1---2license: apache-2.03base_model: t5-base4tags:5- generated_from_trainer6metrics:7- accuracy8model-index:9- name: layer_1_classifier_google10  results: []11---12 13<!-- This model card has been generated automatically according to the information the Trainer had access to. You14should probably proofread and complete it, then remove this comment. -->15 16# layer_1_classifier_google17 18This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the None dataset.19It achieves the following results on the evaluation set:20- Loss: 0.456821- Accuracy: 0.902222 23## Model description24 25More information needed26 27## Intended uses & limitations28 29More information needed30 31## Training and evaluation data32 33More information needed34 35## Training procedure36 37### Training hyperparameters38 39The following hyperparameters were used during training:40- learning_rate: 2e-0541- train_batch_size: 3242- eval_batch_size: 3243- seed: 4244- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-0845- lr_scheduler_type: linear46- num_epochs: 847 48### Training results49 50| Training Loss | Epoch | Step | Validation Loss | Accuracy |51|:-------------:|:-----:|:----:|:---------------:|:--------:|52| No log        | 1.0   | 2    | 0.5103          | 1.0      |53| No log        | 2.0   | 4    | 0.4784          | 1.0      |54| No log        | 3.0   | 6    | 0.4533          | 1.0      |55| No log        | 4.0   | 8    | 0.4340          | 1.0      |56| No log        | 5.0   | 10   | 0.4168          | 1.0      |57| No log        | 6.0   | 12   | 0.4040          | 1.0      |58| No log        | 7.0   | 14   | 0.3956          | 1.0      |59| No log        | 8.0   | 16   | 0.3921          | 1.0      |60 61 62### Framework versions63 64- Transformers 4.32.165- Pytorch 2.0.1+cu11866- Datasets 2.14.467- Tokenizers 0.13.368