This model is a fine-tuned version of varun-v-rao/bert-base-cased-fp-sick on the snli dataset. It achieves the following results on the evaluation set:

Loss: 0.5042
Accuracy: 0.8003

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 256
eval_batch_size: 128
seed: 55
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6476	1.0	2146	0.5550	0.7733
0.5965	2.0	4292	0.5122	0.7993
0.5787	3.0	6438	0.5042	0.8003

Framework versions

Transformers 4.35.2
Pytorch 2.0.1+cu118
Datasets 2.15.0
Tokenizers 0.15.0

varun-v-rao/bert-base-cased-fp-sick-lora-snli-model1

bert-base-cased-fp-sick-lora-snli-model1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

varun-v-rao/
bert-base-cased-fp-sick-lora-snli-model1