Commit History
-
Update README.md
Verified signature202ecf5
-
Update README.md
Verified signature1ea8d08
-
Update README.md
Verified signaturedac415d -
Upload tokenizer
Verified signature3f5837f -
Update README.md
Verified signatured49689e
-
Update README.md
Verified signature78a8594 -
Update README.md
Verified signaturec9b1cb7 -
Update README.md
Verified signaturedd94905
-
Upload model
Verified signature6ef8c97 -
Update README.md
Verified signatureI trained this model just to learn, using a dataset of product reviews ## HYPERPAREMETERS lr = 1e-3 batch_size = 4 num_epochs = 5 weight_decay = 0.01 LoraConfig: r=4 lora_alpha=32 lora_dropout=0.01 target_modules = ['q_lin'] ## F1_SCORE = 0.9146433d1835a -
Upload model
Verified signaturea89ffdc -
Update README.md
Verified signatureF1-score: 0.906715 accuracy: 0.8905783328808037 #hyperparameters lr = 1e-4 batch_size = 4 num_epochs = 5 weight_decay = 0.01 LoraConfig( task_type="SEQ_CLS", ##sequence classification, r=4, ##intrinsic rank of trainable weight matrix lora_alpha=32, ##this is like learning rate lora_dropout=0.01, ## probality of dropout target_modules = ['q_lin'] ##we apply lora to query layer )e598c92 -
Upload model
Verified signature38e8184 -
Upload model
Verified signatureca1e333 -
Update README.md
Verified signature5bc8ba7 -
Upload model
Verified signature329ae82
-
Upload model
Verified signature8aee098 -
initial commit
Verified signature1fc1d3c