Sentence Similarity
sentence-transformers
PyTorch
English
deberta-v2
feature-extraction
Generated from Trainer
dataset_size:78183
loss:AdaptiveLayerLoss
loss:CoSENTLoss
loss:GISTEmbedLoss
loss:OnlineContrastiveLoss
loss:MultipleNegativesSymmetricRankingLoss
Eval Results (legacy)
text-embeddings-inference
Commit History
-
all layer trained for every step.AdaptiveLayerLoss(model=model,
Verified signatureloss=train_loss, n_layers_per_step = -1, last_layer_weight = 1.5, prior_layers_weight= 0.1, kl_div_weight = 0.5, kl_temperature= 1, ) num_epochs = 2 learning_rate = 2e-5 warmup_ratio=0.25 weight_decay = 1e-6 schedule = "cosine_with_restarts" num_cycles = 3d1dc986 -
all layer trained for every step.AdaptiveLayerLoss(model=model,
Verified signatureloss=train_loss, n_layers_per_step = -1, last_layer_weight = 2, prior_layers_weight= 0.1, kl_div_weight = 0.5, kl_temperature= 1, ) learning_rate = 3e-5, warmup_ratio=0.2, weight_decay= 2e-6, per_device_train_batch_size=28,ca0ee78 -
all layer trained for every step.AdaptiveLayerLoss(model=model,
Verified signatureloss=train_loss, n_layers_per_step = -1, last_layer_weight = 2, prior_layers_weight= 0.1, kl_div_weight = 0.5, kl_temperature= 1, ) learning_rate = 3e-5, warmup_ratio=0.2, weight_decay= 2e-6, per_device_train_batch_size=28,8cfc6ec