32 lines
1022 B
Plaintext
32 lines
1022 B
Plaintext
# Loss + optimizer + sampler — symmetric InfoNCE, AdamW, mutex sampler.
|
|
TrainingConfig.loss_type = 'symmetric'
|
|
TrainingConfig.tau_init = 0.07
|
|
TrainingConfig.tau_min = 0.01
|
|
TrainingConfig.tau_max = 0.1
|
|
TrainingConfig.learnable_temperature = True
|
|
TrainingConfig.label_smoothing = 0.1
|
|
|
|
TrainingConfig.tau_final = 0.01
|
|
TrainingConfig.weight_q2g = 0.6
|
|
TrainingConfig.weight_g2q = 0.4
|
|
TrainingConfig.hard_mining_k = 0
|
|
TrainingConfig.neg_bank_size = 0
|
|
|
|
# WeightedInfoNCE-only (unused when loss_type='symmetric').
|
|
TrainingConfig.weighted_loss_k = 5.0
|
|
|
|
TrainingConfig.learning_rate = 1e-4
|
|
TrainingConfig.text_lr_factor = 0.1
|
|
TrainingConfig.weight_decay = 1e-4
|
|
TrainingConfig.grad_clip = 1.0
|
|
|
|
TrainingConfig.sampler_type = 'mutex'
|
|
TrainingConfig.dss_warmup_epochs = 1
|
|
TrainingConfig.dss_reembed_every = 1
|
|
TrainingConfig.dss_knn_device = 'cuda'
|
|
TrainingConfig.dss_use_lsh = False
|
|
TrainingConfig.dss_lsh_num_tables = 8
|
|
TrainingConfig.dss_lsh_num_bits = 14
|
|
TrainingConfig.dss_cache_dir = None
|
|
TrainingConfig.use_mutex_sampler = True
|