Method__init__(
self,
optimizer,
max_lr,
min_lr,
warmup_steps,
decay_steps,
codegeex/megatron/learning_rates.py:26
Method__init__(
self,
hidden_size,
num_attention_heads,
layer_number,
fp16=True,
codegeex/oneflow/codegeex_model.py:58
Method__init__(
self,
hidden_size,
num_attention_heads,
layer_number,
fp16=True,
codegeex/oneflow/codegeex_model.py:285
Method__init__(
self,
hidden_size,
num_attention_heads,
layer_number,
fp16=True,
codegeex/paddle/codegeex_model.py:57
Method__init__(
self,
hidden_size,
num_attention_heads,
layer_number,
fp16=True,
codegeex/paddle/codegeex_model.py:233
Method__init__(self, params, learning_rate=1e-3, beta1=0.9, beta2=0.999, eps=1e-6, weight_decay=0.0)
codegeex/mindspore/src/utils.py:49
Method__init__(self, network, optimizer, config, scale_update_cell=None, enable_global_norm=True)
codegeex/mindspore/src/pangu_alpha_wrapcell_finetune.py:181
Method__init__(self, model, eval_dataset, ppl_metric, validation_loss, print_per_step=250, has_trained_step=0,
codegeex/mindspore/src/callbacks.py:102
Method__init__(self, cache_dir, bucket, local_rank=0, has_trained_epoch=0, has_trained_step=0, syn_times=100)
codegeex/mindspore/src/callbacks.py:162
Method__init__(self, network, optimizer, config, scale_update_cell=None, enable_global_norm=True)
codegeex/mindspore/src/pangu_alpha_wrapcell.py:181
Method__init__(self, params, learning_rate=1e-3, beta1=0.9, beta2=0.999, eps=1e-6, weight_decay=0.0,
clip_n
codegeex/mindspore/src/adam.py:136