Jobs
job-git_github.com_AGMoller_worker_vs_gpt.git_src_worker_vs_gpt___main__.py
Job
14 versions
2 years ago
All versions
Run
State
Job version
Creation date
Creator
lr
bf16
ckpt
fp16
fsdp
seed
tf32
debug
optim
top_k
top_p
prefix
do_eval
no_cuda
do_train
id2label
label2id
run_name
sampling
use_ipex
adafactor
data_seed
deepspeed
do_sample
hub_token
log_level
max_steps
num_beams
ray_scope
report_to
typical_p
use_cache
adam_beta1
adam_beta2
batch_size
do_predict
eval_delay
eval_steps
hidden_act
is_decoder
local_rank
max_length
min_length
model_type
num_epochs
optim_args
output_dir
past_index
save_steps
train_size
vocab_size
ddp_backend
ddp_timeout
fsdp_config
hidden_size
label_names
logging_dir
push_to_hub
return_dict
sharded_ddp
temperature
torch_dtype
torchdynamo
torchscript
xpu_backend
adam_epsilon
bos_token_id
disable_tqdm
eos_token_id
fp16_backend
hub_model_id
hub_strategy
pad_token_id
problem_type
pruned_heads
sep_token_id
use_bfloat16
warmup_ratio
warmup_steps
weight_decay
architectures
bad_words_ids
jit_mode_eval
learning_rate
logging_steps
max_grad_norm
mp_parameters
output_scores
save_strategy
torch_compile
tpu_num_cores
bf16_full_eval
early_stopping
fp16_full_eval
fp16_opt_level
layer_norm_eps
length_penalty
tf_legacy_loss
use_mps_device
eval_batch_size
finetuning_task
group_by_length
num_beam_groups
suppress_tokens
tokenizer_class
type_vocab_size
full_determinism
hub_private_repo
ignore_data_skip
log_on_each_node
logging_strategy
num_train_epochs
save_safetensors
save_total_limit
train_batch_size
ddp_bucket_cap_mb
diversity_penalty
greater_is_better
initializer_range
intermediate_size
log_level_replica
lr_scheduler_type
num_hidden_layers
output_attentions
push_to_hub_token
save_on_each_node
tpu_metrics_debug
augmentation_model
classifier_dropout
is_encoder_decoder
length_column_name
logging_first_step
repetition_penalty
torch_compile_mode
use_augmented_data
add_cross_attention
evaluation_strategy
forced_bos_token_id
forced_eos_token_id
fsdp_min_num_params
hidden_dropout_prob
num_attention_heads
skip_memory_metrics
tie_encoder_decoder
tie_word_embeddings
auto_find_batch_size
dataloader_drop_last
no_repeat_ngram_size
num_return_sequences
output_hidden_states
overwrite_output_dir
prediction_loss_only
push_to_hub_model_id
task_specific_params
transformers_version
begin_suppress_tokens
dataloader_pin_memory
metric_for_best_model
remove_invalid_values
remove_unused_columns
torch_compile_backend
dataloader_num_workers
decoder_start_token_id
gradient_checkpointing
half_precision_backend
label_smoothing_factor
load_best_model_at_end
logging_nan_inf_filter
resume_from_checkpoint
chunk_size_feed_forward
eval_accumulation_steps
max_position_embeddings
per_gpu_eval_batch_size
position_embedding_type
return_dict_in_generate
per_gpu_train_batch_size
push_to_hub_organization
ddp_find_unused_parameters
include_inputs_for_metrics
per_device_eval_batch_size
use_legacy_prediction_loop
cross_attention_hidden_size
gradient_accumulation_steps
per_device_train_batch_size
attention_probs_dropout_prob
encoder_no_repeat_ngram_size
exponential_decay_length_penalty
fsdp_transformer_layer_cls_to_wrap
No rows found
Loading...