File size: 1,488 Bytes
95456ed | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 | {
"lr": 0.0001,
"batch_size": 128,
"microbatch": 64,
"learning_steps": 80000,
"log_interval": 50,
"save_interval": 5000,
"eval_interval": 500,
"ema_rate": "0.9999",
"resume_checkpoint": "none",
"schedule_sampler": "lossaware",
"diffusion_steps": 2000,
"noise_schedule": "sqrt",
"timestep_respacing": "",
"vocab": "bert",
"use_plm_init": "no",
"vocab_size": 0,
"config_name": "bert-base-cased",
"gpt_config_name": "gpt2",
"notes": "folder-notes",
"data_dir": "processed_data_emtec",
"dataset": "dataset-name",
"checkpoint_path": "checkpoint-path/test-run",
"seq_len": 352,
"hidden_t_dim": 352,
"hidden_dim": 256,
"dropout": 0.1,
"use_fp16": false,
"fp16_scale_growth": 0.001,
"seed": 102,
"gradient_clipping": -1.0,
"weight_decay": 0.0,
"learn_sigma": false,
"use_kl": false,
"predict_xstart": true,
"rescale_timesteps": true,
"rescale_learned_sigmas": false,
"sigma_small": false,
"emb_scale_factor": 1.0,
"num_transformer_layers": 12,
"num_transformer_heads": 8,
"one_noise_step": true,
"mask_padding": false,
"celer_only_L1": true,
"data_split_criterion": "scanpath",
"corpus": "emtec",
"inference": "none",
"n_folds": 5,
"ablation_type": "none",
"nll_in_loss": false,
"load_from_checkpoint": false,
"load_train_data": "-"
}
|