mt5_empty2_5k_msp / t5marulog.jsonl
Kajiura Teruno
Deleted 2,500 words from duplicated vocabulary
84e7c73
{"log": "trained", "date": "2023-07-04T12:04:43", "elapsed": "00:07:10", "model": "/home/acd13734km/PACLIC2023/mt5_empty2_5k", "max_length": 128, "target_max_length": 128, "batch_size": 16, "gradient_accumulation_steps": 1, "train_steps": 4084, "accelerator": "gpu", "devices": "auto", "precision": 32, "strategy": "auto", "gradient_clip_val": 1.0, "compile": true, "solver": "adamw", "lr": 0.0003, "warmup_steps": 1, "training_steps": 100000, "adam_epsilon": 1e-08, "weight_decay": 0.0, "epoch": 5, "step": 3675, "saved": "mt5_empty2_5k_msp"}
{"log": "trained", "date": "2023-07-04T13:28:45", "elapsed": "00:07:13", "model": "/home/acd13734km/PACLIC2023/Hugging/unupload_local_model/mt5_empty2_5k", "max_length": 128, "target_max_length": 128, "batch_size": 16, "gradient_accumulation_steps": 1, "train_steps": 4084, "accelerator": "gpu", "devices": "auto", "precision": 32, "strategy": "auto", "gradient_clip_val": 1.0, "compile": true, "solver": "adamw", "lr": 0.0003, "warmup_steps": 1, "training_steps": 100000, "adam_epsilon": 1e-08, "weight_decay": 0.0, "epoch": 5, "step": 3675, "saved": "mt5_empty2_5k_msp"}