{ "training_config": { "training_data_paths": "['/nobackup/projects/bdman17/Choronos/data_round2/time_series_2018.arrow']", "probability": "[1.0]", "context_length": 512, "max_steps": 200000, "save_steps": 25000, "log_steps": 500, "per_device_train_batch_size": 256, "learning_rate": 0.001, "optim": "adamw_torch_fused", "shuffle_buffer_length": 100000, "gradient_accumulation_steps": 1, "model_id": "google/t5-efficient-mini", "model_type": "seq2seq", "random_init": true, "tie_embeddings": true, "output_dir": "/nobackup/projects/bdman17/Choronos/models/Mini_new_R2/2018", "tf32": true, "torch_compile": true, "tokenizer_class": "MeanScaleUniformBins", "tokenizer_kwargs": "{'low_limit': -15.0, 'high_limit': 15.0}", "n_tokens": 4096, "n_special_tokens": 2, "pad_token_id": 0, "eos_token_id": 1, "use_eos_token": true, "lr_scheduler_type": "linear", "warmup_ratio": 0.0, "dataloader_num_workers": 20, "num_samples": 20, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "seed": 1234, "model_name": "Mini_R2_2018", "max_missing_prop": 0.9, "min_past": 60, "prediction_length": 64 }, "job_info": { "cuda_available": true, "device_count": 1, "device_names": { "0": "NVIDIA GH200 480GB" }, "mem_info": { "0": [ 52732624896, 102005473280 ] }, "torchelastic_launched": false, "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "torch_version": "2.3.0a0+ebedce2", "numpy_version": "1.24.4", "gluonts_version": "0.16.0", "transformers_version": "4.41.0.dev0", "accelerate_version": "0.34.2" } }