[scripts.experiment] Reflect changes from evaluation; closes #44 after noticing train-analysis is performed

[engine.predictor] Allow prediction to work when batch-size!=0; Discard CSVs and use JSON for output; Implement lightning logging like in training; Separates batched (collated) data at prediction; Adapts all models to new paradigm; Remove CSVPredictionsWriter; Adapt predict script to all changes