{ "model": "SpliNet", "dataset": "allenai/c4 en", "training_tokens": 2000000000, "validation_tokens": 5120000, "tokenizer_sha256": "119ec6b2af9cbbc56f297bd606b69f79f6e3130a34ee56122ee813a58d15bb9d", "vocab_size": 32000, "sequence_length": 512, "layers": 12, "hidden_size": 768, "heads": 12, "ffn_size": 3072, "spline_order": 2, "spline_radius": 16, "spline_sidedness": "single", "physical_batch": 160, "effective_batch": 1024, "optimizer": "AdamW", "base_learning_rate": 0.0001, "weight_decay": 0.01, "precision": "bfloat16", "gpu": "NVIDIA A100-SXM4-80GB", "final_validation_loss": 4.6145022583007815, "final_validation_perplexity": 100.93757518673716, "best_validation_loss": 4.6145022583007815, "openreview": "https://openreview.net/forum?id=nWHnuiEF3C", "github": "https://github.com/AngshulMajumdar/SpliNet" }