{ "name": "EXLLM-ONI5M-GGUF-companion", "relationship": "separately trained Llama-compatible companion; not converted EX-word weights", "parameters": 5441184, "architecture": { "family": "LlamaForCausalLM", "layers": 6, "hidden_size": 288, "intermediate_size": 608, "attention_heads": 9, "kv_heads": 9, "training_sequence_length": 128, "runtime_context_length": 512, "vocabulary_size": 1024 }, "training_records_including_overlaps": 31842, "validation_records": 2260, "training_files": [ { "path": "oni5m/data/stage1.jsonl", "bytes": 1514468, "sha256": "9ec74f90fbf2066e7d7722af400bb69bad0730b8cd5776eba5ba97b7bd742b60" }, { "path": "oni5m/data/train_balanced.jsonl", "bytes": 2318131, "sha256": "6c4f34db49f5d0cd9a3b825628b763f58685ba2b6ba747f119b6d4e43100c5ef" }, { "path": "oni5m/data/stage3.jsonl", "bytes": 1023877, "sha256": "cdba024563f1dcb975fae9119443ee528556e278a61b960415345fbd901247c9" }, { "path": "oni5m/data/stage4_repair.jsonl", "bytes": 1429497, "sha256": "3fb386a2936a4133ea52e78ad4f43afb175116b909ad9e3b70488e8dc7db501f" }, { "path": "oni5m/data/stage5_mathop.jsonl", "bytes": 175437, "sha256": "128f4d9845b49d44e6f8307ddf76abba16cbed2a3d0daecca34750df7588c6e9" } ], "validation_file": { "path": "oni5m/data/valid.jsonl", "bytes": 447620, "sha256": "fc37b3240a61cde4503f0bd340a94cb813837ce0235e47d47d80dc1f3eac49b8" }, "processed_sequence_tokens": 7154830, "epochs": 10, "steps": 2490, "best_validation_loss": 1.4717197205131836, "seed": 20261002, "history": [ { "epoch": 1, "valid_loss": 1.4717197205131836, "seconds": 11.116554498672485 }, { "epoch": 2, "valid_loss": 1.5578404308833764, "seconds": 20.62734866142273 }, { "epoch": 3, "valid_loss": 1.742609938110946, "seconds": 30.06829810142517 }, { "epoch": 4, "valid_loss": 1.6804442983478163, "seconds": 39.48585367202759 }, { "epoch": 5, "valid_loss": 1.7555806212697047, "seconds": 48.923298835754395 }, { "epoch": 6, "valid_loss": 1.743759198982372, "seconds": 58.34962177276611 }, { "epoch": 7, "valid_loss": 1.7552301105815065, "seconds": 67.88318419456482 }, { "epoch": 8, "valid_loss": 1.848393173895262, "seconds": 77.23627734184265 }, { "epoch": 9, "valid_loss": 1.8836381879996107, "seconds": 86.8110785484314 }, { "epoch": 10, "valid_loss": 1.9468267523296512, "seconds": 96.28844380378723 } ] }