| { |
| "captured_at_utc": "2026-09-10T11:46:55.802958+00:00", |
| "cuda_runtime": "12.8", |
| "cudnn_version": 91900, |
| "finewebedu_dir": "/content/data/finewebedu", |
| "gpu_capability": [ |
| 8, |
| 0 |
| ], |
| "gpu_name": "NVIDIA A100-SXM4-40GB", |
| "gpu_total_memory_bytes": 42405855232, |
| "packages": { |
| "huggingface_hub": "1.29.0", |
| "safetensors": "0.8.0", |
| "torch": "2.11.0+cu128", |
| "triton": "3.6.0" |
| }, |
| "parameters": { |
| "embedding_tables": 109461504, |
| "total": 179847966, |
| "transformer_body": 70386462 |
| }, |
| "performance_implementation": { |
| "attention_mask": "document_endpoints_128_token_blocks", |
| "muon": "small_matrices_batched_by_shape_device_dtype", |
| "rotary_cache": "initialized_before_compile" |
| }, |
| "persistence": { |
| "checkpoint_interval_tokens": 250000000, |
| "keep_checkpoints": 0, |
| "repo_id": "efe-T/Experiment1-C" |
| }, |
| "platform": "Linux-6.6.122+-x86_64-with-glibc2.39", |
| "python": "3.13.15 (main, Aug 6 2026, 11:06:22) [GCC 13.3.0]", |
| "run_id": "c4cd0856-69c4-42d9-9a1b-b278a89c46d5", |
| "torch_version": "2.11.0+cu128", |
| "training_source_sha256": "4410971f223fa2e69e79655412035034f1055aa09d66d929a45e0d00ab3f9de0", |
| "validation": { |
| "attention_window": 32768, |
| "enabled": true, |
| "filename": "finewebedu_val_000000.bin", |
| "revision": "440d9d739f970c5d80492e12e81d63d60622ca30", |
| "sequences": 32, |
| "sha256": "64682bb1bcc5437ac1cce0efd9dcbee2fd78877b74159e21970f6b9cba734c97", |
| "tokens": 1048576 |
| } |
| } |
|
|
