File size: 1,421 Bytes
8231c96 be8f838 8231c96 be8f838 8231c96 be8f838 bea74ce be8f838 8231c96 89e5329 8231c96 be8f838 8231c96 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 | {
"checkpoint_id": "ckpt_20260501_200153_10500_22deff1b_9470fbb7",
"created_at": "2026-05-01T20:01:53.978286",
"iteration": 10500,
"epoch": 0,
"train_loss": 0.0,
"val_loss": 0.0004545312749178265,
"learning_rate": 0.0001351594653179428,
"model_config": {
"n_layer": 4,
"n_head": 4,
"n_embd": 256,
"vocab_size": 50257,
"block_size": 1024,
"dropout": 0.1,
"bias": true,
"initial_connections": 0.1,
"connection_growth_rate": 0.05,
"max_connections": 1.0
},
"training_config": {
"learning_rate": 0.0002,
"batch_size": 2,
"max_iters": 500,
"warmup_iters": 5000,
"lr_decay_iters": 50000,
"min_lr": 1e-05,
"weight_decay": 0.1,
"grad_clip": 1.0,
"enable_curriculum_learning": true,
"enable_introspection": true
},
"data_config": {
"data_dir": "data/nanecho",
"batch_size": 2,
"block_size": 1024
},
"metrics": {
"val_loss": 0.0004545312749178265,
"connection_ratio": 1.0,
"tokens_processed": 21504000,
"training_speed_iters_per_sec": 0.08491136571335567
},
"tags": [
"phase_adaptive_mastery",
"high_quality",
"nanecho",
"curriculum",
"introspection"
],
"parent_checkpoint": null,
"notes": "Training checkpoint at iteration 10500 (resumed from iteration 10000) | Phase: adaptive_mastery",
"file_size_mb": 253.3669786453247,
"quality_score": 1612800.7810844148
} |