From ba73c8a7e8d975c9151ba9acc42a199070d7602f Mon Sep 17 00:00:00 2001 From: rzen Date: Sun, 12 Jul 2026 12:35:47 -0400 Subject: [PATCH] Phase 4: v1 training run results (val loss 1.52, ppl ~4.6) - reports/loss-v1.csv: full train/val loss log over 20k steps - reports/loss-v1.txt: ASCII loss curve (steep descent then flattening tail) Training ran ~58 min on M1 MPS at 5.7 it/s. No overfitting (train~=val). --- reports/loss-v1.csv | 40 ++++++++++++++++++++++++++++++++++++++++ reports/loss-v1.txt | 22 ++++++++++++++++++++++ 2 files changed, 62 insertions(+) create mode 100644 reports/loss-v1.csv create mode 100644 reports/loss-v1.txt diff --git a/reports/loss-v1.csv b/reports/loss-v1.csv new file mode 100644 index 0000000..567ae63 --- /dev/null +++ b/reports/loss-v1.csv @@ -0,0 +1,40 @@ +iter,train_loss,val_loss,lr +500,2.8285,2.8171,0.000600 +1000,2.3311,2.3267,0.000598 +1500,2.1135,2.1026,0.000594 +2000,2.0013,2.0002,0.000589 +2500,1.9253,1.9230,0.000582 +3000,1.8811,1.8752,0.000574 +3500,1.8399,1.8429,0.000564 +4000,1.8119,1.8128,0.000552 +4500,1.7775,1.7905,0.000540 +5000,1.7589,1.7616,0.000525 +5500,1.7466,1.7440,0.000510 +6000,1.7248,1.7261,0.000494 +6500,1.7038,1.7093,0.000476 +7000,1.6980,1.7023,0.000458 +7500,1.6829,1.6890,0.000438 +8000,1.6747,1.6796,0.000418 +8500,1.6572,1.6673,0.000398 +9000,1.6506,1.6452,0.000377 +9500,1.6408,1.6319,0.000356 +10000,1.6290,1.6307,0.000334 +10500,1.6202,1.6215,0.000313 +11000,1.6126,1.6166,0.000292 +11500,1.6132,1.6014,0.000271 +12000,1.5962,1.5903,0.000250 +12500,1.5851,1.5741,0.000230 +13000,1.5807,1.5864,0.000210 +13500,1.5666,1.5754,0.000191 +14000,1.5693,1.5663,0.000173 +14500,1.5564,1.5673,0.000156 +15000,1.5571,1.5529,0.000141 +15500,1.5415,1.5444,0.000126 +16000,1.5441,1.5388,0.000113 +16500,1.5396,1.5356,0.000101 +17000,1.5360,1.5270,0.000090 +17500,1.5305,1.5278,0.000081 +18000,1.5281,1.5263,0.000073 +18500,1.5192,1.5244,0.000068 +19000,1.5191,1.5201,0.000063 +19500,1.5122,1.5198,0.000061 diff --git a/reports/loss-v1.txt b/reports/loss-v1.txt new file mode 100644 index 0000000..77cdf10 --- /dev/null +++ b/reports/loss-v1.txt @@ -0,0 +1,22 @@ +loss curve — v1 (final train 1.5122, val 1.5198 @ iter 19500) + 2.829 |* + 2.751 | + 2.674 | + 2.596 | + 2.519 | + 2.441 | + 2.364 | * + 2.286 | + 2.209 | + 2.132 | * + 2.054 | + 1.977 | * + 1.899 | ** + 1.822 | * ** + 1.744 | . * ** * + 1.667 | . ** * ** * * + 1.590 | * ** * ** * ** * + 1.512 | ** * ** * ** * + +---------------------------------------------------------------- + 500 19500 + legend: '.' train '*' val (x: iter, y: loss)