Views
No views yet
PYTORCH_CUDA_ALLOC_CONF=backend:cudaMallocAsync.eval/ppl.py: -- Bitrate: 3.02 bpw / 6.00 bpw (head)
-- Evaluated: 100 rows of 2048 tokens
-- Perplexity: 4.026279 -- Bitrate: 3.07 bpw / 6.00 bpw (head)
-- Evaluated: 100 rows of 2048 tokens
-- Perplexity: 3.935338eval/model_diff.py courtesy of turboderp: -- original perplexity: 1.76745635
-- original label in top-K:
K = 1: 0.8681
K = 2: 0.9237
K = 3: 0.9411
K = 4: 0.9502
K = 5: 0.9564
-- 3.0bpw-h6 perplexity: 2.14967564
-- 3.0bpw-h6 label in top-K:
K = 1: 0.8142
K = 2: 0.8949
K = 3: 0.9231
K = 4: 0.9368
K = 5: 0.9464
-- Top-K agreement, 3.0bpw-h6 vs original:
K = 1: 0.8820
K = 2: 0.5225
K = 3: 0.2585
K = 4: 0.1132
K = 5: 0.0491
-- KL divergence (3.0bpw-h6, original): 0.23334818 -- original perplexity: 1.76745635
-- original label in top-K:
K = 1: 0.8681
K = 2: 0.9237
K = 3: 0.9411
K = 4: 0.9502
K = 5: 0.9564
-- 3.07bpw-h6-custom perplexity: 2.03357968
-- 3.07bpw-h6-custom label in top-K:
K = 1: 0.8305
K = 2: 0.9021
K = 3: 0.9286
K = 4: 0.9416
K = 5: 0.9504
-- Top-K agreement, 3.07bpw-h6-custom vs original:
K = 1: 0.8981
K = 2: 0.5702
K = 3: 0.3027
K = 4: 0.1461
K = 5: 0.0691
-- KL divergence (3.07bpw-h6-custom, original): 0.17770892