File size: 1,486 Bytes
75442e7 |
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 |
====== Perplexity statistics ======
Mean PPL(Q) : 26.027373 ± 0.255226
Mean PPL(base) : 24.931431 ± 0.241228
Cor(ln(PPL(Q)), ln(PPL(base))): 98.91%
Mean ln(PPL(Q)/PPL(base)) : 0.043020 ± 0.001445
Mean PPL(Q)/PPL(base) : 1.043958 ± 0.001509
Mean PPL(Q)-PPL(base) : 1.095943 ± 0.039245
====== KL divergence statistics ======
Mean KLD: 0.080142 ± 0.000319
Maximum KLD: 6.251925
99.9% KLD: 1.256165
99.0% KLD: 0.545236
99.0% KLD: 0.545236
Median KLD: 0.043817
10.0% KLD: 0.000973
5.0% KLD: 0.000158
1.0% KLD: 0.000006
Minimum KLD: -0.000183
====== Token probability statistics ======
Mean Δp: -0.308 ± 0.018 %
Maximum Δp: 90.671%
99.9% Δp: 40.078%
99.0% Δp: 20.806%
95.0% Δp: 9.213%
90.0% Δp: 4.792%
75.0% Δp: 0.558%
Median Δp: -0.000%
25.0% Δp: -0.862%
10.0% Δp: -5.664%
5.0% Δp: -10.659%
1.0% Δp: -25.039%
0.1% Δp: -47.819%
Minimum Δp: -89.317%
RMS Δp : 6.946 ± 0.038 %
Same top p: 86.343 ± 0.089 %
llama_perf_context_print: load time = 1821.07 ms
llama_perf_context_print: prompt eval time = 1019684.89 ms / 299008 tokens ( 3.41 ms per token, 293.24 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 1045149.32 ms / 299009 tokens
ggml_metal_free: deallocating
|