llama_print_timings: load time = 58445.30 ms
llama_print_timings: sample time = 35.70 ms / 512 runs ( 0.07 ms per token, 14340.13 tokens per second)
llama_print_timings: prompt eval time = 58445.21 ms / 42 tokens ( 1391.55 ms per token, 0.72 tokens per second)
llama_print_timings: eval time = 66351.82 ms / 511 runs ( 129.85 ms per token, 7.70 tokens per second)
llama_print_timings: total time = 125442.37 ms
Output generated in 125.62 seconds (4.08 tokens/s, 512 tokens, context 42, seed 677578319)
Llama.generate: prefix-match hit
llama_print_timings: load time = 58445.30 ms
llama_print_timings: sample time = 31.49 ms / 451 runs ( 0.07 ms per token, 14323.83 tokens per second)
llama_print_timings: prompt eval time = 8599.11 ms / 539 tokens ( 15.95 ms per token, 62.68 tokens per second)
llama_print_timings: eval time = 61571.63 ms / 450 runs ( 136.83 ms per token, 7.31 tokens per second)
llama_print_timings: total time = 70750.09 ms
Output generated in 70.92 seconds (6.35 tokens/s, 450 tokens, context 581, seed 535720188)
Llama.generate: prefix-match hit
llama_print_timings: load time = 58445.30 ms
llama_print_timings: sample time = 32.27 ms / 461 runs ( 0.07 ms per token, 14285.27 tokens per second)
llama_print_timings: prompt eval time = 9435.64 ms / 481 tokens ( 19.62 ms per token, 50.98 tokens per second)
llama_print_timings: eval time = 77026.51 ms / 460 runs ( 167.45 ms per token, 5.97 tokens per second)
llama_print_timings: total time = 87142.41 ms
Output generated in 87.31 seconds (5.27 tokens/s, 460 tokens, context 1062, seed 1621193719)
Llama.generate: prefix-match hit
llama_print_timings: load time = 58445.30 ms
llama_print_timings: sample time = 13.75 ms / 202 runs ( 0.07 ms per token, 14686.64 tokens per second)
llama_print_timings: prompt eval time = 8666.17 ms / 508 tokens ( 17.06 ms per token, 58.62 tokens per second)
llama_print_timings: eval time = 30985.38 ms / 201 runs ( 154.16 ms per token, 6.49 tokens per second)
llama_print_timings: total time = 39896.13 ms
Output generated in 40.07 seconds (5.02 tokens/s, 201 tokens, context 1570, seed 33234143)
Llama.generate: prefix-match hit
llama_print_timings: load time = 58445.30 ms
llama_print_timings: sample time = 1.16 ms / 15 runs ( 0.08 ms per token, 12942.19 tokens per second)
llama_print_timings: prompt eval time = 4272.28 ms / 221 tokens ( 19.33 ms per token, 51.73 tokens per second)
llama_print_timings: eval time = 2117.26 ms / 14 runs ( 151.23 ms per token, 6.61 tokens per second)
llama_print_timings: total time = 6408.49 ms
Output generated in 6.58 seconds (2.13 tokens/s, 14 tokens, context 1791, seed 226652334)
Llama.generate: prefix-match hit
llama_print_timings: load time = 58445.30 ms
llama_print_timings: sample time = 9.23 ms / 130 runs ( 0.07 ms per token, 14082.98 tokens per second)
llama_print_timings: prompt eval time = 2027.22 ms / 38 tokens ( 53.35 ms per token, 18.74 tokens per second)
llama_print_timings: eval time = 19660.25 ms / 129 runs ( 152.41 ms per token, 6.56 tokens per second)
llama_print_timings: total time = 21844.50 ms
Output generated in 22.02 seconds (5.86 tokens/s, 129 tokens, context 1829, seed 1378536619)
Llama.generate: prefix-match hit
llama_print_timings: load time = 58445.30 ms
llama_print_timings: sample time = 0.92 ms / 15 runs ( 0.06 ms per token, 16393.44 tokens per second)
llama_print_timings: prompt eval time = 3276.80 ms / 146 tokens ( 22.44 ms per token, 44.56 tokens per second)
llama_print_timings: eval time = 2071.27 ms / 14 runs ( 147.95 ms per token, 6.76 tokens per second)
llama_print_timings: total time = 5369.76 ms
Output generated in 5.54 seconds (2.53 tokens/s, 14 tokens, context 1975, seed 907151299)
Llama.generate: prefix-match hit
llama_print_timings: load time = 58445.30 ms
llama_print_timings: sample time = 8.53 ms / 123 runs ( 0.07 ms per token, 14414.63 tokens per second)
llama_print_timings: prompt eval time = 1994.31 ms / 46 tokens ( 43.35 ms per token, 23.07 tokens per second)
llama_print_timings: eval time = 18195.41 ms / 122 runs ( 149.14 ms per token, 6.70 tokens per second)
llama_print_timings: total time = 20351.81 ms
Output generated in 20.52 seconds (5.94 tokens/s, 122 tokens, context 2021, seed 847977202)
Llama.generate: prefix-match hit
Output generated in 52.16 seconds (6.10 tokens/s, 318 tokens, context 2171, seed 358705908)