| { | |
| "best_metric": 2.329240560531616, | |
| "best_model_checkpoint": "/mnt/bn/qingyi-bn-lq/llama/saved_bloomfirefly/checkpoint-19200", | |
| "epoch": 2.9836105378171665, | |
| "global_step": 19200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 2.9733, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 2.7809, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 2.6052, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 2.4925, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0003, | |
| "loss": 2.458, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00029968758135902107, | |
| "loss": 2.4281, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00029937516271804216, | |
| "loss": 2.4178, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00029906274407706326, | |
| "loss": 2.3839, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0002987503254360843, | |
| "loss": 2.3521, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00029843790679510545, | |
| "loss": 2.338, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.510117292404175, | |
| "eval_runtime": 69.1765, | |
| "eval_samples_per_second": 28.912, | |
| "eval_steps_per_second": 1.807, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0002981254881541265, | |
| "loss": 2.3401, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0002978130695131476, | |
| "loss": 2.3665, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0002975006508721687, | |
| "loss": 2.3691, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0002971882322311898, | |
| "loss": 2.3514, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0002968758135902109, | |
| "loss": 2.3203, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00029656339494923197, | |
| "loss": 2.3393, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.000296250976308253, | |
| "loss": 2.3289, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00029593855766727416, | |
| "loss": 2.3407, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0002956261390262952, | |
| "loss": 2.3163, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0002953137203853163, | |
| "loss": 2.3212, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 2.473245620727539, | |
| "eval_runtime": 69.0219, | |
| "eval_samples_per_second": 28.976, | |
| "eval_steps_per_second": 1.811, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0002950013017443374, | |
| "loss": 2.2927, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0002946888831033585, | |
| "loss": 2.2927, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0002943764644623796, | |
| "loss": 2.29, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0002940640458214007, | |
| "loss": 2.3099, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0002937516271804217, | |
| "loss": 2.3286, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0002934392085394428, | |
| "loss": 2.2928, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0002931267898984639, | |
| "loss": 2.2956, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.000292814371257485, | |
| "loss": 2.2627, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0002925019526165061, | |
| "loss": 2.2897, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0002921895339755272, | |
| "loss": 2.2994, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.455402374267578, | |
| "eval_runtime": 69.1315, | |
| "eval_samples_per_second": 28.93, | |
| "eval_steps_per_second": 1.808, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00029187711533454824, | |
| "loss": 2.3232, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0002915646966935694, | |
| "loss": 2.2515, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00029125227805259043, | |
| "loss": 2.2856, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0002909398594116115, | |
| "loss": 2.252, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0002906274407706326, | |
| "loss": 2.2891, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0002903150221296537, | |
| "loss": 2.2769, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0002900026034886748, | |
| "loss": 2.2763, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0002896901848476959, | |
| "loss": 2.278, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00028937776620671695, | |
| "loss": 2.3126, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0002890653475657381, | |
| "loss": 2.2698, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 2.4434444904327393, | |
| "eval_runtime": 69.7211, | |
| "eval_samples_per_second": 28.686, | |
| "eval_steps_per_second": 1.793, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00028875292892475914, | |
| "loss": 2.2587, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00028844051028378023, | |
| "loss": 2.2954, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00028812809164280133, | |
| "loss": 2.3102, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0002878156730018224, | |
| "loss": 2.2918, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0002875032543608435, | |
| "loss": 2.2698, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0002871908357198646, | |
| "loss": 2.2514, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00028687841707888566, | |
| "loss": 2.2684, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00028656599843790675, | |
| "loss": 2.2833, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00028625357979692785, | |
| "loss": 2.2709, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00028594116115594894, | |
| "loss": 2.2596, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 2.436037302017212, | |
| "eval_runtime": 69.727, | |
| "eval_samples_per_second": 28.683, | |
| "eval_steps_per_second": 1.793, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00028562874251497004, | |
| "loss": 2.2743, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00028531632387399113, | |
| "loss": 2.23, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0002850039052330122, | |
| "loss": 2.2723, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0002846914865920333, | |
| "loss": 2.2585, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00028437906795105437, | |
| "loss": 2.2463, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00028406664931007546, | |
| "loss": 2.2264, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00028375423066909656, | |
| "loss": 2.223, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00028344181202811765, | |
| "loss": 2.2412, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00028312939338713875, | |
| "loss": 2.2714, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00028281697474615984, | |
| "loss": 2.2638, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_loss": 2.4272871017456055, | |
| "eval_runtime": 69.3748, | |
| "eval_samples_per_second": 28.829, | |
| "eval_steps_per_second": 1.802, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0002825045561051809, | |
| "loss": 2.2303, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.000282192137464202, | |
| "loss": 2.2491, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00028187971882322313, | |
| "loss": 2.2598, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00028156730018224417, | |
| "loss": 2.2566, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00028125488154126527, | |
| "loss": 2.2642, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00028094246290028636, | |
| "loss": 2.2976, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00028063004425930746, | |
| "loss": 2.2144, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00028031762561832855, | |
| "loss": 2.2618, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00028000520697734965, | |
| "loss": 2.2232, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0002796927883363707, | |
| "loss": 2.2349, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 2.422177314758301, | |
| "eval_runtime": 69.7796, | |
| "eval_samples_per_second": 28.662, | |
| "eval_steps_per_second": 1.791, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00027938036969539184, | |
| "loss": 2.2655, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0002790679510544129, | |
| "loss": 2.265, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.000278755532413434, | |
| "loss": 2.2552, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00027844311377245507, | |
| "loss": 2.252, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00027813069513147617, | |
| "loss": 2.255, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00027781827649049726, | |
| "loss": 2.1869, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00027750585784951836, | |
| "loss": 2.2601, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0002771934392085394, | |
| "loss": 2.2607, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0002768810205675605, | |
| "loss": 2.2245, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0002765686019265816, | |
| "loss": 2.2561, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 2.4173202514648438, | |
| "eval_runtime": 69.7813, | |
| "eval_samples_per_second": 28.661, | |
| "eval_steps_per_second": 1.791, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0002762561832856027, | |
| "loss": 2.2472, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0002759437646446238, | |
| "loss": 2.2952, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0002756313460036449, | |
| "loss": 2.1941, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0002753189273626659, | |
| "loss": 2.2396, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00027500650872168707, | |
| "loss": 2.2325, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0002746940900807081, | |
| "loss": 2.2458, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0002743816714397292, | |
| "loss": 2.2464, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0002740692527987503, | |
| "loss": 2.2487, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0002737568341577714, | |
| "loss": 2.2609, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0002734444155167925, | |
| "loss": 2.3016, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 2.4146716594696045, | |
| "eval_runtime": 69.513, | |
| "eval_samples_per_second": 28.772, | |
| "eval_steps_per_second": 1.798, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0002731319968758136, | |
| "loss": 2.2415, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0002728195782348346, | |
| "loss": 2.2512, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0002725071595938558, | |
| "loss": 2.2186, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0002721947409528768, | |
| "loss": 2.1982, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0002718823223118979, | |
| "loss": 2.2358, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.000271569903670919, | |
| "loss": 2.2359, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0002712574850299401, | |
| "loss": 2.2367, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0002709450663889612, | |
| "loss": 2.2209, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0002706326477479823, | |
| "loss": 2.2026, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00027032022910700333, | |
| "loss": 2.2302, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": 2.4096806049346924, | |
| "eval_runtime": 69.8744, | |
| "eval_samples_per_second": 28.623, | |
| "eval_steps_per_second": 1.789, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00027000781046602443, | |
| "loss": 2.2516, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0002696953918250455, | |
| "loss": 2.2173, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0002693829731840666, | |
| "loss": 2.2414, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0002690705545430877, | |
| "loss": 2.1922, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0002687581359021088, | |
| "loss": 2.2396, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00026844571726112985, | |
| "loss": 2.2602, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.000268133298620151, | |
| "loss": 2.2263, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00026782087997917204, | |
| "loss": 2.2082, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00026750846133819314, | |
| "loss": 2.2144, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00026719604269721423, | |
| "loss": 2.2066, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 2.4065375328063965, | |
| "eval_runtime": 69.933, | |
| "eval_samples_per_second": 28.599, | |
| "eval_steps_per_second": 1.787, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00026688362405623533, | |
| "loss": 2.2494, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0002665712054152564, | |
| "loss": 2.2471, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0002662587867742775, | |
| "loss": 2.2512, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00026594636813329856, | |
| "loss": 2.2249, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0002656339494923197, | |
| "loss": 2.2526, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00026532153085134075, | |
| "loss": 2.2375, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00026500911221036185, | |
| "loss": 2.169, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.00026469669356938294, | |
| "loss": 2.2206, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.00026438427492840404, | |
| "loss": 2.2284, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.00026407185628742513, | |
| "loss": 2.2116, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 2.402400255203247, | |
| "eval_runtime": 70.6508, | |
| "eval_samples_per_second": 28.308, | |
| "eval_steps_per_second": 1.769, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00026375943764644623, | |
| "loss": 2.2228, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0002634470190054673, | |
| "loss": 2.2264, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00026313460036448837, | |
| "loss": 2.2212, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.0002628221817235095, | |
| "loss": 2.2164, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00026250976308253056, | |
| "loss": 2.2523, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00026219734444155165, | |
| "loss": 2.2272, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00026188492580057275, | |
| "loss": 2.2381, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00026157250715959384, | |
| "loss": 2.2149, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00026126008851861494, | |
| "loss": 2.228, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00026094766987763603, | |
| "loss": 2.2145, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 2.399576425552368, | |
| "eval_runtime": 69.9194, | |
| "eval_samples_per_second": 28.604, | |
| "eval_steps_per_second": 1.788, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0002606352512366571, | |
| "loss": 2.18, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0002603228325956782, | |
| "loss": 2.1965, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00026001041395469927, | |
| "loss": 2.178, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00025969799531372036, | |
| "loss": 2.194, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00025938557667274146, | |
| "loss": 2.2024, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00025907315803176255, | |
| "loss": 2.2427, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00025876073939078365, | |
| "loss": 2.2246, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00025844832074980474, | |
| "loss": 2.2169, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.0002581359021088258, | |
| "loss": 2.2154, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0002578234834678469, | |
| "loss": 2.1732, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 2.3982491493225098, | |
| "eval_runtime": 70.2191, | |
| "eval_samples_per_second": 28.482, | |
| "eval_steps_per_second": 1.78, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.000257511064826868, | |
| "loss": 2.1951, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00025719864618588907, | |
| "loss": 2.2139, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00025688622754491017, | |
| "loss": 2.197, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00025657380890393126, | |
| "loss": 2.2317, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.0002562613902629523, | |
| "loss": 2.2107, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00025594897162197345, | |
| "loss": 2.2087, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0002556365529809945, | |
| "loss": 2.2124, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0002553241343400156, | |
| "loss": 2.1762, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0002550117156990367, | |
| "loss": 2.2488, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0002546992970580578, | |
| "loss": 2.2316, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 2.394296646118164, | |
| "eval_runtime": 70.2494, | |
| "eval_samples_per_second": 28.47, | |
| "eval_steps_per_second": 1.779, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0002543868784170789, | |
| "loss": 2.2386, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00025407445977609997, | |
| "loss": 2.224, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.000253762041135121, | |
| "loss": 2.2479, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0002534496224941421, | |
| "loss": 2.2396, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0002531372038531632, | |
| "loss": 2.2405, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0002528247852121843, | |
| "loss": 2.1969, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.0002525123665712054, | |
| "loss": 2.2095, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.0002521999479302265, | |
| "loss": 2.2202, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.0002518875292892476, | |
| "loss": 2.2088, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0002515751106482687, | |
| "loss": 2.2075, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 2.3918581008911133, | |
| "eval_runtime": 69.2896, | |
| "eval_samples_per_second": 28.864, | |
| "eval_steps_per_second": 1.804, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0002512626920072897, | |
| "loss": 2.1993, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0002509502733663108, | |
| "loss": 2.2406, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0002506378547253319, | |
| "loss": 2.2352, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.000250325436084353, | |
| "loss": 2.236, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0002500130174433741, | |
| "loss": 2.1805, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.0002497005988023952, | |
| "loss": 2.2249, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00024938818016141624, | |
| "loss": 2.2153, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.0002490757615204374, | |
| "loss": 2.2115, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00024876334287945843, | |
| "loss": 2.2284, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0002484509242384795, | |
| "loss": 2.184, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 2.3887791633605957, | |
| "eval_runtime": 69.2387, | |
| "eval_samples_per_second": 28.886, | |
| "eval_steps_per_second": 1.805, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0002481385055975006, | |
| "loss": 2.2172, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0002478260869565217, | |
| "loss": 2.2347, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0002475136683155428, | |
| "loss": 2.2213, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0002472012496745639, | |
| "loss": 2.2215, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.00024688883103358495, | |
| "loss": 2.2058, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00024657641239260604, | |
| "loss": 2.1918, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.0002462639937516272, | |
| "loss": 2.2021, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00024595157511064824, | |
| "loss": 2.1832, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.00024563915646966933, | |
| "loss": 2.2199, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.0002453267378286904, | |
| "loss": 2.1997, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": 2.386540412902832, | |
| "eval_runtime": 69.2123, | |
| "eval_samples_per_second": 28.897, | |
| "eval_steps_per_second": 1.806, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.0002450143191877115, | |
| "loss": 2.2009, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0002447019005467326, | |
| "loss": 2.2045, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0002443894819057537, | |
| "loss": 2.2231, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.00024407706326477478, | |
| "loss": 2.211, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.00024376464462379588, | |
| "loss": 2.1904, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.00024345222598281694, | |
| "loss": 2.1492, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.00024313980734183807, | |
| "loss": 2.2368, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.00024282738870085914, | |
| "loss": 2.1753, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00024251497005988023, | |
| "loss": 2.179, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.0002422025514189013, | |
| "loss": 2.1811, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 2.3864212036132812, | |
| "eval_runtime": 69.2951, | |
| "eval_samples_per_second": 28.862, | |
| "eval_steps_per_second": 1.804, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.0002418901327779224, | |
| "loss": 2.1496, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.0002415777141369435, | |
| "loss": 2.2071, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00024126529549596459, | |
| "loss": 2.189, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00024095287685498565, | |
| "loss": 2.1838, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00024064045821400675, | |
| "loss": 2.2292, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00024032803957302782, | |
| "loss": 2.1931, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00024001562093204894, | |
| "loss": 2.2293, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00023970320229107, | |
| "loss": 2.2112, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.0002393907836500911, | |
| "loss": 2.1479, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00023907836500911217, | |
| "loss": 2.1661, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": 2.383505344390869, | |
| "eval_runtime": 69.2876, | |
| "eval_samples_per_second": 28.865, | |
| "eval_steps_per_second": 1.804, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.0002387659463681333, | |
| "loss": 2.1783, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00023845352772715436, | |
| "loss": 2.1975, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00023814110908617546, | |
| "loss": 2.2268, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00023782869044519653, | |
| "loss": 2.1815, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00023751627180421765, | |
| "loss": 2.2305, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00023720385316323872, | |
| "loss": 2.2087, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.0002368914345222598, | |
| "loss": 2.2204, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00023657901588128088, | |
| "loss": 2.2138, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.000236266597240302, | |
| "loss": 2.2071, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00023595417859932307, | |
| "loss": 2.1728, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 2.3820013999938965, | |
| "eval_runtime": 69.3049, | |
| "eval_samples_per_second": 28.858, | |
| "eval_steps_per_second": 1.804, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00023564175995834417, | |
| "loss": 2.182, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00023532934131736524, | |
| "loss": 2.1948, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00023501692267638633, | |
| "loss": 2.2178, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00023470450403540743, | |
| "loss": 2.1979, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00023439208539442852, | |
| "loss": 2.222, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0002340796667534496, | |
| "loss": 2.221, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00023376724811247069, | |
| "loss": 2.208, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.00023345482947149175, | |
| "loss": 2.1502, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.00023314241083051288, | |
| "loss": 2.1628, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.00023282999218953395, | |
| "loss": 2.1933, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 2.380128860473633, | |
| "eval_runtime": 69.2864, | |
| "eval_samples_per_second": 28.866, | |
| "eval_steps_per_second": 1.804, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.00023251757354855504, | |
| "loss": 2.2204, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.0002322051549075761, | |
| "loss": 2.218, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.00023189273626659723, | |
| "loss": 2.199, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.0002315803176256183, | |
| "loss": 2.1826, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.0002312678989846394, | |
| "loss": 2.174, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.00023095548034366046, | |
| "loss": 2.2011, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.00023064306170268159, | |
| "loss": 2.1951, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.00023033064306170265, | |
| "loss": 2.2189, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.00023001822442072375, | |
| "loss": 2.1891, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.00022970580577974482, | |
| "loss": 2.1873, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 2.379713296890259, | |
| "eval_runtime": 69.3005, | |
| "eval_samples_per_second": 28.86, | |
| "eval_steps_per_second": 1.804, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.00022939338713876591, | |
| "loss": 2.2191, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.000229080968497787, | |
| "loss": 2.1966, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.0002287685498568081, | |
| "loss": 2.2062, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.00022845613121582917, | |
| "loss": 2.1888, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.00022814371257485027, | |
| "loss": 2.1938, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.0002278312939338714, | |
| "loss": 2.206, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.00022751887529289246, | |
| "loss": 2.1584, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.00022720645665191355, | |
| "loss": 2.1933, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.00022689403801093462, | |
| "loss": 2.2087, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.00022658161936995575, | |
| "loss": 2.2239, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 2.3774757385253906, | |
| "eval_runtime": 69.3137, | |
| "eval_samples_per_second": 28.854, | |
| "eval_steps_per_second": 1.803, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.00022626920072897681, | |
| "loss": 2.2136, | |
| "step": 4820 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.0002259567820879979, | |
| "loss": 2.2046, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.00022564436344701898, | |
| "loss": 2.2031, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.0002253319448060401, | |
| "loss": 2.171, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.00022501952616506117, | |
| "loss": 2.2101, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.00022470710752408226, | |
| "loss": 2.1306, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.00022439468888310333, | |
| "loss": 2.1754, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.00022408227024212443, | |
| "loss": 2.1972, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.00022376985160114552, | |
| "loss": 2.2175, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.00022345743296016662, | |
| "loss": 2.139, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_loss": 2.3760337829589844, | |
| "eval_runtime": 69.3092, | |
| "eval_samples_per_second": 28.856, | |
| "eval_steps_per_second": 1.804, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.0002231450143191877, | |
| "loss": 2.1912, | |
| "step": 5020 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.00022283259567820878, | |
| "loss": 2.2036, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.00022252017703722985, | |
| "loss": 2.1852, | |
| "step": 5060 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.00022220775839625097, | |
| "loss": 2.1672, | |
| "step": 5080 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.00022189533975527204, | |
| "loss": 2.1828, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.00022158292111429314, | |
| "loss": 2.1875, | |
| "step": 5120 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0002212705024733142, | |
| "loss": 2.1997, | |
| "step": 5140 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.00022095808383233533, | |
| "loss": 2.2162, | |
| "step": 5160 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0002206456651913564, | |
| "loss": 2.2213, | |
| "step": 5180 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.0002203332465503775, | |
| "loss": 2.1972, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": 2.374734878540039, | |
| "eval_runtime": 69.2582, | |
| "eval_samples_per_second": 28.877, | |
| "eval_steps_per_second": 1.805, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.00022002082790939856, | |
| "loss": 2.175, | |
| "step": 5220 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.00021970840926841968, | |
| "loss": 2.1951, | |
| "step": 5240 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.00021939599062744075, | |
| "loss": 2.1493, | |
| "step": 5260 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.00021908357198646185, | |
| "loss": 2.1611, | |
| "step": 5280 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.00021877115334548291, | |
| "loss": 2.1621, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.00021845873470450404, | |
| "loss": 2.1875, | |
| "step": 5320 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.0002181463160635251, | |
| "loss": 2.1733, | |
| "step": 5340 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.0002178338974225462, | |
| "loss": 2.242, | |
| "step": 5360 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.00021752147878156727, | |
| "loss": 2.2154, | |
| "step": 5380 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.00021720906014058836, | |
| "loss": 2.1969, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_loss": 2.372680902481079, | |
| "eval_runtime": 69.283, | |
| "eval_samples_per_second": 28.867, | |
| "eval_steps_per_second": 1.804, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.00021689664149960946, | |
| "loss": 2.1245, | |
| "step": 5420 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.00021658422285863056, | |
| "loss": 2.2049, | |
| "step": 5440 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.00021627180421765162, | |
| "loss": 2.1716, | |
| "step": 5460 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.00021595938557667272, | |
| "loss": 2.1891, | |
| "step": 5480 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.0002156469669356938, | |
| "loss": 2.1963, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.0002153345482947149, | |
| "loss": 2.1946, | |
| "step": 5520 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.00021502212965373598, | |
| "loss": 2.1982, | |
| "step": 5540 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.00021470971101275707, | |
| "loss": 2.1759, | |
| "step": 5560 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.00021439729237177814, | |
| "loss": 2.1661, | |
| "step": 5580 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.00021408487373079926, | |
| "loss": 2.2051, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_loss": 2.3719565868377686, | |
| "eval_runtime": 69.321, | |
| "eval_samples_per_second": 28.851, | |
| "eval_steps_per_second": 1.803, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.00021377245508982033, | |
| "loss": 2.1605, | |
| "step": 5620 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.00021346003644884143, | |
| "loss": 2.1375, | |
| "step": 5640 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.0002131476178078625, | |
| "loss": 2.1293, | |
| "step": 5660 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.00021283519916688362, | |
| "loss": 2.2189, | |
| "step": 5680 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.0002125227805259047, | |
| "loss": 2.1784, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.00021221036188492578, | |
| "loss": 2.1764, | |
| "step": 5720 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.00021189794324394685, | |
| "loss": 2.1569, | |
| "step": 5740 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.00021158552460296795, | |
| "loss": 2.1704, | |
| "step": 5760 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.00021127310596198904, | |
| "loss": 2.1614, | |
| "step": 5780 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.00021096068732101014, | |
| "loss": 2.2078, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_loss": 2.370939016342163, | |
| "eval_runtime": 69.2728, | |
| "eval_samples_per_second": 28.871, | |
| "eval_steps_per_second": 1.804, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.0002106482686800312, | |
| "loss": 2.198, | |
| "step": 5820 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.0002103358500390523, | |
| "loss": 2.1735, | |
| "step": 5840 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.00021002343139807342, | |
| "loss": 2.1936, | |
| "step": 5860 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.0002097110127570945, | |
| "loss": 2.1559, | |
| "step": 5880 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.0002093985941161156, | |
| "loss": 2.1856, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.00020908617547513666, | |
| "loss": 2.194, | |
| "step": 5920 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.00020877375683415778, | |
| "loss": 2.1983, | |
| "step": 5940 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.00020846133819317885, | |
| "loss": 2.1788, | |
| "step": 5960 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.00020814891955219994, | |
| "loss": 2.2126, | |
| "step": 5980 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.000207836500911221, | |
| "loss": 2.1454, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 2.369137763977051, | |
| "eval_runtime": 69.3036, | |
| "eval_samples_per_second": 28.859, | |
| "eval_steps_per_second": 1.804, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.00020752408227024213, | |
| "loss": 2.1603, | |
| "step": 6020 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.0002072116636292632, | |
| "loss": 2.2075, | |
| "step": 6040 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.0002068992449882843, | |
| "loss": 2.1817, | |
| "step": 6060 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.00020658682634730537, | |
| "loss": 2.1917, | |
| "step": 6080 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.00020627440770632646, | |
| "loss": 2.1727, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.00020596198906534756, | |
| "loss": 2.1985, | |
| "step": 6120 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.00020564957042436865, | |
| "loss": 2.1888, | |
| "step": 6140 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.00020533715178338972, | |
| "loss": 2.1425, | |
| "step": 6160 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.00020502473314241082, | |
| "loss": 2.1659, | |
| "step": 6180 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.00020471231450143188, | |
| "loss": 2.1768, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 2.368589162826538, | |
| "eval_runtime": 69.4033, | |
| "eval_samples_per_second": 28.817, | |
| "eval_steps_per_second": 1.801, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.000204399895860453, | |
| "loss": 2.1744, | |
| "step": 6220 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.00020408747721947407, | |
| "loss": 2.1484, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.00020377505857849517, | |
| "loss": 2.2154, | |
| "step": 6260 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.00020346263993751624, | |
| "loss": 2.1358, | |
| "step": 6280 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.00020315022129653736, | |
| "loss": 2.1809, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.00020283780265555843, | |
| "loss": 2.1813, | |
| "step": 6320 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.00020252538401457952, | |
| "loss": 2.1903, | |
| "step": 6340 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.0002022129653736006, | |
| "loss": 2.1971, | |
| "step": 6360 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.00020190054673262172, | |
| "loss": 2.2041, | |
| "step": 6380 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.00020158812809164278, | |
| "loss": 2.2169, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": 2.3672330379486084, | |
| "eval_runtime": 69.3516, | |
| "eval_samples_per_second": 28.839, | |
| "eval_steps_per_second": 1.802, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.00020127570945066388, | |
| "loss": 2.2101, | |
| "step": 6420 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.00020096329080968495, | |
| "loss": 2.1739, | |
| "step": 6440 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.00020065087216870604, | |
| "loss": 2.1764, | |
| "step": 6460 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.00020033845352772714, | |
| "loss": 2.1718, | |
| "step": 6480 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.00020002603488674823, | |
| "loss": 2.1688, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.0001997136162457693, | |
| "loss": 2.1322, | |
| "step": 6520 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.0001994011976047904, | |
| "loss": 2.1593, | |
| "step": 6540 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.0001990887789638115, | |
| "loss": 2.179, | |
| "step": 6560 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.0001987763603228326, | |
| "loss": 2.139, | |
| "step": 6580 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.00019846394168185366, | |
| "loss": 2.1594, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "eval_loss": 2.367051839828491, | |
| "eval_runtime": 69.3473, | |
| "eval_samples_per_second": 28.84, | |
| "eval_steps_per_second": 1.803, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.00019815152304087475, | |
| "loss": 2.2033, | |
| "step": 6620 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.00019783910439989582, | |
| "loss": 2.183, | |
| "step": 6640 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.00019752668575891694, | |
| "loss": 2.1517, | |
| "step": 6660 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.000197214267117938, | |
| "loss": 2.183, | |
| "step": 6680 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.0001969018484769591, | |
| "loss": 2.197, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.00019658942983598017, | |
| "loss": 2.1778, | |
| "step": 6720 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.0001962770111950013, | |
| "loss": 2.1745, | |
| "step": 6740 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.00019596459255402237, | |
| "loss": 2.1585, | |
| "step": 6760 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.00019565217391304346, | |
| "loss": 2.1708, | |
| "step": 6780 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.00019533975527206453, | |
| "loss": 2.1649, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "eval_loss": 2.363710880279541, | |
| "eval_runtime": 69.2642, | |
| "eval_samples_per_second": 28.875, | |
| "eval_steps_per_second": 1.805, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.00019502733663108565, | |
| "loss": 2.1391, | |
| "step": 6820 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.00019471491799010672, | |
| "loss": 2.1939, | |
| "step": 6840 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.00019440249934912782, | |
| "loss": 2.1558, | |
| "step": 6860 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.00019409008070814888, | |
| "loss": 2.173, | |
| "step": 6880 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.00019377766206716998, | |
| "loss": 2.1821, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.00019346524342619107, | |
| "loss": 2.16, | |
| "step": 6920 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.00019315282478521217, | |
| "loss": 2.1808, | |
| "step": 6940 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.00019284040614423324, | |
| "loss": 2.1355, | |
| "step": 6960 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.00019252798750325433, | |
| "loss": 2.1813, | |
| "step": 6980 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.00019221556886227546, | |
| "loss": 2.1677, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "eval_loss": 2.3648109436035156, | |
| "eval_runtime": 69.3675, | |
| "eval_samples_per_second": 28.832, | |
| "eval_steps_per_second": 1.802, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.00019190315022129652, | |
| "loss": 2.1479, | |
| "step": 7020 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.00019159073158031762, | |
| "loss": 2.1852, | |
| "step": 7040 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.0001912783129393387, | |
| "loss": 2.14, | |
| "step": 7060 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.0001909658942983598, | |
| "loss": 2.1332, | |
| "step": 7080 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.00019065347565738088, | |
| "loss": 2.178, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.00019034105701640197, | |
| "loss": 2.1661, | |
| "step": 7120 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.00019002863837542304, | |
| "loss": 2.1902, | |
| "step": 7140 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.00018971621973444417, | |
| "loss": 2.1775, | |
| "step": 7160 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.00018940380109346523, | |
| "loss": 2.2007, | |
| "step": 7180 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.00018909138245248633, | |
| "loss": 2.2078, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "eval_loss": 2.3642289638519287, | |
| "eval_runtime": 69.5476, | |
| "eval_samples_per_second": 28.757, | |
| "eval_steps_per_second": 1.797, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.0001887789638115074, | |
| "loss": 2.185, | |
| "step": 7220 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.0001884665451705285, | |
| "loss": 2.1856, | |
| "step": 7240 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.0001881541265295496, | |
| "loss": 2.2049, | |
| "step": 7260 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.00018784170788857068, | |
| "loss": 2.1376, | |
| "step": 7280 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.00018752928924759175, | |
| "loss": 2.1693, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.00018721687060661285, | |
| "loss": 2.1825, | |
| "step": 7320 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.00018690445196563392, | |
| "loss": 2.1649, | |
| "step": 7340 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.00018659203332465504, | |
| "loss": 2.1936, | |
| "step": 7360 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.0001862796146836761, | |
| "loss": 2.143, | |
| "step": 7380 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.0001859671960426972, | |
| "loss": 2.1617, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "eval_loss": 2.362150192260742, | |
| "eval_runtime": 69.3218, | |
| "eval_samples_per_second": 28.851, | |
| "eval_steps_per_second": 1.803, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.00018565477740171827, | |
| "loss": 2.1555, | |
| "step": 7420 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.0001853423587607394, | |
| "loss": 2.1639, | |
| "step": 7440 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.00018502994011976046, | |
| "loss": 2.1678, | |
| "step": 7460 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.00018471752147878156, | |
| "loss": 2.1775, | |
| "step": 7480 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.00018440510283780263, | |
| "loss": 2.1784, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.00018409268419682375, | |
| "loss": 2.1499, | |
| "step": 7520 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.00018378026555584482, | |
| "loss": 2.154, | |
| "step": 7540 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.0001834678469148659, | |
| "loss": 2.1793, | |
| "step": 7560 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.00018315542827388698, | |
| "loss": 2.2292, | |
| "step": 7580 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.00018284300963290808, | |
| "loss": 2.1578, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "eval_loss": 2.3628857135772705, | |
| "eval_runtime": 69.2564, | |
| "eval_samples_per_second": 28.878, | |
| "eval_steps_per_second": 1.805, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.00018253059099192917, | |
| "loss": 2.1494, | |
| "step": 7620 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.00018221817235095027, | |
| "loss": 2.1669, | |
| "step": 7640 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.00018190575370997133, | |
| "loss": 2.1447, | |
| "step": 7660 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.00018159333506899243, | |
| "loss": 2.1663, | |
| "step": 7680 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.0001812809164280135, | |
| "loss": 2.1871, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.00018096849778703462, | |
| "loss": 2.1338, | |
| "step": 7720 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.0001806560791460557, | |
| "loss": 2.1767, | |
| "step": 7740 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.00018034366050507678, | |
| "loss": 2.1694, | |
| "step": 7760 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.00018003124186409785, | |
| "loss": 2.1674, | |
| "step": 7780 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.00017971882322311898, | |
| "loss": 2.1863, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "eval_loss": 2.3613035678863525, | |
| "eval_runtime": 69.2881, | |
| "eval_samples_per_second": 28.865, | |
| "eval_steps_per_second": 1.804, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.00017940640458214004, | |
| "loss": 2.1441, | |
| "step": 7820 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.00017909398594116114, | |
| "loss": 2.1885, | |
| "step": 7840 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.0001787815673001822, | |
| "loss": 2.1514, | |
| "step": 7860 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.00017846914865920333, | |
| "loss": 2.2002, | |
| "step": 7880 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.0001781567300182244, | |
| "loss": 2.1759, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.0001778443113772455, | |
| "loss": 2.1611, | |
| "step": 7920 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.00017753189273626656, | |
| "loss": 2.1667, | |
| "step": 7940 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.00017721947409528768, | |
| "loss": 2.1717, | |
| "step": 7960 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.00017690705545430875, | |
| "loss": 2.1983, | |
| "step": 7980 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.00017659463681332985, | |
| "loss": 2.2092, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "eval_loss": 2.3608274459838867, | |
| "eval_runtime": 69.3364, | |
| "eval_samples_per_second": 28.845, | |
| "eval_steps_per_second": 1.803, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.00017628221817235092, | |
| "loss": 2.1305, | |
| "step": 8020 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.000175969799531372, | |
| "loss": 2.1431, | |
| "step": 8040 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.0001756573808903931, | |
| "loss": 2.1384, | |
| "step": 8060 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.0001753449622494142, | |
| "loss": 2.2093, | |
| "step": 8080 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.00017503254360843527, | |
| "loss": 2.1271, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.00017472012496745637, | |
| "loss": 2.1466, | |
| "step": 8120 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.0001744077063264775, | |
| "loss": 2.1578, | |
| "step": 8140 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 0.00017409528768549856, | |
| "loss": 2.1632, | |
| "step": 8160 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 0.00017378286904451965, | |
| "loss": 2.1465, | |
| "step": 8180 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 0.00017347045040354072, | |
| "loss": 2.2226, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "eval_loss": 2.35835599899292, | |
| "eval_runtime": 69.2657, | |
| "eval_samples_per_second": 28.874, | |
| "eval_steps_per_second": 1.805, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.00017315803176256184, | |
| "loss": 2.1585, | |
| "step": 8220 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.0001728456131215829, | |
| "loss": 2.1529, | |
| "step": 8240 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.000172533194480604, | |
| "loss": 2.1663, | |
| "step": 8260 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.00017222077583962508, | |
| "loss": 2.1422, | |
| "step": 8280 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.00017190835719864617, | |
| "loss": 2.158, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.00017159593855766727, | |
| "loss": 2.1984, | |
| "step": 8320 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 0.00017128351991668836, | |
| "loss": 2.1395, | |
| "step": 8340 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 0.00017097110127570943, | |
| "loss": 2.14, | |
| "step": 8360 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 0.00017065868263473053, | |
| "loss": 2.1657, | |
| "step": 8380 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.00017036188492580056, | |
| "loss": 2.167, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "eval_loss": 2.35697603225708, | |
| "eval_runtime": 69.2685, | |
| "eval_samples_per_second": 28.873, | |
| "eval_steps_per_second": 1.805, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.00017004946628482165, | |
| "loss": 2.1396, | |
| "step": 8420 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.00016973704764384272, | |
| "loss": 2.1777, | |
| "step": 8440 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.00016942462900286384, | |
| "loss": 2.1366, | |
| "step": 8460 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.0001691122103618849, | |
| "loss": 2.1625, | |
| "step": 8480 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.000168799791720906, | |
| "loss": 2.1859, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.00016848737307992707, | |
| "loss": 2.1705, | |
| "step": 8520 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.0001681749544389482, | |
| "loss": 2.1971, | |
| "step": 8540 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.00016786253579796927, | |
| "loss": 2.1937, | |
| "step": 8560 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.00016755011715699036, | |
| "loss": 2.1436, | |
| "step": 8580 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.00016723769851601143, | |
| "loss": 2.1592, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "eval_loss": 2.3576247692108154, | |
| "eval_runtime": 69.277, | |
| "eval_samples_per_second": 28.87, | |
| "eval_steps_per_second": 1.804, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.00016692527987503252, | |
| "loss": 2.1745, | |
| "step": 8620 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.00016661286123405362, | |
| "loss": 2.1517, | |
| "step": 8640 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.00016630044259307472, | |
| "loss": 2.1921, | |
| "step": 8660 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.00016598802395209578, | |
| "loss": 2.1703, | |
| "step": 8680 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.00016567560531111688, | |
| "loss": 2.1223, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.00016536318667013795, | |
| "loss": 2.1748, | |
| "step": 8720 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.00016505076802915907, | |
| "loss": 2.145, | |
| "step": 8740 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.00016473834938818014, | |
| "loss": 2.1077, | |
| "step": 8760 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.00016442593074720123, | |
| "loss": 2.1571, | |
| "step": 8780 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 0.0001641135121062223, | |
| "loss": 2.1946, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "eval_loss": 2.3559648990631104, | |
| "eval_runtime": 69.3886, | |
| "eval_samples_per_second": 28.823, | |
| "eval_steps_per_second": 1.801, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 0.00016380109346524342, | |
| "loss": 2.1635, | |
| "step": 8820 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 0.0001634886748242645, | |
| "loss": 2.1546, | |
| "step": 8840 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.0001631762561832856, | |
| "loss": 2.1359, | |
| "step": 8860 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.00016286383754230666, | |
| "loss": 2.1741, | |
| "step": 8880 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.00016255141890132778, | |
| "loss": 2.1382, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 0.00016223900026034885, | |
| "loss": 2.1514, | |
| "step": 8920 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 0.00016192658161936994, | |
| "loss": 2.17, | |
| "step": 8940 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 0.000161614162978391, | |
| "loss": 2.1784, | |
| "step": 8960 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.0001613017443374121, | |
| "loss": 2.1869, | |
| "step": 8980 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.0001609893256964332, | |
| "loss": 2.155, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "eval_loss": 2.3562612533569336, | |
| "eval_runtime": 70.7208, | |
| "eval_samples_per_second": 28.28, | |
| "eval_steps_per_second": 1.768, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.0001606769070554543, | |
| "loss": 2.1467, | |
| "step": 9020 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.00016036448841447537, | |
| "loss": 2.1662, | |
| "step": 9040 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.00016005206977349646, | |
| "loss": 2.1928, | |
| "step": 9060 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.00015973965113251756, | |
| "loss": 2.1084, | |
| "step": 9080 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.00015942723249153865, | |
| "loss": 2.182, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 0.00015911481385055975, | |
| "loss": 2.1502, | |
| "step": 9120 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 0.00015880239520958082, | |
| "loss": 2.1645, | |
| "step": 9140 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 0.00015848997656860194, | |
| "loss": 2.1246, | |
| "step": 9160 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 0.000158177557927623, | |
| "loss": 2.1769, | |
| "step": 9180 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 0.0001578651392866441, | |
| "loss": 2.1772, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "eval_loss": 2.354128360748291, | |
| "eval_runtime": 70.4883, | |
| "eval_samples_per_second": 28.374, | |
| "eval_steps_per_second": 1.773, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 0.00015755272064566517, | |
| "loss": 2.1777, | |
| "step": 9220 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.0001572403020046863, | |
| "loss": 2.1749, | |
| "step": 9240 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.00015692788336370736, | |
| "loss": 2.1861, | |
| "step": 9260 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.00015661546472272846, | |
| "loss": 2.1567, | |
| "step": 9280 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.00015630304608174952, | |
| "loss": 2.1426, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.00015599062744077062, | |
| "loss": 2.1658, | |
| "step": 9320 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.00015567820879979172, | |
| "loss": 2.1639, | |
| "step": 9340 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.0001553657901588128, | |
| "loss": 2.1897, | |
| "step": 9360 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 0.00015505337151783388, | |
| "loss": 2.1439, | |
| "step": 9380 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 0.00015474095287685497, | |
| "loss": 2.1326, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "eval_loss": 2.352673292160034, | |
| "eval_runtime": 69.2871, | |
| "eval_samples_per_second": 28.865, | |
| "eval_steps_per_second": 1.804, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 0.00015442853423587604, | |
| "loss": 2.139, | |
| "step": 9420 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.00015411611559489717, | |
| "loss": 2.1087, | |
| "step": 9440 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.00015380369695391823, | |
| "loss": 2.1528, | |
| "step": 9460 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.00015349127831293933, | |
| "loss": 2.1866, | |
| "step": 9480 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 0.0001531788596719604, | |
| "loss": 2.1436, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 0.00015286644103098152, | |
| "loss": 2.1699, | |
| "step": 9520 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 0.0001525540223900026, | |
| "loss": 2.1415, | |
| "step": 9540 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 0.00015224160374902368, | |
| "loss": 2.1092, | |
| "step": 9560 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 0.00015192918510804475, | |
| "loss": 2.1422, | |
| "step": 9580 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 0.00015161676646706587, | |
| "loss": 2.1677, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "eval_loss": 2.3518292903900146, | |
| "eval_runtime": 69.3029, | |
| "eval_samples_per_second": 28.859, | |
| "eval_steps_per_second": 1.804, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 0.00015130434782608694, | |
| "loss": 2.1594, | |
| "step": 9620 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.00015099192918510804, | |
| "loss": 2.1539, | |
| "step": 9640 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.0001506795105441291, | |
| "loss": 2.1343, | |
| "step": 9660 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.00015036709190315023, | |
| "loss": 2.1386, | |
| "step": 9680 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 0.0001500546732621713, | |
| "loss": 2.1512, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 0.0001497422546211924, | |
| "loss": 2.1669, | |
| "step": 9720 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 0.0001494298359802135, | |
| "loss": 2.158, | |
| "step": 9740 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 0.00014911741733923456, | |
| "loss": 2.1643, | |
| "step": 9760 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 0.00014880499869825565, | |
| "loss": 2.1612, | |
| "step": 9780 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 0.00014849258005727675, | |
| "loss": 2.1441, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "eval_loss": 2.35211181640625, | |
| "eval_runtime": 69.2821, | |
| "eval_samples_per_second": 28.867, | |
| "eval_steps_per_second": 1.804, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 0.00014818016141629784, | |
| "loss": 2.1704, | |
| "step": 9820 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 0.0001478677427753189, | |
| "loss": 2.1546, | |
| "step": 9840 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 0.00014755532413434, | |
| "loss": 2.1909, | |
| "step": 9860 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 0.0001472429054933611, | |
| "loss": 2.149, | |
| "step": 9880 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 0.00014693048685238217, | |
| "loss": 2.1419, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 0.00014661806821140327, | |
| "loss": 2.1465, | |
| "step": 9920 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 0.00014630564957042436, | |
| "loss": 2.1551, | |
| "step": 9940 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 0.00014599323092944546, | |
| "loss": 2.1526, | |
| "step": 9960 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 0.00014568081228846653, | |
| "loss": 2.1437, | |
| "step": 9980 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 0.00014536839364748762, | |
| "loss": 2.1659, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "eval_loss": 2.3507654666900635, | |
| "eval_runtime": 69.2997, | |
| "eval_samples_per_second": 28.86, | |
| "eval_steps_per_second": 1.804, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 0.00014505597500650872, | |
| "loss": 2.14, | |
| "step": 10020 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 0.0001447435563655298, | |
| "loss": 2.1289, | |
| "step": 10040 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 0.00014443113772455088, | |
| "loss": 2.1226, | |
| "step": 10060 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 0.00014411871908357198, | |
| "loss": 2.1627, | |
| "step": 10080 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 0.00014380630044259307, | |
| "loss": 2.1759, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 0.00014349388180161414, | |
| "loss": 2.1511, | |
| "step": 10120 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 0.00014318146316063523, | |
| "loss": 2.1275, | |
| "step": 10140 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 0.00014286904451965633, | |
| "loss": 2.1638, | |
| "step": 10160 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 0.00014255662587867743, | |
| "loss": 2.1494, | |
| "step": 10180 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 0.0001422442072376985, | |
| "loss": 2.1554, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "eval_loss": 2.349271059036255, | |
| "eval_runtime": 69.2627, | |
| "eval_samples_per_second": 28.876, | |
| "eval_steps_per_second": 1.805, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 0.0001419317885967196, | |
| "loss": 2.133, | |
| "step": 10220 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 0.00014161936995574068, | |
| "loss": 2.1515, | |
| "step": 10240 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 0.00014130695131476178, | |
| "loss": 2.1262, | |
| "step": 10260 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.00014099453267378285, | |
| "loss": 2.142, | |
| "step": 10280 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.00014068211403280394, | |
| "loss": 2.1578, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.00014036969539182504, | |
| "loss": 2.1583, | |
| "step": 10320 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 0.0001400572767508461, | |
| "loss": 2.1043, | |
| "step": 10340 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 0.0001397448581098672, | |
| "loss": 2.1539, | |
| "step": 10360 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 0.0001394324394688883, | |
| "loss": 2.1189, | |
| "step": 10380 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 0.0001391200208279094, | |
| "loss": 2.1484, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "eval_loss": 2.3479487895965576, | |
| "eval_runtime": 69.2625, | |
| "eval_samples_per_second": 28.876, | |
| "eval_steps_per_second": 1.805, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 0.00013880760218693046, | |
| "loss": 2.1993, | |
| "step": 10420 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 0.00013849518354595156, | |
| "loss": 2.1869, | |
| "step": 10440 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 0.00013818276490497265, | |
| "loss": 2.1644, | |
| "step": 10460 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 0.00013787034626399375, | |
| "loss": 2.1751, | |
| "step": 10480 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 0.00013755792762301482, | |
| "loss": 2.1416, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 0.0001372455089820359, | |
| "loss": 2.1809, | |
| "step": 10520 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 0.000136933090341057, | |
| "loss": 2.1653, | |
| "step": 10540 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 0.00013662067170007808, | |
| "loss": 2.1026, | |
| "step": 10560 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 0.00013630825305909917, | |
| "loss": 2.1503, | |
| "step": 10580 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 0.00013599583441812027, | |
| "loss": 2.1289, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "eval_loss": 2.3468515872955322, | |
| "eval_runtime": 69.2274, | |
| "eval_samples_per_second": 28.89, | |
| "eval_steps_per_second": 1.806, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 0.00013568341577714136, | |
| "loss": 2.1929, | |
| "step": 10620 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 0.00013537099713616243, | |
| "loss": 2.1547, | |
| "step": 10640 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 0.00013505857849518353, | |
| "loss": 2.1571, | |
| "step": 10660 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 0.00013474615985420462, | |
| "loss": 2.1649, | |
| "step": 10680 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 0.00013443374121322572, | |
| "loss": 2.1647, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.00013412132257224679, | |
| "loss": 2.206, | |
| "step": 10720 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.00013380890393126788, | |
| "loss": 2.1377, | |
| "step": 10740 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.00013349648529028898, | |
| "loss": 2.1347, | |
| "step": 10760 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.00013318406664931004, | |
| "loss": 2.1948, | |
| "step": 10780 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.00013287164800833114, | |
| "loss": 2.1844, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "eval_loss": 2.347837209701538, | |
| "eval_runtime": 69.2425, | |
| "eval_samples_per_second": 28.884, | |
| "eval_steps_per_second": 1.805, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.00013255922936735224, | |
| "loss": 2.1515, | |
| "step": 10820 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.00013224681072637333, | |
| "loss": 2.1885, | |
| "step": 10840 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 0.00013193439208539443, | |
| "loss": 2.143, | |
| "step": 10860 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 0.00013162197344441552, | |
| "loss": 2.1671, | |
| "step": 10880 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 0.0001313095548034366, | |
| "loss": 2.1426, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 0.00013099713616245769, | |
| "loss": 2.1653, | |
| "step": 10920 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 0.00013068471752147878, | |
| "loss": 2.1774, | |
| "step": 10940 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 0.00013037229888049988, | |
| "loss": 2.1344, | |
| "step": 10960 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 0.00013005988023952094, | |
| "loss": 2.1217, | |
| "step": 10980 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 0.00012974746159854204, | |
| "loss": 2.1281, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "eval_loss": 2.345808982849121, | |
| "eval_runtime": 69.2499, | |
| "eval_samples_per_second": 28.881, | |
| "eval_steps_per_second": 1.805, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 0.00012943504295756314, | |
| "loss": 2.1459, | |
| "step": 11020 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 0.0001291226243165842, | |
| "loss": 2.1294, | |
| "step": 11040 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 0.0001288102056756053, | |
| "loss": 2.1455, | |
| "step": 11060 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 0.0001284977870346264, | |
| "loss": 2.1219, | |
| "step": 11080 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 0.0001281853683936475, | |
| "loss": 2.1696, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.00012787294975266856, | |
| "loss": 2.1474, | |
| "step": 11120 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.00012756053111168965, | |
| "loss": 2.1436, | |
| "step": 11140 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.00012724811247071075, | |
| "loss": 2.1785, | |
| "step": 11160 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 0.00012693569382973184, | |
| "loss": 2.1677, | |
| "step": 11180 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 0.0001266232751887529, | |
| "loss": 2.1564, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "eval_loss": 2.3451294898986816, | |
| "eval_runtime": 69.2454, | |
| "eval_samples_per_second": 28.883, | |
| "eval_steps_per_second": 1.805, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 0.000126310856547774, | |
| "loss": 2.1793, | |
| "step": 11220 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 0.0001259984379067951, | |
| "loss": 2.1583, | |
| "step": 11240 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 0.00012568601926581617, | |
| "loss": 2.1482, | |
| "step": 11260 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 0.00012537360062483727, | |
| "loss": 2.1393, | |
| "step": 11280 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.00012506118198385836, | |
| "loss": 2.1586, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.00012474876334287946, | |
| "loss": 2.1533, | |
| "step": 11320 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.00012443634470190053, | |
| "loss": 2.1516, | |
| "step": 11340 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.00012412392606092162, | |
| "loss": 2.1184, | |
| "step": 11360 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.00012381150741994272, | |
| "loss": 2.1162, | |
| "step": 11380 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.0001234990887789638, | |
| "loss": 2.1588, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "eval_loss": 2.3451669216156006, | |
| "eval_runtime": 69.2383, | |
| "eval_samples_per_second": 28.886, | |
| "eval_steps_per_second": 1.805, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.00012318667013798488, | |
| "loss": 2.1588, | |
| "step": 11420 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 0.00012287425149700598, | |
| "loss": 2.1463, | |
| "step": 11440 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 0.00012256183285602707, | |
| "loss": 2.1498, | |
| "step": 11460 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 0.00012224941421504814, | |
| "loss": 2.1663, | |
| "step": 11480 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 0.00012193699557406924, | |
| "loss": 2.1306, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 0.00012162457693309033, | |
| "loss": 2.1542, | |
| "step": 11520 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 0.00012131215829211141, | |
| "loss": 2.1513, | |
| "step": 11540 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 0.00012099973965113251, | |
| "loss": 2.2031, | |
| "step": 11560 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 0.00012068732101015359, | |
| "loss": 2.1438, | |
| "step": 11580 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 0.00012037490236917469, | |
| "loss": 2.1431, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "eval_loss": 2.3447554111480713, | |
| "eval_runtime": 69.2865, | |
| "eval_samples_per_second": 28.866, | |
| "eval_steps_per_second": 1.804, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 0.00012006248372819577, | |
| "loss": 2.1272, | |
| "step": 11620 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 0.00011975006508721686, | |
| "loss": 2.1584, | |
| "step": 11640 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 0.00011943764644623794, | |
| "loss": 2.128, | |
| "step": 11660 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.00011912522780525903, | |
| "loss": 2.1461, | |
| "step": 11680 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.00011881280916428012, | |
| "loss": 2.1411, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.0001185003905233012, | |
| "loss": 2.1592, | |
| "step": 11720 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.0001181879718823223, | |
| "loss": 2.1642, | |
| "step": 11740 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 0.00011787555324134338, | |
| "loss": 2.1914, | |
| "step": 11760 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 0.00011756313460036448, | |
| "loss": 2.1612, | |
| "step": 11780 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 0.00011725071595938556, | |
| "loss": 2.1452, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "eval_loss": 2.3442630767822266, | |
| "eval_runtime": 69.2459, | |
| "eval_samples_per_second": 28.883, | |
| "eval_steps_per_second": 1.805, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 0.00011693829731840665, | |
| "loss": 2.1453, | |
| "step": 11820 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 0.00011662587867742774, | |
| "loss": 2.1251, | |
| "step": 11840 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 0.00011631346003644882, | |
| "loss": 2.1412, | |
| "step": 11860 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 0.00011600104139546991, | |
| "loss": 2.1033, | |
| "step": 11880 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 0.000115688622754491, | |
| "loss": 2.1219, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 0.00011537620411351209, | |
| "loss": 2.1831, | |
| "step": 11920 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.00011506378547253317, | |
| "loss": 2.1434, | |
| "step": 11940 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.00011475136683155427, | |
| "loss": 2.1439, | |
| "step": 11960 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.00011443894819057536, | |
| "loss": 2.1377, | |
| "step": 11980 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.00011412652954959646, | |
| "loss": 2.1345, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "eval_loss": 2.342855453491211, | |
| "eval_runtime": 69.2714, | |
| "eval_samples_per_second": 28.872, | |
| "eval_steps_per_second": 1.804, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.00011381411090861754, | |
| "loss": 2.1527, | |
| "step": 12020 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.00011350169226763864, | |
| "loss": 2.1737, | |
| "step": 12040 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.00011318927362665972, | |
| "loss": 2.137, | |
| "step": 12060 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.00011287685498568081, | |
| "loss": 2.1616, | |
| "step": 12080 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.0001125644363447019, | |
| "loss": 2.1688, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.00011225201770372299, | |
| "loss": 2.1746, | |
| "step": 12120 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 0.00011193959906274407, | |
| "loss": 2.1552, | |
| "step": 12140 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 0.00011162718042176515, | |
| "loss": 2.1643, | |
| "step": 12160 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 0.00011131476178078625, | |
| "loss": 2.1494, | |
| "step": 12180 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 0.00011100234313980733, | |
| "loss": 2.1112, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "eval_loss": 2.34304141998291, | |
| "eval_runtime": 72.1422, | |
| "eval_samples_per_second": 27.723, | |
| "eval_steps_per_second": 1.733, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 0.00011068992449882843, | |
| "loss": 2.1505, | |
| "step": 12220 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 0.00011037750585784951, | |
| "loss": 2.1722, | |
| "step": 12240 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 0.0001100650872168706, | |
| "loss": 2.1582, | |
| "step": 12260 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 0.00010975266857589169, | |
| "loss": 2.1806, | |
| "step": 12280 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 0.00010944024993491278, | |
| "loss": 2.1508, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 0.00010912783129393386, | |
| "loss": 2.1654, | |
| "step": 12320 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.00010881541265295496, | |
| "loss": 2.131, | |
| "step": 12340 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.00010850299401197604, | |
| "loss": 2.1301, | |
| "step": 12360 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.00010819057537099712, | |
| "loss": 2.1312, | |
| "step": 12380 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 0.00010787815673001822, | |
| "loss": 2.1301, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "eval_loss": 2.3404922485351562, | |
| "eval_runtime": 71.3367, | |
| "eval_samples_per_second": 28.036, | |
| "eval_steps_per_second": 1.752, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 0.00010758135902108825, | |
| "loss": 2.1398, | |
| "step": 12420 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 0.00010726894038010933, | |
| "loss": 2.1449, | |
| "step": 12440 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 0.00010695652173913043, | |
| "loss": 2.1498, | |
| "step": 12460 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 0.00010664410309815151, | |
| "loss": 2.1484, | |
| "step": 12480 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 0.0001063316844571726, | |
| "loss": 2.1705, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.00010601926581619368, | |
| "loss": 2.1236, | |
| "step": 12520 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.00010570684717521478, | |
| "loss": 2.1435, | |
| "step": 12540 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.00010539442853423586, | |
| "loss": 2.1656, | |
| "step": 12560 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.00010508200989325696, | |
| "loss": 2.1459, | |
| "step": 12580 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 0.00010476959125227804, | |
| "loss": 2.1392, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "eval_loss": 2.3410892486572266, | |
| "eval_runtime": 72.1407, | |
| "eval_samples_per_second": 27.724, | |
| "eval_steps_per_second": 1.733, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 0.00010445717261129913, | |
| "loss": 2.1399, | |
| "step": 12620 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 0.00010414475397032022, | |
| "loss": 2.1979, | |
| "step": 12640 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 0.0001038323353293413, | |
| "loss": 2.1596, | |
| "step": 12660 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 0.0001035199166883624, | |
| "loss": 2.1817, | |
| "step": 12680 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 0.00010320749804738348, | |
| "loss": 2.0972, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.00010289507940640457, | |
| "loss": 2.1293, | |
| "step": 12720 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.00010258266076542565, | |
| "loss": 2.1362, | |
| "step": 12740 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.00010227024212444675, | |
| "loss": 2.1474, | |
| "step": 12760 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 0.00010195782348346783, | |
| "loss": 2.2004, | |
| "step": 12780 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 0.00010164540484248893, | |
| "loss": 2.1221, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_loss": 2.340029716491699, | |
| "eval_runtime": 72.0796, | |
| "eval_samples_per_second": 27.747, | |
| "eval_steps_per_second": 1.734, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 0.00010133298620151001, | |
| "loss": 2.1782, | |
| "step": 12820 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.00010102056756053109, | |
| "loss": 2.1358, | |
| "step": 12840 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.00010070814891955218, | |
| "loss": 2.122, | |
| "step": 12860 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.00010039573027857327, | |
| "loss": 2.1494, | |
| "step": 12880 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.00010008331163759436, | |
| "loss": 2.1522, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 9.977089299661544e-05, | |
| "loss": 2.1241, | |
| "step": 12920 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 9.945847435563654e-05, | |
| "loss": 2.1456, | |
| "step": 12940 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 9.914605571465763e-05, | |
| "loss": 2.1495, | |
| "step": 12960 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 9.883363707367873e-05, | |
| "loss": 2.1734, | |
| "step": 12980 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 9.852121843269981e-05, | |
| "loss": 2.1711, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "eval_loss": 2.339312791824341, | |
| "eval_runtime": 69.2994, | |
| "eval_samples_per_second": 28.86, | |
| "eval_steps_per_second": 1.804, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 9.820879979172091e-05, | |
| "loss": 2.1483, | |
| "step": 13020 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 9.789638115074199e-05, | |
| "loss": 2.124, | |
| "step": 13040 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 9.758396250976308e-05, | |
| "loss": 2.1337, | |
| "step": 13060 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 9.727154386878417e-05, | |
| "loss": 2.137, | |
| "step": 13080 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 9.695912522780526e-05, | |
| "loss": 2.1225, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 9.664670658682634e-05, | |
| "loss": 2.1384, | |
| "step": 13120 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 9.633428794584743e-05, | |
| "loss": 2.1052, | |
| "step": 13140 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 9.602186930486852e-05, | |
| "loss": 2.1489, | |
| "step": 13160 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 9.57094506638896e-05, | |
| "loss": 2.1154, | |
| "step": 13180 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 9.53970320229107e-05, | |
| "loss": 2.1476, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "eval_loss": 2.3396096229553223, | |
| "eval_runtime": 69.2833, | |
| "eval_samples_per_second": 28.867, | |
| "eval_steps_per_second": 1.804, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 9.508461338193178e-05, | |
| "loss": 2.1109, | |
| "step": 13220 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 9.477219474095288e-05, | |
| "loss": 2.0973, | |
| "step": 13240 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 9.445977609997396e-05, | |
| "loss": 2.1281, | |
| "step": 13260 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 9.414735745899505e-05, | |
| "loss": 2.1216, | |
| "step": 13280 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 9.383493881801614e-05, | |
| "loss": 2.1323, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 9.352252017703723e-05, | |
| "loss": 2.1477, | |
| "step": 13320 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 9.321010153605831e-05, | |
| "loss": 2.1309, | |
| "step": 13340 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 9.28976828950794e-05, | |
| "loss": 2.0899, | |
| "step": 13360 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 9.258526425410049e-05, | |
| "loss": 2.1402, | |
| "step": 13380 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 9.227284561312157e-05, | |
| "loss": 2.0768, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "eval_loss": 2.3376858234405518, | |
| "eval_runtime": 69.4568, | |
| "eval_samples_per_second": 28.795, | |
| "eval_steps_per_second": 1.8, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 9.196042697214267e-05, | |
| "loss": 2.1405, | |
| "step": 13420 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 9.164800833116375e-05, | |
| "loss": 2.1118, | |
| "step": 13440 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 9.133558969018484e-05, | |
| "loss": 2.1525, | |
| "step": 13460 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 9.102317104920593e-05, | |
| "loss": 2.1369, | |
| "step": 13480 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 9.071075240822702e-05, | |
| "loss": 2.1683, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 9.03983337672481e-05, | |
| "loss": 2.1193, | |
| "step": 13520 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 9.00859151262692e-05, | |
| "loss": 2.1222, | |
| "step": 13540 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 8.977349648529028e-05, | |
| "loss": 2.1461, | |
| "step": 13560 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 8.946107784431136e-05, | |
| "loss": 2.1106, | |
| "step": 13580 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 8.914865920333246e-05, | |
| "loss": 2.1307, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "eval_loss": 2.3381118774414062, | |
| "eval_runtime": 69.5609, | |
| "eval_samples_per_second": 28.752, | |
| "eval_steps_per_second": 1.797, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 8.883624056235354e-05, | |
| "loss": 2.1679, | |
| "step": 13620 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 8.852382192137464e-05, | |
| "loss": 2.1418, | |
| "step": 13640 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 8.821140328039572e-05, | |
| "loss": 2.1238, | |
| "step": 13660 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 8.789898463941681e-05, | |
| "loss": 2.0995, | |
| "step": 13680 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 8.75865659984379e-05, | |
| "loss": 2.1596, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 8.727414735745899e-05, | |
| "loss": 2.1478, | |
| "step": 13720 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 8.696172871648007e-05, | |
| "loss": 2.1299, | |
| "step": 13740 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 8.664931007550115e-05, | |
| "loss": 2.1405, | |
| "step": 13760 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 8.633689143452225e-05, | |
| "loss": 2.174, | |
| "step": 13780 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 8.602447279354333e-05, | |
| "loss": 2.129, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "eval_loss": 2.337769031524658, | |
| "eval_runtime": 69.7472, | |
| "eval_samples_per_second": 28.675, | |
| "eval_steps_per_second": 1.792, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 8.571205415256443e-05, | |
| "loss": 2.1368, | |
| "step": 13820 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 8.539963551158551e-05, | |
| "loss": 2.1573, | |
| "step": 13840 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 8.50872168706066e-05, | |
| "loss": 2.1132, | |
| "step": 13860 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 8.477479822962769e-05, | |
| "loss": 2.1131, | |
| "step": 13880 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 8.446237958864878e-05, | |
| "loss": 2.1351, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 8.414996094766986e-05, | |
| "loss": 2.1738, | |
| "step": 13920 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 8.383754230669096e-05, | |
| "loss": 2.1551, | |
| "step": 13940 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 8.352512366571204e-05, | |
| "loss": 2.1195, | |
| "step": 13960 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 8.321270502473312e-05, | |
| "loss": 2.1125, | |
| "step": 13980 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 8.290028638375422e-05, | |
| "loss": 2.1549, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "eval_loss": 2.337301731109619, | |
| "eval_runtime": 69.7462, | |
| "eval_samples_per_second": 28.675, | |
| "eval_steps_per_second": 1.792, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 8.25878677427753e-05, | |
| "loss": 2.1573, | |
| "step": 14020 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 8.22754491017964e-05, | |
| "loss": 2.1125, | |
| "step": 14040 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 8.196303046081748e-05, | |
| "loss": 2.161, | |
| "step": 14060 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 8.165061181983857e-05, | |
| "loss": 2.1511, | |
| "step": 14080 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 8.133819317885967e-05, | |
| "loss": 2.1737, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 8.102577453788076e-05, | |
| "loss": 2.1158, | |
| "step": 14120 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 8.071335589690184e-05, | |
| "loss": 2.1398, | |
| "step": 14140 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 8.040093725592294e-05, | |
| "loss": 2.1183, | |
| "step": 14160 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 8.008851861494402e-05, | |
| "loss": 2.1295, | |
| "step": 14180 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 7.977609997396512e-05, | |
| "loss": 2.1416, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "eval_loss": 2.336796760559082, | |
| "eval_runtime": 69.3578, | |
| "eval_samples_per_second": 28.836, | |
| "eval_steps_per_second": 1.802, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 7.94636813329862e-05, | |
| "loss": 2.1461, | |
| "step": 14220 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 7.91512626920073e-05, | |
| "loss": 2.0931, | |
| "step": 14240 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 7.883884405102838e-05, | |
| "loss": 2.1341, | |
| "step": 14260 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 7.852642541004946e-05, | |
| "loss": 2.1369, | |
| "step": 14280 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 7.821400676907055e-05, | |
| "loss": 2.1431, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 7.790158812809164e-05, | |
| "loss": 2.1508, | |
| "step": 14320 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 7.758916948711273e-05, | |
| "loss": 2.1456, | |
| "step": 14340 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 7.727675084613381e-05, | |
| "loss": 2.1448, | |
| "step": 14360 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 7.696433220515491e-05, | |
| "loss": 2.1637, | |
| "step": 14380 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 7.665191356417599e-05, | |
| "loss": 2.114, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "eval_loss": 2.3362655639648438, | |
| "eval_runtime": 69.5792, | |
| "eval_samples_per_second": 28.744, | |
| "eval_steps_per_second": 1.797, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 7.633949492319709e-05, | |
| "loss": 2.1222, | |
| "step": 14420 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 7.602707628221817e-05, | |
| "loss": 2.1776, | |
| "step": 14440 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 7.57302785732882e-05, | |
| "loss": 2.1414, | |
| "step": 14460 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 7.541785993230929e-05, | |
| "loss": 2.1231, | |
| "step": 14480 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 7.510544129133038e-05, | |
| "loss": 2.1345, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 7.479302265035147e-05, | |
| "loss": 2.1339, | |
| "step": 14520 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 7.448060400937255e-05, | |
| "loss": 2.1562, | |
| "step": 14540 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 7.416818536839363e-05, | |
| "loss": 2.1649, | |
| "step": 14560 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 7.385576672741473e-05, | |
| "loss": 2.1339, | |
| "step": 14580 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 7.354334808643581e-05, | |
| "loss": 2.1347, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "eval_loss": 2.335818290710449, | |
| "eval_runtime": 69.5131, | |
| "eval_samples_per_second": 28.772, | |
| "eval_steps_per_second": 1.798, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 7.323092944545691e-05, | |
| "loss": 2.1078, | |
| "step": 14620 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 7.291851080447799e-05, | |
| "loss": 2.1446, | |
| "step": 14640 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 7.260609216349908e-05, | |
| "loss": 2.1076, | |
| "step": 14660 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 7.229367352252017e-05, | |
| "loss": 2.1548, | |
| "step": 14680 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 7.198125488154126e-05, | |
| "loss": 2.1317, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 7.166883624056234e-05, | |
| "loss": 2.0991, | |
| "step": 14720 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 7.135641759958343e-05, | |
| "loss": 2.1507, | |
| "step": 14740 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 7.104399895860452e-05, | |
| "loss": 2.1173, | |
| "step": 14760 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 7.073158031762562e-05, | |
| "loss": 2.104, | |
| "step": 14780 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 7.043478260869565e-05, | |
| "loss": 2.1118, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "eval_loss": 2.334048271179199, | |
| "eval_runtime": 69.3816, | |
| "eval_samples_per_second": 28.826, | |
| "eval_steps_per_second": 1.802, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 7.012236396771674e-05, | |
| "loss": 2.0738, | |
| "step": 14820 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 6.980994532673782e-05, | |
| "loss": 2.1221, | |
| "step": 14840 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 6.94975266857589e-05, | |
| "loss": 2.1531, | |
| "step": 14860 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 6.918510804478e-05, | |
| "loss": 2.1318, | |
| "step": 14880 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 6.887268940380108e-05, | |
| "loss": 2.1251, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 6.856027076282218e-05, | |
| "loss": 2.1212, | |
| "step": 14920 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 6.824785212184326e-05, | |
| "loss": 2.0927, | |
| "step": 14940 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 6.793543348086436e-05, | |
| "loss": 2.1277, | |
| "step": 14960 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 6.762301483988544e-05, | |
| "loss": 2.156, | |
| "step": 14980 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 6.731059619890653e-05, | |
| "loss": 2.1276, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "eval_loss": 2.3340351581573486, | |
| "eval_runtime": 69.2926, | |
| "eval_samples_per_second": 28.863, | |
| "eval_steps_per_second": 1.804, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 6.699817755792761e-05, | |
| "loss": 2.1313, | |
| "step": 15020 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 6.668575891694871e-05, | |
| "loss": 2.1452, | |
| "step": 15040 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 6.637334027596979e-05, | |
| "loss": 2.1148, | |
| "step": 15060 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 6.606092163499087e-05, | |
| "loss": 2.1193, | |
| "step": 15080 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 6.574850299401197e-05, | |
| "loss": 2.1672, | |
| "step": 15100 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 6.543608435303305e-05, | |
| "loss": 2.0789, | |
| "step": 15120 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 6.512366571205415e-05, | |
| "loss": 2.1438, | |
| "step": 15140 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 6.481124707107523e-05, | |
| "loss": 2.1597, | |
| "step": 15160 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 6.449882843009632e-05, | |
| "loss": 2.11, | |
| "step": 15180 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 6.418640978911742e-05, | |
| "loss": 2.1279, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "eval_loss": 2.3344008922576904, | |
| "eval_runtime": 69.3363, | |
| "eval_samples_per_second": 28.845, | |
| "eval_steps_per_second": 1.803, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 6.38739911481385e-05, | |
| "loss": 2.1459, | |
| "step": 15220 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 6.35615725071596e-05, | |
| "loss": 2.1702, | |
| "step": 15240 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 6.324915386618068e-05, | |
| "loss": 2.1262, | |
| "step": 15260 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 6.293673522520177e-05, | |
| "loss": 2.0988, | |
| "step": 15280 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 6.262431658422286e-05, | |
| "loss": 2.1224, | |
| "step": 15300 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 6.231189794324394e-05, | |
| "loss": 2.1102, | |
| "step": 15320 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 6.199947930226503e-05, | |
| "loss": 2.1168, | |
| "step": 15340 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 6.168706066128611e-05, | |
| "loss": 2.1205, | |
| "step": 15360 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 6.137464202030721e-05, | |
| "loss": 2.0855, | |
| "step": 15380 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 6.106222337932829e-05, | |
| "loss": 2.1548, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "eval_loss": 2.333451271057129, | |
| "eval_runtime": 69.3334, | |
| "eval_samples_per_second": 28.846, | |
| "eval_steps_per_second": 1.803, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 6.074980473834938e-05, | |
| "loss": 2.1433, | |
| "step": 15420 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 6.043738609737047e-05, | |
| "loss": 2.123, | |
| "step": 15440 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 6.012496745639156e-05, | |
| "loss": 2.0965, | |
| "step": 15460 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 5.9812548815412647e-05, | |
| "loss": 2.1498, | |
| "step": 15480 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 5.9500130174433735e-05, | |
| "loss": 2.1456, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 5.9187711533454824e-05, | |
| "loss": 2.1295, | |
| "step": 15520 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 5.887529289247591e-05, | |
| "loss": 2.108, | |
| "step": 15540 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 5.8562874251497e-05, | |
| "loss": 2.1592, | |
| "step": 15560 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 5.825045561051809e-05, | |
| "loss": 2.1214, | |
| "step": 15580 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 5.793803696953918e-05, | |
| "loss": 2.1561, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "eval_loss": 2.3329403400421143, | |
| "eval_runtime": 69.6034, | |
| "eval_samples_per_second": 28.734, | |
| "eval_steps_per_second": 1.796, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 5.762561832856026e-05, | |
| "loss": 2.1382, | |
| "step": 15620 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 5.731319968758135e-05, | |
| "loss": 2.109, | |
| "step": 15640 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 5.700078104660244e-05, | |
| "loss": 2.1283, | |
| "step": 15660 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 5.6688362405623526e-05, | |
| "loss": 2.15, | |
| "step": 15680 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 5.6375943764644615e-05, | |
| "loss": 2.1125, | |
| "step": 15700 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 5.6063525123665704e-05, | |
| "loss": 2.1709, | |
| "step": 15720 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 5.575110648268679e-05, | |
| "loss": 2.1622, | |
| "step": 15740 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 5.543868784170789e-05, | |
| "loss": 2.0769, | |
| "step": 15760 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 5.5126269200728976e-05, | |
| "loss": 2.137, | |
| "step": 15780 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 5.4813850559750065e-05, | |
| "loss": 2.1294, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "eval_loss": 2.3324475288391113, | |
| "eval_runtime": 69.559, | |
| "eval_samples_per_second": 28.753, | |
| "eval_steps_per_second": 1.797, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 5.4501431918771154e-05, | |
| "loss": 2.1425, | |
| "step": 15820 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 5.418901327779224e-05, | |
| "loss": 2.128, | |
| "step": 15840 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 5.387659463681333e-05, | |
| "loss": 2.1553, | |
| "step": 15860 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 5.356417599583441e-05, | |
| "loss": 2.1339, | |
| "step": 15880 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 5.32517573548555e-05, | |
| "loss": 2.1536, | |
| "step": 15900 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 5.293933871387659e-05, | |
| "loss": 2.1669, | |
| "step": 15920 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 5.262692007289768e-05, | |
| "loss": 2.122, | |
| "step": 15940 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 5.231450143191877e-05, | |
| "loss": 2.1435, | |
| "step": 15960 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 5.2002082790939856e-05, | |
| "loss": 2.1406, | |
| "step": 15980 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 5.1689664149960945e-05, | |
| "loss": 2.1174, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "eval_loss": 2.332836866378784, | |
| "eval_runtime": 69.3739, | |
| "eval_samples_per_second": 28.829, | |
| "eval_steps_per_second": 1.802, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 5.137724550898203e-05, | |
| "loss": 2.1286, | |
| "step": 16020 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 5.106482686800312e-05, | |
| "loss": 2.1343, | |
| "step": 16040 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 5.075240822702421e-05, | |
| "loss": 2.1134, | |
| "step": 16060 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 5.043998958604529e-05, | |
| "loss": 2.1633, | |
| "step": 16080 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 5.012757094506638e-05, | |
| "loss": 2.1473, | |
| "step": 16100 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 4.981515230408747e-05, | |
| "loss": 2.1535, | |
| "step": 16120 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 4.950273366310856e-05, | |
| "loss": 2.112, | |
| "step": 16140 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 4.919031502212965e-05, | |
| "loss": 2.1399, | |
| "step": 16160 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 4.8877896381150736e-05, | |
| "loss": 2.0913, | |
| "step": 16180 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 4.8565477740171824e-05, | |
| "loss": 2.1179, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "eval_loss": 2.332409143447876, | |
| "eval_runtime": 69.3294, | |
| "eval_samples_per_second": 28.848, | |
| "eval_steps_per_second": 1.803, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 4.825305909919291e-05, | |
| "loss": 2.1756, | |
| "step": 16220 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 4.7940640458214e-05, | |
| "loss": 2.1466, | |
| "step": 16240 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 4.762822181723509e-05, | |
| "loss": 2.1443, | |
| "step": 16260 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 4.731580317625618e-05, | |
| "loss": 2.1207, | |
| "step": 16280 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 4.700338453527726e-05, | |
| "loss": 2.1275, | |
| "step": 16300 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 4.669096589429835e-05, | |
| "loss": 2.1305, | |
| "step": 16320 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 4.6378547253319445e-05, | |
| "loss": 2.134, | |
| "step": 16340 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 4.6066128612340534e-05, | |
| "loss": 2.1681, | |
| "step": 16360 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 4.575370997136162e-05, | |
| "loss": 2.1627, | |
| "step": 16380 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 4.544129133038271e-05, | |
| "loss": 2.1421, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "eval_loss": 2.3318614959716797, | |
| "eval_runtime": 69.3251, | |
| "eval_samples_per_second": 28.85, | |
| "eval_steps_per_second": 1.803, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 4.51288726894038e-05, | |
| "loss": 2.1225, | |
| "step": 16420 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 4.481645404842489e-05, | |
| "loss": 2.156, | |
| "step": 16440 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 4.450403540744598e-05, | |
| "loss": 2.1573, | |
| "step": 16460 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 4.4191616766467066e-05, | |
| "loss": 2.1295, | |
| "step": 16480 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 4.3879198125488154e-05, | |
| "loss": 2.14, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 4.356677948450924e-05, | |
| "loss": 2.1046, | |
| "step": 16520 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 4.3254360843530325e-05, | |
| "loss": 2.1201, | |
| "step": 16540 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 4.2941942202551413e-05, | |
| "loss": 2.1767, | |
| "step": 16560 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 4.26295235615725e-05, | |
| "loss": 2.1244, | |
| "step": 16580 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 4.231710492059359e-05, | |
| "loss": 2.1301, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "eval_loss": 2.331899881362915, | |
| "eval_runtime": 69.3398, | |
| "eval_samples_per_second": 28.843, | |
| "eval_steps_per_second": 1.803, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 4.200468627961468e-05, | |
| "loss": 2.1022, | |
| "step": 16620 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 4.169226763863577e-05, | |
| "loss": 2.1121, | |
| "step": 16640 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 4.137984899765686e-05, | |
| "loss": 2.1014, | |
| "step": 16660 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 4.1067430356677945e-05, | |
| "loss": 2.1867, | |
| "step": 16680 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 4.0755011715699034e-05, | |
| "loss": 2.1055, | |
| "step": 16700 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 4.044259307472012e-05, | |
| "loss": 2.1435, | |
| "step": 16720 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 4.013017443374121e-05, | |
| "loss": 2.09, | |
| "step": 16740 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 3.981775579276229e-05, | |
| "loss": 2.1317, | |
| "step": 16760 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 3.950533715178338e-05, | |
| "loss": 2.0683, | |
| "step": 16780 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 3.919291851080447e-05, | |
| "loss": 2.1249, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "eval_loss": 2.331566572189331, | |
| "eval_runtime": 69.3154, | |
| "eval_samples_per_second": 28.854, | |
| "eval_steps_per_second": 1.803, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 3.888049986982556e-05, | |
| "loss": 2.164, | |
| "step": 16820 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 3.856808122884665e-05, | |
| "loss": 2.16, | |
| "step": 16840 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 3.8255662587867736e-05, | |
| "loss": 2.1603, | |
| "step": 16860 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 3.7943243946888825e-05, | |
| "loss": 2.1346, | |
| "step": 16880 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 3.7630825305909914e-05, | |
| "loss": 2.1082, | |
| "step": 16900 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 3.7318406664931e-05, | |
| "loss": 2.1014, | |
| "step": 16920 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 3.700598802395209e-05, | |
| "loss": 2.1088, | |
| "step": 16940 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 3.669356938297318e-05, | |
| "loss": 2.0975, | |
| "step": 16960 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 3.638115074199427e-05, | |
| "loss": 2.1212, | |
| "step": 16980 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 3.606873210101536e-05, | |
| "loss": 2.1226, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "eval_loss": 2.3310983180999756, | |
| "eval_runtime": 69.3945, | |
| "eval_samples_per_second": 28.821, | |
| "eval_steps_per_second": 1.801, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 3.5756313460036446e-05, | |
| "loss": 2.1318, | |
| "step": 17020 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 3.5443894819057534e-05, | |
| "loss": 2.1073, | |
| "step": 17040 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 3.513147617807862e-05, | |
| "loss": 2.1411, | |
| "step": 17060 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 3.481905753709971e-05, | |
| "loss": 2.0959, | |
| "step": 17080 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 3.45066388961208e-05, | |
| "loss": 2.0858, | |
| "step": 17100 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 3.419422025514189e-05, | |
| "loss": 2.1174, | |
| "step": 17120 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 3.388180161416298e-05, | |
| "loss": 2.1459, | |
| "step": 17140 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 3.3569382973184066e-05, | |
| "loss": 2.1425, | |
| "step": 17160 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 3.3256964332205155e-05, | |
| "loss": 2.0971, | |
| "step": 17180 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 3.2944545691226243e-05, | |
| "loss": 2.1176, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "eval_loss": 2.330962896347046, | |
| "eval_runtime": 69.3407, | |
| "eval_samples_per_second": 28.843, | |
| "eval_steps_per_second": 1.803, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 3.2632127050247325e-05, | |
| "loss": 2.1471, | |
| "step": 17220 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 3.2319708409268414e-05, | |
| "loss": 2.1064, | |
| "step": 17240 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 3.20072897682895e-05, | |
| "loss": 2.1347, | |
| "step": 17260 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 3.169487112731059e-05, | |
| "loss": 2.142, | |
| "step": 17280 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 3.138245248633168e-05, | |
| "loss": 2.1773, | |
| "step": 17300 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 3.107003384535277e-05, | |
| "loss": 2.1489, | |
| "step": 17320 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 3.075761520437386e-05, | |
| "loss": 2.1257, | |
| "step": 17340 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 3.044519656339495e-05, | |
| "loss": 2.1288, | |
| "step": 17360 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 3.0132777922416038e-05, | |
| "loss": 2.1258, | |
| "step": 17380 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 2.9820359281437123e-05, | |
| "loss": 2.1322, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "eval_loss": 2.3309593200683594, | |
| "eval_runtime": 69.3923, | |
| "eval_samples_per_second": 28.822, | |
| "eval_steps_per_second": 1.801, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 2.9507940640458212e-05, | |
| "loss": 2.1495, | |
| "step": 17420 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 2.91955219994793e-05, | |
| "loss": 2.0843, | |
| "step": 17440 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 2.888310335850039e-05, | |
| "loss": 2.11, | |
| "step": 17460 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 2.8570684717521478e-05, | |
| "loss": 2.1005, | |
| "step": 17480 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 2.827388700859151e-05, | |
| "loss": 2.1302, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 2.79614683676126e-05, | |
| "loss": 2.1086, | |
| "step": 17520 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 2.7649049726633688e-05, | |
| "loss": 2.1302, | |
| "step": 17540 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 2.7336631085654777e-05, | |
| "loss": 2.1417, | |
| "step": 17560 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 2.7024212444675862e-05, | |
| "loss": 2.1369, | |
| "step": 17580 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 2.671179380369695e-05, | |
| "loss": 2.1384, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "eval_loss": 2.33089017868042, | |
| "eval_runtime": 69.3747, | |
| "eval_samples_per_second": 28.829, | |
| "eval_steps_per_second": 1.802, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 2.639937516271804e-05, | |
| "loss": 2.1243, | |
| "step": 17620 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 2.6086956521739128e-05, | |
| "loss": 2.1161, | |
| "step": 17640 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 2.5774537880760217e-05, | |
| "loss": 2.1051, | |
| "step": 17660 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 2.5462119239781302e-05, | |
| "loss": 2.0762, | |
| "step": 17680 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 2.514970059880239e-05, | |
| "loss": 2.1105, | |
| "step": 17700 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 2.483728195782348e-05, | |
| "loss": 2.1535, | |
| "step": 17720 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 2.452486331684457e-05, | |
| "loss": 2.1706, | |
| "step": 17740 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 2.421244467586566e-05, | |
| "loss": 2.0857, | |
| "step": 17760 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 2.390002603488675e-05, | |
| "loss": 2.1553, | |
| "step": 17780 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 2.3587607393907834e-05, | |
| "loss": 2.0983, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "eval_loss": 2.3304569721221924, | |
| "eval_runtime": 69.35, | |
| "eval_samples_per_second": 28.839, | |
| "eval_steps_per_second": 1.802, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 2.3275188752928923e-05, | |
| "loss": 2.1212, | |
| "step": 17820 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 2.296277011195001e-05, | |
| "loss": 2.0816, | |
| "step": 17840 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 2.26503514709711e-05, | |
| "loss": 2.0935, | |
| "step": 17860 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 2.233793282999219e-05, | |
| "loss": 2.1576, | |
| "step": 17880 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 2.2025514189013274e-05, | |
| "loss": 2.1076, | |
| "step": 17900 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 2.1713095548034362e-05, | |
| "loss": 2.1184, | |
| "step": 17920 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 2.140067690705545e-05, | |
| "loss": 2.1169, | |
| "step": 17940 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 2.108825826607654e-05, | |
| "loss": 2.1442, | |
| "step": 17960 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 2.077583962509763e-05, | |
| "loss": 2.1332, | |
| "step": 17980 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 2.0463420984118717e-05, | |
| "loss": 2.1553, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "eval_loss": 2.330599069595337, | |
| "eval_runtime": 69.346, | |
| "eval_samples_per_second": 28.841, | |
| "eval_steps_per_second": 1.803, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 2.0151002343139802e-05, | |
| "loss": 2.1055, | |
| "step": 18020 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 1.9838583702160894e-05, | |
| "loss": 2.0778, | |
| "step": 18040 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 1.9526165061181983e-05, | |
| "loss": 2.143, | |
| "step": 18060 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 1.921374642020307e-05, | |
| "loss": 2.0886, | |
| "step": 18080 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 1.890132777922416e-05, | |
| "loss": 2.1236, | |
| "step": 18100 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 1.858890913824525e-05, | |
| "loss": 2.1307, | |
| "step": 18120 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 1.8276490497266334e-05, | |
| "loss": 2.1192, | |
| "step": 18140 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 1.7964071856287423e-05, | |
| "loss": 2.0999, | |
| "step": 18160 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 1.765165321530851e-05, | |
| "loss": 2.0792, | |
| "step": 18180 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 1.73392345743296e-05, | |
| "loss": 2.1015, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "eval_loss": 2.330050230026245, | |
| "eval_runtime": 69.3278, | |
| "eval_samples_per_second": 28.848, | |
| "eval_steps_per_second": 1.803, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 1.702681593335069e-05, | |
| "loss": 2.1226, | |
| "step": 18220 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 1.6714397292371778e-05, | |
| "loss": 2.0924, | |
| "step": 18240 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 1.6401978651392866e-05, | |
| "loss": 2.1272, | |
| "step": 18260 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 1.6089560010413955e-05, | |
| "loss": 2.1175, | |
| "step": 18280 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 1.577714136943504e-05, | |
| "loss": 2.1396, | |
| "step": 18300 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 1.546472272845613e-05, | |
| "loss": 2.1514, | |
| "step": 18320 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 1.5152304087477217e-05, | |
| "loss": 2.1257, | |
| "step": 18340 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 1.4839885446498306e-05, | |
| "loss": 2.1459, | |
| "step": 18360 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 1.4527466805519396e-05, | |
| "loss": 2.09, | |
| "step": 18380 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 1.4215048164540483e-05, | |
| "loss": 2.1442, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "eval_loss": 2.330048084259033, | |
| "eval_runtime": 69.2975, | |
| "eval_samples_per_second": 28.861, | |
| "eval_steps_per_second": 1.804, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 1.3902629523561572e-05, | |
| "loss": 2.1816, | |
| "step": 18420 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 1.3590210882582659e-05, | |
| "loss": 2.0965, | |
| "step": 18440 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 1.3277792241603748e-05, | |
| "loss": 2.1178, | |
| "step": 18460 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 1.2965373600624836e-05, | |
| "loss": 2.1562, | |
| "step": 18480 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 1.2652954959645923e-05, | |
| "loss": 2.095, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 1.2340536318667012e-05, | |
| "loss": 2.1522, | |
| "step": 18520 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 1.2028117677688102e-05, | |
| "loss": 2.1729, | |
| "step": 18540 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 1.1715699036709189e-05, | |
| "loss": 2.141, | |
| "step": 18560 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 1.1403280395730278e-05, | |
| "loss": 2.148, | |
| "step": 18580 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 1.1090861754751366e-05, | |
| "loss": 2.1619, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "eval_loss": 2.329728603363037, | |
| "eval_runtime": 69.3412, | |
| "eval_samples_per_second": 28.843, | |
| "eval_steps_per_second": 1.803, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 1.0778443113772453e-05, | |
| "loss": 2.1199, | |
| "step": 18620 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 1.0466024472793542e-05, | |
| "loss": 2.131, | |
| "step": 18640 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 1.0153605831814629e-05, | |
| "loss": 2.1512, | |
| "step": 18660 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 9.84118719083572e-06, | |
| "loss": 2.1292, | |
| "step": 18680 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 9.528768549856808e-06, | |
| "loss": 2.0928, | |
| "step": 18700 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 9.216349908877897e-06, | |
| "loss": 2.1168, | |
| "step": 18720 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 8.903931267898984e-06, | |
| "loss": 2.1316, | |
| "step": 18740 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 8.591512626920072e-06, | |
| "loss": 2.1198, | |
| "step": 18760 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 8.279093985941161e-06, | |
| "loss": 2.1226, | |
| "step": 18780 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 7.96667534496225e-06, | |
| "loss": 2.1234, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "eval_loss": 2.3294034004211426, | |
| "eval_runtime": 69.3303, | |
| "eval_samples_per_second": 28.847, | |
| "eval_steps_per_second": 1.803, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 7.654256703983337e-06, | |
| "loss": 2.1251, | |
| "step": 18820 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 7.341838063004425e-06, | |
| "loss": 2.1278, | |
| "step": 18840 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 7.029419422025514e-06, | |
| "loss": 2.1115, | |
| "step": 18860 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 6.717000781046602e-06, | |
| "loss": 2.1468, | |
| "step": 18880 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 6.4045821400676894e-06, | |
| "loss": 2.0903, | |
| "step": 18900 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 6.092163499088779e-06, | |
| "loss": 2.1271, | |
| "step": 18920 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 5.779744858109867e-06, | |
| "loss": 2.1253, | |
| "step": 18940 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 5.4673262171309545e-06, | |
| "loss": 2.0903, | |
| "step": 18960 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 5.154907576152043e-06, | |
| "loss": 2.1566, | |
| "step": 18980 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 4.842488935173132e-06, | |
| "loss": 2.1477, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "eval_loss": 2.3293075561523438, | |
| "eval_runtime": 69.6518, | |
| "eval_samples_per_second": 28.714, | |
| "eval_steps_per_second": 1.795, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 4.53007029419422e-06, | |
| "loss": 2.1145, | |
| "step": 19020 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 4.217651653215308e-06, | |
| "loss": 2.1255, | |
| "step": 19040 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 3.905233012236396e-06, | |
| "loss": 2.1122, | |
| "step": 19060 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 3.5928143712574848e-06, | |
| "loss": 2.1299, | |
| "step": 19080 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 3.280395730278573e-06, | |
| "loss": 2.1272, | |
| "step": 19100 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 2.9679770892996616e-06, | |
| "loss": 2.1234, | |
| "step": 19120 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 2.6555584483207494e-06, | |
| "loss": 2.1791, | |
| "step": 19140 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 2.343139807341838e-06, | |
| "loss": 2.1565, | |
| "step": 19160 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 2.0307211663629263e-06, | |
| "loss": 2.1256, | |
| "step": 19180 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 1.7183025253840145e-06, | |
| "loss": 2.1641, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "eval_loss": 2.329240560531616, | |
| "eval_runtime": 69.5753, | |
| "eval_samples_per_second": 28.746, | |
| "eval_steps_per_second": 1.797, | |
| "step": 19200 | |
| } | |
| ], | |
| "max_steps": 19305, | |
| "num_train_epochs": 3, | |
| "total_flos": 5.372174060814231e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |