instrucode
/
with_input
/decomp_code_with_intermediates
/code-llama-13b
/checkpoint-7600
/trainer_state.json
| { | |
| "best_metric": 0.3120864927768707, | |
| "best_model_checkpoint": "checkpoints/instrucode/with_input/decomp_code_with_intermediates/code-llama-13b/checkpoint-4600", | |
| "epoch": 4.887459807073955, | |
| "eval_steps": 200, | |
| "global_step": 7600, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 1.0023, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 0.9538, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 0.8457, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 0.6184, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00015, | |
| "loss": 0.4717, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 0.4208, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 0.4056, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 0.4016, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00027, | |
| "loss": 0.3856, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0003, | |
| "loss": 0.3906, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00029960912052117263, | |
| "loss": 0.3818, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0002992182410423453, | |
| "loss": 0.381, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0002988273615635179, | |
| "loss": 0.3717, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00029843648208469054, | |
| "loss": 0.3659, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00029804560260586314, | |
| "loss": 0.3723, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0002976547231270358, | |
| "loss": 0.3677, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00029726384364820845, | |
| "loss": 0.3609, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00029687296416938105, | |
| "loss": 0.3815, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0002964820846905537, | |
| "loss": 0.3655, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00029609120521172636, | |
| "loss": 0.3754, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 0.35924971103668213, | |
| "eval_runtime": 651.3475, | |
| "eval_samples_per_second": 3.071, | |
| "eval_steps_per_second": 0.384, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.000295700325732899, | |
| "loss": 0.3679, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0002953094462540716, | |
| "loss": 0.3615, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0002949185667752443, | |
| "loss": 0.3502, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00029452768729641693, | |
| "loss": 0.3393, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00029413680781758953, | |
| "loss": 0.3604, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0002937459283387622, | |
| "loss": 0.3654, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00029335504885993484, | |
| "loss": 0.3654, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00029296416938110744, | |
| "loss": 0.3507, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0002925732899022801, | |
| "loss": 0.3611, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00029218241042345275, | |
| "loss": 0.3431, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0002917915309446254, | |
| "loss": 0.3542, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.000291400651465798, | |
| "loss": 0.3453, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00029100977198697066, | |
| "loss": 0.3557, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00029061889250814327, | |
| "loss": 0.3521, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0002902280130293159, | |
| "loss": 0.3444, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0002898371335504886, | |
| "loss": 0.3551, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00028944625407166123, | |
| "loss": 0.3506, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0002890553745928339, | |
| "loss": 0.3618, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0002886644951140065, | |
| "loss": 0.3475, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00028827361563517914, | |
| "loss": 0.3478, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 0.34671008586883545, | |
| "eval_runtime": 650.6789, | |
| "eval_samples_per_second": 3.074, | |
| "eval_steps_per_second": 0.384, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00028788273615635174, | |
| "loss": 0.355, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0002874918566775244, | |
| "loss": 0.3491, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00028710097719869705, | |
| "loss": 0.3462, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00028671009771986966, | |
| "loss": 0.3483, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0002863192182410423, | |
| "loss": 0.3557, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00028592833876221497, | |
| "loss": 0.3374, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0002855374592833876, | |
| "loss": 0.3547, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0002851465798045602, | |
| "loss": 0.3425, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0002847557003257329, | |
| "loss": 0.343, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0002843648208469055, | |
| "loss": 0.3509, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00028397394136807813, | |
| "loss": 0.3465, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0002835830618892508, | |
| "loss": 0.3346, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00028319218241042344, | |
| "loss": 0.3557, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00028280130293159605, | |
| "loss": 0.3448, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0002824104234527687, | |
| "loss": 0.3526, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00028201954397394136, | |
| "loss": 0.3366, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.000281628664495114, | |
| "loss": 0.3512, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0002812377850162866, | |
| "loss": 0.333, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00028084690553745927, | |
| "loss": 0.3334, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00028045602605863187, | |
| "loss": 0.3432, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_loss": 0.33927789330482483, | |
| "eval_runtime": 650.6946, | |
| "eval_samples_per_second": 3.074, | |
| "eval_steps_per_second": 0.384, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.0002800651465798045, | |
| "loss": 0.3422, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0002796742671009772, | |
| "loss": 0.3361, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00027928338762214983, | |
| "loss": 0.3469, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00027889250814332244, | |
| "loss": 0.3325, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.0002785016286644951, | |
| "loss": 0.3384, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00027811074918566775, | |
| "loss": 0.3407, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00027771986970684035, | |
| "loss": 0.3434, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.000277328990228013, | |
| "loss": 0.3367, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00027693811074918566, | |
| "loss": 0.3514, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00027654723127035826, | |
| "loss": 0.3425, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0002761563517915309, | |
| "loss": 0.3385, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00027576547231270357, | |
| "loss": 0.3426, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0002753745928338762, | |
| "loss": 0.3428, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0002749837133550488, | |
| "loss": 0.3376, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0002745928338762215, | |
| "loss": 0.3531, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.0002742019543973941, | |
| "loss": 0.3384, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00027381107491856674, | |
| "loss": 0.3363, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0002734201954397394, | |
| "loss": 0.3459, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00027302931596091205, | |
| "loss": 0.339, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00027263843648208465, | |
| "loss": 0.3394, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 0.3341918885707855, | |
| "eval_runtime": 650.6673, | |
| "eval_samples_per_second": 3.074, | |
| "eval_steps_per_second": 0.384, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.0002722475570032573, | |
| "loss": 0.334, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00027185667752442996, | |
| "loss": 0.3448, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0002714657980456026, | |
| "loss": 0.3454, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0002710749185667752, | |
| "loss": 0.3476, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00027068403908794787, | |
| "loss": 0.3284, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00027029315960912047, | |
| "loss": 0.3363, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.0002699022801302931, | |
| "loss": 0.3386, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0002695114006514658, | |
| "loss": 0.3272, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.00026912052117263844, | |
| "loss": 0.3241, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.00026872964169381104, | |
| "loss": 0.3337, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.0002683387622149837, | |
| "loss": 0.329, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00026794788273615635, | |
| "loss": 0.3296, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00026755700325732895, | |
| "loss": 0.3323, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.0002671661237785016, | |
| "loss": 0.3275, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.0002667752442996742, | |
| "loss": 0.3384, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00026638436482084686, | |
| "loss": 0.3447, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.0002659934853420195, | |
| "loss": 0.3262, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00026560260586319217, | |
| "loss": 0.3273, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.0002652117263843648, | |
| "loss": 0.3356, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00026482084690553743, | |
| "loss": 0.3443, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 0.33089369535446167, | |
| "eval_runtime": 651.3231, | |
| "eval_samples_per_second": 3.071, | |
| "eval_steps_per_second": 0.384, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.0002644299674267101, | |
| "loss": 0.3372, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.0002640390879478827, | |
| "loss": 0.3115, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00026364820846905534, | |
| "loss": 0.3284, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.000263257328990228, | |
| "loss": 0.3452, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.0002628664495114006, | |
| "loss": 0.3347, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.00026247557003257325, | |
| "loss": 0.3331, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.0002620846905537459, | |
| "loss": 0.3202, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.00026169381107491856, | |
| "loss": 0.3393, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.0002613029315960912, | |
| "loss": 0.3336, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.0002609120521172638, | |
| "loss": 0.3352, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.0002605211726384365, | |
| "loss": 0.3441, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.0002601302931596091, | |
| "loss": 0.3328, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.00025973941368078173, | |
| "loss": 0.3349, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.0002593485342019544, | |
| "loss": 0.3173, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.00025895765472312704, | |
| "loss": 0.326, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.00025856677524429964, | |
| "loss": 0.3458, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.0002581758957654723, | |
| "loss": 0.3474, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.00025778501628664495, | |
| "loss": 0.3365, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.00025739413680781755, | |
| "loss": 0.3189, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.0002570032573289902, | |
| "loss": 0.3341, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 0.3276467025279999, | |
| "eval_runtime": 651.2067, | |
| "eval_samples_per_second": 3.071, | |
| "eval_steps_per_second": 0.384, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.0002566123778501628, | |
| "loss": 0.3326, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.00025622149837133546, | |
| "loss": 0.3222, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.0002558306188925081, | |
| "loss": 0.3354, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0002554397394136808, | |
| "loss": 0.3394, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.00025504885993485343, | |
| "loss": 0.3234, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.00025465798045602603, | |
| "loss": 0.3325, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.0002542671009771987, | |
| "loss": 0.329, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.0002538762214983713, | |
| "loss": 0.3169, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.00025348534201954394, | |
| "loss": 0.3328, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.0002530944625407166, | |
| "loss": 0.3267, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.0002527035830618892, | |
| "loss": 0.3254, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.00025231270358306185, | |
| "loss": 0.3282, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.0002519218241042345, | |
| "loss": 0.3336, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.00025153094462540716, | |
| "loss": 0.3195, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.0002511400651465798, | |
| "loss": 0.3261, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.0002507491856677524, | |
| "loss": 0.338, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.0002503583061889251, | |
| "loss": 0.3247, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.0002499674267100977, | |
| "loss": 0.3266, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.00024957654723127033, | |
| "loss": 0.3382, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.000249185667752443, | |
| "loss": 0.3256, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_loss": 0.3250886797904968, | |
| "eval_runtime": 651.1313, | |
| "eval_samples_per_second": 3.072, | |
| "eval_steps_per_second": 0.384, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.0002487947882736156, | |
| "loss": 0.327, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.00024840390879478824, | |
| "loss": 0.3199, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.0002480130293159609, | |
| "loss": 0.3223, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.00024762214983713355, | |
| "loss": 0.331, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.00024723127035830616, | |
| "loss": 0.3352, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.0002468403908794788, | |
| "loss": 0.328, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.0002464495114006514, | |
| "loss": 0.3361, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.00024605863192182407, | |
| "loss": 0.3302, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.0002456677524429967, | |
| "loss": 0.3405, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.0002452768729641694, | |
| "loss": 0.3305, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.00024488599348534203, | |
| "loss": 0.3405, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.00024449511400651463, | |
| "loss": 0.3286, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.00024410423452768726, | |
| "loss": 0.3255, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.00024371335504885992, | |
| "loss": 0.3301, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.00024332247557003257, | |
| "loss": 0.3226, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0002429315960912052, | |
| "loss": 0.3269, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.00024254071661237783, | |
| "loss": 0.3237, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.00024214983713355046, | |
| "loss": 0.305, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.0002417589576547231, | |
| "loss": 0.3232, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.00024136807817589574, | |
| "loss": 0.312, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "eval_loss": 0.32348474860191345, | |
| "eval_runtime": 650.6657, | |
| "eval_samples_per_second": 3.074, | |
| "eval_steps_per_second": 0.384, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.0002409771986970684, | |
| "loss": 0.3029, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.000240586319218241, | |
| "loss": 0.3194, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.00024019543973941365, | |
| "loss": 0.3252, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.0002398045602605863, | |
| "loss": 0.3173, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.00023941368078175893, | |
| "loss": 0.3224, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0002390228013029316, | |
| "loss": 0.3171, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0002386319218241042, | |
| "loss": 0.3172, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.00023824104234527685, | |
| "loss": 0.3175, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.0002378501628664495, | |
| "loss": 0.3255, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.00023745928338762213, | |
| "loss": 0.3085, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.00023706840390879478, | |
| "loss": 0.3199, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.00023667752442996739, | |
| "loss": 0.3064, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.00023628664495114004, | |
| "loss": 0.3056, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.00023589576547231267, | |
| "loss": 0.3146, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.00023550488599348532, | |
| "loss": 0.3117, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.00023511400651465798, | |
| "loss": 0.3149, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.00023472312703583058, | |
| "loss": 0.3246, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.00023433224755700324, | |
| "loss": 0.3166, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.00023394136807817586, | |
| "loss": 0.3136, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.00023355048859934852, | |
| "loss": 0.3219, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "eval_loss": 0.32202833890914917, | |
| "eval_runtime": 654.7577, | |
| "eval_samples_per_second": 3.055, | |
| "eval_steps_per_second": 0.382, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.00023315960912052117, | |
| "loss": 0.3262, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.00023276872964169378, | |
| "loss": 0.3194, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.00023237785016286643, | |
| "loss": 0.3158, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.00023198697068403906, | |
| "loss": 0.3088, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.00023159609120521171, | |
| "loss": 0.3101, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.00023120521172638434, | |
| "loss": 0.3205, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.000230814332247557, | |
| "loss": 0.3134, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.0002304234527687296, | |
| "loss": 0.3218, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.00023003257328990225, | |
| "loss": 0.3181, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.0002296416938110749, | |
| "loss": 0.3154, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.00022925081433224754, | |
| "loss": 0.3086, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.0002288599348534202, | |
| "loss": 0.3179, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.0002284690553745928, | |
| "loss": 0.317, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.00022807817589576545, | |
| "loss": 0.3055, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.0002276872964169381, | |
| "loss": 0.328, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.00022729641693811073, | |
| "loss": 0.3084, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 0.0002269055374592834, | |
| "loss": 0.3149, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 0.000226514657980456, | |
| "loss": 0.314, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.00022612377850162864, | |
| "loss": 0.3127, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.00022573289902280127, | |
| "loss": 0.2997, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "eval_loss": 0.3208238184452057, | |
| "eval_runtime": 656.3169, | |
| "eval_samples_per_second": 3.047, | |
| "eval_steps_per_second": 0.381, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.00022534201954397393, | |
| "loss": 0.3162, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 0.00022495114006514658, | |
| "loss": 0.3144, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.00022456026058631918, | |
| "loss": 0.3121, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.00022416938110749184, | |
| "loss": 0.3112, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.00022377850162866447, | |
| "loss": 0.3143, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.00022338762214983712, | |
| "loss": 0.3008, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.00022299674267100978, | |
| "loss": 0.3195, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.00022260586319218238, | |
| "loss": 0.303, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.00022221498371335503, | |
| "loss": 0.3177, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.00022182410423452766, | |
| "loss": 0.3241, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.00022143322475570032, | |
| "loss": 0.3222, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.00022104234527687295, | |
| "loss": 0.3214, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 0.00022065146579804557, | |
| "loss": 0.3015, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.0002202605863192182, | |
| "loss": 0.3151, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.00021986970684039086, | |
| "loss": 0.3109, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 0.0002194788273615635, | |
| "loss": 0.3149, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.00021908794788273614, | |
| "loss": 0.3094, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.00021869706840390877, | |
| "loss": 0.2915, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.0002183061889250814, | |
| "loss": 0.3169, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.00021791530944625405, | |
| "loss": 0.3139, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "eval_loss": 0.31933295726776123, | |
| "eval_runtime": 652.3614, | |
| "eval_samples_per_second": 3.066, | |
| "eval_steps_per_second": 0.383, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 0.0002175244299674267, | |
| "loss": 0.3019, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 0.00021713355048859934, | |
| "loss": 0.3184, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 0.000216742671009772, | |
| "loss": 0.3186, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.0002163517915309446, | |
| "loss": 0.3084, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.00021596091205211725, | |
| "loss": 0.3276, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.00021557003257328987, | |
| "loss": 0.3031, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 0.00021517915309446253, | |
| "loss": 0.3164, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.00021478827361563519, | |
| "loss": 0.3093, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.00021439739413680779, | |
| "loss": 0.3146, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 0.00021400651465798044, | |
| "loss": 0.3123, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 0.00021361563517915307, | |
| "loss": 0.3119, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 0.00021322475570032572, | |
| "loss": 0.3115, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.00021283387622149838, | |
| "loss": 0.314, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.00021244299674267098, | |
| "loss": 0.3088, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 0.00021205211726384364, | |
| "loss": 0.3043, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 0.00021166123778501626, | |
| "loss": 0.3146, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 0.00021127035830618892, | |
| "loss": 0.3113, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 0.00021087947882736155, | |
| "loss": 0.302, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 0.00021048859934853418, | |
| "loss": 0.3156, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 0.0002100977198697068, | |
| "loss": 0.3277, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "eval_loss": 0.31793293356895447, | |
| "eval_runtime": 653.5553, | |
| "eval_samples_per_second": 3.06, | |
| "eval_steps_per_second": 0.383, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 0.00020970684039087946, | |
| "loss": 0.3117, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 0.00020931596091205211, | |
| "loss": 0.32, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 0.00020892508143322474, | |
| "loss": 0.3134, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 0.00020853420195439737, | |
| "loss": 0.3093, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 0.00020814332247557, | |
| "loss": 0.3084, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 0.00020775244299674265, | |
| "loss": 0.3065, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 0.0002073615635179153, | |
| "loss": 0.318, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 0.00020697068403908794, | |
| "loss": 0.3212, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.00020657980456026057, | |
| "loss": 0.3069, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 0.0002061889250814332, | |
| "loss": 0.3056, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 0.00020579804560260585, | |
| "loss": 0.3008, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 0.00020540716612377848, | |
| "loss": 0.314, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 0.00020501628664495113, | |
| "loss": 0.3054, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 0.00020462540716612373, | |
| "loss": 0.3035, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 0.0002042345276872964, | |
| "loss": 0.3055, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 0.00020384364820846904, | |
| "loss": 0.3062, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 0.00020345276872964167, | |
| "loss": 0.2984, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 0.00020306188925081433, | |
| "loss": 0.2982, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.00020267100977198693, | |
| "loss": 0.3202, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.00020228013029315958, | |
| "loss": 0.3101, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "eval_loss": 0.31705713272094727, | |
| "eval_runtime": 651.8579, | |
| "eval_samples_per_second": 3.068, | |
| "eval_steps_per_second": 0.384, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.00020188925081433224, | |
| "loss": 0.3105, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.00020149837133550487, | |
| "loss": 0.3176, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 0.00020110749185667752, | |
| "loss": 0.3158, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 0.00020071661237785015, | |
| "loss": 0.3117, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 0.00020032573289902278, | |
| "loss": 0.3105, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 0.0001999348534201954, | |
| "loss": 0.3061, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 0.00019954397394136806, | |
| "loss": 0.3147, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 0.00019915309446254072, | |
| "loss": 0.3246, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.00019876221498371335, | |
| "loss": 0.3072, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 0.00019837133550488597, | |
| "loss": 0.3283, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 0.0001979804560260586, | |
| "loss": 0.332, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 0.00019758957654723126, | |
| "loss": 0.3208, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.0001971986970684039, | |
| "loss": 0.3027, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.00019680781758957654, | |
| "loss": 0.3205, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.00019641693811074917, | |
| "loss": 0.3075, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.0001960260586319218, | |
| "loss": 0.3089, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 0.00019563517915309445, | |
| "loss": 0.3232, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 0.00019524429967426708, | |
| "loss": 0.3119, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 0.00019485342019543974, | |
| "loss": 0.3287, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 0.00019446254071661234, | |
| "loss": 0.3166, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "eval_loss": 0.31592896580696106, | |
| "eval_runtime": 651.8958, | |
| "eval_samples_per_second": 3.068, | |
| "eval_steps_per_second": 0.383, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 0.000194071661237785, | |
| "loss": 0.3084, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 0.00019368078175895765, | |
| "loss": 0.3067, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.00019328990228013028, | |
| "loss": 0.3161, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 0.00019289902280130293, | |
| "loss": 0.3177, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 0.00019250814332247553, | |
| "loss": 0.3122, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 0.0001921172638436482, | |
| "loss": 0.3066, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 0.00019172638436482084, | |
| "loss": 0.3113, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 0.00019133550488599347, | |
| "loss": 0.3102, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.00019094462540716613, | |
| "loss": 0.3142, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.00019055374592833873, | |
| "loss": 0.3135, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.00019016286644951138, | |
| "loss": 0.3067, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.000189771986970684, | |
| "loss": 0.3164, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.00018938110749185666, | |
| "loss": 0.3105, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 0.00018899022801302932, | |
| "loss": 0.3213, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 0.00018859934853420192, | |
| "loss": 0.3078, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 0.00018820846905537458, | |
| "loss": 0.3189, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 0.0001878175895765472, | |
| "loss": 0.3038, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.00018742671009771986, | |
| "loss": 0.2951, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.00018703583061889252, | |
| "loss": 0.3066, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 0.00018664495114006514, | |
| "loss": 0.3125, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "eval_loss": 0.315193235874176, | |
| "eval_runtime": 651.5893, | |
| "eval_samples_per_second": 3.069, | |
| "eval_steps_per_second": 0.384, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 0.00018625407166123777, | |
| "loss": 0.3046, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 0.0001858631921824104, | |
| "loss": 0.3014, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.00018547231270358305, | |
| "loss": 0.3165, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.00018508143322475568, | |
| "loss": 0.3204, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 0.00018469055374592834, | |
| "loss": 0.3055, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 0.00018429967426710094, | |
| "loss": 0.3129, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 0.0001839087947882736, | |
| "loss": 0.3113, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.00018351791530944625, | |
| "loss": 0.3122, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 0.00018312703583061888, | |
| "loss": 0.3196, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 0.00018273615635179153, | |
| "loss": 0.2973, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.00018234527687296413, | |
| "loss": 0.3144, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 0.0001819543973941368, | |
| "loss": 0.2944, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 0.00018156351791530944, | |
| "loss": 0.3017, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 0.00018117263843648207, | |
| "loss": 0.2892, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 0.00018078175895765473, | |
| "loss": 0.2859, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 0.00018039087947882733, | |
| "loss": 0.2959, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 0.2902, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 0.0001796091205211726, | |
| "loss": 0.2874, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 0.00017921824104234527, | |
| "loss": 0.2983, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 0.00017882736156351792, | |
| "loss": 0.302, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "eval_loss": 0.31586387753486633, | |
| "eval_runtime": 650.8775, | |
| "eval_samples_per_second": 3.073, | |
| "eval_steps_per_second": 0.384, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 0.00017843648208469052, | |
| "loss": 0.2919, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 0.00017804560260586318, | |
| "loss": 0.2999, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 0.0001776547231270358, | |
| "loss": 0.2885, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 0.00017726384364820846, | |
| "loss": 0.2895, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 0.0001768729641693811, | |
| "loss": 0.283, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 0.00017648208469055372, | |
| "loss": 0.3017, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 0.00017609120521172637, | |
| "loss": 0.2906, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 0.000175700325732899, | |
| "loss": 0.2973, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 0.00017530944625407166, | |
| "loss": 0.2994, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 0.00017491856677524429, | |
| "loss": 0.2873, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 0.00017452768729641691, | |
| "loss": 0.2929, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 0.00017413680781758954, | |
| "loss": 0.2901, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 0.0001737459283387622, | |
| "loss": 0.298, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 0.00017335504885993485, | |
| "loss": 0.292, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 0.00017296416938110748, | |
| "loss": 0.2983, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 0.0001725732899022801, | |
| "loss": 0.2945, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 0.00017218241042345274, | |
| "loss": 0.3045, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 0.0001717915309446254, | |
| "loss": 0.2923, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 0.00017140065146579802, | |
| "loss": 0.3095, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 0.00017100977198697068, | |
| "loss": 0.3024, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "eval_loss": 0.3156301975250244, | |
| "eval_runtime": 650.8764, | |
| "eval_samples_per_second": 3.073, | |
| "eval_steps_per_second": 0.384, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 0.00017061889250814333, | |
| "loss": 0.3029, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 0.00017022801302931593, | |
| "loss": 0.3011, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 0.0001698371335504886, | |
| "loss": 0.3066, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 0.00016944625407166122, | |
| "loss": 0.3086, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 0.00016905537459283387, | |
| "loss": 0.3017, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 0.00016866449511400653, | |
| "loss": 0.3006, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 0.00016827361563517913, | |
| "loss": 0.2922, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 0.00016788273615635178, | |
| "loss": 0.2886, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 0.0001674918566775244, | |
| "loss": 0.3047, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 0.00016710097719869707, | |
| "loss": 0.3112, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 0.0001667100977198697, | |
| "loss": 0.2864, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 0.00016631921824104232, | |
| "loss": 0.2884, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 0.00016592833876221495, | |
| "loss": 0.3027, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 0.0001655374592833876, | |
| "loss": 0.2962, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 0.00016514657980456026, | |
| "loss": 0.2983, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 0.0001647557003257329, | |
| "loss": 0.2948, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 0.00016436482084690552, | |
| "loss": 0.2862, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 0.00016397394136807814, | |
| "loss": 0.3039, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 0.0001635830618892508, | |
| "loss": 0.2884, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 0.00016319218241042346, | |
| "loss": 0.2947, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "eval_loss": 0.3153843879699707, | |
| "eval_runtime": 654.4326, | |
| "eval_samples_per_second": 3.056, | |
| "eval_steps_per_second": 0.382, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 0.00016280130293159608, | |
| "loss": 0.3057, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 0.0001624104234527687, | |
| "loss": 0.2993, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 0.00016201954397394134, | |
| "loss": 0.2936, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 0.000161628664495114, | |
| "loss": 0.2928, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 0.00016123778501628662, | |
| "loss": 0.2922, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 0.00016084690553745928, | |
| "loss": 0.2932, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 0.00016045602605863188, | |
| "loss": 0.2914, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 0.00016006514657980453, | |
| "loss": 0.3014, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 0.0001596742671009772, | |
| "loss": 0.2916, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 0.00015928338762214982, | |
| "loss": 0.2882, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 0.00015889250814332247, | |
| "loss": 0.2803, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 0.00015850162866449507, | |
| "loss": 0.2995, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 0.00015811074918566773, | |
| "loss": 0.2914, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 0.00015771986970684038, | |
| "loss": 0.2923, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 0.000157328990228013, | |
| "loss": 0.3085, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 0.00015693811074918567, | |
| "loss": 0.2913, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 0.0001565472312703583, | |
| "loss": 0.3032, | |
| "step": 3770 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 0.00015615635179153092, | |
| "loss": 0.2977, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 0.00015576547231270355, | |
| "loss": 0.302, | |
| "step": 3790 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 0.0001553745928338762, | |
| "loss": 0.2906, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "eval_loss": 0.3143232762813568, | |
| "eval_runtime": 659.1405, | |
| "eval_samples_per_second": 3.034, | |
| "eval_steps_per_second": 0.379, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 0.00015498371335504886, | |
| "loss": 0.2976, | |
| "step": 3810 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 0.0001545928338762215, | |
| "loss": 0.2907, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 0.00015420195439739412, | |
| "loss": 0.293, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 0.00015381107491856675, | |
| "loss": 0.3042, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 0.0001534201954397394, | |
| "loss": 0.3012, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 0.00015302931596091206, | |
| "loss": 0.2781, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 0.00015263843648208469, | |
| "loss": 0.277, | |
| "step": 3870 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 0.00015224755700325731, | |
| "loss": 0.288, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 0.00015185667752442994, | |
| "loss": 0.283, | |
| "step": 3890 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 0.0001514657980456026, | |
| "loss": 0.3001, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 0.00015107491856677523, | |
| "loss": 0.2873, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 0.00015068403908794788, | |
| "loss": 0.2955, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 0.00015029315960912048, | |
| "loss": 0.299, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 0.00014990228013029314, | |
| "loss": 0.2902, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 0.0001495114006514658, | |
| "loss": 0.2974, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 0.00014912052117263842, | |
| "loss": 0.2927, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 0.00014872964169381105, | |
| "loss": 0.301, | |
| "step": 3970 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 0.0001483387622149837, | |
| "loss": 0.2916, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 0.00014794788273615633, | |
| "loss": 0.2829, | |
| "step": 3990 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 0.000147557003257329, | |
| "loss": 0.2973, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "eval_loss": 0.3140289783477783, | |
| "eval_runtime": 651.5672, | |
| "eval_samples_per_second": 3.07, | |
| "eval_steps_per_second": 0.384, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 0.00014716612377850162, | |
| "loss": 0.3171, | |
| "step": 4010 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 0.00014677524429967424, | |
| "loss": 0.2929, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 0.0001463843648208469, | |
| "loss": 0.2937, | |
| "step": 4030 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 0.00014599348534201953, | |
| "loss": 0.2864, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 0.00014560260586319216, | |
| "loss": 0.2974, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 0.0001452117263843648, | |
| "loss": 0.2953, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 0.00014482084690553744, | |
| "loss": 0.2963, | |
| "step": 4070 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 0.0001444299674267101, | |
| "loss": 0.299, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 0.00014403908794788272, | |
| "loss": 0.2827, | |
| "step": 4090 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 0.00014364820846905535, | |
| "loss": 0.3003, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 0.000143257328990228, | |
| "loss": 0.296, | |
| "step": 4110 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 0.00014286644951140063, | |
| "loss": 0.2932, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 0.0001424755700325733, | |
| "loss": 0.299, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 0.00014208469055374592, | |
| "loss": 0.2869, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 0.00014169381107491854, | |
| "loss": 0.2856, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 0.0001413029315960912, | |
| "loss": 0.2992, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 0.00014091205211726383, | |
| "loss": 0.2931, | |
| "step": 4170 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 0.00014052117263843646, | |
| "loss": 0.2952, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 0.0001401302931596091, | |
| "loss": 0.2889, | |
| "step": 4190 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 0.00013973941368078174, | |
| "loss": 0.2926, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "eval_loss": 0.3132728040218353, | |
| "eval_runtime": 651.4109, | |
| "eval_samples_per_second": 3.07, | |
| "eval_steps_per_second": 0.384, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 0.0001393485342019544, | |
| "loss": 0.2863, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 0.00013895765472312702, | |
| "loss": 0.2988, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 0.00013856677524429965, | |
| "loss": 0.2905, | |
| "step": 4230 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 0.0001381758957654723, | |
| "loss": 0.2855, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 0.00013778501628664493, | |
| "loss": 0.2884, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 0.0001373941368078176, | |
| "loss": 0.2906, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 0.00013700325732899022, | |
| "loss": 0.2911, | |
| "step": 4270 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 0.00013661237785016285, | |
| "loss": 0.3035, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 0.0001362214983713355, | |
| "loss": 0.3051, | |
| "step": 4290 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 0.00013583061889250813, | |
| "loss": 0.29, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 0.00013543973941368076, | |
| "loss": 0.2901, | |
| "step": 4310 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 0.0001350488599348534, | |
| "loss": 0.2997, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 0.00013465798045602604, | |
| "loss": 0.3043, | |
| "step": 4330 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 0.0001342671009771987, | |
| "loss": 0.304, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 0.00013387622149837132, | |
| "loss": 0.2936, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 0.00013348534201954395, | |
| "loss": 0.3078, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 0.0001330944625407166, | |
| "loss": 0.2952, | |
| "step": 4370 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 0.00013270358306188924, | |
| "loss": 0.2868, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 0.0001323127035830619, | |
| "loss": 0.2907, | |
| "step": 4390 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 0.00013192182410423452, | |
| "loss": 0.2931, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "eval_loss": 0.3124812841415405, | |
| "eval_runtime": 652.2686, | |
| "eval_samples_per_second": 3.066, | |
| "eval_steps_per_second": 0.383, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 0.00013153094462540715, | |
| "loss": 0.305, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 0.0001311400651465798, | |
| "loss": 0.2879, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 0.00013074918566775243, | |
| "loss": 0.2961, | |
| "step": 4430 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 0.00013035830618892506, | |
| "loss": 0.2977, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 0.00012996742671009771, | |
| "loss": 0.2981, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 0.00012957654723127034, | |
| "loss": 0.3004, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 0.000129185667752443, | |
| "loss": 0.2964, | |
| "step": 4470 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 0.00012879478827361563, | |
| "loss": 0.2919, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 0.00012840390879478825, | |
| "loss": 0.2889, | |
| "step": 4490 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 0.0001280130293159609, | |
| "loss": 0.2964, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 0.00012762214983713354, | |
| "loss": 0.2795, | |
| "step": 4510 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 0.0001272312703583062, | |
| "loss": 0.3012, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 0.00012684039087947882, | |
| "loss": 0.2946, | |
| "step": 4530 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 0.00012644951140065145, | |
| "loss": 0.2794, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 0.0001260586319218241, | |
| "loss": 0.2906, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 0.00012566775244299673, | |
| "loss": 0.2937, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 0.00012527687296416936, | |
| "loss": 0.2939, | |
| "step": 4570 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 0.000124885993485342, | |
| "loss": 0.3047, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 0.00012449511400651464, | |
| "loss": 0.2902, | |
| "step": 4590 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 0.0001241042345276873, | |
| "loss": 0.296, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "eval_loss": 0.3120864927768707, | |
| "eval_runtime": 652.0947, | |
| "eval_samples_per_second": 3.067, | |
| "eval_steps_per_second": 0.383, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 0.00012371335504885993, | |
| "loss": 0.3052, | |
| "step": 4610 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 0.00012332247557003256, | |
| "loss": 0.2934, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 0.0001229315960912052, | |
| "loss": 0.3002, | |
| "step": 4630 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 0.00012254071661237784, | |
| "loss": 0.2924, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 0.0001221498371335505, | |
| "loss": 0.2779, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.00012175895765472311, | |
| "loss": 0.302, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.00012136807817589575, | |
| "loss": 0.2842, | |
| "step": 4670 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 0.0001209771986970684, | |
| "loss": 0.2739, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 0.00012058631921824103, | |
| "loss": 0.2799, | |
| "step": 4690 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 0.00012019543973941368, | |
| "loss": 0.286, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 0.0001198045602605863, | |
| "loss": 0.27, | |
| "step": 4710 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 0.00011941368078175895, | |
| "loss": 0.2797, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 0.00011902280130293159, | |
| "loss": 0.2792, | |
| "step": 4730 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 0.00011863192182410422, | |
| "loss": 0.2786, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 0.00011824104234527687, | |
| "loss": 0.2786, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 0.0001178501628664495, | |
| "loss": 0.2866, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 0.00011745928338762214, | |
| "loss": 0.291, | |
| "step": 4770 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 0.00011706840390879478, | |
| "loss": 0.2659, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 0.00011667752442996741, | |
| "loss": 0.2802, | |
| "step": 4790 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 0.00011628664495114005, | |
| "loss": 0.2882, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "eval_loss": 0.3151525557041168, | |
| "eval_runtime": 650.6435, | |
| "eval_samples_per_second": 3.074, | |
| "eval_steps_per_second": 0.384, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 0.00011589576547231271, | |
| "loss": 0.2688, | |
| "step": 4810 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 0.00011550488599348534, | |
| "loss": 0.2808, | |
| "step": 4820 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 0.00011511400651465798, | |
| "loss": 0.2718, | |
| "step": 4830 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 0.0001147231270358306, | |
| "loss": 0.2782, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 0.00011433224755700325, | |
| "loss": 0.2716, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 0.00011394136807817589, | |
| "loss": 0.2731, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 0.00011355048859934852, | |
| "loss": 0.2881, | |
| "step": 4870 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 0.00011315960912052117, | |
| "loss": 0.2846, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 0.0001127687296416938, | |
| "loss": 0.2708, | |
| "step": 4890 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 0.00011237785016286644, | |
| "loss": 0.2746, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 0.00011198697068403908, | |
| "loss": 0.273, | |
| "step": 4910 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 0.00011159609120521171, | |
| "loss": 0.2754, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 0.00011120521172638435, | |
| "loss": 0.2791, | |
| "step": 4930 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 0.00011081433224755698, | |
| "loss": 0.2728, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 0.00011042345276872964, | |
| "loss": 0.2864, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 0.00011003257328990228, | |
| "loss": 0.2805, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 0.0001096416938110749, | |
| "loss": 0.2835, | |
| "step": 4970 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 0.00010925081433224755, | |
| "loss": 0.2844, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 0.00010885993485342018, | |
| "loss": 0.2726, | |
| "step": 4990 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 0.00010846905537459282, | |
| "loss": 0.2858, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "eval_loss": 0.3143126964569092, | |
| "eval_runtime": 650.8625, | |
| "eval_samples_per_second": 3.073, | |
| "eval_steps_per_second": 0.384, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 0.00010807817589576547, | |
| "loss": 0.2662, | |
| "step": 5010 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 0.0001076872964169381, | |
| "loss": 0.281, | |
| "step": 5020 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 0.00010729641693811074, | |
| "loss": 0.2712, | |
| "step": 5030 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 0.00010690553745928338, | |
| "loss": 0.2806, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 0.00010651465798045601, | |
| "loss": 0.2968, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 0.00010612377850162865, | |
| "loss": 0.2761, | |
| "step": 5060 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 0.00010573289902280128, | |
| "loss": 0.2784, | |
| "step": 5070 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 0.00010534201954397394, | |
| "loss": 0.273, | |
| "step": 5080 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 0.00010495114006514658, | |
| "loss": 0.2808, | |
| "step": 5090 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 0.00010456026058631921, | |
| "loss": 0.2814, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 0.00010416938110749185, | |
| "loss": 0.2729, | |
| "step": 5110 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 0.00010377850162866448, | |
| "loss": 0.2764, | |
| "step": 5120 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 0.00010338762214983712, | |
| "loss": 0.279, | |
| "step": 5130 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 0.00010299674267100977, | |
| "loss": 0.2724, | |
| "step": 5140 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 0.0001026058631921824, | |
| "loss": 0.2831, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 0.00010221498371335504, | |
| "loss": 0.2909, | |
| "step": 5160 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 0.00010182410423452767, | |
| "loss": 0.2727, | |
| "step": 5170 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 0.00010143322475570031, | |
| "loss": 0.2961, | |
| "step": 5180 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 0.00010104234527687296, | |
| "loss": 0.274, | |
| "step": 5190 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 0.00010065146579804558, | |
| "loss": 0.2697, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "eval_loss": 0.3147611618041992, | |
| "eval_runtime": 650.9005, | |
| "eval_samples_per_second": 3.073, | |
| "eval_steps_per_second": 0.384, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 0.00010026058631921824, | |
| "loss": 0.2735, | |
| "step": 5210 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 9.986970684039088e-05, | |
| "loss": 0.2771, | |
| "step": 5220 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 9.947882736156351e-05, | |
| "loss": 0.2747, | |
| "step": 5230 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "learning_rate": 9.908794788273615e-05, | |
| "loss": 0.2728, | |
| "step": 5240 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 9.869706840390878e-05, | |
| "loss": 0.2667, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 9.830618892508142e-05, | |
| "loss": 0.2703, | |
| "step": 5260 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 9.791530944625408e-05, | |
| "loss": 0.2766, | |
| "step": 5270 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 9.75244299674267e-05, | |
| "loss": 0.2839, | |
| "step": 5280 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 9.713355048859935e-05, | |
| "loss": 0.2872, | |
| "step": 5290 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 9.674267100977197e-05, | |
| "loss": 0.2775, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 9.635179153094462e-05, | |
| "loss": 0.2778, | |
| "step": 5310 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 9.596091205211726e-05, | |
| "loss": 0.2846, | |
| "step": 5320 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "learning_rate": 9.557003257328989e-05, | |
| "loss": 0.2858, | |
| "step": 5330 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "learning_rate": 9.517915309446254e-05, | |
| "loss": 0.28, | |
| "step": 5340 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 9.478827361563517e-05, | |
| "loss": 0.2843, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 9.439739413680781e-05, | |
| "loss": 0.2798, | |
| "step": 5360 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 9.400651465798045e-05, | |
| "loss": 0.2895, | |
| "step": 5370 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 9.361563517915308e-05, | |
| "loss": 0.2784, | |
| "step": 5380 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 9.322475570032572e-05, | |
| "loss": 0.2871, | |
| "step": 5390 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 9.283387622149838e-05, | |
| "loss": 0.2744, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "eval_loss": 0.31436505913734436, | |
| "eval_runtime": 650.8376, | |
| "eval_samples_per_second": 3.073, | |
| "eval_steps_per_second": 0.384, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 9.2442996742671e-05, | |
| "loss": 0.2759, | |
| "step": 5410 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 9.205211726384365e-05, | |
| "loss": 0.2825, | |
| "step": 5420 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 9.166123778501628e-05, | |
| "loss": 0.2876, | |
| "step": 5430 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 9.127035830618892e-05, | |
| "loss": 0.2738, | |
| "step": 5440 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 9.087947882736156e-05, | |
| "loss": 0.2945, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 9.048859934853419e-05, | |
| "loss": 0.2869, | |
| "step": 5460 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 9.009771986970684e-05, | |
| "loss": 0.2613, | |
| "step": 5470 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 8.970684039087947e-05, | |
| "loss": 0.2778, | |
| "step": 5480 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 8.931596091205211e-05, | |
| "loss": 0.2793, | |
| "step": 5490 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 8.892508143322475e-05, | |
| "loss": 0.2763, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 8.853420195439738e-05, | |
| "loss": 0.2729, | |
| "step": 5510 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 8.814332247557002e-05, | |
| "loss": 0.285, | |
| "step": 5520 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 8.775244299674265e-05, | |
| "loss": 0.2717, | |
| "step": 5530 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 8.73615635179153e-05, | |
| "loss": 0.2876, | |
| "step": 5540 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 8.697068403908795e-05, | |
| "loss": 0.2798, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 8.657980456026058e-05, | |
| "loss": 0.2691, | |
| "step": 5560 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 8.618892508143322e-05, | |
| "loss": 0.2839, | |
| "step": 5570 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "learning_rate": 8.579804560260586e-05, | |
| "loss": 0.2817, | |
| "step": 5580 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "learning_rate": 8.540716612377849e-05, | |
| "loss": 0.2667, | |
| "step": 5590 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 8.501628664495114e-05, | |
| "loss": 0.2831, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "eval_loss": 0.31451472640037537, | |
| "eval_runtime": 650.7694, | |
| "eval_samples_per_second": 3.073, | |
| "eval_steps_per_second": 0.384, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 8.462540716612377e-05, | |
| "loss": 0.271, | |
| "step": 5610 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 8.423452768729641e-05, | |
| "loss": 0.2848, | |
| "step": 5620 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "learning_rate": 8.384364820846905e-05, | |
| "loss": 0.2933, | |
| "step": 5630 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 8.345276872964168e-05, | |
| "loss": 0.2787, | |
| "step": 5640 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 8.306188925081432e-05, | |
| "loss": 0.2858, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 8.267100977198695e-05, | |
| "loss": 0.2788, | |
| "step": 5660 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "learning_rate": 8.228013029315961e-05, | |
| "loss": 0.2837, | |
| "step": 5670 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "learning_rate": 8.188925081433225e-05, | |
| "loss": 0.2857, | |
| "step": 5680 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 8.149837133550488e-05, | |
| "loss": 0.2735, | |
| "step": 5690 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 8.110749185667752e-05, | |
| "loss": 0.2802, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 8.071661237785015e-05, | |
| "loss": 0.2894, | |
| "step": 5710 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 8.032573289902279e-05, | |
| "loss": 0.2749, | |
| "step": 5720 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 7.993485342019544e-05, | |
| "loss": 0.2792, | |
| "step": 5730 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 7.954397394136807e-05, | |
| "loss": 0.2795, | |
| "step": 5740 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 7.915309446254071e-05, | |
| "loss": 0.2741, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 7.876221498371334e-05, | |
| "loss": 0.2701, | |
| "step": 5760 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "learning_rate": 7.837133550488598e-05, | |
| "loss": 0.2712, | |
| "step": 5770 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 7.798045602605863e-05, | |
| "loss": 0.2851, | |
| "step": 5780 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 7.758957654723125e-05, | |
| "loss": 0.2773, | |
| "step": 5790 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 7.719869706840391e-05, | |
| "loss": 0.2725, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "eval_loss": 0.3135795295238495, | |
| "eval_runtime": 650.7409, | |
| "eval_samples_per_second": 3.073, | |
| "eval_steps_per_second": 0.384, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 7.680781758957655e-05, | |
| "loss": 0.2811, | |
| "step": 5810 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 7.641693811074918e-05, | |
| "loss": 0.2765, | |
| "step": 5820 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 7.602605863192182e-05, | |
| "loss": 0.2809, | |
| "step": 5830 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 7.563517915309445e-05, | |
| "loss": 0.2799, | |
| "step": 5840 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 7.524429967426709e-05, | |
| "loss": 0.2869, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 7.485342019543973e-05, | |
| "loss": 0.2848, | |
| "step": 5860 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 7.446254071661237e-05, | |
| "loss": 0.2832, | |
| "step": 5870 | |
| }, | |
| { | |
| "epoch": 3.78, | |
| "learning_rate": 7.407166123778502e-05, | |
| "loss": 0.2781, | |
| "step": 5880 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 7.368078175895764e-05, | |
| "loss": 0.279, | |
| "step": 5890 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 7.328990228013029e-05, | |
| "loss": 0.2705, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 7.289902280130293e-05, | |
| "loss": 0.2792, | |
| "step": 5910 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 7.250814332247557e-05, | |
| "loss": 0.2781, | |
| "step": 5920 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 7.211726384364821e-05, | |
| "loss": 0.2724, | |
| "step": 5930 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 7.172638436482084e-05, | |
| "loss": 0.2701, | |
| "step": 5940 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 7.133550488599348e-05, | |
| "loss": 0.289, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 7.094462540716611e-05, | |
| "loss": 0.2785, | |
| "step": 5960 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 7.055374592833876e-05, | |
| "loss": 0.2748, | |
| "step": 5970 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 7.016286644951139e-05, | |
| "loss": 0.2811, | |
| "step": 5980 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 6.977198697068403e-05, | |
| "loss": 0.2868, | |
| "step": 5990 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "learning_rate": 6.938110749185668e-05, | |
| "loss": 0.2891, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "eval_loss": 0.31298649311065674, | |
| "eval_runtime": 650.7161, | |
| "eval_samples_per_second": 3.074, | |
| "eval_steps_per_second": 0.384, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "learning_rate": 6.899022801302932e-05, | |
| "loss": 0.269, | |
| "step": 6010 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 6.859934853420195e-05, | |
| "loss": 0.2818, | |
| "step": 6020 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 6.820846905537459e-05, | |
| "loss": 0.2866, | |
| "step": 6030 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 6.781758957654723e-05, | |
| "loss": 0.2701, | |
| "step": 6040 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "learning_rate": 6.742671009771986e-05, | |
| "loss": 0.2839, | |
| "step": 6050 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "learning_rate": 6.703583061889251e-05, | |
| "loss": 0.282, | |
| "step": 6060 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "learning_rate": 6.664495114006514e-05, | |
| "loss": 0.2749, | |
| "step": 6070 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 6.625407166123778e-05, | |
| "loss": 0.276, | |
| "step": 6080 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 6.586319218241041e-05, | |
| "loss": 0.2758, | |
| "step": 6090 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 6.547231270358307e-05, | |
| "loss": 0.2786, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 6.50814332247557e-05, | |
| "loss": 0.2735, | |
| "step": 6110 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 6.469055374592834e-05, | |
| "loss": 0.2747, | |
| "step": 6120 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 6.429967426710098e-05, | |
| "loss": 0.2891, | |
| "step": 6130 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "learning_rate": 6.39087947882736e-05, | |
| "loss": 0.2734, | |
| "step": 6140 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "learning_rate": 6.351791530944625e-05, | |
| "loss": 0.278, | |
| "step": 6150 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 6.312703583061889e-05, | |
| "loss": 0.2843, | |
| "step": 6160 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "learning_rate": 6.273615635179153e-05, | |
| "loss": 0.2916, | |
| "step": 6170 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "learning_rate": 6.234527687296416e-05, | |
| "loss": 0.2876, | |
| "step": 6180 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 6.19543973941368e-05, | |
| "loss": 0.28, | |
| "step": 6190 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 6.156351791530944e-05, | |
| "loss": 0.2815, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "eval_loss": 0.3130280673503876, | |
| "eval_runtime": 650.8269, | |
| "eval_samples_per_second": 3.073, | |
| "eval_steps_per_second": 0.384, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 6.117263843648208e-05, | |
| "loss": 0.2905, | |
| "step": 6210 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 6.078175895765472e-05, | |
| "loss": 0.2777, | |
| "step": 6220 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 6.039087947882735e-05, | |
| "loss": 0.2629, | |
| "step": 6230 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 0.279, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 5.9609120521172636e-05, | |
| "loss": 0.2829, | |
| "step": 6250 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 5.921824104234527e-05, | |
| "loss": 0.2599, | |
| "step": 6260 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 5.8827361563517906e-05, | |
| "loss": 0.2649, | |
| "step": 6270 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 5.843648208469055e-05, | |
| "loss": 0.2785, | |
| "step": 6280 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 5.804560260586319e-05, | |
| "loss": 0.2698, | |
| "step": 6290 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 5.7654723127035825e-05, | |
| "loss": 0.2692, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 5.726384364820846e-05, | |
| "loss": 0.2627, | |
| "step": 6310 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 5.68729641693811e-05, | |
| "loss": 0.2518, | |
| "step": 6320 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 5.648208469055374e-05, | |
| "loss": 0.2743, | |
| "step": 6330 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 5.609120521172638e-05, | |
| "loss": 0.2716, | |
| "step": 6340 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 5.570032573289902e-05, | |
| "loss": 0.2626, | |
| "step": 6350 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 5.5309446254071654e-05, | |
| "loss": 0.2736, | |
| "step": 6360 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 5.491856677524429e-05, | |
| "loss": 0.2742, | |
| "step": 6370 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 5.452768729641694e-05, | |
| "loss": 0.2717, | |
| "step": 6380 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 5.413680781758957e-05, | |
| "loss": 0.2667, | |
| "step": 6390 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 5.374592833876221e-05, | |
| "loss": 0.27, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "eval_loss": 0.31636786460876465, | |
| "eval_runtime": 650.805, | |
| "eval_samples_per_second": 3.073, | |
| "eval_steps_per_second": 0.384, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 5.335504885993484e-05, | |
| "loss": 0.2632, | |
| "step": 6410 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "learning_rate": 5.296416938110749e-05, | |
| "loss": 0.2701, | |
| "step": 6420 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 5.2573289902280126e-05, | |
| "loss": 0.2697, | |
| "step": 6430 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 5.218241042345276e-05, | |
| "loss": 0.2627, | |
| "step": 6440 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 5.17915309446254e-05, | |
| "loss": 0.2684, | |
| "step": 6450 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 5.140065146579804e-05, | |
| "loss": 0.2643, | |
| "step": 6460 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 5.100977198697068e-05, | |
| "loss": 0.2706, | |
| "step": 6470 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 5.061889250814332e-05, | |
| "loss": 0.2507, | |
| "step": 6480 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 5.0228013029315956e-05, | |
| "loss": 0.2767, | |
| "step": 6490 | |
| }, | |
| { | |
| "epoch": 4.18, | |
| "learning_rate": 4.983713355048859e-05, | |
| "loss": 0.2698, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 4.944625407166124e-05, | |
| "loss": 0.2647, | |
| "step": 6510 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 4.9055374592833874e-05, | |
| "loss": 0.2589, | |
| "step": 6520 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 4.866449511400651e-05, | |
| "loss": 0.2731, | |
| "step": 6530 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 4.8273615635179144e-05, | |
| "loss": 0.2752, | |
| "step": 6540 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 4.7882736156351786e-05, | |
| "loss": 0.2785, | |
| "step": 6550 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 4.749185667752443e-05, | |
| "loss": 0.2671, | |
| "step": 6560 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "learning_rate": 4.710097719869706e-05, | |
| "loss": 0.2682, | |
| "step": 6570 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "learning_rate": 4.6710097719869704e-05, | |
| "loss": 0.2757, | |
| "step": 6580 | |
| }, | |
| { | |
| "epoch": 4.24, | |
| "learning_rate": 4.631921824104234e-05, | |
| "loss": 0.2663, | |
| "step": 6590 | |
| }, | |
| { | |
| "epoch": 4.24, | |
| "learning_rate": 4.592833876221498e-05, | |
| "loss": 0.2655, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 4.24, | |
| "eval_loss": 0.31645169854164124, | |
| "eval_runtime": 651.1939, | |
| "eval_samples_per_second": 3.071, | |
| "eval_steps_per_second": 0.384, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 4.553745928338762e-05, | |
| "loss": 0.262, | |
| "step": 6610 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 4.514657980456026e-05, | |
| "loss": 0.2548, | |
| "step": 6620 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 4.475570032573289e-05, | |
| "loss": 0.2684, | |
| "step": 6630 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "learning_rate": 4.436482084690553e-05, | |
| "loss": 0.2574, | |
| "step": 6640 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "learning_rate": 4.3973941368078175e-05, | |
| "loss": 0.2595, | |
| "step": 6650 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "learning_rate": 4.358306188925081e-05, | |
| "loss": 0.2728, | |
| "step": 6660 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 4.3192182410423445e-05, | |
| "loss": 0.2632, | |
| "step": 6670 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 4.280130293159609e-05, | |
| "loss": 0.2608, | |
| "step": 6680 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 4.241042345276873e-05, | |
| "loss": 0.2641, | |
| "step": 6690 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "learning_rate": 4.2019543973941364e-05, | |
| "loss": 0.2695, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "learning_rate": 4.1628664495114005e-05, | |
| "loss": 0.2788, | |
| "step": 6710 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "learning_rate": 4.123778501628664e-05, | |
| "loss": 0.2559, | |
| "step": 6720 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 4.0846905537459275e-05, | |
| "loss": 0.2681, | |
| "step": 6730 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 4.0456026058631924e-05, | |
| "loss": 0.2729, | |
| "step": 6740 | |
| }, | |
| { | |
| "epoch": 4.34, | |
| "learning_rate": 4.006514657980456e-05, | |
| "loss": 0.2784, | |
| "step": 6750 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 3.9674267100977193e-05, | |
| "loss": 0.2739, | |
| "step": 6760 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 3.928338762214983e-05, | |
| "loss": 0.264, | |
| "step": 6770 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "learning_rate": 3.889250814332248e-05, | |
| "loss": 0.2508, | |
| "step": 6780 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "learning_rate": 3.850162866449511e-05, | |
| "loss": 0.2621, | |
| "step": 6790 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "learning_rate": 3.8110749185667747e-05, | |
| "loss": 0.2751, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "eval_loss": 0.3162127435207367, | |
| "eval_runtime": 650.6413, | |
| "eval_samples_per_second": 3.074, | |
| "eval_steps_per_second": 0.384, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 3.771986970684039e-05, | |
| "loss": 0.2742, | |
| "step": 6810 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "learning_rate": 3.732899022801303e-05, | |
| "loss": 0.2709, | |
| "step": 6820 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "learning_rate": 3.6938110749185665e-05, | |
| "loss": 0.2682, | |
| "step": 6830 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 3.6547231270358307e-05, | |
| "loss": 0.2604, | |
| "step": 6840 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 3.615635179153094e-05, | |
| "loss": 0.2708, | |
| "step": 6850 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 3.576547231270358e-05, | |
| "loss": 0.2693, | |
| "step": 6860 | |
| }, | |
| { | |
| "epoch": 4.42, | |
| "learning_rate": 3.537459283387622e-05, | |
| "loss": 0.2678, | |
| "step": 6870 | |
| }, | |
| { | |
| "epoch": 4.42, | |
| "learning_rate": 3.498371335504885e-05, | |
| "loss": 0.2602, | |
| "step": 6880 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "learning_rate": 3.4592833876221495e-05, | |
| "loss": 0.2688, | |
| "step": 6890 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 3.420195439739413e-05, | |
| "loss": 0.2577, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 3.381107491856677e-05, | |
| "loss": 0.268, | |
| "step": 6910 | |
| }, | |
| { | |
| "epoch": 4.45, | |
| "learning_rate": 3.342019543973941e-05, | |
| "loss": 0.2709, | |
| "step": 6920 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "learning_rate": 3.302931596091205e-05, | |
| "loss": 0.2582, | |
| "step": 6930 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "learning_rate": 3.263843648208469e-05, | |
| "loss": 0.2477, | |
| "step": 6940 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "learning_rate": 3.224755700325733e-05, | |
| "loss": 0.2649, | |
| "step": 6950 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 3.1856677524429966e-05, | |
| "loss": 0.2755, | |
| "step": 6960 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 3.14657980456026e-05, | |
| "loss": 0.2703, | |
| "step": 6970 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "learning_rate": 3.107491856677524e-05, | |
| "loss": 0.2676, | |
| "step": 6980 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 3.068403908794788e-05, | |
| "loss": 0.2631, | |
| "step": 6990 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 3.029315960912052e-05, | |
| "loss": 0.2572, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "eval_loss": 0.31602758169174194, | |
| "eval_runtime": 650.7389, | |
| "eval_samples_per_second": 3.073, | |
| "eval_steps_per_second": 0.384, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "learning_rate": 2.9902280130293158e-05, | |
| "loss": 0.2584, | |
| "step": 7010 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "learning_rate": 2.9511400651465796e-05, | |
| "loss": 0.2611, | |
| "step": 7020 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "learning_rate": 2.9120521172638434e-05, | |
| "loss": 0.2595, | |
| "step": 7030 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "learning_rate": 2.8729641693811073e-05, | |
| "loss": 0.2629, | |
| "step": 7040 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "learning_rate": 2.833876221498371e-05, | |
| "loss": 0.2787, | |
| "step": 7050 | |
| }, | |
| { | |
| "epoch": 4.54, | |
| "learning_rate": 2.7947882736156346e-05, | |
| "loss": 0.2618, | |
| "step": 7060 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 2.7557003257328988e-05, | |
| "loss": 0.2624, | |
| "step": 7070 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 2.7166123778501626e-05, | |
| "loss": 0.2615, | |
| "step": 7080 | |
| }, | |
| { | |
| "epoch": 4.56, | |
| "learning_rate": 2.6775244299674264e-05, | |
| "loss": 0.281, | |
| "step": 7090 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 2.6384364820846903e-05, | |
| "loss": 0.2685, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 2.5993485342019544e-05, | |
| "loss": 0.2649, | |
| "step": 7110 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 2.560260586319218e-05, | |
| "loss": 0.2772, | |
| "step": 7120 | |
| }, | |
| { | |
| "epoch": 4.59, | |
| "learning_rate": 2.521172638436482e-05, | |
| "loss": 0.2618, | |
| "step": 7130 | |
| }, | |
| { | |
| "epoch": 4.59, | |
| "learning_rate": 2.4820846905537456e-05, | |
| "loss": 0.2764, | |
| "step": 7140 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 2.4429967426710094e-05, | |
| "loss": 0.2617, | |
| "step": 7150 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 2.4039087947882736e-05, | |
| "loss": 0.272, | |
| "step": 7160 | |
| }, | |
| { | |
| "epoch": 4.61, | |
| "learning_rate": 2.364820846905537e-05, | |
| "loss": 0.2604, | |
| "step": 7170 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 2.3257328990228012e-05, | |
| "loss": 0.2619, | |
| "step": 7180 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 2.2866449511400647e-05, | |
| "loss": 0.2669, | |
| "step": 7190 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "learning_rate": 2.247557003257329e-05, | |
| "loss": 0.2724, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "eval_loss": 0.31608501076698303, | |
| "eval_runtime": 650.6688, | |
| "eval_samples_per_second": 3.074, | |
| "eval_steps_per_second": 0.384, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "learning_rate": 2.2084690553745927e-05, | |
| "loss": 0.2649, | |
| "step": 7210 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "learning_rate": 2.1693811074918562e-05, | |
| "loss": 0.2697, | |
| "step": 7220 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "learning_rate": 2.1302931596091204e-05, | |
| "loss": 0.2569, | |
| "step": 7230 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "learning_rate": 2.091205211726384e-05, | |
| "loss": 0.2691, | |
| "step": 7240 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "learning_rate": 2.052117263843648e-05, | |
| "loss": 0.2707, | |
| "step": 7250 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "learning_rate": 2.013029315960912e-05, | |
| "loss": 0.2634, | |
| "step": 7260 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 1.9739413680781757e-05, | |
| "loss": 0.2703, | |
| "step": 7270 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 1.9348534201954395e-05, | |
| "loss": 0.2706, | |
| "step": 7280 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "learning_rate": 1.8957654723127037e-05, | |
| "loss": 0.2671, | |
| "step": 7290 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "learning_rate": 1.8566775244299672e-05, | |
| "loss": 0.2714, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "learning_rate": 1.817589576547231e-05, | |
| "loss": 0.2773, | |
| "step": 7310 | |
| }, | |
| { | |
| "epoch": 4.71, | |
| "learning_rate": 1.778501628664495e-05, | |
| "loss": 0.2658, | |
| "step": 7320 | |
| }, | |
| { | |
| "epoch": 4.71, | |
| "learning_rate": 1.739413680781759e-05, | |
| "loss": 0.2658, | |
| "step": 7330 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "learning_rate": 1.700325732899023e-05, | |
| "loss": 0.2714, | |
| "step": 7340 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 1.6612377850162864e-05, | |
| "loss": 0.2625, | |
| "step": 7350 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 1.6221498371335502e-05, | |
| "loss": 0.2605, | |
| "step": 7360 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 1.583061889250814e-05, | |
| "loss": 0.2705, | |
| "step": 7370 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "learning_rate": 1.5439739413680782e-05, | |
| "loss": 0.2673, | |
| "step": 7380 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "learning_rate": 1.5048859934853418e-05, | |
| "loss": 0.2611, | |
| "step": 7390 | |
| }, | |
| { | |
| "epoch": 4.76, | |
| "learning_rate": 1.4657980456026057e-05, | |
| "loss": 0.2675, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 4.76, | |
| "eval_loss": 0.3155960738658905, | |
| "eval_runtime": 650.8763, | |
| "eval_samples_per_second": 3.073, | |
| "eval_steps_per_second": 0.384, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 4.77, | |
| "learning_rate": 1.4267100977198697e-05, | |
| "loss": 0.2604, | |
| "step": 7410 | |
| }, | |
| { | |
| "epoch": 4.77, | |
| "learning_rate": 1.3876221498371335e-05, | |
| "loss": 0.2565, | |
| "step": 7420 | |
| }, | |
| { | |
| "epoch": 4.78, | |
| "learning_rate": 1.3485342019543973e-05, | |
| "loss": 0.2707, | |
| "step": 7430 | |
| }, | |
| { | |
| "epoch": 4.78, | |
| "learning_rate": 1.309446254071661e-05, | |
| "loss": 0.2625, | |
| "step": 7440 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "learning_rate": 1.2703583061889248e-05, | |
| "loss": 0.2686, | |
| "step": 7450 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 1.2312703583061888e-05, | |
| "loss": 0.2713, | |
| "step": 7460 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 1.1921824104234527e-05, | |
| "loss": 0.2601, | |
| "step": 7470 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 1.1530944625407165e-05, | |
| "loss": 0.2508, | |
| "step": 7480 | |
| }, | |
| { | |
| "epoch": 4.82, | |
| "learning_rate": 1.1140065146579803e-05, | |
| "loss": 0.2627, | |
| "step": 7490 | |
| }, | |
| { | |
| "epoch": 4.82, | |
| "learning_rate": 1.0749185667752443e-05, | |
| "loss": 0.2576, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 1.0358306188925082e-05, | |
| "loss": 0.2627, | |
| "step": 7510 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "learning_rate": 9.967426710097718e-06, | |
| "loss": 0.2744, | |
| "step": 7520 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "learning_rate": 9.576547231270356e-06, | |
| "loss": 0.2717, | |
| "step": 7530 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "learning_rate": 9.185667752442995e-06, | |
| "loss": 0.266, | |
| "step": 7540 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "learning_rate": 8.794788273615635e-06, | |
| "loss": 0.2784, | |
| "step": 7550 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "learning_rate": 8.403908794788273e-06, | |
| "loss": 0.2764, | |
| "step": 7560 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "learning_rate": 8.013029315960911e-06, | |
| "loss": 0.2655, | |
| "step": 7570 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "learning_rate": 7.6221498371335505e-06, | |
| "loss": 0.2597, | |
| "step": 7580 | |
| }, | |
| { | |
| "epoch": 4.88, | |
| "learning_rate": 7.231270358306188e-06, | |
| "loss": 0.2622, | |
| "step": 7590 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 6.840390879478826e-06, | |
| "loss": 0.2636, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "eval_loss": 0.31572845578193665, | |
| "eval_runtime": 650.7955, | |
| "eval_samples_per_second": 3.073, | |
| "eval_steps_per_second": 0.384, | |
| "step": 7600 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 7775, | |
| "num_train_epochs": 5, | |
| "save_steps": 200, | |
| "total_flos": 1.3402577704260157e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |