| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.09142857142857143, | |
| "eval_steps": 500, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.563270330429077, | |
| "learning_rate": 4e-05, | |
| "loss": 2.4127, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.333299160003662, | |
| "learning_rate": 8e-05, | |
| "loss": 2.3102, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 1.8613317012786865, | |
| "learning_rate": 0.00012, | |
| "loss": 2.1983, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 1.620126485824585, | |
| "learning_rate": 0.00016, | |
| "loss": 2.0917, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 1.0352119207382202, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9613, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 0.8601917624473572, | |
| "learning_rate": 0.00019979899497487438, | |
| "loss": 1.6927, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 1.273868203163147, | |
| "learning_rate": 0.00019959798994974876, | |
| "loss": 1.6828, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 1.0873847007751465, | |
| "learning_rate": 0.00019939698492462313, | |
| "loss": 1.5088, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 0.5800795555114746, | |
| "learning_rate": 0.0001991959798994975, | |
| "loss": 1.3702, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 0.693160355091095, | |
| "learning_rate": 0.00019899497487437187, | |
| "loss": 1.3718, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.49409618973731995, | |
| "learning_rate": 0.00019879396984924622, | |
| "loss": 1.3583, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.47029319405555725, | |
| "learning_rate": 0.00019859296482412062, | |
| "loss": 1.2791, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.43618088960647583, | |
| "learning_rate": 0.000198391959798995, | |
| "loss": 1.3161, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.3907912075519562, | |
| "learning_rate": 0.00019819095477386937, | |
| "loss": 1.2954, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.6292415857315063, | |
| "learning_rate": 0.0001979899497487437, | |
| "loss": 1.3397, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.37423521280288696, | |
| "learning_rate": 0.0001977889447236181, | |
| "loss": 1.3983, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.3845643699169159, | |
| "learning_rate": 0.00019758793969849249, | |
| "loss": 1.3349, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.3657298982143402, | |
| "learning_rate": 0.00019738693467336683, | |
| "loss": 1.2767, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.3727971315383911, | |
| "learning_rate": 0.0001971859296482412, | |
| "loss": 1.3672, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.35123032331466675, | |
| "learning_rate": 0.0001969849246231156, | |
| "loss": 1.3692, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.4003850221633911, | |
| "learning_rate": 0.00019678391959798995, | |
| "loss": 1.3412, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.3638221323490143, | |
| "learning_rate": 0.00019658291457286432, | |
| "loss": 1.2813, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.391216903924942, | |
| "learning_rate": 0.0001963819095477387, | |
| "loss": 1.2853, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.4370620846748352, | |
| "learning_rate": 0.0001961809045226131, | |
| "loss": 1.2524, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.3566085696220398, | |
| "learning_rate": 0.00019597989949748744, | |
| "loss": 1.3192, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.35438084602355957, | |
| "learning_rate": 0.00019577889447236181, | |
| "loss": 1.2858, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.3968108296394348, | |
| "learning_rate": 0.0001955778894472362, | |
| "loss": 1.3112, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.36512017250061035, | |
| "learning_rate": 0.00019537688442211056, | |
| "loss": 1.278, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.3982504606246948, | |
| "learning_rate": 0.00019517587939698493, | |
| "loss": 1.2392, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.38377949595451355, | |
| "learning_rate": 0.0001949748743718593, | |
| "loss": 1.2843, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.3582867980003357, | |
| "learning_rate": 0.00019477386934673368, | |
| "loss": 1.3008, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.3572194576263428, | |
| "learning_rate": 0.00019457286432160805, | |
| "loss": 1.294, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.35502907633781433, | |
| "learning_rate": 0.00019437185929648243, | |
| "loss": 1.3877, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.3649040460586548, | |
| "learning_rate": 0.0001941708542713568, | |
| "loss": 1.2966, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.3649256229400635, | |
| "learning_rate": 0.00019396984924623117, | |
| "loss": 1.2354, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.36085084080696106, | |
| "learning_rate": 0.00019376884422110552, | |
| "loss": 1.2409, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.35929059982299805, | |
| "learning_rate": 0.00019356783919597992, | |
| "loss": 1.243, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.3897881805896759, | |
| "learning_rate": 0.0001933668341708543, | |
| "loss": 1.3945, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.35484543442726135, | |
| "learning_rate": 0.00019316582914572864, | |
| "loss": 1.3433, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.35691192746162415, | |
| "learning_rate": 0.000192964824120603, | |
| "loss": 1.3243, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.3804129958152771, | |
| "learning_rate": 0.0001927638190954774, | |
| "loss": 1.2509, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.3623339831829071, | |
| "learning_rate": 0.00019256281407035178, | |
| "loss": 1.1799, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.3411855697631836, | |
| "learning_rate": 0.00019236180904522613, | |
| "loss": 1.2372, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.36590930819511414, | |
| "learning_rate": 0.0001921608040201005, | |
| "loss": 1.2585, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.30974116921424866, | |
| "learning_rate": 0.0001919597989949749, | |
| "loss": 1.2974, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.32794803380966187, | |
| "learning_rate": 0.00019175879396984925, | |
| "loss": 1.2696, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.33263906836509705, | |
| "learning_rate": 0.00019155778894472362, | |
| "loss": 1.3209, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.31748828291893005, | |
| "learning_rate": 0.000191356783919598, | |
| "loss": 1.278, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.34738561511039734, | |
| "learning_rate": 0.0001911557788944724, | |
| "loss": 1.2105, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.3313944339752197, | |
| "learning_rate": 0.00019095477386934674, | |
| "loss": 1.2527, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.33137476444244385, | |
| "learning_rate": 0.0001907537688442211, | |
| "loss": 1.2984, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.31752490997314453, | |
| "learning_rate": 0.00019055276381909548, | |
| "loss": 1.307, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.3111082911491394, | |
| "learning_rate": 0.00019035175879396986, | |
| "loss": 1.2769, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.31065696477890015, | |
| "learning_rate": 0.00019015075376884423, | |
| "loss": 1.3082, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.3382773697376251, | |
| "learning_rate": 0.0001899497487437186, | |
| "loss": 1.2744, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.34320947527885437, | |
| "learning_rate": 0.00018974874371859298, | |
| "loss": 1.3013, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.33131280541419983, | |
| "learning_rate": 0.00018954773869346732, | |
| "loss": 1.4066, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.3357389569282532, | |
| "learning_rate": 0.00018934673366834172, | |
| "loss": 1.2841, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.3200838267803192, | |
| "learning_rate": 0.0001891457286432161, | |
| "loss": 1.2654, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.3336584270000458, | |
| "learning_rate": 0.00018894472361809047, | |
| "loss": 1.1716, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.3128441274166107, | |
| "learning_rate": 0.00018874371859296481, | |
| "loss": 1.3009, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.30249112844467163, | |
| "learning_rate": 0.00018854271356783921, | |
| "loss": 1.2311, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.3263241946697235, | |
| "learning_rate": 0.0001883417085427136, | |
| "loss": 1.2344, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.32348358631134033, | |
| "learning_rate": 0.00018814070351758793, | |
| "loss": 1.3023, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.6508419513702393, | |
| "learning_rate": 0.0001879396984924623, | |
| "loss": 1.2028, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.34560996294021606, | |
| "learning_rate": 0.0001877386934673367, | |
| "loss": 1.389, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.36555996537208557, | |
| "learning_rate": 0.00018753768844221108, | |
| "loss": 1.3653, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.3195466697216034, | |
| "learning_rate": 0.00018733668341708543, | |
| "loss": 1.2412, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.30555933713912964, | |
| "learning_rate": 0.0001871356783919598, | |
| "loss": 1.2357, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.30776411294937134, | |
| "learning_rate": 0.0001869346733668342, | |
| "loss": 1.3112, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.31933915615081787, | |
| "learning_rate": 0.00018673366834170854, | |
| "loss": 1.1951, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.3241545259952545, | |
| "learning_rate": 0.00018653266331658292, | |
| "loss": 1.2717, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.3117482364177704, | |
| "learning_rate": 0.0001863316582914573, | |
| "loss": 1.3031, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.33056551218032837, | |
| "learning_rate": 0.0001861306532663317, | |
| "loss": 1.2098, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.32441195845603943, | |
| "learning_rate": 0.00018592964824120604, | |
| "loss": 1.2135, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.34216779470443726, | |
| "learning_rate": 0.0001857286432160804, | |
| "loss": 1.2531, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.32885247468948364, | |
| "learning_rate": 0.00018552763819095478, | |
| "loss": 1.3054, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.34541794657707214, | |
| "learning_rate": 0.00018532663316582915, | |
| "loss": 1.3207, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.30329057574272156, | |
| "learning_rate": 0.00018512562814070353, | |
| "loss": 1.2652, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.31469491124153137, | |
| "learning_rate": 0.0001849246231155779, | |
| "loss": 1.1961, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.3181230127811432, | |
| "learning_rate": 0.00018472361809045227, | |
| "loss": 1.3111, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.3181725740432739, | |
| "learning_rate": 0.00018452261306532662, | |
| "loss": 1.3353, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.3154084384441376, | |
| "learning_rate": 0.00018432160804020102, | |
| "loss": 1.2418, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.35061103105545044, | |
| "learning_rate": 0.0001841206030150754, | |
| "loss": 1.2332, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.3259966969490051, | |
| "learning_rate": 0.00018391959798994977, | |
| "loss": 1.3633, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.31192857027053833, | |
| "learning_rate": 0.0001837185929648241, | |
| "loss": 1.1886, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.32024237513542175, | |
| "learning_rate": 0.0001835175879396985, | |
| "loss": 1.2141, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.302498459815979, | |
| "learning_rate": 0.00018331658291457288, | |
| "loss": 1.237, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.3569789230823517, | |
| "learning_rate": 0.00018311557788944723, | |
| "loss": 1.3015, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.3121156692504883, | |
| "learning_rate": 0.0001829145728643216, | |
| "loss": 1.281, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.31279826164245605, | |
| "learning_rate": 0.000182713567839196, | |
| "loss": 1.2924, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.3210877478122711, | |
| "learning_rate": 0.00018251256281407038, | |
| "loss": 1.3082, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.331406831741333, | |
| "learning_rate": 0.00018231155778894472, | |
| "loss": 1.2434, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.3135213255882263, | |
| "learning_rate": 0.0001821105527638191, | |
| "loss": 1.2188, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.31146401166915894, | |
| "learning_rate": 0.0001819095477386935, | |
| "loss": 1.2484, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.32071712613105774, | |
| "learning_rate": 0.00018170854271356784, | |
| "loss": 1.1927, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.3343571722507477, | |
| "learning_rate": 0.00018150753768844221, | |
| "loss": 1.3443, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.3510550558567047, | |
| "learning_rate": 0.0001813065326633166, | |
| "loss": 1.2832, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.33436939120292664, | |
| "learning_rate": 0.00018110552763819096, | |
| "loss": 1.252, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.3175451159477234, | |
| "learning_rate": 0.00018090452261306533, | |
| "loss": 1.251, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.32603979110717773, | |
| "learning_rate": 0.0001807035175879397, | |
| "loss": 1.228, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.3073003590106964, | |
| "learning_rate": 0.00018050251256281408, | |
| "loss": 1.2659, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.3285619616508484, | |
| "learning_rate": 0.00018030150753768845, | |
| "loss": 1.2826, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.3038572072982788, | |
| "learning_rate": 0.00018010050251256282, | |
| "loss": 1.217, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.35778746008872986, | |
| "learning_rate": 0.0001798994974874372, | |
| "loss": 1.2901, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.2900612950325012, | |
| "learning_rate": 0.00017969849246231157, | |
| "loss": 1.2651, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.32928743958473206, | |
| "learning_rate": 0.00017949748743718592, | |
| "loss": 1.3143, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.32471874356269836, | |
| "learning_rate": 0.00017929648241206032, | |
| "loss": 1.1834, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.30989256501197815, | |
| "learning_rate": 0.0001790954773869347, | |
| "loss": 1.2216, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.3371771275997162, | |
| "learning_rate": 0.00017889447236180906, | |
| "loss": 1.197, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.31041428446769714, | |
| "learning_rate": 0.0001786934673366834, | |
| "loss": 1.27, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.3152185082435608, | |
| "learning_rate": 0.0001784924623115578, | |
| "loss": 1.2436, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.3227459490299225, | |
| "learning_rate": 0.00017829145728643218, | |
| "loss": 1.2401, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.3246959149837494, | |
| "learning_rate": 0.00017809045226130653, | |
| "loss": 1.2703, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.38032859563827515, | |
| "learning_rate": 0.0001778894472361809, | |
| "loss": 1.3266, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.33325478434562683, | |
| "learning_rate": 0.0001776884422110553, | |
| "loss": 1.2954, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.3178690969944, | |
| "learning_rate": 0.00017748743718592967, | |
| "loss": 1.1793, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.31393784284591675, | |
| "learning_rate": 0.00017728643216080402, | |
| "loss": 1.277, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.3150279223918915, | |
| "learning_rate": 0.0001770854271356784, | |
| "loss": 1.293, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.32476913928985596, | |
| "learning_rate": 0.0001768844221105528, | |
| "loss": 1.2569, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.36075925827026367, | |
| "learning_rate": 0.00017668341708542714, | |
| "loss": 1.205, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.33134496212005615, | |
| "learning_rate": 0.0001764824120603015, | |
| "loss": 1.2299, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.30507662892341614, | |
| "learning_rate": 0.00017628140703517588, | |
| "loss": 1.2883, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.34049952030181885, | |
| "learning_rate": 0.00017608040201005026, | |
| "loss": 1.214, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.3405919373035431, | |
| "learning_rate": 0.00017587939698492463, | |
| "loss": 1.2738, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.3306083679199219, | |
| "learning_rate": 0.000175678391959799, | |
| "loss": 1.2415, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.33770737051963806, | |
| "learning_rate": 0.00017547738693467338, | |
| "loss": 1.3233, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.3261878788471222, | |
| "learning_rate": 0.00017527638190954775, | |
| "loss": 1.2695, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.3433193266391754, | |
| "learning_rate": 0.00017507537688442212, | |
| "loss": 1.2052, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.3111405670642853, | |
| "learning_rate": 0.0001748743718592965, | |
| "loss": 1.2798, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.3630310297012329, | |
| "learning_rate": 0.00017467336683417087, | |
| "loss": 1.2567, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.31963038444519043, | |
| "learning_rate": 0.00017447236180904521, | |
| "loss": 1.2455, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.299695760011673, | |
| "learning_rate": 0.00017427135678391961, | |
| "loss": 1.207, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.3167514503002167, | |
| "learning_rate": 0.000174070351758794, | |
| "loss": 1.2378, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.31375688314437866, | |
| "learning_rate": 0.00017386934673366836, | |
| "loss": 1.2658, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.34311383962631226, | |
| "learning_rate": 0.0001736683417085427, | |
| "loss": 1.2004, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.31706517934799194, | |
| "learning_rate": 0.0001734673366834171, | |
| "loss": 1.1879, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.31296172738075256, | |
| "learning_rate": 0.00017326633165829148, | |
| "loss": 1.1866, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.3254072368144989, | |
| "learning_rate": 0.00017306532663316582, | |
| "loss": 1.1952, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.3165453374385834, | |
| "learning_rate": 0.0001728643216080402, | |
| "loss": 1.3459, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.35455992817878723, | |
| "learning_rate": 0.0001726633165829146, | |
| "loss": 1.2494, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.3116908073425293, | |
| "learning_rate": 0.00017246231155778897, | |
| "loss": 1.2225, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.3141638934612274, | |
| "learning_rate": 0.00017226130653266332, | |
| "loss": 1.3385, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.3096507787704468, | |
| "learning_rate": 0.0001720603015075377, | |
| "loss": 1.3257, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.3160630464553833, | |
| "learning_rate": 0.00017185929648241206, | |
| "loss": 1.2683, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.3342824876308441, | |
| "learning_rate": 0.00017165829145728644, | |
| "loss": 1.2551, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.3086145222187042, | |
| "learning_rate": 0.0001714572864321608, | |
| "loss": 1.2456, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.3001709282398224, | |
| "learning_rate": 0.00017125628140703518, | |
| "loss": 1.2287, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.3277103304862976, | |
| "learning_rate": 0.00017105527638190955, | |
| "loss": 1.3302, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.33616161346435547, | |
| "learning_rate": 0.00017085427135678393, | |
| "loss": 1.2604, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.3231915533542633, | |
| "learning_rate": 0.0001706532663316583, | |
| "loss": 1.2367, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.3305569291114807, | |
| "learning_rate": 0.00017045226130653267, | |
| "loss": 1.2387, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.35031118988990784, | |
| "learning_rate": 0.00017025125628140705, | |
| "loss": 1.2464, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.3142334222793579, | |
| "learning_rate": 0.00017005025125628142, | |
| "loss": 1.3614, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.31159430742263794, | |
| "learning_rate": 0.0001698492462311558, | |
| "loss": 1.2556, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.3273050785064697, | |
| "learning_rate": 0.00016964824120603016, | |
| "loss": 1.3519, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.3299296796321869, | |
| "learning_rate": 0.0001694472361809045, | |
| "loss": 1.1763, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.33138513565063477, | |
| "learning_rate": 0.0001692462311557789, | |
| "loss": 1.17, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.30424776673316956, | |
| "learning_rate": 0.00016904522613065328, | |
| "loss": 1.123, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.3452983498573303, | |
| "learning_rate": 0.00016884422110552766, | |
| "loss": 1.2999, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.33614206314086914, | |
| "learning_rate": 0.000168643216080402, | |
| "loss": 1.262, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.32416558265686035, | |
| "learning_rate": 0.0001684422110552764, | |
| "loss": 1.2514, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.29827457666397095, | |
| "learning_rate": 0.00016824120603015078, | |
| "loss": 1.2461, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.32572871446609497, | |
| "learning_rate": 0.00016804020100502512, | |
| "loss": 1.2393, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.32171282172203064, | |
| "learning_rate": 0.0001678391959798995, | |
| "loss": 1.3045, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.34592801332473755, | |
| "learning_rate": 0.0001676381909547739, | |
| "loss": 1.2669, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.33795440196990967, | |
| "learning_rate": 0.00016743718592964827, | |
| "loss": 1.1404, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.32598641514778137, | |
| "learning_rate": 0.0001672361809045226, | |
| "loss": 1.2495, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.31816181540489197, | |
| "learning_rate": 0.00016703517587939699, | |
| "loss": 1.3003, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.3340943157672882, | |
| "learning_rate": 0.00016683417085427136, | |
| "loss": 1.2615, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.3242477476596832, | |
| "learning_rate": 0.00016663316582914573, | |
| "loss": 1.2527, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.308652400970459, | |
| "learning_rate": 0.0001664321608040201, | |
| "loss": 1.3241, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.31818273663520813, | |
| "learning_rate": 0.00016623115577889448, | |
| "loss": 1.3712, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.32885751128196716, | |
| "learning_rate": 0.00016603015075376885, | |
| "loss": 1.2583, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.32561740279197693, | |
| "learning_rate": 0.00016582914572864322, | |
| "loss": 1.2458, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.3278496563434601, | |
| "learning_rate": 0.0001656281407035176, | |
| "loss": 1.2205, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.32530438899993896, | |
| "learning_rate": 0.00016542713567839197, | |
| "loss": 1.2235, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.31232836842536926, | |
| "learning_rate": 0.00016522613065326634, | |
| "loss": 1.199, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.3209743797779083, | |
| "learning_rate": 0.00016502512562814072, | |
| "loss": 1.2717, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.329940527677536, | |
| "learning_rate": 0.0001648241206030151, | |
| "loss": 1.2425, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.3144824802875519, | |
| "learning_rate": 0.00016462311557788946, | |
| "loss": 1.2444, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.3218553066253662, | |
| "learning_rate": 0.0001644221105527638, | |
| "loss": 1.2815, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.33460506796836853, | |
| "learning_rate": 0.0001642211055276382, | |
| "loss": 1.3774, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.3300727605819702, | |
| "learning_rate": 0.00016402010050251258, | |
| "loss": 1.3436, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.3530360460281372, | |
| "learning_rate": 0.00016381909547738695, | |
| "loss": 1.2605, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.3326485753059387, | |
| "learning_rate": 0.0001636180904522613, | |
| "loss": 1.2202, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.31355732679367065, | |
| "learning_rate": 0.0001634170854271357, | |
| "loss": 1.2798, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.3162304759025574, | |
| "learning_rate": 0.00016321608040201007, | |
| "loss": 1.2118, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.32264095544815063, | |
| "learning_rate": 0.00016301507537688442, | |
| "loss": 1.2775, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.30425918102264404, | |
| "learning_rate": 0.0001628140703517588, | |
| "loss": 1.1438, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.33907556533813477, | |
| "learning_rate": 0.00016261306532663316, | |
| "loss": 1.4077, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.32334232330322266, | |
| "learning_rate": 0.00016241206030150756, | |
| "loss": 1.2673, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.32999834418296814, | |
| "learning_rate": 0.0001622110552763819, | |
| "loss": 1.257, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.3223746120929718, | |
| "learning_rate": 0.00016201005025125628, | |
| "loss": 1.2125, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.3236989378929138, | |
| "learning_rate": 0.00016180904522613066, | |
| "loss": 1.3645, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.3303336203098297, | |
| "learning_rate": 0.00016160804020100503, | |
| "loss": 1.2786, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.3135005831718445, | |
| "learning_rate": 0.0001614070351758794, | |
| "loss": 1.2775, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.3185466527938843, | |
| "learning_rate": 0.00016120603015075378, | |
| "loss": 1.2128, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.3355714976787567, | |
| "learning_rate": 0.00016100502512562815, | |
| "loss": 1.307, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.339216023683548, | |
| "learning_rate": 0.00016080402010050252, | |
| "loss": 1.2845, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 1000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 200, | |
| "total_flos": 9.299042116288512e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |