| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9990645463049579, | |
| "eval_steps": 201, | |
| "global_step": 801, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0012472715933894605, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012472715933894605, | |
| "eval_loss": NaN, | |
| "eval_runtime": 60.7649, | |
| "eval_samples_per_second": 22.233, | |
| "eval_steps_per_second": 5.562, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002494543186778921, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0037418147801683817, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004989086373557842, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006236357966947303, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007483629560336763, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008730901153726224, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8000000000000003e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.009978172747115684, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.011225444340505144, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.6e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.012472715933894606, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.013719987527284067, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.014967259120673527, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.8e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.016214530714062987, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.2000000000000004e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.017461802307452447, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.6000000000000006e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.018709073900841908, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.019956345494231368, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.400000000000001e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.021203617087620828, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.800000000000001e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.02245088868101029, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.2e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02369816027439975, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.6e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.024945431867789213, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.026192703461178673, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.4e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.027439975054568133, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.800000000000001e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.028687246647957593, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.200000000000001e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.029934518241347054, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.6e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.031181789834736514, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.032429061428125974, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010400000000000001, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.03367633302151544, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010800000000000001, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.034923604614904895, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011200000000000001, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03617087620829436, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000116, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.037418147801683815, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03866541939507328, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000124, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.039912690988462736, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012800000000000002, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0411599625818522, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000132, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.042407234175241657, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013600000000000003, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.04365450576863112, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04490177736202058, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000144, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.04614904895541004, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000148, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0473963205487995, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000152, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.04864359214218896, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015600000000000002, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.049890863735578425, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05113813532896788, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000164, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.052385406922357346, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000168, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0536326785157468, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000172, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.054879950109136266, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017600000000000002, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.05612722170252572, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.05737449329591519, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018400000000000003, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.058621764889304644, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000188, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.05986903648269411, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000192, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.061116308076083564, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000196, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.06236357966947303, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06361085126286249, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019999912503789813, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.06485812285625195, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019999650016690364, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.0661053944496414, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001999921254329498, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.06735266604303088, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019998600091259113, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.06859993763642033, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019997812671300214, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.06984720922980979, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001999685029719753, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.07109448082319925, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001999571298579188, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.07234175241658872, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001999440075698535, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.07358902400997817, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019992913633740957, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.07483629560336763, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001999125164208222, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.07608356719675709, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001998941481109274, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.07733083879014656, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019987403172915666, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.07857811038353602, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019985216762753139, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.07982538197692547, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001998285561886568, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.08107265357031494, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019980319782571523, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.0823199251637044, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019977609298245873, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.08356719675709386, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019974724213320157, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.08481446835048331, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019971664578281173, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.08606173994387278, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019968430446670212, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.08730901153726224, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001996502187508213, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0885562831306517, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019961438923164345, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.08980355472404115, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019957681653615797, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.09105082631743062, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001995375013218586, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.09229809791082008, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019949644427673177, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.09354536950420954, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019945364611924463, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.094792641097599, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001994091075983325, | |
| "loss": 0.0, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.09603991269098847, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019936282949338578, | |
| "loss": 0.0, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.09728718428437792, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019931481261423618, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.09853445587776738, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019926505780114276, | |
| "loss": 0.0, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.09978172747115685, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001992135659247769, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.10102899906454631, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019916033788620755, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.10227627065793576, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000199105374616885, | |
| "loss": 0.0, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.10352354225132522, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019904867707862476, | |
| "loss": 0.0, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.10477081384471469, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001989902462635908, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.10601808543810415, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019893008319427812, | |
| "loss": 0.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.1072653570314936, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019886818892349482, | |
| "loss": 0.0, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.10851262862488306, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019880456453434369, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.10975990021827253, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019873921114020333, | |
| "loss": 0.0, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.11100717181166199, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019867212988470864, | |
| "loss": 0.0, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.11225444340505145, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001986033219417307, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.11350171499844092, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019853278851535638, | |
| "loss": 0.0, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.11474898659183037, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019846053083986717, | |
| "loss": 0.0, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.11599625818521983, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019838655017971767, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.11724352977860929, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019831084782951326, | |
| "loss": 0.0, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.11849080137199876, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019823342511398776, | |
| "loss": 0.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.11973807296538821, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019815428338798002, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.12098534455877767, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001980734240364102, | |
| "loss": 0.0, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.12223261615216713, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019799084847425572, | |
| "loss": 0.0, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.1234798877455566, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001979065581465263, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.12472715933894606, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019782055452823878, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.1259744309323355, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019773283912439133, | |
| "loss": 0.0, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.12722170252572498, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019764341346993698, | |
| "loss": 0.0, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.12846897411911443, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019755227912975697, | |
| "loss": 0.0, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.1297162457125039, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001974594376986331, | |
| "loss": 0.0, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.13096351730589337, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019736489080122006, | |
| "loss": 0.0, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.1322107888992828, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019726864009201694, | |
| "loss": 0.0, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.13345806049267228, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019717068725533818, | |
| "loss": 0.0, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.13470533208606175, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019707103400528415, | |
| "loss": 0.0, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.1359526036794512, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001969696820857112, | |
| "loss": 0.0, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.13719987527284067, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001968666332702011, | |
| "loss": 0.0, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.1384471468662301, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019676188936203006, | |
| "loss": 0.0, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.13969441845961958, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019665545219413701, | |
| "loss": 0.0, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.14094169005300905, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019654732362909177, | |
| "loss": 0.0, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.1421889616463985, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019643750555906224, | |
| "loss": 0.0, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.14343623323978796, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019632599990578143, | |
| "loss": 0.0, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.14468350483317743, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019621280862051373, | |
| "loss": 0.0, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.14593077642656688, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019609793368402086, | |
| "loss": 0.0, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.14717804801995635, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001959813771065271, | |
| "loss": 0.0, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.14842531961334582, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019586314092768424, | |
| "loss": 0.0, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.14967259120673526, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019574322721653583, | |
| "loss": 0.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.15091986280012473, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019562163807148084, | |
| "loss": 0.0, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.15216713439351418, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001954983756202372, | |
| "loss": 0.0, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.15341440598690365, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001953734420198044, | |
| "loss": 0.0, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.15466167758029312, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001952468394564257, | |
| "loss": 0.0, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.15590894917368256, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019511857014555, | |
| "loss": 0.0, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.15715622076707203, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019498863633179308, | |
| "loss": 0.0, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.1584034923604615, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019485704028889813, | |
| "loss": 0.0, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.15965076395385094, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001947237843196962, | |
| "loss": 0.0, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.16089803554724041, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001945888707560657, | |
| "loss": 0.0, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.16214530714062989, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001944523019588918, | |
| "loss": 0.0, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.16339257873401933, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019431408031802486, | |
| "loss": 0.0, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.1646398503274088, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019417420825223891, | |
| "loss": 0.0, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.16588712192079824, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000194032688209189, | |
| "loss": 0.0, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.1671343935141877, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019388952266536868, | |
| "loss": 0.0, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.16838166510757718, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019374471412606642, | |
| "loss": 0.0, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.16962893670096663, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019359826512532194, | |
| "loss": 0.0, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.1708762082943561, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019345017822588168, | |
| "loss": 0.0, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.17212347988774557, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001933004560191542, | |
| "loss": 0.0, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.173370751481135, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019314910112516463, | |
| "loss": 0.0, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.17461802307452448, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019299611619250881, | |
| "loss": 0.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.17586529466791395, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019284150389830721, | |
| "loss": 0.0, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.1771125662613034, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019268526694815773, | |
| "loss": 0.0, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.17835983785469287, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001925274080760886, | |
| "loss": 0.0, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.1796071094480823, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019236793004451044, | |
| "loss": 0.0, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.18085438104147178, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019220683564416787, | |
| "loss": 0.0, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.18210165263486125, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019204412769409086, | |
| "loss": 0.0, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.1833489242282507, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019187980904154515, | |
| "loss": 0.0, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.18459619582164016, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019171388256198268, | |
| "loss": 0.0, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.18584346741502963, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000191546351158991, | |
| "loss": 0.0, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.18709073900841908, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019137721776424274, | |
| "loss": 0.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.18833801060180855, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001912064853374441, | |
| "loss": 0.0, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.189585282195198, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001910341568662831, | |
| "loss": 0.0, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.19083255378858746, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019086023536637737, | |
| "loss": 0.0, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.19207982538197693, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001906847238812214, | |
| "loss": 0.0, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.19332709697536637, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001905076254821331, | |
| "loss": 0.0, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.19457436856875585, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019032894326820023, | |
| "loss": 0.0, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.19582164016214532, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001901486803662261, | |
| "loss": 0.0, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.19706891175553476, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018996683993067483, | |
| "loss": 0.0, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.19831618334892423, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018978342514361626, | |
| "loss": 0.0, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.1995634549423137, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018959843921467014, | |
| "loss": 0.0, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.20081072653570314, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018941188538094999, | |
| "loss": 0.0, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.20205799812909261, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001892237669070065, | |
| "loss": 0.0, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.20330526972248206, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001890340870847704, | |
| "loss": 0.0, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.20455254131587153, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018884284923349477, | |
| "loss": 0.0, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.205799812909261, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018865005669969708, | |
| "loss": 0.0, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.20704708450265044, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018845571285710058, | |
| "loss": 0.0, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.2082943560960399, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018825982110657515, | |
| "loss": 0.0, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.20954162768942938, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018806238487607794, | |
| "loss": 0.0, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.21078889928281883, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001878634076205934, | |
| "loss": 0.0, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.2120361708762083, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018766289282207263, | |
| "loss": 0.0, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.21328344246959777, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018746084398937266, | |
| "loss": 0.0, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.2145307140629872, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018725726465819488, | |
| "loss": 0.0, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.21577798565637668, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018705215839102328, | |
| "loss": 0.0, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.21702525724976612, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001868455287770621, | |
| "loss": 0.0, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.2182725288431556, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018663737943217296, | |
| "loss": 0.0, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.21951980043654507, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018642771399881162, | |
| "loss": 0.0, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.2207670720299345, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018621653614596425, | |
| "loss": 0.0, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.22201434362332398, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018600384956908323, | |
| "loss": 0.0, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.22326161521671345, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018578965799002236, | |
| "loss": 0.0, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.2245088868101029, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018557396515697202, | |
| "loss": 0.0, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.22575615840349236, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001853567748443933, | |
| "loss": 0.0, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.22700342999688183, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000185138090852952, | |
| "loss": 0.0, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.22825070159027128, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001849179170094522, | |
| "loss": 0.0, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.22949797318366075, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018469625716676933, | |
| "loss": 0.0, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.2307452447770502, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018447311520378262, | |
| "loss": 0.0, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.23199251637043966, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001842484950253073, | |
| "loss": 0.0, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.23323978796382913, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018402240056202614, | |
| "loss": 0.0, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.23448705955721857, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018379483577042103, | |
| "loss": 0.0, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.23573433115060805, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018356580463270322, | |
| "loss": 0.0, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.23698160274399752, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018333531115674408, | |
| "loss": 0.0, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.23822887433738696, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001831033593760047, | |
| "loss": 0.0, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.23947614593077643, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018286995334946545, | |
| "loss": 0.0, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.2407234175241659, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001826350971615549, | |
| "loss": 0.0, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.24197068911755534, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018239879492207831, | |
| "loss": 0.0, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.2432179607109448, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018216105076614576, | |
| "loss": 0.0, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.24446523230433426, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018192186885409973, | |
| "loss": 0.0, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.24571250389772373, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001816812533714425, | |
| "loss": 0.0, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.2469597754911132, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018143920852876257, | |
| "loss": 0.0, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.24820704708450264, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001811957385616612, | |
| "loss": 0.0, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.2494543186778921, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001809508477306783, | |
| "loss": 0.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.2507015902712816, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018070454032121787, | |
| "loss": 0.0, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.2507015902712816, | |
| "eval_loss": NaN, | |
| "eval_runtime": 60.4112, | |
| "eval_samples_per_second": 22.363, | |
| "eval_steps_per_second": 5.595, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.251948861864671, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018045682064347275, | |
| "loss": 0.0, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.25319613345806047, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018020769303234962, | |
| "loss": 0.0, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.25444340505144997, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017995716184739284, | |
| "loss": 0.0, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.2556906766448394, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017970523147270822, | |
| "loss": 0.0, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.25693794823822885, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001794519063168864, | |
| "loss": 0.0, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.25818521983161835, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001791971908129256, | |
| "loss": 0.0, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.2594324914250078, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000178941089418154, | |
| "loss": 0.0, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.26067976301839724, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000178683606614152, | |
| "loss": 0.0, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.26192703461178674, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017842474690667344, | |
| "loss": 0.0, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.2631743062051762, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017816451482556702, | |
| "loss": 0.0, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.2644215777985656, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001779029149246969, | |
| "loss": 0.0, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.2656688493919551, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017763995178186307, | |
| "loss": 0.0, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.26691612098534456, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017737562999872118, | |
| "loss": 0.0, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.268163392578734, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017710995420070215, | |
| "loss": 0.0, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.2694106641721235, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017684292903693102, | |
| "loss": 0.0, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.27065793576551295, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017657455918014582, | |
| "loss": 0.0, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.2719052073589024, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017630484932661559, | |
| "loss": 0.0, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.2731524789522919, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001760338041960583, | |
| "loss": 0.0, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.27439975054568133, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017576142853155838, | |
| "loss": 0.0, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.2756470221390708, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017548772709948343, | |
| "loss": 0.0, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.2768942937324602, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001752127046894011, | |
| "loss": 0.0, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.2781415653258497, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001749363661139951, | |
| "loss": 0.0, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 0.27938883691923916, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017465871620898102, | |
| "loss": 0.0, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.2806361085126286, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017437975983302178, | |
| "loss": 0.0, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.2818833801060181, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001740995018676425, | |
| "loss": 0.0, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.28313065169940754, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001738179472171452, | |
| "loss": 0.0, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 0.284377923292797, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017353510080852282, | |
| "loss": 0.0, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.2856251948861865, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001732509675913731, | |
| "loss": 0.0, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 0.2868724664795759, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000172965552537812, | |
| "loss": 0.0, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.28811973807296537, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017267886064238662, | |
| "loss": 0.0, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.28936700966635487, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017239089692198785, | |
| "loss": 0.0, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.2906142812597443, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001721016664157625, | |
| "loss": 0.0, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 0.29186155285313375, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017181117418502525, | |
| "loss": 0.0, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.29310882444652325, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017151942531316988, | |
| "loss": 0.0, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.2943560960399127, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017122642490558055, | |
| "loss": 0.0, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.29560336763330214, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017093217808954232, | |
| "loss": 0.0, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.29685063922669164, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017063669001415145, | |
| "loss": 0.0, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.2980979108200811, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017033996585022528, | |
| "loss": 0.0, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 0.2993451824134705, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017004201079021176, | |
| "loss": 0.0, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.30059245400686, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016974283004809858, | |
| "loss": 0.0, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 0.30183972560024946, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016944242885932206, | |
| "loss": 0.0, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 0.3030869971936389, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001691408124806752, | |
| "loss": 0.0, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 0.30433426878702835, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016883798619021608, | |
| "loss": 0.0, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 0.30558154038041785, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001685339552871752, | |
| "loss": 0.0, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.3068288119738073, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016822872509186297, | |
| "loss": 0.0, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.30807608356719673, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001679223009455764, | |
| "loss": 0.0, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 0.30932335516058623, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016761468821050585, | |
| "loss": 0.0, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 0.3105706267539757, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016730589226964098, | |
| "loss": 0.0, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 0.3118178983473651, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016699591852667673, | |
| "loss": 0.0, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.3130651699407546, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016668477240591864, | |
| "loss": 0.0, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 0.31431244153414406, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016637245935218799, | |
| "loss": 0.0, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.3155597131275335, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016605898483072648, | |
| "loss": 0.0, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 0.316806984720923, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016574435432710068, | |
| "loss": 0.0, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 0.31805425631431244, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001654285733471059, | |
| "loss": 0.0, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.3193015279077019, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001651116474166699, | |
| "loss": 0.0, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.3205487995010914, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016479358208175627, | |
| "loss": 0.0, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 0.32179607109448083, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016447438290826733, | |
| "loss": 0.0, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.32304334268787027, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016415405548194663, | |
| "loss": 0.0, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 0.32429061428125977, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016383260540828135, | |
| "loss": 0.0, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.3255378858746492, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016351003831240415, | |
| "loss": 0.0, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 0.32678515746803866, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016318635983899465, | |
| "loss": 0.0, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 0.3280324290614281, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001628615756521809, | |
| "loss": 0.0, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 0.3292797006548176, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001625356914354399, | |
| "loss": 0.0, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.33052697224820704, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001622087128914985, | |
| "loss": 0.0, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.3317742438415965, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016188064574223335, | |
| "loss": 0.0, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 0.333021515434986, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001615514957285709, | |
| "loss": 0.0, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 0.3342687870283754, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016122126861038688, | |
| "loss": 0.0, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 0.33551605862176487, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016088997016640562, | |
| "loss": 0.0, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 0.33676333021515437, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016055760619409877, | |
| "loss": 0.0, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.3380106018085438, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016022418250958385, | |
| "loss": 0.0, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 0.33925787340193325, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015988970494752272, | |
| "loss": 0.0, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 0.34050514499532275, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015955417936101913, | |
| "loss": 0.0, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 0.3417524165887122, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015921761162151653, | |
| "loss": 0.0, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 0.34299968818210164, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015888000761869528, | |
| "loss": 0.0, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.34424695977549113, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001585413732603695, | |
| "loss": 0.0, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.3454942313688806, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015820171447238383, | |
| "loss": 0.0, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 0.34674150296227, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001578610371985096, | |
| "loss": 0.0, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 0.3479887745556595, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015751934740034092, | |
| "loss": 0.0, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 0.34923604614904896, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015717665105719015, | |
| "loss": 0.0, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.3504833177424384, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015683295416598367, | |
| "loss": 0.0, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 0.3517305893358279, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015648826274115653, | |
| "loss": 0.0, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 0.35297786092921735, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015614258281454734, | |
| "loss": 0.0, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 0.3542251325226068, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015579592043529292, | |
| "loss": 0.0, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 0.35547240411599623, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015544828166972203, | |
| "loss": 0.0, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.35671967570938573, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015509967260124964, | |
| "loss": 0.0, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 0.3579669473027752, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001547500993302702, | |
| "loss": 0.0, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 0.3592142188961646, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000154399567974051, | |
| "loss": 0.0, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.3604614904895541, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015404808466662508, | |
| "loss": 0.0, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 0.36170876208294356, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001536956555586839, | |
| "loss": 0.0, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.362956033676333, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001533422868174697, | |
| "loss": 0.0, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 0.3642033052697225, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015298798462666765, | |
| "loss": 0.0, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 0.36545057686311194, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015263275518629754, | |
| "loss": 0.0, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 0.3666978484565014, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015227660471260528, | |
| "loss": 0.0, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.3679451200498909, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015191953943795427, | |
| "loss": 0.0, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.3691923916432803, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015156156561071612, | |
| "loss": 0.0, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 0.37043966323666977, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001512026894951615, | |
| "loss": 0.0, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 0.37168693483005927, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015084291737135048, | |
| "loss": 0.0, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 0.3729342064234487, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015048225553502244, | |
| "loss": 0.0, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 0.37418147801683815, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015012071029748614, | |
| "loss": 0.0, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.37542874961022765, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014975828798550933, | |
| "loss": 0.0, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 0.3766760212036171, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014939499494120761, | |
| "loss": 0.0, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 0.37792329279700654, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014903083752193397, | |
| "loss": 0.0, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 0.379170564390396, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001486658221001672, | |
| "loss": 0.0, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 0.3804178359837855, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001482999550634006, | |
| "loss": 0.0, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.3816651075771749, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001479332428140299, | |
| "loss": 0.0, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 0.38291237917056437, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014756569176924153, | |
| "loss": 0.0, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 0.38415965076395386, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001471973083609002, | |
| "loss": 0.0, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 0.3854069223573433, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014682809903543632, | |
| "loss": 0.0, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 0.38665419395073275, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014645807025373328, | |
| "loss": 0.0, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.38790146554412225, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001460872284910143, | |
| "loss": 0.0, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 0.3891487371375117, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000145715580236729, | |
| "loss": 0.0, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.39039600873090113, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014534313199444031, | |
| "loss": 0.0, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 0.39164328032429063, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014496989028171012, | |
| "loss": 0.0, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 0.3928905519176801, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014459586162998545, | |
| "loss": 0.0, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.3941378235110695, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014422105258448425, | |
| "loss": 0.0, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 0.395385095104459, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014384546970408067, | |
| "loss": 0.0, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 0.39663236669784846, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001434691195611905, | |
| "loss": 0.0, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 0.3978796382912379, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000143092008741656, | |
| "loss": 0.0, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 0.3991269098846274, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014271414384463063, | |
| "loss": 0.0, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.40037418147801684, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014233553148246364, | |
| "loss": 0.0, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 0.4016214530714063, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014195617828058446, | |
| "loss": 0.0, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 0.4028687246647958, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014157609087738656, | |
| "loss": 0.0, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 0.40411599625818523, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014119527592411146, | |
| "loss": 0.0, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 0.40536326785157467, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014081374008473213, | |
| "loss": 0.0, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.4066105394449641, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001404314900358366, | |
| "loss": 0.0, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 0.4078578110383536, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014004853246651092, | |
| "loss": 0.0, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 0.40910508263174306, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001396648740782224, | |
| "loss": 0.0, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 0.4103523542251325, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000139280521584702, | |
| "loss": 0.0, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 0.411599625818522, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013889548171182702, | |
| "loss": 0.0, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.41284689741191144, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001385097611975034, | |
| "loss": 0.0, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 0.4140941690053009, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013812336679154777, | |
| "loss": 0.0, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 0.4153414405986904, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001377363052555693, | |
| "loss": 0.0, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 0.4165887121920798, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013734858336285162, | |
| "loss": 0.0, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 0.41783598378546927, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013696020789823388, | |
| "loss": 0.0, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.41908325537885877, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013657118565799236, | |
| "loss": 0.0, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 0.4203305269722482, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013618152344972142, | |
| "loss": 0.0, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 0.42157779856563765, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013579122809221432, | |
| "loss": 0.0, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 0.42282507015902715, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013540030641534404, | |
| "loss": 0.0, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 0.4240723417524166, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013500876525994354, | |
| "loss": 0.0, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.42531961334580604, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013461661147768633, | |
| "loss": 0.0, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 0.42656688493919553, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013422385193096636, | |
| "loss": 0.0, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 0.427814156532585, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000133830493492778, | |
| "loss": 0.0, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 0.4290614281259744, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013343654304659574, | |
| "loss": 0.0, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 0.4303086997193639, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013304200748625377, | |
| "loss": 0.0, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.43155597131275336, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001326468937158254, | |
| "loss": 0.0, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 0.4328032429061428, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013225120864950217, | |
| "loss": 0.0, | |
| "step": 347 | |
| }, | |
| { | |
| "epoch": 0.43405051449953225, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013185495921147272, | |
| "loss": 0.0, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 0.43529778609292175, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013145815233580192, | |
| "loss": 0.0, | |
| "step": 349 | |
| }, | |
| { | |
| "epoch": 0.4365450576863112, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013106079496630937, | |
| "loss": 0.0, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.43779232927970063, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013066289405644778, | |
| "loss": 0.0, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 0.43903960087309013, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013026445656918155, | |
| "loss": 0.0, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 0.4402868724664796, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012986548947686467, | |
| "loss": 0.0, | |
| "step": 353 | |
| }, | |
| { | |
| "epoch": 0.441534144059869, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012946599976111883, | |
| "loss": 0.0, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 0.4427814156532585, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001290659944127113, | |
| "loss": 0.0, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.44402868724664796, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001286654804314325, | |
| "loss": 0.0, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 0.4452759588400374, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001282644648259735, | |
| "loss": 0.0, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 0.4465232304334269, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012786295461380344, | |
| "loss": 0.0, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 0.44777050202681634, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012746095682104669, | |
| "loss": 0.0, | |
| "step": 359 | |
| }, | |
| { | |
| "epoch": 0.4490177736202058, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012705847848235995, | |
| "loss": 0.0, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.4502650452135953, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012665552664080907, | |
| "loss": 0.0, | |
| "step": 361 | |
| }, | |
| { | |
| "epoch": 0.4515123168069847, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012625210834774585, | |
| "loss": 0.0, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 0.45275958840037417, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012584823066268466, | |
| "loss": 0.0, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 0.45400685999376367, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012544390065317887, | |
| "loss": 0.0, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 0.4552541315871531, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012503912539469714, | |
| "loss": 0.0, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.45650140318054255, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012463391197049977, | |
| "loss": 0.0, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 0.457748674773932, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012422826747151444, | |
| "loss": 0.0, | |
| "step": 367 | |
| }, | |
| { | |
| "epoch": 0.4589959463673215, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012382219899621246, | |
| "loss": 0.0, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 0.46024321796071094, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012341571365048442, | |
| "loss": 0.0, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 0.4614904895541004, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012300881854751568, | |
| "loss": 0.0, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.4627377611474899, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001226015208076622, | |
| "loss": 0.0, | |
| "step": 371 | |
| }, | |
| { | |
| "epoch": 0.4639850327408793, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001221938275583257, | |
| "loss": 0.0, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 0.46523230433426876, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012178574593382899, | |
| "loss": 0.0, | |
| "step": 373 | |
| }, | |
| { | |
| "epoch": 0.46647957592765826, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001213772830752912, | |
| "loss": 0.0, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 0.4677268475210477, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001209684461305028, | |
| "loss": 0.0, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.46897411911443715, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012055924225380038, | |
| "loss": 0.0, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 0.47022139070782665, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012014967860594164, | |
| "loss": 0.0, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 0.4714686623012161, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011973976235398, | |
| "loss": 0.0, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 0.47271593389460553, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001193295006711392, | |
| "loss": 0.0, | |
| "step": 379 | |
| }, | |
| { | |
| "epoch": 0.47396320548799503, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011891890073668763, | |
| "loss": 0.0, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.4752104770813845, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011850796973581302, | |
| "loss": 0.0, | |
| "step": 381 | |
| }, | |
| { | |
| "epoch": 0.4764577486747739, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011809671485949636, | |
| "loss": 0.0, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 0.4777050202681634, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011768514330438627, | |
| "loss": 0.0, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 0.47895229186155286, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011727326227267308, | |
| "loss": 0.0, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 0.4801995634549423, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011686107897196255, | |
| "loss": 0.0, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.4814468350483318, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011644860061515008, | |
| "loss": 0.0, | |
| "step": 386 | |
| }, | |
| { | |
| "epoch": 0.48269410664172124, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011603583442029426, | |
| "loss": 0.0, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 0.4839413782351107, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011562278761049066, | |
| "loss": 0.0, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 0.48518864982850013, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011520946741374534, | |
| "loss": 0.0, | |
| "step": 389 | |
| }, | |
| { | |
| "epoch": 0.4864359214218896, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011479588106284848, | |
| "loss": 0.0, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.48768319301527907, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011438203579524778, | |
| "loss": 0.0, | |
| "step": 391 | |
| }, | |
| { | |
| "epoch": 0.4889304646086685, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011396793885292165, | |
| "loss": 0.0, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 0.490177736202058, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011355359748225279, | |
| "loss": 0.0, | |
| "step": 393 | |
| }, | |
| { | |
| "epoch": 0.49142500779544745, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011313901893390113, | |
| "loss": 0.0, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 0.4926722793888369, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011272421046267696, | |
| "loss": 0.0, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.4939195509822264, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011230917932741418, | |
| "loss": 0.0, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 0.49516682257561584, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011189393279084308, | |
| "loss": 0.0, | |
| "step": 397 | |
| }, | |
| { | |
| "epoch": 0.4964140941690053, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011147847811946328, | |
| "loss": 0.0, | |
| "step": 398 | |
| }, | |
| { | |
| "epoch": 0.4976613657623948, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011106282258341665, | |
| "loss": 0.0, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 0.4989086373557842, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011064697345636002, | |
| "loss": 0.0, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.5001559089491737, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011023093801533785, | |
| "loss": 0.0, | |
| "step": 401 | |
| }, | |
| { | |
| "epoch": 0.5014031805425632, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010981472354065514, | |
| "loss": 0.0, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 0.5014031805425632, | |
| "eval_loss": NaN, | |
| "eval_runtime": 60.5505, | |
| "eval_samples_per_second": 22.312, | |
| "eval_steps_per_second": 5.582, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 0.5026504521359526, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010939833731574967, | |
| "loss": 0.0, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 0.503897723729342, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010898178662706471, | |
| "loss": 0.0, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 0.5051449953227315, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010856507876392166, | |
| "loss": 0.0, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.5063922669161209, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010814822101839224, | |
| "loss": 0.0, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 0.5076395385095105, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010773122068517103, | |
| "loss": 0.0, | |
| "step": 407 | |
| }, | |
| { | |
| "epoch": 0.5088868101028999, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010731408506144782, | |
| "loss": 0.0, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 0.5101340816962894, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010689682144677983, | |
| "loss": 0.0, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 0.5113813532896788, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010647943714296405, | |
| "loss": 0.0, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.5126286248830683, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010606193945390943, | |
| "loss": 0.0, | |
| "step": 411 | |
| }, | |
| { | |
| "epoch": 0.5138758964764577, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010564433568550909, | |
| "loss": 0.0, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 0.5151231680698473, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010522663314551247, | |
| "loss": 0.0, | |
| "step": 413 | |
| }, | |
| { | |
| "epoch": 0.5163704396632367, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010480883914339736, | |
| "loss": 0.0, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 0.5176177112566261, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001043909609902422, | |
| "loss": 0.0, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.5188649828500156, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010397300599859785, | |
| "loss": 0.0, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 0.520112254443405, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010355498148235996, | |
| "loss": 0.0, | |
| "step": 417 | |
| }, | |
| { | |
| "epoch": 0.5213595260367945, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010313689475664063, | |
| "loss": 0.0, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 0.522606797630184, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001027187531376407, | |
| "loss": 0.0, | |
| "step": 419 | |
| }, | |
| { | |
| "epoch": 0.5238540692235735, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010230056394252161, | |
| "loss": 0.0, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.5251013408169629, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010188233448927724, | |
| "loss": 0.0, | |
| "step": 421 | |
| }, | |
| { | |
| "epoch": 0.5263486124103524, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010146407209660607, | |
| "loss": 0.0, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 0.5275958840037418, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010104578408378289, | |
| "loss": 0.0, | |
| "step": 423 | |
| }, | |
| { | |
| "epoch": 0.5288431555971312, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010062747777053094, | |
| "loss": 0.0, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 0.5300904271905207, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010020916047689358, | |
| "loss": 0.0, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.5313376987839102, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.979083952310643e-05, | |
| "loss": 0.0, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 0.5325849703772997, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.937252222946908e-05, | |
| "loss": 0.0, | |
| "step": 427 | |
| }, | |
| { | |
| "epoch": 0.5338322419706891, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.895421591621712e-05, | |
| "loss": 0.0, | |
| "step": 428 | |
| }, | |
| { | |
| "epoch": 0.5350795135640786, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.853592790339396e-05, | |
| "loss": 0.0, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 0.536326785157468, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.811766551072278e-05, | |
| "loss": 0.0, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.5375740567508575, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.769943605747844e-05, | |
| "loss": 0.0, | |
| "step": 431 | |
| }, | |
| { | |
| "epoch": 0.538821328344247, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.72812468623593e-05, | |
| "loss": 0.0, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 0.5400685999376365, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.686310524335938e-05, | |
| "loss": 0.0, | |
| "step": 433 | |
| }, | |
| { | |
| "epoch": 0.5413158715310259, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.644501851764007e-05, | |
| "loss": 0.0, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 0.5425631431244153, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.602699400140218e-05, | |
| "loss": 0.0, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.5438104147178048, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.560903900975785e-05, | |
| "loss": 0.0, | |
| "step": 436 | |
| }, | |
| { | |
| "epoch": 0.5450576863111942, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.519116085660267e-05, | |
| "loss": 0.0, | |
| "step": 437 | |
| }, | |
| { | |
| "epoch": 0.5463049579045838, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.477336685448754e-05, | |
| "loss": 0.0, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 0.5475522294979732, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.435566431449092e-05, | |
| "loss": 0.0, | |
| "step": 439 | |
| }, | |
| { | |
| "epoch": 0.5487995010913627, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.39380605460906e-05, | |
| "loss": 0.0, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.5500467726847521, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.352056285703599e-05, | |
| "loss": 0.0, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 0.5512940442781415, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.31031785532202e-05, | |
| "loss": 0.0, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 0.552541315871531, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.268591493855222e-05, | |
| "loss": 0.0, | |
| "step": 443 | |
| }, | |
| { | |
| "epoch": 0.5537885874649204, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.226877931482898e-05, | |
| "loss": 0.0, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 0.55503585905831, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.18517789816078e-05, | |
| "loss": 0.0, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.5562831306516994, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.143492123607838e-05, | |
| "loss": 0.0, | |
| "step": 446 | |
| }, | |
| { | |
| "epoch": 0.5575304022450889, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.101821337293532e-05, | |
| "loss": 0.0, | |
| "step": 447 | |
| }, | |
| { | |
| "epoch": 0.5587776738384783, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.060166268425038e-05, | |
| "loss": 0.0, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 0.5600249454318678, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.018527645934488e-05, | |
| "loss": 0.0, | |
| "step": 449 | |
| }, | |
| { | |
| "epoch": 0.5612722170252572, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.976906198466213e-05, | |
| "loss": 0.0, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.5625194886186468, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.935302654364e-05, | |
| "loss": 0.0, | |
| "step": 451 | |
| }, | |
| { | |
| "epoch": 0.5637667602120362, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.893717741658336e-05, | |
| "loss": 0.0, | |
| "step": 452 | |
| }, | |
| { | |
| "epoch": 0.5650140318054256, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.852152188053674e-05, | |
| "loss": 0.0, | |
| "step": 453 | |
| }, | |
| { | |
| "epoch": 0.5662613033988151, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.810606720915697e-05, | |
| "loss": 0.0, | |
| "step": 454 | |
| }, | |
| { | |
| "epoch": 0.5675085749922045, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.769082067258585e-05, | |
| "loss": 0.0, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.568755846585594, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.727578953732303e-05, | |
| "loss": 0.0, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 0.5700031181789835, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.686098106609889e-05, | |
| "loss": 0.0, | |
| "step": 457 | |
| }, | |
| { | |
| "epoch": 0.571250389772373, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.644640251774722e-05, | |
| "loss": 0.0, | |
| "step": 458 | |
| }, | |
| { | |
| "epoch": 0.5724976613657624, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.603206114707837e-05, | |
| "loss": 0.0, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 0.5737449329591519, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.561796420475227e-05, | |
| "loss": 0.0, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.5749922045525413, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.52041189371515e-05, | |
| "loss": 0.0, | |
| "step": 461 | |
| }, | |
| { | |
| "epoch": 0.5762394761459307, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.479053258625467e-05, | |
| "loss": 0.0, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 0.5774867477393202, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.437721238950938e-05, | |
| "loss": 0.0, | |
| "step": 463 | |
| }, | |
| { | |
| "epoch": 0.5787340193327097, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.396416557970576e-05, | |
| "loss": 0.0, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 0.5799812909260992, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.355139938484995e-05, | |
| "loss": 0.0, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.5812285625194886, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.313892102803749e-05, | |
| "loss": 0.0, | |
| "step": 466 | |
| }, | |
| { | |
| "epoch": 0.5824758341128781, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.272673772732695e-05, | |
| "loss": 0.0, | |
| "step": 467 | |
| }, | |
| { | |
| "epoch": 0.5837231057062675, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.231485669561371e-05, | |
| "loss": 0.0, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 0.584970377299657, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.190328514050365e-05, | |
| "loss": 0.0, | |
| "step": 469 | |
| }, | |
| { | |
| "epoch": 0.5862176488930465, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.1492030264187e-05, | |
| "loss": 0.0, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.587464920486436, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.108109926331238e-05, | |
| "loss": 0.0, | |
| "step": 471 | |
| }, | |
| { | |
| "epoch": 0.5887121920798254, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.067049932886084e-05, | |
| "loss": 0.0, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 0.5899594636732148, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.026023764601999e-05, | |
| "loss": 0.0, | |
| "step": 473 | |
| }, | |
| { | |
| "epoch": 0.5912067352666043, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.985032139405836e-05, | |
| "loss": 0.0, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 0.5924540068599937, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.944075774619963e-05, | |
| "loss": 0.0, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.5937012784533833, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.903155386949723e-05, | |
| "loss": 0.0, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 0.5949485500467727, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.862271692470884e-05, | |
| "loss": 0.0, | |
| "step": 477 | |
| }, | |
| { | |
| "epoch": 0.5961958216401622, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.821425406617106e-05, | |
| "loss": 0.0, | |
| "step": 478 | |
| }, | |
| { | |
| "epoch": 0.5974430932335516, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.780617244167432e-05, | |
| "loss": 0.0, | |
| "step": 479 | |
| }, | |
| { | |
| "epoch": 0.598690364826941, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.739847919233781e-05, | |
| "loss": 0.0, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.5999376364203305, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.699118145248434e-05, | |
| "loss": 0.0, | |
| "step": 481 | |
| }, | |
| { | |
| "epoch": 0.60118490801372, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.658428634951562e-05, | |
| "loss": 0.0, | |
| "step": 482 | |
| }, | |
| { | |
| "epoch": 0.6024321796071095, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.617780100378756e-05, | |
| "loss": 0.0, | |
| "step": 483 | |
| }, | |
| { | |
| "epoch": 0.6036794512004989, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.57717325284856e-05, | |
| "loss": 0.0, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 0.6049267227938884, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.536608802950027e-05, | |
| "loss": 0.0, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.6061739943872778, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.496087460530285e-05, | |
| "loss": 0.0, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 0.6074212659806673, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.455609934682116e-05, | |
| "loss": 0.0, | |
| "step": 487 | |
| }, | |
| { | |
| "epoch": 0.6086685375740567, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.415176933731536e-05, | |
| "loss": 0.0, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 0.6099158091674463, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.374789165225416e-05, | |
| "loss": 0.0, | |
| "step": 489 | |
| }, | |
| { | |
| "epoch": 0.6111630807608357, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.334447335919096e-05, | |
| "loss": 0.0, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.6124103523542251, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.294152151764006e-05, | |
| "loss": 0.0, | |
| "step": 491 | |
| }, | |
| { | |
| "epoch": 0.6136576239476146, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.253904317895332e-05, | |
| "loss": 0.0, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 0.614904895541004, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.21370453861966e-05, | |
| "loss": 0.0, | |
| "step": 493 | |
| }, | |
| { | |
| "epoch": 0.6161521671343935, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.173553517402652e-05, | |
| "loss": 0.0, | |
| "step": 494 | |
| }, | |
| { | |
| "epoch": 0.617399438727783, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.133451956856751e-05, | |
| "loss": 0.0, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.6186467103211725, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.093400558728871e-05, | |
| "loss": 0.0, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 0.6198939819145619, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.053400023888115e-05, | |
| "loss": 0.0, | |
| "step": 497 | |
| }, | |
| { | |
| "epoch": 0.6211412535079514, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.013451052313534e-05, | |
| "loss": 0.0, | |
| "step": 498 | |
| }, | |
| { | |
| "epoch": 0.6223885251013408, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.973554343081846e-05, | |
| "loss": 0.0, | |
| "step": 499 | |
| }, | |
| { | |
| "epoch": 0.6236357966947302, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.933710594355225e-05, | |
| "loss": 0.0, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.6248830682881198, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.893920503369068e-05, | |
| "loss": 0.0, | |
| "step": 501 | |
| }, | |
| { | |
| "epoch": 0.6261303398815092, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.854184766419812e-05, | |
| "loss": 0.0, | |
| "step": 502 | |
| }, | |
| { | |
| "epoch": 0.6273776114748987, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.814504078852729e-05, | |
| "loss": 0.0, | |
| "step": 503 | |
| }, | |
| { | |
| "epoch": 0.6286248830682881, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.774879135049787e-05, | |
| "loss": 0.0, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 0.6298721546616776, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.735310628417461e-05, | |
| "loss": 0.0, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.631119426255067, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.695799251374625e-05, | |
| "loss": 0.0, | |
| "step": 506 | |
| }, | |
| { | |
| "epoch": 0.6323666978484564, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.656345695340431e-05, | |
| "loss": 0.0, | |
| "step": 507 | |
| }, | |
| { | |
| "epoch": 0.633613969441846, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.616950650722205e-05, | |
| "loss": 0.0, | |
| "step": 508 | |
| }, | |
| { | |
| "epoch": 0.6348612410352354, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.577614806903365e-05, | |
| "loss": 0.0, | |
| "step": 509 | |
| }, | |
| { | |
| "epoch": 0.6361085126286249, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.538338852231367e-05, | |
| "loss": 0.0, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.6373557842220143, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.499123474005647e-05, | |
| "loss": 0.0, | |
| "step": 511 | |
| }, | |
| { | |
| "epoch": 0.6386030558154038, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.4599693584656e-05, | |
| "loss": 0.0, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 0.6398503274087932, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.420877190778569e-05, | |
| "loss": 0.0, | |
| "step": 513 | |
| }, | |
| { | |
| "epoch": 0.6410975990021828, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.381847655027864e-05, | |
| "loss": 0.0, | |
| "step": 514 | |
| }, | |
| { | |
| "epoch": 0.6423448705955722, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.342881434200765e-05, | |
| "loss": 0.0, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 0.6435921421889617, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.303979210176614e-05, | |
| "loss": 0.0, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 0.6448394137823511, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.26514166371484e-05, | |
| "loss": 0.0, | |
| "step": 517 | |
| }, | |
| { | |
| "epoch": 0.6460866853757405, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.226369474443072e-05, | |
| "loss": 0.0, | |
| "step": 518 | |
| }, | |
| { | |
| "epoch": 0.64733395696913, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.18766332084523e-05, | |
| "loss": 0.0, | |
| "step": 519 | |
| }, | |
| { | |
| "epoch": 0.6485812285625195, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.149023880249665e-05, | |
| "loss": 0.0, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.649828500155909, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.110451828817298e-05, | |
| "loss": 0.0, | |
| "step": 521 | |
| }, | |
| { | |
| "epoch": 0.6510757717492984, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.071947841529801e-05, | |
| "loss": 0.0, | |
| "step": 522 | |
| }, | |
| { | |
| "epoch": 0.6523230433426879, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.03351259217776e-05, | |
| "loss": 0.0, | |
| "step": 523 | |
| }, | |
| { | |
| "epoch": 0.6535703149360773, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.995146753348909e-05, | |
| "loss": 0.0, | |
| "step": 524 | |
| }, | |
| { | |
| "epoch": 0.6548175865294668, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.9568509964163464e-05, | |
| "loss": 0.0, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.6560648581228562, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.9186259915267916e-05, | |
| "loss": 0.0, | |
| "step": 526 | |
| }, | |
| { | |
| "epoch": 0.6573121297162458, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.880472407588857e-05, | |
| "loss": 0.0, | |
| "step": 527 | |
| }, | |
| { | |
| "epoch": 0.6585594013096352, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.842390912261344e-05, | |
| "loss": 0.0, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 0.6598066729030246, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.8043821719415534e-05, | |
| "loss": 0.0, | |
| "step": 529 | |
| }, | |
| { | |
| "epoch": 0.6610539444964141, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.7664468517536395e-05, | |
| "loss": 0.0, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.6623012160898035, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.728585615536946e-05, | |
| "loss": 0.0, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 0.663548487683193, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.6907991258344e-05, | |
| "loss": 0.0, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 0.6647957592765825, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.6530880438809494e-05, | |
| "loss": 0.0, | |
| "step": 533 | |
| }, | |
| { | |
| "epoch": 0.666043030869972, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.615453029591935e-05, | |
| "loss": 0.0, | |
| "step": 534 | |
| }, | |
| { | |
| "epoch": 0.6672903024633614, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.5778947415515784e-05, | |
| "loss": 0.0, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 0.6685375740567508, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.540413837001459e-05, | |
| "loss": 0.0, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 0.6697848456501403, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.50301097182899e-05, | |
| "loss": 0.0, | |
| "step": 537 | |
| }, | |
| { | |
| "epoch": 0.6710321172435297, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.465686800555967e-05, | |
| "loss": 0.0, | |
| "step": 538 | |
| }, | |
| { | |
| "epoch": 0.6722793888369193, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.4284419763271e-05, | |
| "loss": 0.0, | |
| "step": 539 | |
| }, | |
| { | |
| "epoch": 0.6735266604303087, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.391277150898575e-05, | |
| "loss": 0.0, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.6747739320236982, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.354192974626674e-05, | |
| "loss": 0.0, | |
| "step": 541 | |
| }, | |
| { | |
| "epoch": 0.6760212036170876, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.317190096456368e-05, | |
| "loss": 0.0, | |
| "step": 542 | |
| }, | |
| { | |
| "epoch": 0.6772684752104771, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.2802691639099834e-05, | |
| "loss": 0.0, | |
| "step": 543 | |
| }, | |
| { | |
| "epoch": 0.6785157468038665, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.24343082307585e-05, | |
| "loss": 0.0, | |
| "step": 544 | |
| }, | |
| { | |
| "epoch": 0.679763018397256, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.206675718597012e-05, | |
| "loss": 0.0, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 0.6810102899906455, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.1700044936599434e-05, | |
| "loss": 0.0, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 0.6822575615840349, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.133417789983277e-05, | |
| "loss": 0.0, | |
| "step": 547 | |
| }, | |
| { | |
| "epoch": 0.6835048331774244, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.0969162478066055e-05, | |
| "loss": 0.0, | |
| "step": 548 | |
| }, | |
| { | |
| "epoch": 0.6847521047708138, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.060500505879244e-05, | |
| "loss": 0.0, | |
| "step": 549 | |
| }, | |
| { | |
| "epoch": 0.6859993763642033, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.0241712014490684e-05, | |
| "loss": 0.0, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.6872466479575927, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.9879289702513845e-05, | |
| "loss": 0.0, | |
| "step": 551 | |
| }, | |
| { | |
| "epoch": 0.6884939195509823, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.95177444649776e-05, | |
| "loss": 0.0, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 0.6897411911443717, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.9157082628649545e-05, | |
| "loss": 0.0, | |
| "step": 553 | |
| }, | |
| { | |
| "epoch": 0.6909884627377612, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.87973105048385e-05, | |
| "loss": 0.0, | |
| "step": 554 | |
| }, | |
| { | |
| "epoch": 0.6922357343311506, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.8438434389283895e-05, | |
| "loss": 0.0, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 0.69348300592454, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.8080460562045736e-05, | |
| "loss": 0.0, | |
| "step": 556 | |
| }, | |
| { | |
| "epoch": 0.6947302775179295, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.7723395287394746e-05, | |
| "loss": 0.0, | |
| "step": 557 | |
| }, | |
| { | |
| "epoch": 0.695977549111319, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.736724481370248e-05, | |
| "loss": 0.0, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 0.6972248207047085, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.701201537333237e-05, | |
| "loss": 0.0, | |
| "step": 559 | |
| }, | |
| { | |
| "epoch": 0.6984720922980979, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.6657713182530316e-05, | |
| "loss": 0.0, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.6997193638914874, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.630434444131615e-05, | |
| "loss": 0.0, | |
| "step": 561 | |
| }, | |
| { | |
| "epoch": 0.7009666354848768, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.595191533337494e-05, | |
| "loss": 0.0, | |
| "step": 562 | |
| }, | |
| { | |
| "epoch": 0.7022139070782663, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.560043202594899e-05, | |
| "loss": 0.0, | |
| "step": 563 | |
| }, | |
| { | |
| "epoch": 0.7034611786716558, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.524990066972982e-05, | |
| "loss": 0.0, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 0.7047084502650452, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.4900327398750363e-05, | |
| "loss": 0.0, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 0.7059557218584347, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.4551718330278006e-05, | |
| "loss": 0.0, | |
| "step": 566 | |
| }, | |
| { | |
| "epoch": 0.7072029934518241, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.4204079564707144e-05, | |
| "loss": 0.0, | |
| "step": 567 | |
| }, | |
| { | |
| "epoch": 0.7084502650452136, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.3857417185452644e-05, | |
| "loss": 0.0, | |
| "step": 568 | |
| }, | |
| { | |
| "epoch": 0.709697536638603, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.351173725884351e-05, | |
| "loss": 0.0, | |
| "step": 569 | |
| }, | |
| { | |
| "epoch": 0.7109448082319925, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.3167045834016326e-05, | |
| "loss": 0.0, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.712192079825382, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.282334894280986e-05, | |
| "loss": 0.0, | |
| "step": 571 | |
| }, | |
| { | |
| "epoch": 0.7134393514187715, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2480652599659154e-05, | |
| "loss": 0.0, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 0.7146866230121609, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.213896280149041e-05, | |
| "loss": 0.0, | |
| "step": 573 | |
| }, | |
| { | |
| "epoch": 0.7159338946055503, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.179828552761617e-05, | |
| "loss": 0.0, | |
| "step": 574 | |
| }, | |
| { | |
| "epoch": 0.7171811661989398, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.1458626739630526e-05, | |
| "loss": 0.0, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.7184284377923292, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.1119992381304754e-05, | |
| "loss": 0.0, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 0.7196757093857188, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.078238837848352e-05, | |
| "loss": 0.0, | |
| "step": 577 | |
| }, | |
| { | |
| "epoch": 0.7209229809791082, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.04458206389809e-05, | |
| "loss": 0.0, | |
| "step": 578 | |
| }, | |
| { | |
| "epoch": 0.7221702525724977, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.011029505247732e-05, | |
| "loss": 0.0, | |
| "step": 579 | |
| }, | |
| { | |
| "epoch": 0.7234175241658871, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.977581749041616e-05, | |
| "loss": 0.0, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.7246647957592766, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.9442393805901245e-05, | |
| "loss": 0.0, | |
| "step": 581 | |
| }, | |
| { | |
| "epoch": 0.725912067352666, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.91100298335944e-05, | |
| "loss": 0.0, | |
| "step": 582 | |
| }, | |
| { | |
| "epoch": 0.7271593389460556, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.877873138961311e-05, | |
| "loss": 0.0, | |
| "step": 583 | |
| }, | |
| { | |
| "epoch": 0.728406610539445, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.844850427142914e-05, | |
| "loss": 0.0, | |
| "step": 584 | |
| }, | |
| { | |
| "epoch": 0.7296538821328344, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.811935425776667e-05, | |
| "loss": 0.0, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 0.7309011537262239, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.779128710850151e-05, | |
| "loss": 0.0, | |
| "step": 586 | |
| }, | |
| { | |
| "epoch": 0.7321484253196133, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.7464308564560106e-05, | |
| "loss": 0.0, | |
| "step": 587 | |
| }, | |
| { | |
| "epoch": 0.7333956969130028, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.71384243478191e-05, | |
| "loss": 0.0, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 0.7346429685063922, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.681364016100535e-05, | |
| "loss": 0.0, | |
| "step": 589 | |
| }, | |
| { | |
| "epoch": 0.7358902400997818, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.64899616875959e-05, | |
| "loss": 0.0, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.7371375116931712, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.616739459171866e-05, | |
| "loss": 0.0, | |
| "step": 591 | |
| }, | |
| { | |
| "epoch": 0.7383847832865607, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5845944518053376e-05, | |
| "loss": 0.0, | |
| "step": 592 | |
| }, | |
| { | |
| "epoch": 0.7396320548799501, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.552561709173266e-05, | |
| "loss": 0.0, | |
| "step": 593 | |
| }, | |
| { | |
| "epoch": 0.7408793264733395, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.520641791824374e-05, | |
| "loss": 0.0, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 0.742126598066729, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.488835258333014e-05, | |
| "loss": 0.0, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.7433738696601185, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4571426652894144e-05, | |
| "loss": 0.0, | |
| "step": 596 | |
| }, | |
| { | |
| "epoch": 0.744621141253508, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4255645672899325e-05, | |
| "loss": 0.0, | |
| "step": 597 | |
| }, | |
| { | |
| "epoch": 0.7458684128468974, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3941015169273524e-05, | |
| "loss": 0.0, | |
| "step": 598 | |
| }, | |
| { | |
| "epoch": 0.7471156844402869, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.362754064781202e-05, | |
| "loss": 0.0, | |
| "step": 599 | |
| }, | |
| { | |
| "epoch": 0.7483629560336763, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.331522759408138e-05, | |
| "loss": 0.0, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.7496102276270658, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.300408147332327e-05, | |
| "loss": 0.0, | |
| "step": 601 | |
| }, | |
| { | |
| "epoch": 0.7508574992204553, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.269410773035903e-05, | |
| "loss": 0.0, | |
| "step": 602 | |
| }, | |
| { | |
| "epoch": 0.7521047708138447, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.238531178949417e-05, | |
| "loss": 0.0, | |
| "step": 603 | |
| }, | |
| { | |
| "epoch": 0.7521047708138447, | |
| "eval_loss": NaN, | |
| "eval_runtime": 60.7212, | |
| "eval_samples_per_second": 22.249, | |
| "eval_steps_per_second": 5.566, | |
| "step": 603 | |
| }, | |
| { | |
| "epoch": 0.7533520424072342, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.207769905442359e-05, | |
| "loss": 0.0, | |
| "step": 604 | |
| }, | |
| { | |
| "epoch": 0.7545993140006236, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.177127490813706e-05, | |
| "loss": 0.0, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 0.7558465855940131, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.1466044712824805e-05, | |
| "loss": 0.0, | |
| "step": 606 | |
| }, | |
| { | |
| "epoch": 0.7570938571874025, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.1162013809783955e-05, | |
| "loss": 0.0, | |
| "step": 607 | |
| }, | |
| { | |
| "epoch": 0.758341128780792, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0859187519324806e-05, | |
| "loss": 0.0, | |
| "step": 608 | |
| }, | |
| { | |
| "epoch": 0.7595884003741815, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.055757114067794e-05, | |
| "loss": 0.0, | |
| "step": 609 | |
| }, | |
| { | |
| "epoch": 0.760835671967571, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.025716995190141e-05, | |
| "loss": 0.0, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.7620829435609604, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.995798920978825e-05, | |
| "loss": 0.0, | |
| "step": 611 | |
| }, | |
| { | |
| "epoch": 0.7633302151543498, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.966003414977475e-05, | |
| "loss": 0.0, | |
| "step": 612 | |
| }, | |
| { | |
| "epoch": 0.7645774867477393, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9363309985848585e-05, | |
| "loss": 0.0, | |
| "step": 613 | |
| }, | |
| { | |
| "epoch": 0.7658247583411287, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9067821910457704e-05, | |
| "loss": 0.0, | |
| "step": 614 | |
| }, | |
| { | |
| "epoch": 0.7670720299345183, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.877357509441947e-05, | |
| "loss": 0.0, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 0.7683193015279077, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8480574686830142e-05, | |
| "loss": 0.0, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 0.7695665731212972, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8188825814974795e-05, | |
| "loss": 0.0, | |
| "step": 617 | |
| }, | |
| { | |
| "epoch": 0.7708138447146866, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7898333584237534e-05, | |
| "loss": 0.0, | |
| "step": 618 | |
| }, | |
| { | |
| "epoch": 0.7720611163080761, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7609103078012166e-05, | |
| "loss": 0.0, | |
| "step": 619 | |
| }, | |
| { | |
| "epoch": 0.7733083879014655, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7321139357613412e-05, | |
| "loss": 0.0, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.774555659494855, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.703444746218802e-05, | |
| "loss": 0.0, | |
| "step": 621 | |
| }, | |
| { | |
| "epoch": 0.7758029310882445, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6749032408626907e-05, | |
| "loss": 0.0, | |
| "step": 622 | |
| }, | |
| { | |
| "epoch": 0.7770502026816339, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.646489919147721e-05, | |
| "loss": 0.0, | |
| "step": 623 | |
| }, | |
| { | |
| "epoch": 0.7782974742750234, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6182052782854806e-05, | |
| "loss": 0.0, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 0.7795447458684128, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.59004981323575e-05, | |
| "loss": 0.0, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.7807920174618023, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5620240166978226e-05, | |
| "loss": 0.0, | |
| "step": 626 | |
| }, | |
| { | |
| "epoch": 0.7820392890551918, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5341283791018988e-05, | |
| "loss": 0.0, | |
| "step": 627 | |
| }, | |
| { | |
| "epoch": 0.7832865606485813, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5063633886004935e-05, | |
| "loss": 0.0, | |
| "step": 628 | |
| }, | |
| { | |
| "epoch": 0.7845338322419707, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4787295310598913e-05, | |
| "loss": 0.0, | |
| "step": 629 | |
| }, | |
| { | |
| "epoch": 0.7857811038353602, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.45122729005166e-05, | |
| "loss": 0.0, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.7870283754287496, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.423857146844164e-05, | |
| "loss": 0.0, | |
| "step": 631 | |
| }, | |
| { | |
| "epoch": 0.788275647022139, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3966195803941715e-05, | |
| "loss": 0.0, | |
| "step": 632 | |
| }, | |
| { | |
| "epoch": 0.7895229186155285, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3695150673384437e-05, | |
| "loss": 0.0, | |
| "step": 633 | |
| }, | |
| { | |
| "epoch": 0.790770190208918, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3425440819854185e-05, | |
| "loss": 0.0, | |
| "step": 634 | |
| }, | |
| { | |
| "epoch": 0.7920174618023075, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3157070963068984e-05, | |
| "loss": 0.0, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 0.7932647333956969, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2890045799297876e-05, | |
| "loss": 0.0, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 0.7945120049890864, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2624370001278838e-05, | |
| "loss": 0.0, | |
| "step": 637 | |
| }, | |
| { | |
| "epoch": 0.7957592765824758, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2360048218136985e-05, | |
| "loss": 0.0, | |
| "step": 638 | |
| }, | |
| { | |
| "epoch": 0.7970065481758652, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2097085075303138e-05, | |
| "loss": 0.0, | |
| "step": 639 | |
| }, | |
| { | |
| "epoch": 0.7982538197692548, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1835485174433002e-05, | |
| "loss": 0.0, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.7995010913626442, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1575253093326586e-05, | |
| "loss": 0.0, | |
| "step": 641 | |
| }, | |
| { | |
| "epoch": 0.8007483629560337, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.131639338584801e-05, | |
| "loss": 0.0, | |
| "step": 642 | |
| }, | |
| { | |
| "epoch": 0.8019956345494231, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1058910581846013e-05, | |
| "loss": 0.0, | |
| "step": 643 | |
| }, | |
| { | |
| "epoch": 0.8032429061428126, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0802809187074434e-05, | |
| "loss": 0.0, | |
| "step": 644 | |
| }, | |
| { | |
| "epoch": 0.804490177736202, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.05480936831136e-05, | |
| "loss": 0.0, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 0.8057374493295916, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0294768527291796e-05, | |
| "loss": 0.0, | |
| "step": 646 | |
| }, | |
| { | |
| "epoch": 0.806984720922981, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.004283815260717e-05, | |
| "loss": 0.0, | |
| "step": 647 | |
| }, | |
| { | |
| "epoch": 0.8082319925163705, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9792306967650398e-05, | |
| "loss": 0.0, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 0.8094792641097599, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9543179356527252e-05, | |
| "loss": 0.0, | |
| "step": 649 | |
| }, | |
| { | |
| "epoch": 0.8107265357031493, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9295459678782168e-05, | |
| "loss": 0.0, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.8119738072965388, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.904915226932169e-05, | |
| "loss": 0.0, | |
| "step": 651 | |
| }, | |
| { | |
| "epoch": 0.8132210788899282, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.88042614383388e-05, | |
| "loss": 0.0, | |
| "step": 652 | |
| }, | |
| { | |
| "epoch": 0.8144683504833178, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.856079147123746e-05, | |
| "loss": 0.0, | |
| "step": 653 | |
| }, | |
| { | |
| "epoch": 0.8157156220767072, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8318746628557526e-05, | |
| "loss": 0.0, | |
| "step": 654 | |
| }, | |
| { | |
| "epoch": 0.8169628936700967, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8078131145900267e-05, | |
| "loss": 0.0, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 0.8182101652634861, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7838949233854284e-05, | |
| "loss": 0.0, | |
| "step": 656 | |
| }, | |
| { | |
| "epoch": 0.8194574368568756, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.760120507792169e-05, | |
| "loss": 0.0, | |
| "step": 657 | |
| }, | |
| { | |
| "epoch": 0.820704708450265, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7364902838445106e-05, | |
| "loss": 0.0, | |
| "step": 658 | |
| }, | |
| { | |
| "epoch": 0.8219519800436546, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.713004665053457e-05, | |
| "loss": 0.0, | |
| "step": 659 | |
| }, | |
| { | |
| "epoch": 0.823199251637044, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6896640623995318e-05, | |
| "loss": 0.0, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.8244465232304334, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.666468884325596e-05, | |
| "loss": 0.0, | |
| "step": 661 | |
| }, | |
| { | |
| "epoch": 0.8256937948238229, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6434195367296802e-05, | |
| "loss": 0.0, | |
| "step": 662 | |
| }, | |
| { | |
| "epoch": 0.8269410664172123, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6205164229578994e-05, | |
| "loss": 0.0, | |
| "step": 663 | |
| }, | |
| { | |
| "epoch": 0.8281883380106018, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5977599437973867e-05, | |
| "loss": 0.0, | |
| "step": 664 | |
| }, | |
| { | |
| "epoch": 0.8294356096039913, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5751504974692733e-05, | |
| "loss": 0.0, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 0.8306828811973808, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.55268847962174e-05, | |
| "loss": 0.0, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 0.8319301527907702, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5303742833230673e-05, | |
| "loss": 0.0, | |
| "step": 667 | |
| }, | |
| { | |
| "epoch": 0.8331774243841596, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5082082990547796e-05, | |
| "loss": 0.0, | |
| "step": 668 | |
| }, | |
| { | |
| "epoch": 0.8344246959775491, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4861909147048025e-05, | |
| "loss": 0.0, | |
| "step": 669 | |
| }, | |
| { | |
| "epoch": 0.8356719675709385, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.464322515560671e-05, | |
| "loss": 0.0, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.836919239164328, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4426034843027969e-05, | |
| "loss": 0.0, | |
| "step": 671 | |
| }, | |
| { | |
| "epoch": 0.8381665107577175, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4210342009977628e-05, | |
| "loss": 0.0, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 0.839413782351107, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3996150430916799e-05, | |
| "loss": 0.0, | |
| "step": 673 | |
| }, | |
| { | |
| "epoch": 0.8406610539444964, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.378346385403575e-05, | |
| "loss": 0.0, | |
| "step": 674 | |
| }, | |
| { | |
| "epoch": 0.8419083255378859, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.357228600118836e-05, | |
| "loss": 0.0, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.8431555971312753, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3362620567827033e-05, | |
| "loss": 0.0, | |
| "step": 676 | |
| }, | |
| { | |
| "epoch": 0.8444028687246647, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3154471222937903e-05, | |
| "loss": 0.0, | |
| "step": 677 | |
| }, | |
| { | |
| "epoch": 0.8456501403180543, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2947841608976718e-05, | |
| "loss": 0.0, | |
| "step": 678 | |
| }, | |
| { | |
| "epoch": 0.8468974119114437, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2742735341805145e-05, | |
| "loss": 0.0, | |
| "step": 679 | |
| }, | |
| { | |
| "epoch": 0.8481446835048332, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.253915601062734e-05, | |
| "loss": 0.0, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.8493919550982226, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2337107177927365e-05, | |
| "loss": 0.0, | |
| "step": 681 | |
| }, | |
| { | |
| "epoch": 0.8506392266916121, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.213659237940662e-05, | |
| "loss": 0.0, | |
| "step": 682 | |
| }, | |
| { | |
| "epoch": 0.8518864982850015, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1937615123922052e-05, | |
| "loss": 0.0, | |
| "step": 683 | |
| }, | |
| { | |
| "epoch": 0.8531337698783911, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.174017889342489e-05, | |
| "loss": 0.0, | |
| "step": 684 | |
| }, | |
| { | |
| "epoch": 0.8543810414717805, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1544287142899446e-05, | |
| "loss": 0.0, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 0.85562831306517, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1349943300302913e-05, | |
| "loss": 0.0, | |
| "step": 686 | |
| }, | |
| { | |
| "epoch": 0.8568755846585594, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1157150766505253e-05, | |
| "loss": 0.0, | |
| "step": 687 | |
| }, | |
| { | |
| "epoch": 0.8581228562519488, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0965912915229625e-05, | |
| "loss": 0.0, | |
| "step": 688 | |
| }, | |
| { | |
| "epoch": 0.8593701278453383, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0776233092993527e-05, | |
| "loss": 0.0, | |
| "step": 689 | |
| }, | |
| { | |
| "epoch": 0.8606173994387278, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0588114619050028e-05, | |
| "loss": 0.0, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.8618646710321173, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.040156078532989e-05, | |
| "loss": 0.0, | |
| "step": 691 | |
| }, | |
| { | |
| "epoch": 0.8631119426255067, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0216574856383742e-05, | |
| "loss": 0.0, | |
| "step": 692 | |
| }, | |
| { | |
| "epoch": 0.8643592142188962, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0033160069325166e-05, | |
| "loss": 0.0, | |
| "step": 693 | |
| }, | |
| { | |
| "epoch": 0.8656064858122856, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.851319633773926e-06, | |
| "loss": 0.0, | |
| "step": 694 | |
| }, | |
| { | |
| "epoch": 0.866853757405675, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.671056731799777e-06, | |
| "loss": 0.0, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 0.8681010289990645, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.49237451786692e-06, | |
| "loss": 0.0, | |
| "step": 696 | |
| }, | |
| { | |
| "epoch": 0.869348300592454, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.315276118778627e-06, | |
| "loss": 0.0, | |
| "step": 697 | |
| }, | |
| { | |
| "epoch": 0.8705955721858435, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.139764633622617e-06, | |
| "loss": 0.0, | |
| "step": 698 | |
| }, | |
| { | |
| "epoch": 0.8718428437792329, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.965843133716933e-06, | |
| "loss": 0.0, | |
| "step": 699 | |
| }, | |
| { | |
| "epoch": 0.8730901153726224, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.793514662555946e-06, | |
| "loss": 0.0, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.8743373869660118, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.622782235757276e-06, | |
| "loss": 0.0, | |
| "step": 701 | |
| }, | |
| { | |
| "epoch": 0.8755846585594013, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.453648841009021e-06, | |
| "loss": 0.0, | |
| "step": 702 | |
| }, | |
| { | |
| "epoch": 0.8768319301527908, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.286117438017337e-06, | |
| "loss": 0.0, | |
| "step": 703 | |
| }, | |
| { | |
| "epoch": 0.8780792017461803, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.120190958454843e-06, | |
| "loss": 0.0, | |
| "step": 704 | |
| }, | |
| { | |
| "epoch": 0.8793264733395697, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.955872305909152e-06, | |
| "loss": 0.0, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 0.8805737449329591, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.793164355832127e-06, | |
| "loss": 0.0, | |
| "step": 706 | |
| }, | |
| { | |
| "epoch": 0.8818210165263486, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.632069955489585e-06, | |
| "loss": 0.0, | |
| "step": 707 | |
| }, | |
| { | |
| "epoch": 0.883068288119738, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.472591923911398e-06, | |
| "loss": 0.0, | |
| "step": 708 | |
| }, | |
| { | |
| "epoch": 0.8843155597131276, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.314733051842282e-06, | |
| "loss": 0.0, | |
| "step": 709 | |
| }, | |
| { | |
| "epoch": 0.885562831306517, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.158496101692802e-06, | |
| "loss": 0.0, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.8868101028999065, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.003883807491185e-06, | |
| "loss": 0.0, | |
| "step": 711 | |
| }, | |
| { | |
| "epoch": 0.8880573744932959, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.85089887483541e-06, | |
| "loss": 0.0, | |
| "step": 712 | |
| }, | |
| { | |
| "epoch": 0.8893046460866854, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.699543980845801e-06, | |
| "loss": 0.0, | |
| "step": 713 | |
| }, | |
| { | |
| "epoch": 0.8905519176800748, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.549821774118325e-06, | |
| "loss": 0.0, | |
| "step": 714 | |
| }, | |
| { | |
| "epoch": 0.8917991892734642, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.401734874678089e-06, | |
| "loss": 0.0, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 0.8930464608668538, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.255285873933569e-06, | |
| "loss": 0.0, | |
| "step": 716 | |
| }, | |
| { | |
| "epoch": 0.8942937324602432, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.110477334631326e-06, | |
| "loss": 0.0, | |
| "step": 717 | |
| }, | |
| { | |
| "epoch": 0.8955410040536327, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.967311790811014e-06, | |
| "loss": 0.0, | |
| "step": 718 | |
| }, | |
| { | |
| "epoch": 0.8967882756470221, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.825791747761123e-06, | |
| "loss": 0.0, | |
| "step": 719 | |
| }, | |
| { | |
| "epoch": 0.8980355472404116, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.685919681975149e-06, | |
| "loss": 0.0, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.899282818833801, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.547698041108229e-06, | |
| "loss": 0.0, | |
| "step": 721 | |
| }, | |
| { | |
| "epoch": 0.9005300904271906, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.4111292439342986e-06, | |
| "loss": 0.0, | |
| "step": 722 | |
| }, | |
| { | |
| "epoch": 0.90177736202058, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.276215680303831e-06, | |
| "loss": 0.0, | |
| "step": 723 | |
| }, | |
| { | |
| "epoch": 0.9030246336139695, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.14295971110188e-06, | |
| "loss": 0.0, | |
| "step": 724 | |
| }, | |
| { | |
| "epoch": 0.9042719052073589, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.011363668206948e-06, | |
| "loss": 0.0, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.9055191768007483, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.881429854450004e-06, | |
| "loss": 0.0, | |
| "step": 726 | |
| }, | |
| { | |
| "epoch": 0.9067664483941378, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.753160543574331e-06, | |
| "loss": 0.0, | |
| "step": 727 | |
| }, | |
| { | |
| "epoch": 0.9080137199875273, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.626557980195623e-06, | |
| "loss": 0.0, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 0.9092609915809168, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.501624379762803e-06, | |
| "loss": 0.0, | |
| "step": 729 | |
| }, | |
| { | |
| "epoch": 0.9105082631743062, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.3783619285191705e-06, | |
| "loss": 0.0, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.9117555347676957, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2567727834641915e-06, | |
| "loss": 0.0, | |
| "step": 731 | |
| }, | |
| { | |
| "epoch": 0.9130028063610851, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.136859072315758e-06, | |
| "loss": 0.0, | |
| "step": 732 | |
| }, | |
| { | |
| "epoch": 0.9142500779544745, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.018622893472912e-06, | |
| "loss": 0.0, | |
| "step": 733 | |
| }, | |
| { | |
| "epoch": 0.915497349547864, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.902066315979158e-06, | |
| "loss": 0.0, | |
| "step": 734 | |
| }, | |
| { | |
| "epoch": 0.9167446211412535, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.787191379486288e-06, | |
| "loss": 0.0, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 0.917991892734643, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.674000094218577e-06, | |
| "loss": 0.0, | |
| "step": 736 | |
| }, | |
| { | |
| "epoch": 0.9192391643280324, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.562494440937769e-06, | |
| "loss": 0.0, | |
| "step": 737 | |
| }, | |
| { | |
| "epoch": 0.9204864359214219, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4526763709082476e-06, | |
| "loss": 0.0, | |
| "step": 738 | |
| }, | |
| { | |
| "epoch": 0.9217337075148113, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.344547805862985e-06, | |
| "loss": 0.0, | |
| "step": 739 | |
| }, | |
| { | |
| "epoch": 0.9229809791082008, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.2381106379699488e-06, | |
| "loss": 0.0, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.9242282507015903, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.1333667297989035e-06, | |
| "loss": 0.0, | |
| "step": 741 | |
| }, | |
| { | |
| "epoch": 0.9254755222949798, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.030317914288816e-06, | |
| "loss": 0.0, | |
| "step": 742 | |
| }, | |
| { | |
| "epoch": 0.9267227938883692, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.928965994715882e-06, | |
| "loss": 0.0, | |
| "step": 743 | |
| }, | |
| { | |
| "epoch": 0.9279700654817586, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8293127446618383e-06, | |
| "loss": 0.0, | |
| "step": 744 | |
| }, | |
| { | |
| "epoch": 0.9292173370751481, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7313599079830666e-06, | |
| "loss": 0.0, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 0.9304646086685375, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.63510919877995e-06, | |
| "loss": 0.0, | |
| "step": 746 | |
| }, | |
| { | |
| "epoch": 0.9317118802619271, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.540562301366922e-06, | |
| "loss": 0.0, | |
| "step": 747 | |
| }, | |
| { | |
| "epoch": 0.9329591518553165, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.447720870243064e-06, | |
| "loss": 0.0, | |
| "step": 748 | |
| }, | |
| { | |
| "epoch": 0.934206423448706, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3565865300630206e-06, | |
| "loss": 0.0, | |
| "step": 749 | |
| }, | |
| { | |
| "epoch": 0.9354536950420954, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.267160875608687e-06, | |
| "loss": 0.0, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.9367009666354849, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.179445471761221e-06, | |
| "loss": 0.0, | |
| "step": 751 | |
| }, | |
| { | |
| "epoch": 0.9379482382288743, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0934418534737098e-06, | |
| "loss": 0.0, | |
| "step": 752 | |
| }, | |
| { | |
| "epoch": 0.9391955098222639, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0091515257442904e-06, | |
| "loss": 0.0, | |
| "step": 753 | |
| }, | |
| { | |
| "epoch": 0.9404427814156533, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.926575963589805e-06, | |
| "loss": 0.0, | |
| "step": 754 | |
| }, | |
| { | |
| "epoch": 0.9416900530090427, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8457166120199987e-06, | |
| "loss": 0.0, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 0.9429373246024322, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7665748860122512e-06, | |
| "loss": 0.0, | |
| "step": 756 | |
| }, | |
| { | |
| "epoch": 0.9441845961958216, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.689152170486752e-06, | |
| "loss": 0.0, | |
| "step": 757 | |
| }, | |
| { | |
| "epoch": 0.9454318677892111, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6134498202823645e-06, | |
| "loss": 0.0, | |
| "step": 758 | |
| }, | |
| { | |
| "epoch": 0.9466791393826005, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5394691601328338e-06, | |
| "loss": 0.0, | |
| "step": 759 | |
| }, | |
| { | |
| "epoch": 0.9479264109759901, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.467211484643627e-06, | |
| "loss": 0.0, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.9491736825693795, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3966780582693185e-06, | |
| "loss": 0.0, | |
| "step": 761 | |
| }, | |
| { | |
| "epoch": 0.950420954162769, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3278701152913742e-06, | |
| "loss": 0.0, | |
| "step": 762 | |
| }, | |
| { | |
| "epoch": 0.9516682257561584, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2607888597966688e-06, | |
| "loss": 0.0, | |
| "step": 763 | |
| }, | |
| { | |
| "epoch": 0.9529154973495478, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.195435465656325e-06, | |
| "loss": 0.0, | |
| "step": 764 | |
| }, | |
| { | |
| "epoch": 0.9541627689429373, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.131811076505196e-06, | |
| "loss": 0.0, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 0.9554100405363268, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0699168057218823e-06, | |
| "loss": 0.0, | |
| "step": 766 | |
| }, | |
| { | |
| "epoch": 0.9566573121297163, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0097537364091914e-06, | |
| "loss": 0.0, | |
| "step": 767 | |
| }, | |
| { | |
| "epoch": 0.9579045837231057, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.513229213752417e-07, | |
| "loss": 0.0, | |
| "step": 768 | |
| }, | |
| { | |
| "epoch": 0.9591518553164952, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.946253831150109e-07, | |
| "loss": 0.0, | |
| "step": 769 | |
| }, | |
| { | |
| "epoch": 0.9603991269098846, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.396621137924388e-07, | |
| "loss": 0.0, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.961646398503274, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.864340752230859e-07, | |
| "loss": 0.0, | |
| "step": 771 | |
| }, | |
| { | |
| "epoch": 0.9628936700966636, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.349421988572691e-07, | |
| "loss": 0.0, | |
| "step": 772 | |
| }, | |
| { | |
| "epoch": 0.964140941690053, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.851873857638192e-07, | |
| "loss": 0.0, | |
| "step": 773 | |
| }, | |
| { | |
| "epoch": 0.9653882132834425, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.371705066142264e-07, | |
| "loss": 0.0, | |
| "step": 774 | |
| }, | |
| { | |
| "epoch": 0.9666354848768319, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.908924016674977e-07, | |
| "loss": 0.0, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.9678827564702214, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.463538807553903e-07, | |
| "loss": 0.0, | |
| "step": 776 | |
| }, | |
| { | |
| "epoch": 0.9691300280636108, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.035557232682564e-07, | |
| "loss": 0.0, | |
| "step": 777 | |
| }, | |
| { | |
| "epoch": 0.9703772996570003, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.624986781414098e-07, | |
| "loss": 0.0, | |
| "step": 778 | |
| }, | |
| { | |
| "epoch": 0.9716245712503898, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.231834638420362e-07, | |
| "loss": 0.0, | |
| "step": 779 | |
| }, | |
| { | |
| "epoch": 0.9728718428437793, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8561076835657017e-07, | |
| "loss": 0.0, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.9741191144371687, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4978124917871556e-07, | |
| "loss": 0.0, | |
| "step": 781 | |
| }, | |
| { | |
| "epoch": 0.9753663860305581, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.1569553329788836e-07, | |
| "loss": 0.0, | |
| "step": 782 | |
| }, | |
| { | |
| "epoch": 0.9766136576239476, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8335421718829193e-07, | |
| "loss": 0.0, | |
| "step": 783 | |
| }, | |
| { | |
| "epoch": 0.977860929217337, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.527578667984365e-07, | |
| "loss": 0.0, | |
| "step": 784 | |
| }, | |
| { | |
| "epoch": 0.9791082008107266, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.239070175412694e-07, | |
| "loss": 0.0, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 0.980355472404116, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9680217428479364e-07, | |
| "loss": 0.0, | |
| "step": 786 | |
| }, | |
| { | |
| "epoch": 0.9816027439975055, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.714438113431971e-07, | |
| "loss": 0.0, | |
| "step": 787 | |
| }, | |
| { | |
| "epoch": 0.9828500155908949, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4783237246862592e-07, | |
| "loss": 0.0, | |
| "step": 788 | |
| }, | |
| { | |
| "epoch": 0.9840972871842844, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.259682708433574e-07, | |
| "loss": 0.0, | |
| "step": 789 | |
| }, | |
| { | |
| "epoch": 0.9853445587776738, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0585188907260569e-07, | |
| "loss": 0.0, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.9865918303710633, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.748357917780503e-08, | |
| "loss": 0.0, | |
| "step": 791 | |
| }, | |
| { | |
| "epoch": 0.9878391019644528, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.086366259044796e-08, | |
| "loss": 0.0, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 0.9890863735578422, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.59924301464898e-08, | |
| "loss": 0.0, | |
| "step": 793 | |
| }, | |
| { | |
| "epoch": 0.9903336451512317, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.287014208120832e-08, | |
| "loss": 0.0, | |
| "step": 794 | |
| }, | |
| { | |
| "epoch": 0.9915809167446211, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.149702802470733e-08, | |
| "loss": 0.0, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 0.9928281883380106, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1873286997875498e-08, | |
| "loss": 0.0, | |
| "step": 796 | |
| }, | |
| { | |
| "epoch": 0.9940754599314, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3999087408866906e-08, | |
| "loss": 0.0, | |
| "step": 797 | |
| }, | |
| { | |
| "epoch": 0.9953227315247896, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.874567050214499e-09, | |
| "loss": 0.0, | |
| "step": 798 | |
| }, | |
| { | |
| "epoch": 0.996570003118179, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4998330963764705e-09, | |
| "loss": 0.0, | |
| "step": 799 | |
| }, | |
| { | |
| "epoch": 0.9978172747115684, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.749621018822041e-10, | |
| "loss": 0.0, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.9990645463049579, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 801 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 801, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 201, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.299641599763415e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |