| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 1.6799163179916317, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03347280334728033, | |
| "grad_norm": 8.088847160339355, | |
| "learning_rate": 5e-05, | |
| "loss": 7.826, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03347280334728033, | |
| "eval_loss": NaN, | |
| "eval_runtime": 6.3212, | |
| "eval_samples_per_second": 31.956, | |
| "eval_steps_per_second": 4.113, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06694560669456066, | |
| "grad_norm": 8.330794334411621, | |
| "learning_rate": 0.0001, | |
| "loss": 8.0513, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.100418410041841, | |
| "grad_norm": 8.672752380371094, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 7.5682, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.13389121338912133, | |
| "grad_norm": 9.171895980834961, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 5.607, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.16736401673640167, | |
| "grad_norm": 12.540803909301758, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.5742, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.200836820083682, | |
| "grad_norm": 6.736896991729736, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.4277, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.23430962343096234, | |
| "grad_norm": 5.682157039642334, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.5788, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.26778242677824265, | |
| "grad_norm": 6.538768291473389, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.0026, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.301255230125523, | |
| "grad_norm": 4.085902690887451, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.4155, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.33472803347280333, | |
| "grad_norm": 2.660781145095825, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.302, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3682008368200837, | |
| "grad_norm": 3.4498322010040283, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.2272, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.401673640167364, | |
| "grad_norm": 3.035562515258789, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.2806, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.4351464435146444, | |
| "grad_norm": 4.8460187911987305, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.3164, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.4686192468619247, | |
| "grad_norm": 2.6207001209259033, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.2605, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.502092050209205, | |
| "grad_norm": 3.7983176708221436, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.2615, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5355648535564853, | |
| "grad_norm": 2.213376998901367, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.2127, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.5690376569037657, | |
| "grad_norm": 3.4225707054138184, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.2296, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.602510460251046, | |
| "grad_norm": 1.8404970169067383, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.1837, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.6359832635983264, | |
| "grad_norm": 2.730863332748413, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.2082, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.6694560669456067, | |
| "grad_norm": 1.4051350355148315, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.2023, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.702928870292887, | |
| "grad_norm": 2.741030693054199, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.2204, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.7364016736401674, | |
| "grad_norm": 1.5392065048217773, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.2281, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.7698744769874477, | |
| "grad_norm": 0.6374655365943909, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.1378, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.803347280334728, | |
| "grad_norm": 1.2255406379699707, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.1448, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.8368200836820083, | |
| "grad_norm": 1.4551048278808594, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.1592, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8368200836820083, | |
| "eval_loss": NaN, | |
| "eval_runtime": 6.3155, | |
| "eval_samples_per_second": 31.985, | |
| "eval_steps_per_second": 4.117, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8702928870292888, | |
| "grad_norm": 1.2969869375228882, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1293, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.9037656903765691, | |
| "grad_norm": 1.183563470840454, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.1323, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.9372384937238494, | |
| "grad_norm": 0.6034805178642273, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.1447, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.9707112970711297, | |
| "grad_norm": 1.0187960863113403, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.1809, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.010460251046025, | |
| "grad_norm": 2.551266670227051, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.2435, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.0439330543933054, | |
| "grad_norm": 1.363511085510254, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.1345, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.0774058577405858, | |
| "grad_norm": 0.8237060308456421, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.1068, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.110878661087866, | |
| "grad_norm": 0.8394637107849121, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.1252, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.1443514644351465, | |
| "grad_norm": 1.3592426776885986, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.114, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.1778242677824267, | |
| "grad_norm": 0.8103972673416138, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.1411, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.211297071129707, | |
| "grad_norm": 0.5803283452987671, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.1132, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.2447698744769875, | |
| "grad_norm": 1.0763193368911743, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.1371, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.2782426778242677, | |
| "grad_norm": 1.7600771188735962, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.1414, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.3117154811715481, | |
| "grad_norm": 0.844605565071106, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.1074, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.3451882845188283, | |
| "grad_norm": 0.7922542095184326, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.1396, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.3786610878661087, | |
| "grad_norm": 0.7589727640151978, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.1046, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.4121338912133892, | |
| "grad_norm": 1.1158431768417358, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.1242, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.4456066945606696, | |
| "grad_norm": 0.8884672522544861, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.1562, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.4790794979079498, | |
| "grad_norm": 1.0795230865478516, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.1548, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.51255230125523, | |
| "grad_norm": 1.3964478969573975, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.1468, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.5460251046025104, | |
| "grad_norm": 0.47748827934265137, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.102, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.5794979079497908, | |
| "grad_norm": 0.47063204646110535, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.1303, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.6129707112970713, | |
| "grad_norm": 0.7242940068244934, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.1158, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.6464435146443515, | |
| "grad_norm": 0.6986421942710876, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.1134, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.6799163179916317, | |
| "grad_norm": 0.6429162621498108, | |
| "learning_rate": 0.0, | |
| "loss": 0.1399, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.6799163179916317, | |
| "eval_loss": NaN, | |
| "eval_runtime": 6.3067, | |
| "eval_samples_per_second": 32.029, | |
| "eval_steps_per_second": 4.123, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.968083617316864e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |