| { | |
| "best_metric": 1.7651193141937256, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.4672897196261682, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009345794392523364, | |
| "grad_norm": 0.20883876085281372, | |
| "learning_rate": 5e-05, | |
| "loss": 1.96, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009345794392523364, | |
| "eval_loss": 2.763558864593506, | |
| "eval_runtime": 15.5549, | |
| "eval_samples_per_second": 46.352, | |
| "eval_steps_per_second": 5.85, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.018691588785046728, | |
| "grad_norm": 0.3325205147266388, | |
| "learning_rate": 0.0001, | |
| "loss": 1.9598, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.028037383177570093, | |
| "grad_norm": 0.4296382665634155, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.1008, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.037383177570093455, | |
| "grad_norm": 0.5535058975219727, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.1672, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04672897196261682, | |
| "grad_norm": 0.9975932240486145, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.211, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.056074766355140186, | |
| "grad_norm": 0.9110355377197266, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.2146, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06542056074766354, | |
| "grad_norm": 0.7600714564323425, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.2267, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.07476635514018691, | |
| "grad_norm": 1.035683274269104, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.2748, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.08411214953271028, | |
| "grad_norm": 1.4653292894363403, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.0741, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.09345794392523364, | |
| "grad_norm": 1.9323017597198486, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.1013, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.102803738317757, | |
| "grad_norm": 3.514230251312256, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.2467, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.11214953271028037, | |
| "grad_norm": 5.160649299621582, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.5004, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.12149532710280374, | |
| "grad_norm": 1.7584232091903687, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.6738, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1308411214953271, | |
| "grad_norm": 2.204019546508789, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.9386, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.14018691588785046, | |
| "grad_norm": 2.1689414978027344, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.0005, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.14953271028037382, | |
| "grad_norm": 1.568786859512329, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.9803, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.1588785046728972, | |
| "grad_norm": 0.9446658492088318, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.9562, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.16822429906542055, | |
| "grad_norm": 0.4800756275653839, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.0307, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.17757009345794392, | |
| "grad_norm": 1.4060454368591309, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 2.0356, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.18691588785046728, | |
| "grad_norm": 1.863488793373108, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.9865, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.19626168224299065, | |
| "grad_norm": 2.1688661575317383, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.7282, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.205607476635514, | |
| "grad_norm": 2.732743501663208, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.8433, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.21495327102803738, | |
| "grad_norm": 3.2595133781433105, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.9288, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.22429906542056074, | |
| "grad_norm": 4.204493045806885, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.7511, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2336448598130841, | |
| "grad_norm": 12.205188751220703, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 2.6001, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2336448598130841, | |
| "eval_loss": 1.8273491859436035, | |
| "eval_runtime": 16.0652, | |
| "eval_samples_per_second": 44.88, | |
| "eval_steps_per_second": 5.664, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.24299065420560748, | |
| "grad_norm": 0.3034875690937042, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5706, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.2523364485981308, | |
| "grad_norm": 0.6375843286514282, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.8791, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.2616822429906542, | |
| "grad_norm": 0.803412139415741, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.7813, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.27102803738317754, | |
| "grad_norm": 0.855148196220398, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.9444, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.2803738317757009, | |
| "grad_norm": 0.8513876795768738, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.8844, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2897196261682243, | |
| "grad_norm": 0.5708866715431213, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 2.0226, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.29906542056074764, | |
| "grad_norm": 0.487387090921402, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.9533, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.308411214953271, | |
| "grad_norm": 0.4321051836013794, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.8319, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.3177570093457944, | |
| "grad_norm": 0.47179585695266724, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.7397, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.32710280373831774, | |
| "grad_norm": 0.8138007521629333, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.7525, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3364485981308411, | |
| "grad_norm": 1.496353030204773, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.7203, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.34579439252336447, | |
| "grad_norm": 2.553820848464966, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.6391, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.35514018691588783, | |
| "grad_norm": 0.33150145411491394, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.6745, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.3644859813084112, | |
| "grad_norm": 0.23893839120864868, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.6146, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.37383177570093457, | |
| "grad_norm": 0.2919956147670746, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.8551, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.38317757009345793, | |
| "grad_norm": 0.33135730028152466, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.8577, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.3925233644859813, | |
| "grad_norm": 0.3283659815788269, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.8772, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.40186915887850466, | |
| "grad_norm": 0.30547505617141724, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.9234, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.411214953271028, | |
| "grad_norm": 0.3091796636581421, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.9524, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.4205607476635514, | |
| "grad_norm": 0.3936629891395569, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.9619, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.42990654205607476, | |
| "grad_norm": 0.4935019910335541, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.8527, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.4392523364485981, | |
| "grad_norm": 0.6257709264755249, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.6672, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.4485981308411215, | |
| "grad_norm": 1.0982800722122192, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.9316, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.45794392523364486, | |
| "grad_norm": 1.8124440908432007, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.7562, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.4672897196261682, | |
| "grad_norm": 5.867586135864258, | |
| "learning_rate": 0.0, | |
| "loss": 2.547, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4672897196261682, | |
| "eval_loss": 1.7651193141937256, | |
| "eval_runtime": 16.0955, | |
| "eval_samples_per_second": 44.795, | |
| "eval_steps_per_second": 5.654, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.0635096147099648e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |