| { | |
| "best_metric": 1.0031893253326416, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.0943396226415096, | |
| "eval_steps": 25, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.10062893081761007, | |
| "grad_norm": 0.3649255335330963, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3684, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.10062893081761007, | |
| "eval_loss": 1.4094620943069458, | |
| "eval_runtime": 6.6502, | |
| "eval_samples_per_second": 7.519, | |
| "eval_steps_per_second": 1.955, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.20125786163522014, | |
| "grad_norm": 0.30139613151550293, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2944, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.3018867924528302, | |
| "grad_norm": 0.33318033814430237, | |
| "learning_rate": 9.971704944519594e-05, | |
| "loss": 1.4054, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.4025157232704403, | |
| "grad_norm": 0.29401275515556335, | |
| "learning_rate": 9.887175604818206e-05, | |
| "loss": 1.2595, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.5031446540880503, | |
| "grad_norm": 0.31839922070503235, | |
| "learning_rate": 9.747474986387654e-05, | |
| "loss": 1.3276, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.6037735849056604, | |
| "grad_norm": 0.26795294880867004, | |
| "learning_rate": 9.554359905560886e-05, | |
| "loss": 1.1699, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.7044025157232704, | |
| "grad_norm": 0.24816186726093292, | |
| "learning_rate": 9.310258896527278e-05, | |
| "loss": 1.2222, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.8050314465408805, | |
| "grad_norm": 0.30153927206993103, | |
| "learning_rate": 9.018241671106134e-05, | |
| "loss": 1.1705, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.9056603773584906, | |
| "grad_norm": 0.28425419330596924, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.1431, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.0314465408805031, | |
| "grad_norm": 0.3570249378681183, | |
| "learning_rate": 8.305704108364301e-05, | |
| "loss": 1.3933, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.1320754716981132, | |
| "grad_norm": 0.23974794149398804, | |
| "learning_rate": 7.894144344319014e-05, | |
| "loss": 1.0418, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.2327044025157232, | |
| "grad_norm": 0.20039339363574982, | |
| "learning_rate": 7.452476826029011e-05, | |
| "loss": 0.9259, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 0.22616326808929443, | |
| "learning_rate": 6.986255778798253e-05, | |
| "loss": 1.1102, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.4339622641509435, | |
| "grad_norm": 0.18564777076244354, | |
| "learning_rate": 6.501344202803414e-05, | |
| "loss": 1.0617, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.5345911949685536, | |
| "grad_norm": 0.21298491954803467, | |
| "learning_rate": 6.003840142464886e-05, | |
| "loss": 1.0035, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.6352201257861636, | |
| "grad_norm": 0.19629953801631927, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.0182, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.7358490566037736, | |
| "grad_norm": 0.20243975520133972, | |
| "learning_rate": 4.9961598575351155e-05, | |
| "loss": 1.0048, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.8364779874213837, | |
| "grad_norm": 0.19140854477882385, | |
| "learning_rate": 4.498655797196586e-05, | |
| "loss": 0.998, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.9371069182389937, | |
| "grad_norm": 0.22857725620269775, | |
| "learning_rate": 4.01374422120175e-05, | |
| "loss": 1.1565, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 2.0628930817610063, | |
| "grad_norm": 0.20002713799476624, | |
| "learning_rate": 3.547523173970989e-05, | |
| "loss": 1.0742, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.1635220125786163, | |
| "grad_norm": 0.1631658673286438, | |
| "learning_rate": 3.105855655680986e-05, | |
| "loss": 0.9238, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 2.2641509433962264, | |
| "grad_norm": 0.18039830029010773, | |
| "learning_rate": 2.6942958916356998e-05, | |
| "loss": 0.9401, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.3647798742138364, | |
| "grad_norm": 0.18136851489543915, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.9679, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.4654088050314464, | |
| "grad_norm": 0.1782331019639969, | |
| "learning_rate": 1.981758328893866e-05, | |
| "loss": 0.9677, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.5660377358490565, | |
| "grad_norm": 0.1870107799768448, | |
| "learning_rate": 1.6897411034727218e-05, | |
| "loss": 0.9624, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.5660377358490565, | |
| "eval_loss": 1.0031893253326416, | |
| "eval_runtime": 6.6639, | |
| "eval_samples_per_second": 7.503, | |
| "eval_steps_per_second": 1.951, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 0.18223722279071808, | |
| "learning_rate": 1.4456400944391146e-05, | |
| "loss": 0.9384, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.767295597484277, | |
| "grad_norm": 0.1712333709001541, | |
| "learning_rate": 1.252525013612346e-05, | |
| "loss": 0.8976, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.867924528301887, | |
| "grad_norm": 0.1786852926015854, | |
| "learning_rate": 1.1128243951817937e-05, | |
| "loss": 0.91, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.968553459119497, | |
| "grad_norm": 0.21840958297252655, | |
| "learning_rate": 1.0282950554804085e-05, | |
| "loss": 1.1865, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 3.0943396226415096, | |
| "grad_norm": 0.17944976687431335, | |
| "learning_rate": 1e-05, | |
| "loss": 0.9459, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "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": 1.679578899551355e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |