| { | |
| "best_metric": 1.2678906917572021, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.04224757076468103, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0016899028305872412, | |
| "grad_norm": 1.6414018869400024, | |
| "learning_rate": 2e-05, | |
| "loss": 1.9963, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016899028305872412, | |
| "eval_loss": 1.6815574169158936, | |
| "eval_runtime": 24.144, | |
| "eval_samples_per_second": 10.355, | |
| "eval_steps_per_second": 5.177, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0033798056611744824, | |
| "grad_norm": 1.6165648698806763, | |
| "learning_rate": 4e-05, | |
| "loss": 1.5502, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005069708491761723, | |
| "grad_norm": 1.6910970211029053, | |
| "learning_rate": 6e-05, | |
| "loss": 1.6826, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006759611322348965, | |
| "grad_norm": 1.6870752573013306, | |
| "learning_rate": 8e-05, | |
| "loss": 1.5904, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.008449514152936205, | |
| "grad_norm": 1.5745503902435303, | |
| "learning_rate": 0.0001, | |
| "loss": 1.9308, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008449514152936205, | |
| "eval_loss": 1.6589946746826172, | |
| "eval_runtime": 22.7842, | |
| "eval_samples_per_second": 10.972, | |
| "eval_steps_per_second": 5.486, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.010139416983523447, | |
| "grad_norm": 1.6141451597213745, | |
| "learning_rate": 0.00012, | |
| "loss": 1.7972, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011829319814110688, | |
| "grad_norm": 1.4239213466644287, | |
| "learning_rate": 0.00014, | |
| "loss": 1.4184, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01351922264469793, | |
| "grad_norm": 1.4339450597763062, | |
| "learning_rate": 0.00016, | |
| "loss": 1.6283, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.015209125475285171, | |
| "grad_norm": 1.3972442150115967, | |
| "learning_rate": 0.00018, | |
| "loss": 1.5116, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01689902830587241, | |
| "grad_norm": 1.4806090593338013, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1733, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01689902830587241, | |
| "eval_loss": 1.4723725318908691, | |
| "eval_runtime": 22.7662, | |
| "eval_samples_per_second": 10.981, | |
| "eval_steps_per_second": 5.491, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.018588931136459652, | |
| "grad_norm": 1.509872555732727, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 1.4891, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.020278833967046894, | |
| "grad_norm": 1.6094928979873657, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 1.6946, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.021968736797634135, | |
| "grad_norm": 1.5100297927856445, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 1.5713, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.023658639628221376, | |
| "grad_norm": 1.6203187704086304, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 1.7319, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.025348542458808618, | |
| "grad_norm": 1.366817593574524, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.1443, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.025348542458808618, | |
| "eval_loss": 1.325199007987976, | |
| "eval_runtime": 23.2566, | |
| "eval_samples_per_second": 10.75, | |
| "eval_steps_per_second": 5.375, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02703844528939586, | |
| "grad_norm": 1.5522985458374023, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.2413, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0287283481199831, | |
| "grad_norm": 1.5510913133621216, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 1.2517, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.030418250950570342, | |
| "grad_norm": 1.658223271369934, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 1.4299, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03210815378115758, | |
| "grad_norm": 2.0415923595428467, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 1.44, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.03379805661174482, | |
| "grad_norm": 1.5060479640960693, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.1204, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03379805661174482, | |
| "eval_loss": 1.2771832942962646, | |
| "eval_runtime": 26.3745, | |
| "eval_samples_per_second": 9.479, | |
| "eval_steps_per_second": 4.739, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.035487959442332066, | |
| "grad_norm": 1.4412484169006348, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 1.2307, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.037177862272919304, | |
| "grad_norm": 1.5268642902374268, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 1.0532, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03886776510350655, | |
| "grad_norm": 1.7212144136428833, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 1.3446, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.04055766793409379, | |
| "grad_norm": 1.8049415349960327, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 1.1612, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.04224757076468103, | |
| "grad_norm": 1.7907023429870605, | |
| "learning_rate": 0.0, | |
| "loss": 1.4934, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04224757076468103, | |
| "eval_loss": 1.2678906917572021, | |
| "eval_runtime": 24.2693, | |
| "eval_samples_per_second": 10.301, | |
| "eval_steps_per_second": 5.151, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "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": 869692726050816.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |