| { | |
| "best_metric": 0.6481190919876099, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.015570260801868432, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006228104320747372, | |
| "grad_norm": 34.961917877197266, | |
| "learning_rate": 5e-05, | |
| "loss": 4.4055, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006228104320747372, | |
| "eval_loss": 5.756421089172363, | |
| "eval_runtime": 463.9618, | |
| "eval_samples_per_second": 23.314, | |
| "eval_steps_per_second": 2.916, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012456208641494744, | |
| "grad_norm": 25.625226974487305, | |
| "learning_rate": 0.0001, | |
| "loss": 4.1662, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0018684312962242117, | |
| "grad_norm": 18.706308364868164, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 3.099, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002491241728298949, | |
| "grad_norm": 14.237258911132812, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.2839, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003114052160373686, | |
| "grad_norm": 7.653135299682617, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.7328, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0037368625924484233, | |
| "grad_norm": 7.604238986968994, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.6975, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004359673024523161, | |
| "grad_norm": 4.739212512969971, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.6526, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004982483456597898, | |
| "grad_norm": 4.953818321228027, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.6595, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005605293888672635, | |
| "grad_norm": 5.076328754425049, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.8259, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006228104320747372, | |
| "grad_norm": 4.2572736740112305, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.7653, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00685091475282211, | |
| "grad_norm": 5.306685447692871, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.9771, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.007473725184896847, | |
| "grad_norm": 5.197048187255859, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.1657, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.008096535616971585, | |
| "grad_norm": 5.541998863220215, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.0405, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.008719346049046322, | |
| "grad_norm": 4.117219924926758, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.7929, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.009342156481121059, | |
| "grad_norm": 3.033407688140869, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.5813, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.009964966913195795, | |
| "grad_norm": 3.0356810092926025, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.5848, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.010587777345270534, | |
| "grad_norm": 3.6332268714904785, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.5569, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01121058777734527, | |
| "grad_norm": 4.638049602508545, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.575, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.011833398209420008, | |
| "grad_norm": 3.121140718460083, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.4935, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.012456208641494744, | |
| "grad_norm": 3.2301628589630127, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.6655, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.013079019073569483, | |
| "grad_norm": 3.529449462890625, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.6141, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.01370182950564422, | |
| "grad_norm": 3.159022808074951, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.5717, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.014324639937718956, | |
| "grad_norm": 3.829219341278076, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.6012, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.014947450369793693, | |
| "grad_norm": 4.6542487144470215, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.832, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.015570260801868432, | |
| "grad_norm": 5.967838764190674, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.376, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.015570260801868432, | |
| "eval_loss": 0.6481190919876099, | |
| "eval_runtime": 464.1823, | |
| "eval_samples_per_second": 23.303, | |
| "eval_steps_per_second": 2.915, | |
| "step": 25 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.217745394630656e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |