| { | |
| "best_metric": 0.5757180452346802, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.5571030640668524, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.022284122562674095, | |
| "grad_norm": 30.866960525512695, | |
| "learning_rate": 5e-05, | |
| "loss": 9.0769, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.022284122562674095, | |
| "eval_loss": 8.731489181518555, | |
| "eval_runtime": 4.6802, | |
| "eval_samples_per_second": 64.741, | |
| "eval_steps_per_second": 8.119, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04456824512534819, | |
| "grad_norm": 35.00822067260742, | |
| "learning_rate": 0.0001, | |
| "loss": 8.9305, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.06685236768802229, | |
| "grad_norm": 29.040769577026367, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 7.1472, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.08913649025069638, | |
| "grad_norm": 17.517667770385742, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 3.5425, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.11142061281337047, | |
| "grad_norm": 9.844194412231445, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.0754, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.13370473537604458, | |
| "grad_norm": 6.558274269104004, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.3057, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.15598885793871867, | |
| "grad_norm": 4.910419940948486, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.8803, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.17827298050139276, | |
| "grad_norm": 3.809398651123047, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.6958, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.20055710306406685, | |
| "grad_norm": 5.165838241577148, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.6014, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.22284122562674094, | |
| "grad_norm": 9.54565715789795, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.6692, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.24512534818941503, | |
| "grad_norm": 7.332498550415039, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.585, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.26740947075208915, | |
| "grad_norm": 11.09341812133789, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.6227, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.28969359331476324, | |
| "grad_norm": 12.350174903869629, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.6362, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.31197771587743733, | |
| "grad_norm": 3.0692760944366455, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.5194, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3342618384401114, | |
| "grad_norm": 3.36543607711792, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.5659, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3565459610027855, | |
| "grad_norm": 5.607704162597656, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.5629, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.3788300835654596, | |
| "grad_norm": 6.10757303237915, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.5898, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.4011142061281337, | |
| "grad_norm": 4.869055271148682, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.5669, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.4233983286908078, | |
| "grad_norm": 2.869997262954712, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.5249, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.4456824512534819, | |
| "grad_norm": 3.0591838359832764, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.558, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.467966573816156, | |
| "grad_norm": 2.3886196613311768, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.5523, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.49025069637883006, | |
| "grad_norm": 2.7517380714416504, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.5185, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.5125348189415042, | |
| "grad_norm": 4.07460880279541, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.5284, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.5348189415041783, | |
| "grad_norm": 0.6786271929740906, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.5028, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5571030640668524, | |
| "grad_norm": 2.6502835750579834, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.4916, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5571030640668524, | |
| "eval_loss": 0.5757180452346802, | |
| "eval_runtime": 4.406, | |
| "eval_samples_per_second": 68.769, | |
| "eval_steps_per_second": 8.625, | |
| "step": 25 | |
| } | |
| ], | |
| "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": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8.051627496623309e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |