| { | |
| "best_metric": 1.246433138847351, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.5012531328320802, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.020050125313283207, | |
| "grad_norm": 57.262550354003906, | |
| "learning_rate": 5e-05, | |
| "loss": 29.8366, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.020050125313283207, | |
| "eval_loss": 1.9029018878936768, | |
| "eval_runtime": 9.9628, | |
| "eval_samples_per_second": 33.826, | |
| "eval_steps_per_second": 4.316, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.040100250626566414, | |
| "grad_norm": 61.9777946472168, | |
| "learning_rate": 0.0001, | |
| "loss": 30.5166, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.06015037593984962, | |
| "grad_norm": 41.373321533203125, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 28.2141, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.08020050125313283, | |
| "grad_norm": 35.427249908447266, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 25.9472, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.10025062656641603, | |
| "grad_norm": 32.058868408203125, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 25.0425, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.12030075187969924, | |
| "grad_norm": 31.39280891418457, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 22.7109, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.14035087719298245, | |
| "grad_norm": 27.022315979003906, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 22.0858, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.16040100250626566, | |
| "grad_norm": 22.689998626708984, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 21.8407, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.18045112781954886, | |
| "grad_norm": 23.095903396606445, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 21.4493, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.20050125313283207, | |
| "grad_norm": 15.283258438110352, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 20.7956, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.22055137844611528, | |
| "grad_norm": 19.957977294921875, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 20.4935, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.24060150375939848, | |
| "grad_norm": 14.825860023498535, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 21.3076, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2606516290726817, | |
| "grad_norm": 32.27811813354492, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 22.9758, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.2807017543859649, | |
| "grad_norm": 14.461236000061035, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 21.7338, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3007518796992481, | |
| "grad_norm": 13.161033630371094, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 21.4966, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3208020050125313, | |
| "grad_norm": 13.530344009399414, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 20.3507, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.3408521303258145, | |
| "grad_norm": 15.065783500671387, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 19.967, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.3609022556390977, | |
| "grad_norm": 10.283108711242676, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 20.2849, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.38095238095238093, | |
| "grad_norm": 11.738165855407715, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 19.5285, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.40100250626566414, | |
| "grad_norm": 12.6289701461792, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 19.7657, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": 11.915717124938965, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 19.1391, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.44110275689223055, | |
| "grad_norm": 12.708892822265625, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 18.9334, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.46115288220551376, | |
| "grad_norm": 11.339106559753418, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 19.3876, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.48120300751879697, | |
| "grad_norm": 13.785265922546387, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 19.19, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5012531328320802, | |
| "grad_norm": 13.614476203918457, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 20.1636, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5012531328320802, | |
| "eval_loss": 1.246433138847351, | |
| "eval_runtime": 9.9398, | |
| "eval_samples_per_second": 33.904, | |
| "eval_steps_per_second": 4.326, | |
| "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": 2.829013890367488e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |