| { | |
| "best_metric": 2.268191337585449, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.41025641025641024, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01641025641025641, | |
| "grad_norm": 0.105502188205719, | |
| "learning_rate": 5e-05, | |
| "loss": 2.2908, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01641025641025641, | |
| "eval_loss": 2.355482339859009, | |
| "eval_runtime": 5.5155, | |
| "eval_samples_per_second": 74.517, | |
| "eval_steps_per_second": 9.428, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03282051282051282, | |
| "grad_norm": 0.13886846601963043, | |
| "learning_rate": 0.0001, | |
| "loss": 2.3437, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04923076923076923, | |
| "grad_norm": 0.1492706537246704, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.4043, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.06564102564102564, | |
| "grad_norm": 0.144420325756073, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.3847, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.08205128205128205, | |
| "grad_norm": 0.16961826384067535, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.3608, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.09846153846153846, | |
| "grad_norm": 0.1963823437690735, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.3869, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.11487179487179487, | |
| "grad_norm": 0.19351187348365784, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.4213, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.13128205128205128, | |
| "grad_norm": 0.19201019406318665, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.339, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1476923076923077, | |
| "grad_norm": 0.19801242649555206, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.285, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1641025641025641, | |
| "grad_norm": 0.22390833497047424, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.2343, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.18051282051282053, | |
| "grad_norm": 0.2744271755218506, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.2227, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.19692307692307692, | |
| "grad_norm": 0.33234903216362, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.2162, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.21333333333333335, | |
| "grad_norm": 0.1719486117362976, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.3278, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.22974358974358974, | |
| "grad_norm": 0.18371833860874176, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.3421, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.24615384615384617, | |
| "grad_norm": 0.18443404138088226, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.4136, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.26256410256410256, | |
| "grad_norm": 0.16663940250873566, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.3608, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.27897435897435896, | |
| "grad_norm": 0.1506539136171341, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 2.3462, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.2953846153846154, | |
| "grad_norm": 0.14351533353328705, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.2904, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.3117948717948718, | |
| "grad_norm": 0.15008053183555603, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 2.3119, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.3282051282051282, | |
| "grad_norm": 0.156484454870224, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.329, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3446153846153846, | |
| "grad_norm": 0.1854938119649887, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 2.352, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.36102564102564105, | |
| "grad_norm": 0.2080937772989273, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 2.2663, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.37743589743589745, | |
| "grad_norm": 0.2580544650554657, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 2.3672, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.39384615384615385, | |
| "grad_norm": 0.3285817801952362, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 2.3384, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.41025641025641024, | |
| "grad_norm": 0.6451262831687927, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 2.2175, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.41025641025641024, | |
| "eval_loss": 2.268191337585449, | |
| "eval_runtime": 5.4153, | |
| "eval_samples_per_second": 75.895, | |
| "eval_steps_per_second": 9.602, | |
| "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": 5.522833269797683e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |