| { | |
| "best_metric": 0.576792299747467, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.46296296296296297, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.018518518518518517, | |
| "grad_norm": 0.5647748708724976, | |
| "learning_rate": 5e-05, | |
| "loss": 1.097, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.018518518518518517, | |
| "eval_loss": 1.6396740674972534, | |
| "eval_runtime": 4.1727, | |
| "eval_samples_per_second": 87.234, | |
| "eval_steps_per_second": 11.024, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.037037037037037035, | |
| "grad_norm": 0.704931914806366, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2547, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.05555555555555555, | |
| "grad_norm": 0.7352797985076904, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.2515, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.07407407407407407, | |
| "grad_norm": 0.6545394062995911, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.228, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.09259259259259259, | |
| "grad_norm": 0.6046964526176453, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.2025, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1111111111111111, | |
| "grad_norm": 0.5980863571166992, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.131, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.12962962962962962, | |
| "grad_norm": 0.5863988399505615, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.0939, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.14814814814814814, | |
| "grad_norm": 0.5570467114448547, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.0675, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.16666666666666666, | |
| "grad_norm": 0.5377064943313599, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.976, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.18518518518518517, | |
| "grad_norm": 0.593476414680481, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.9628, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2037037037037037, | |
| "grad_norm": 0.561056911945343, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.9599, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "grad_norm": 0.560419499874115, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.9372, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.24074074074074073, | |
| "grad_norm": 0.25102630257606506, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.6954, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.25925925925925924, | |
| "grad_norm": 0.21997065842151642, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.6822, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.2777777777777778, | |
| "grad_norm": 0.2169683426618576, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.6982, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2962962962962963, | |
| "grad_norm": 0.23189207911491394, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.6494, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.3148148148148148, | |
| "grad_norm": 0.24518410861492157, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.6537, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": 0.24312365055084229, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.6322, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.35185185185185186, | |
| "grad_norm": 0.2416844218969345, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.6625, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.37037037037037035, | |
| "grad_norm": 0.26255324482917786, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.6631, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3888888888888889, | |
| "grad_norm": 0.26637887954711914, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.6135, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.4074074074074074, | |
| "grad_norm": 0.2723131775856018, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.5994, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.42592592592592593, | |
| "grad_norm": 0.2862944006919861, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.5824, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 0.3188299238681793, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.6065, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.46296296296296297, | |
| "grad_norm": 0.4002661406993866, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.6144, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.46296296296296297, | |
| "eval_loss": 0.576792299747467, | |
| "eval_runtime": 4.1618, | |
| "eval_samples_per_second": 87.462, | |
| "eval_steps_per_second": 11.053, | |
| "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": 5.29768176943104e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |