| { | |
| "best_metric": 1.6913299560546875, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.016559032952475575, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000662361318099023, | |
| "grad_norm": 40.82220458984375, | |
| "learning_rate": 5e-05, | |
| "loss": 27.5824, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000662361318099023, | |
| "eval_loss": 2.2696444988250732, | |
| "eval_runtime": 432.347, | |
| "eval_samples_per_second": 23.525, | |
| "eval_steps_per_second": 2.942, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001324722636198046, | |
| "grad_norm": 36.23447799682617, | |
| "learning_rate": 0.0001, | |
| "loss": 27.0301, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001987083954297069, | |
| "grad_norm": 41.014190673828125, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 29.9936, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002649445272396092, | |
| "grad_norm": 36.32714080810547, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 27.1201, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003311806590495115, | |
| "grad_norm": 36.35200500488281, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 30.1767, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003974167908594138, | |
| "grad_norm": 34.66734313964844, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 32.16, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004636529226693161, | |
| "grad_norm": 27.75533103942871, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 28.1419, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.005298890544792184, | |
| "grad_norm": 39.82036209106445, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 31.4935, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005961251862891207, | |
| "grad_norm": 32.18791198730469, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 29.9285, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00662361318099023, | |
| "grad_norm": 33.4499626159668, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 29.7212, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007285974499089253, | |
| "grad_norm": 38.62579345703125, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 33.2777, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.007948335817188276, | |
| "grad_norm": 36.961639404296875, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 31.1595, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0086106971352873, | |
| "grad_norm": 37.11787414550781, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 30.9798, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.009273058453386322, | |
| "grad_norm": 35.7690315246582, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 26.4066, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.009935419771485345, | |
| "grad_norm": 25.68424415588379, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 26.8711, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.010597781089584368, | |
| "grad_norm": 20.35919189453125, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 24.8348, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.011260142407683391, | |
| "grad_norm": 20.65962028503418, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 24.6985, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.011922503725782414, | |
| "grad_norm": 20.867441177368164, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 26.0421, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.012584865043881437, | |
| "grad_norm": 23.38364028930664, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 25.5464, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.01324722636198046, | |
| "grad_norm": 24.096189498901367, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 26.3065, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.013909587680079483, | |
| "grad_norm": 25.358400344848633, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 27.5427, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.014571948998178506, | |
| "grad_norm": 25.04808235168457, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 27.4076, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01523431031627753, | |
| "grad_norm": 29.721607208251953, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 27.733, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.015896671634376552, | |
| "grad_norm": 34.963172912597656, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 29.4103, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.016559032952475575, | |
| "grad_norm": 36.04214096069336, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 29.9496, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.016559032952475575, | |
| "eval_loss": 1.6913299560546875, | |
| "eval_runtime": 435.6417, | |
| "eval_samples_per_second": 23.347, | |
| "eval_steps_per_second": 2.92, | |
| "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 | |
| } | |