| { | |
| "best_metric": 1.0841188430786133, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.3125, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00625, | |
| "grad_norm": 1.8498634099960327, | |
| "learning_rate": 5e-06, | |
| "loss": 4.5813, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00625, | |
| "eval_loss": 1.2194494009017944, | |
| "eval_runtime": 18.6921, | |
| "eval_samples_per_second": 14.445, | |
| "eval_steps_per_second": 1.819, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0125, | |
| "grad_norm": 1.8300238847732544, | |
| "learning_rate": 1e-05, | |
| "loss": 4.3592, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01875, | |
| "grad_norm": 2.127028703689575, | |
| "learning_rate": 1.5e-05, | |
| "loss": 5.1297, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.025, | |
| "grad_norm": 1.9777432680130005, | |
| "learning_rate": 2e-05, | |
| "loss": 5.1958, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03125, | |
| "grad_norm": 2.015655279159546, | |
| "learning_rate": 2.5e-05, | |
| "loss": 4.7181, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0375, | |
| "grad_norm": 2.0624945163726807, | |
| "learning_rate": 3e-05, | |
| "loss": 5.4952, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.04375, | |
| "grad_norm": 3.5970277786254883, | |
| "learning_rate": 3.5e-05, | |
| "loss": 5.2734, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 2.0029900074005127, | |
| "learning_rate": 4e-05, | |
| "loss": 4.5544, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.05625, | |
| "grad_norm": 1.8359339237213135, | |
| "learning_rate": 4.5e-05, | |
| "loss": 4.6155, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0625, | |
| "grad_norm": 2.2517831325531006, | |
| "learning_rate": 5e-05, | |
| "loss": 5.4694, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06875, | |
| "grad_norm": 1.879914402961731, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 4.2894, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.075, | |
| "grad_norm": 1.739548683166504, | |
| "learning_rate": 6e-05, | |
| "loss": 4.2815, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.08125, | |
| "grad_norm": 1.5380457639694214, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 4.3312, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0875, | |
| "grad_norm": 1.6644234657287598, | |
| "learning_rate": 7e-05, | |
| "loss": 4.7402, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.09375, | |
| "grad_norm": 1.525267243385315, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 4.8961, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 1.6433475017547607, | |
| "learning_rate": 8e-05, | |
| "loss": 4.1454, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.10625, | |
| "grad_norm": 1.6035125255584717, | |
| "learning_rate": 8.5e-05, | |
| "loss": 4.5186, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1125, | |
| "grad_norm": 1.508162260055542, | |
| "learning_rate": 9e-05, | |
| "loss": 4.481, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.11875, | |
| "grad_norm": 1.4459158182144165, | |
| "learning_rate": 9.5e-05, | |
| "loss": 3.9967, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.125, | |
| "grad_norm": 1.5539876222610474, | |
| "learning_rate": 0.0001, | |
| "loss": 4.7728, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.13125, | |
| "grad_norm": 1.608622670173645, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 3.9576, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1375, | |
| "grad_norm": 1.5555155277252197, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 3.9051, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.14375, | |
| "grad_norm": 1.7010705471038818, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 4.9004, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 1.5186794996261597, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 4.1984, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.15625, | |
| "grad_norm": 1.3770533800125122, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 3.8048, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.15625, | |
| "eval_loss": 1.0969889163970947, | |
| "eval_runtime": 19.0256, | |
| "eval_samples_per_second": 14.191, | |
| "eval_steps_per_second": 1.787, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1625, | |
| "grad_norm": 1.3446524143218994, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 3.6103, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.16875, | |
| "grad_norm": 1.5091419219970703, | |
| "learning_rate": 8.715724127386972e-05, | |
| "loss": 3.9509, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.175, | |
| "grad_norm": 1.3692712783813477, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 4.7267, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.18125, | |
| "grad_norm": 1.6524736881256104, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 4.5399, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.1875, | |
| "grad_norm": 1.4372515678405762, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 4.2252, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.19375, | |
| "grad_norm": 1.5296458005905151, | |
| "learning_rate": 7.033683215379002e-05, | |
| "loss": 4.8885, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 1.1811058521270752, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 4.2151, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.20625, | |
| "grad_norm": 1.5564839839935303, | |
| "learning_rate": 6.0395584540887963e-05, | |
| "loss": 4.3257, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.2125, | |
| "grad_norm": 1.625295639038086, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 4.3592, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.21875, | |
| "grad_norm": 1.2795021533966064, | |
| "learning_rate": 5e-05, | |
| "loss": 4.2706, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.225, | |
| "grad_norm": 1.1677732467651367, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 3.8508, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.23125, | |
| "grad_norm": 1.923035740852356, | |
| "learning_rate": 3.960441545911204e-05, | |
| "loss": 5.2749, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.2375, | |
| "grad_norm": 1.4094065427780151, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 4.0751, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.24375, | |
| "grad_norm": 1.5134934186935425, | |
| "learning_rate": 2.9663167846209998e-05, | |
| "loss": 4.2217, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 1.3699042797088623, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 3.7734, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.25625, | |
| "grad_norm": 1.2489789724349976, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 3.9079, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.2625, | |
| "grad_norm": 1.3061996698379517, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 4.6819, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.26875, | |
| "grad_norm": 1.2688488960266113, | |
| "learning_rate": 1.2842758726130283e-05, | |
| "loss": 3.826, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.275, | |
| "grad_norm": 1.2382211685180664, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 4.64, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.28125, | |
| "grad_norm": 2.0334558486938477, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 5.6532, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2875, | |
| "grad_norm": 1.1454434394836426, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 4.5027, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.29375, | |
| "grad_norm": 1.526947259902954, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 4.1062, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 1.1723829507827759, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 4.713, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.30625, | |
| "grad_norm": 1.2639137506484985, | |
| "learning_rate": 2.7390523158633554e-07, | |
| "loss": 4.1751, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.3125, | |
| "grad_norm": 1.3471728563308716, | |
| "learning_rate": 0.0, | |
| "loss": 4.5387, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3125, | |
| "eval_loss": 1.0841188430786133, | |
| "eval_runtime": 19.034, | |
| "eval_samples_per_second": 14.185, | |
| "eval_steps_per_second": 1.786, | |
| "step": 50 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.951840420515021e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |