| { | |
| "best_metric": 1.314715027809143, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.02348037920812421, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004696075841624842, | |
| "grad_norm": 1.1471283435821533, | |
| "learning_rate": 5e-05, | |
| "loss": 2.3028, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004696075841624842, | |
| "eval_loss": 2.3973193168640137, | |
| "eval_runtime": 409.6335, | |
| "eval_samples_per_second": 35.022, | |
| "eval_steps_per_second": 4.38, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009392151683249684, | |
| "grad_norm": 1.2805126905441284, | |
| "learning_rate": 0.0001, | |
| "loss": 2.3099, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0014088227524874527, | |
| "grad_norm": 1.2114781141281128, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.1535, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0018784303366499368, | |
| "grad_norm": 1.1774989366531372, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.0386, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002348037920812421, | |
| "grad_norm": 0.9971995949745178, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.9225, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0028176455049749053, | |
| "grad_norm": 0.8790279626846313, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.794, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0032872530891373897, | |
| "grad_norm": 1.1751753091812134, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.6115, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0037568606732998736, | |
| "grad_norm": 1.080180048942566, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.4857, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0042264682574623584, | |
| "grad_norm": 0.8699567914009094, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.4314, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004696075841624842, | |
| "grad_norm": 0.8253223299980164, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.3567, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005165683425787326, | |
| "grad_norm": 0.713810384273529, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.291, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.005635291009949811, | |
| "grad_norm": 0.6765950918197632, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.2962, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.006104898594112295, | |
| "grad_norm": 0.6236306428909302, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.4941, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.006574506178274779, | |
| "grad_norm": 0.6000515222549438, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.509, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.007044113762437264, | |
| "grad_norm": 0.5057103037834167, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.4013, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007513721346599747, | |
| "grad_norm": 0.5185362100601196, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.4515, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.007983328930762233, | |
| "grad_norm": 0.5617626309394836, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.4217, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.008452936514924717, | |
| "grad_norm": 0.504992663860321, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.4164, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0089225440990872, | |
| "grad_norm": 0.4376147389411926, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.3283, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.009392151683249684, | |
| "grad_norm": 0.4149356186389923, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.2588, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.009861759267412168, | |
| "grad_norm": 0.42740723490715027, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.2959, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.010331366851574653, | |
| "grad_norm": 0.4079449474811554, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.2151, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.010800974435737137, | |
| "grad_norm": 0.41314637660980225, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.2394, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.011270582019899621, | |
| "grad_norm": 0.38211390376091003, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.1939, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.011740189604062106, | |
| "grad_norm": 0.4124298393726349, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.1733, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.011740189604062106, | |
| "eval_loss": 1.3360475301742554, | |
| "eval_runtime": 409.1341, | |
| "eval_samples_per_second": 35.064, | |
| "eval_steps_per_second": 4.385, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01220979718822459, | |
| "grad_norm": 0.43993884325027466, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5061, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.012679404772387074, | |
| "grad_norm": 0.41342392563819885, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.4372, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.013149012356549559, | |
| "grad_norm": 0.44319623708724976, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.3508, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.013618619940712043, | |
| "grad_norm": 0.3479222059249878, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.342, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.014088227524874528, | |
| "grad_norm": 0.38919132947921753, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.3623, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01455783510903701, | |
| "grad_norm": 0.35072675347328186, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.2877, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.015027442693199495, | |
| "grad_norm": 0.38517889380455017, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.3297, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.015497050277361979, | |
| "grad_norm": 0.3642725348472595, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.3139, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.015966657861524465, | |
| "grad_norm": 0.3697044551372528, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.2089, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.016436265445686948, | |
| "grad_norm": 0.4046227037906647, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.2511, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.016905873029849434, | |
| "grad_norm": 0.37819936871528625, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.1577, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.017375480614011916, | |
| "grad_norm": 0.40968626737594604, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.1753, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0178450881981744, | |
| "grad_norm": 0.4086762070655823, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.3645, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.018314695782336885, | |
| "grad_norm": 0.38058918714523315, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.4081, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.018784303366499368, | |
| "grad_norm": 0.3770791292190552, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.4182, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.019253910950661854, | |
| "grad_norm": 0.39039525389671326, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.4629, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.019723518534824337, | |
| "grad_norm": 0.3564213514328003, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.3281, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.020193126118986823, | |
| "grad_norm": 0.4056853652000427, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.2944, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.020662733703149305, | |
| "grad_norm": 0.36049678921699524, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.3175, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.02113234128731179, | |
| "grad_norm": 0.3310118317604065, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.2527, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.021601948871474274, | |
| "grad_norm": 0.34343573451042175, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.2651, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.02207155645563676, | |
| "grad_norm": 0.3476006090641022, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.2322, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.022541164039799243, | |
| "grad_norm": 0.3565845489501953, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.2381, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.023010771623961725, | |
| "grad_norm": 0.3808521628379822, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.1995, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.02348037920812421, | |
| "grad_norm": 0.4298349916934967, | |
| "learning_rate": 0.0, | |
| "loss": 1.1051, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02348037920812421, | |
| "eval_loss": 1.314715027809143, | |
| "eval_runtime": 409.369, | |
| "eval_samples_per_second": 35.044, | |
| "eval_steps_per_second": 4.382, | |
| "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": 6.093040386509373e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |