| { | |
| "best_metric": 0.21533425152301788, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.4406474820143884, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02877697841726619, | |
| "grad_norm": 43.36970138549805, | |
| "learning_rate": 5e-05, | |
| "loss": 14.2414, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02877697841726619, | |
| "eval_loss": 14.855347633361816, | |
| "eval_runtime": 9.3052, | |
| "eval_samples_per_second": 25.147, | |
| "eval_steps_per_second": 3.224, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05755395683453238, | |
| "grad_norm": 46.15438461303711, | |
| "learning_rate": 0.0001, | |
| "loss": 14.7473, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.08633093525179857, | |
| "grad_norm": 29.833412170410156, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 11.523, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.11510791366906475, | |
| "grad_norm": 30.06519889831543, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 5.6078, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.14388489208633093, | |
| "grad_norm": 17.41543960571289, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.0468, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.17266187050359713, | |
| "grad_norm": 9.9285249710083, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.2268, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2014388489208633, | |
| "grad_norm": 7.611830234527588, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.7729, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.2302158273381295, | |
| "grad_norm": 3.3866260051727295, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.3699, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.2589928057553957, | |
| "grad_norm": 4.976719856262207, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.4128, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.28776978417266186, | |
| "grad_norm": 6.964507102966309, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.7489, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.31654676258992803, | |
| "grad_norm": 2.7925236225128174, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.567, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.34532374100719426, | |
| "grad_norm": 3.0825459957122803, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.4569, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.37410071942446044, | |
| "grad_norm": 1.5685139894485474, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.3966, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.4028776978417266, | |
| "grad_norm": 2.1865251064300537, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.3561, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.4316546762589928, | |
| "grad_norm": 1.3713597059249878, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.4017, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.460431654676259, | |
| "grad_norm": 1.0574811697006226, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.3263, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.4892086330935252, | |
| "grad_norm": 1.3450047969818115, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.2309, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.5179856115107914, | |
| "grad_norm": 3.1891255378723145, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.5413, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.5467625899280576, | |
| "grad_norm": 3.5631210803985596, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.5645, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.5755395683453237, | |
| "grad_norm": 2.20904541015625, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.4799, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.60431654676259, | |
| "grad_norm": 1.2742122411727905, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.4097, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.6330935251798561, | |
| "grad_norm": 1.21361243724823, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.3763, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.6618705035971223, | |
| "grad_norm": 1.2304342985153198, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.3347, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.6906474820143885, | |
| "grad_norm": 0.7123867869377136, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.2559, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.7194244604316546, | |
| "grad_norm": 1.585843563079834, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.2423, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.7194244604316546, | |
| "eval_loss": 0.29774895310401917, | |
| "eval_runtime": 9.2776, | |
| "eval_samples_per_second": 25.222, | |
| "eval_steps_per_second": 3.234, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.7482014388489209, | |
| "grad_norm": 1.5737944841384888, | |
| "learning_rate": 5e-05, | |
| "loss": 0.2944, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.7769784172661871, | |
| "grad_norm": 1.186069130897522, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.3601, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.8057553956834532, | |
| "grad_norm": 1.3156697750091553, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.4084, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.8345323741007195, | |
| "grad_norm": 0.8197304010391235, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.3833, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.8633093525179856, | |
| "grad_norm": 0.7455169558525085, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.3442, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.8920863309352518, | |
| "grad_norm": 0.647731363773346, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.2965, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.920863309352518, | |
| "grad_norm": 0.9201293587684631, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.182, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.9496402877697842, | |
| "grad_norm": 0.8363877534866333, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.1878, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.9784172661870504, | |
| "grad_norm": 0.5325927734375, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.1111, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.0089928057553956, | |
| "grad_norm": 1.7002311944961548, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.3383, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.0377697841726619, | |
| "grad_norm": 4.443037509918213, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.5528, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.066546762589928, | |
| "grad_norm": 2.736210346221924, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.4109, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.0953237410071943, | |
| "grad_norm": 1.8709927797317505, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.3634, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.1241007194244603, | |
| "grad_norm": 1.336185097694397, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.3063, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.1528776978417266, | |
| "grad_norm": 0.8743398189544678, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.2986, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.1816546762589928, | |
| "grad_norm": 1.1188706159591675, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.2025, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.210431654676259, | |
| "grad_norm": 0.7593362331390381, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.1725, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.2392086330935252, | |
| "grad_norm": 0.6174198985099792, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.1326, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.2679856115107913, | |
| "grad_norm": 0.37820106744766235, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.261, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.2967625899280575, | |
| "grad_norm": 0.6265496015548706, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.3512, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.3255395683453237, | |
| "grad_norm": 0.5311719179153442, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.3005, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.35431654676259, | |
| "grad_norm": 0.6251354217529297, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.3055, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.3830935251798562, | |
| "grad_norm": 0.7828004956245422, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.2657, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.4118705035971222, | |
| "grad_norm": 0.9686384201049805, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.2564, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.4406474820143884, | |
| "grad_norm": 0.9383431077003479, | |
| "learning_rate": 0.0, | |
| "loss": 0.2077, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.4406474820143884, | |
| "eval_loss": 0.21533425152301788, | |
| "eval_runtime": 9.3202, | |
| "eval_samples_per_second": 25.107, | |
| "eval_steps_per_second": 3.219, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 6.635526345478636e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |