| { | |
| "best_metric": 0.7136812210083008, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.024351637647631805, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00048703275295263604, | |
| "grad_norm": 0.9573298096656799, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7861, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00048703275295263604, | |
| "eval_loss": 0.8942872285842896, | |
| "eval_runtime": 51.7477, | |
| "eval_samples_per_second": 66.844, | |
| "eval_steps_per_second": 8.368, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009740655059052721, | |
| "grad_norm": 1.1015108823776245, | |
| "learning_rate": 4e-05, | |
| "loss": 0.7208, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0014610982588579083, | |
| "grad_norm": 0.8909242749214172, | |
| "learning_rate": 6e-05, | |
| "loss": 0.7673, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0019481310118105442, | |
| "grad_norm": 0.7424329519271851, | |
| "learning_rate": 8e-05, | |
| "loss": 0.7395, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0024351637647631805, | |
| "grad_norm": 0.9434481859207153, | |
| "learning_rate": 0.0001, | |
| "loss": 0.787, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0029221965177158166, | |
| "grad_norm": 0.9193047285079956, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.7995, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0034092292706684527, | |
| "grad_norm": 0.754969596862793, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 0.7585, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0038962620236210883, | |
| "grad_norm": 0.7523470520973206, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.8996, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004383294776573725, | |
| "grad_norm": 0.7241211533546448, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 0.7754, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004870327529526361, | |
| "grad_norm": 0.7039156556129456, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.7447, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005357360282478997, | |
| "grad_norm": 0.6671916246414185, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 0.7752, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.005844393035431633, | |
| "grad_norm": 0.6283051371574402, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.6935, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.006331425788384269, | |
| "grad_norm": 0.6730511784553528, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 0.8745, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.006818458541336905, | |
| "grad_norm": 0.6273585557937622, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.7794, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0073054912942895405, | |
| "grad_norm": 0.7080639004707336, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.7291, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007792524047242177, | |
| "grad_norm": 0.7021536827087402, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 0.7387, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.008279556800194814, | |
| "grad_norm": 0.7203246355056763, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 0.7773, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.00876658955314745, | |
| "grad_norm": 0.6584762930870056, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 0.7241, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.009253622306100086, | |
| "grad_norm": 0.7460336089134216, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 0.7961, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.009740655059052722, | |
| "grad_norm": 0.7008330821990967, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.7538, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.010227687812005358, | |
| "grad_norm": 0.7185075283050537, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 0.7684, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.010714720564957994, | |
| "grad_norm": 0.64677494764328, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 0.7141, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01120175331791063, | |
| "grad_norm": 0.6538144946098328, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.7265, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.011688786070863266, | |
| "grad_norm": 0.645527184009552, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 0.7708, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.012175818823815902, | |
| "grad_norm": 0.627602756023407, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 0.7138, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.012175818823815902, | |
| "eval_loss": 0.7274222373962402, | |
| "eval_runtime": 51.8201, | |
| "eval_samples_per_second": 66.75, | |
| "eval_steps_per_second": 8.356, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.012662851576768538, | |
| "grad_norm": 0.6254714131355286, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 0.8063, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.013149884329721175, | |
| "grad_norm": 0.6492407917976379, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 0.7139, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.01363691708267381, | |
| "grad_norm": 0.6935194730758667, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 0.771, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.014123949835626447, | |
| "grad_norm": 0.6273863911628723, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 0.7476, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.014610982588579081, | |
| "grad_norm": 0.6156079769134521, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.6538, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.015098015341531717, | |
| "grad_norm": 0.7052273154258728, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 0.6745, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.015585048094484353, | |
| "grad_norm": 0.6338075995445251, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.6955, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.01607208084743699, | |
| "grad_norm": 0.6787643432617188, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 0.7626, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.016559113600389627, | |
| "grad_norm": 0.6908796429634094, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 0.7369, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.017046146353342263, | |
| "grad_norm": 0.7850337624549866, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.8234, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0175331791062949, | |
| "grad_norm": 0.6327264308929443, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 0.6598, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.018020211859247535, | |
| "grad_norm": 0.6976511478424072, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 0.6776, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.01850724461220017, | |
| "grad_norm": 0.7151832580566406, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 0.7479, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.018994277365152808, | |
| "grad_norm": 0.6975402235984802, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 0.6475, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.019481310118105444, | |
| "grad_norm": 0.6512317657470703, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 0.7253, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01996834287105808, | |
| "grad_norm": 0.6642155647277832, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.6675, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.020455375624010716, | |
| "grad_norm": 0.7088849544525146, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 0.6854, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.020942408376963352, | |
| "grad_norm": 0.765938937664032, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 0.6859, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.021429441129915988, | |
| "grad_norm": 0.7077057957649231, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 0.6543, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.021916473882868624, | |
| "grad_norm": 0.7243754863739014, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 0.7089, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02240350663582126, | |
| "grad_norm": 0.7536875009536743, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 0.6674, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.022890539388773896, | |
| "grad_norm": 0.7189517617225647, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 0.6465, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.023377572141726533, | |
| "grad_norm": 0.7736000418663025, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 0.6447, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.02386460489467917, | |
| "grad_norm": 0.872376024723053, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 0.7028, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.024351637647631805, | |
| "grad_norm": 0.932105302810669, | |
| "learning_rate": 0.0, | |
| "loss": 0.5758, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.024351637647631805, | |
| "eval_loss": 0.7136812210083008, | |
| "eval_runtime": 51.7795, | |
| "eval_samples_per_second": 66.802, | |
| "eval_steps_per_second": 8.362, | |
| "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": 5, | |
| "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": 3603404933824512.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |