| { | |
| "best_metric": 10.368718147277832, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.0308370044052864, | |
| "eval_steps": 25, | |
| "global_step": 43, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07048458149779736, | |
| "grad_norm": 0.15103048086166382, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3794, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07048458149779736, | |
| "eval_loss": 10.385944366455078, | |
| "eval_runtime": 0.1758, | |
| "eval_samples_per_second": 284.408, | |
| "eval_steps_per_second": 73.946, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.14096916299559473, | |
| "grad_norm": 0.15679699182510376, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3862, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.21145374449339208, | |
| "grad_norm": 0.16282032430171967, | |
| "learning_rate": 9.986796105326832e-05, | |
| "loss": 10.387, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.28193832599118945, | |
| "grad_norm": 0.15456366539001465, | |
| "learning_rate": 9.947261907011569e-05, | |
| "loss": 10.3798, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.3524229074889868, | |
| "grad_norm": 0.16235828399658203, | |
| "learning_rate": 9.881629407450006e-05, | |
| "loss": 10.3822, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.42290748898678415, | |
| "grad_norm": 0.16534823179244995, | |
| "learning_rate": 9.790283764247188e-05, | |
| "loss": 10.3842, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.4933920704845815, | |
| "grad_norm": 0.17237423360347748, | |
| "learning_rate": 9.673761029959427e-05, | |
| "loss": 10.3851, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.5638766519823789, | |
| "grad_norm": 0.15661656856536865, | |
| "learning_rate": 9.53274500632475e-05, | |
| "loss": 10.3734, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.6343612334801763, | |
| "grad_norm": 0.17029444873332977, | |
| "learning_rate": 9.368063231442406e-05, | |
| "loss": 10.3804, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.7048458149779736, | |
| "grad_norm": 0.1816568821668625, | |
| "learning_rate": 9.18068212345023e-05, | |
| "loss": 10.3824, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.775330396475771, | |
| "grad_norm": 0.16436423361301422, | |
| "learning_rate": 8.971701309198744e-05, | |
| "loss": 10.3737, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.8458149779735683, | |
| "grad_norm": 0.1768498420715332, | |
| "learning_rate": 8.742347171203542e-05, | |
| "loss": 10.3766, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.9162995594713657, | |
| "grad_norm": 0.18194836378097534, | |
| "learning_rate": 8.493965650745043e-05, | |
| "loss": 10.3783, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.986784140969163, | |
| "grad_norm": 0.19210250675678253, | |
| "learning_rate": 8.228014349349872e-05, | |
| "loss": 10.3796, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.0572687224669604, | |
| "grad_norm": 0.32867375016212463, | |
| "learning_rate": 7.946053975005496e-05, | |
| "loss": 19.3742, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.1277533039647576, | |
| "grad_norm": 0.18255069851875305, | |
| "learning_rate": 7.649739183305184e-05, | |
| "loss": 9.9392, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.198237885462555, | |
| "grad_norm": 0.20073361694812775, | |
| "learning_rate": 7.34080886727103e-05, | |
| "loss": 10.3462, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.2687224669603525, | |
| "grad_norm": 0.18839029967784882, | |
| "learning_rate": 7.021075952838262e-05, | |
| "loss": 10.3914, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.3392070484581498, | |
| "grad_norm": 0.1993706077337265, | |
| "learning_rate": 6.692416759884978e-05, | |
| "loss": 10.3801, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.4096916299559472, | |
| "grad_norm": 0.20379072427749634, | |
| "learning_rate": 6.356759991241008e-05, | |
| "loss": 10.3467, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.4801762114537445, | |
| "grad_norm": 0.2293168157339096, | |
| "learning_rate": 6.016075414292803e-05, | |
| "loss": 10.4305, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.550660792951542, | |
| "grad_norm": 0.21386025846004486, | |
| "learning_rate": 5.6723623016051596e-05, | |
| "loss": 10.8684, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.6211453744493394, | |
| "grad_norm": 0.20540174841880798, | |
| "learning_rate": 5.3276376983948415e-05, | |
| "loss": 9.8329, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.6916299559471366, | |
| "grad_norm": 0.2285604327917099, | |
| "learning_rate": 4.9839245857071994e-05, | |
| "loss": 10.3722, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.7621145374449338, | |
| "grad_norm": 0.2136184275150299, | |
| "learning_rate": 4.643240008758992e-05, | |
| "loss": 10.1935, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.7621145374449338, | |
| "eval_loss": 10.368718147277832, | |
| "eval_runtime": 0.1874, | |
| "eval_samples_per_second": 266.863, | |
| "eval_steps_per_second": 69.384, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.8325991189427313, | |
| "grad_norm": 0.23158004879951477, | |
| "learning_rate": 4.307583240115024e-05, | |
| "loss": 10.6369, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.9030837004405288, | |
| "grad_norm": 0.23809461295604706, | |
| "learning_rate": 3.9789240471617385e-05, | |
| "loss": 10.3091, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.973568281938326, | |
| "grad_norm": 0.2416485697031021, | |
| "learning_rate": 3.659191132728971e-05, | |
| "loss": 10.3553, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.0440528634361232, | |
| "grad_norm": 0.4224947988986969, | |
| "learning_rate": 3.350260816694816e-05, | |
| "loss": 19.7858, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.1145374449339207, | |
| "grad_norm": 0.21910975873470306, | |
| "learning_rate": 3.0539460249945056e-05, | |
| "loss": 9.4865, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.185022026431718, | |
| "grad_norm": 0.2511979639530182, | |
| "learning_rate": 2.7719856506501306e-05, | |
| "loss": 10.3491, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.255506607929515, | |
| "grad_norm": 0.21490304172039032, | |
| "learning_rate": 2.5060343492549566e-05, | |
| "loss": 9.5953, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.3259911894273126, | |
| "grad_norm": 0.25810712575912476, | |
| "learning_rate": 2.257652828796459e-05, | |
| "loss": 11.2614, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.39647577092511, | |
| "grad_norm": 0.24142640829086304, | |
| "learning_rate": 2.0282986908012567e-05, | |
| "loss": 10.2079, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.4669603524229076, | |
| "grad_norm": 0.2538101077079773, | |
| "learning_rate": 1.819317876549771e-05, | |
| "loss": 10.3802, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.537444933920705, | |
| "grad_norm": 0.26082903146743774, | |
| "learning_rate": 1.631936768557596e-05, | |
| "loss": 11.26, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.607929515418502, | |
| "grad_norm": 0.23028650879859924, | |
| "learning_rate": 1.4672549936752506e-05, | |
| "loss": 9.44, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.6784140969162995, | |
| "grad_norm": 0.2575504779815674, | |
| "learning_rate": 1.3262389700405744e-05, | |
| "loss": 10.3462, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.748898678414097, | |
| "grad_norm": 0.234547421336174, | |
| "learning_rate": 1.2097162357528127e-05, | |
| "loss": 9.6301, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.8193832599118944, | |
| "grad_norm": 0.27662456035614014, | |
| "learning_rate": 1.1183705925499948e-05, | |
| "loss": 11.245, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.889867841409692, | |
| "grad_norm": 0.2530806362628937, | |
| "learning_rate": 1.0527380929884324e-05, | |
| "loss": 10.1797, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.960352422907489, | |
| "grad_norm": 0.267768919467926, | |
| "learning_rate": 1.013203894673168e-05, | |
| "loss": 10.3897, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 3.0308370044052864, | |
| "grad_norm": 0.47571516036987305, | |
| "learning_rate": 1e-05, | |
| "loss": 20.5396, | |
| "step": 43 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 43, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "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": 36920863948800.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |