| { | |
| "best_metric": 1.4401788711547852, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.1009549795361528, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.021828103683492497, | |
| "grad_norm": 0.9245114922523499, | |
| "learning_rate": 5e-05, | |
| "loss": 1.9363, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.021828103683492497, | |
| "eval_loss": 2.335273027420044, | |
| "eval_runtime": 8.882, | |
| "eval_samples_per_second": 34.789, | |
| "eval_steps_per_second": 4.391, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04365620736698499, | |
| "grad_norm": 1.0181593894958496, | |
| "learning_rate": 0.0001, | |
| "loss": 1.9793, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.06548431105047749, | |
| "grad_norm": 0.9561858177185059, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.0359, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.08731241473396999, | |
| "grad_norm": 1.0221854448318481, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.8991, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.10914051841746249, | |
| "grad_norm": 1.0572049617767334, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.8444, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.13096862210095497, | |
| "grad_norm": 0.8805914521217346, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.6764, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.15279672578444747, | |
| "grad_norm": 0.9553704261779785, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.5805, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.17462482946793997, | |
| "grad_norm": 0.7353147864341736, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.5651, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.19645293315143247, | |
| "grad_norm": 1.216279149055481, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.6492, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.21828103683492497, | |
| "grad_norm": 1.324072003364563, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.8397, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.24010914051841747, | |
| "grad_norm": 1.6015604734420776, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.7865, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.26193724420190995, | |
| "grad_norm": 1.8760219812393188, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.6829, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2837653478854025, | |
| "grad_norm": 1.904744267463684, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.5403, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.30559345156889495, | |
| "grad_norm": 0.7079086899757385, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.4967, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3274215552523875, | |
| "grad_norm": 0.8759621381759644, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.5518, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.34924965893587995, | |
| "grad_norm": 0.860069751739502, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.5761, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.3710777626193724, | |
| "grad_norm": 0.5536974668502808, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.4873, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.39290586630286495, | |
| "grad_norm": 0.5986688733100891, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.5059, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.4147339699863574, | |
| "grad_norm": 0.7362739443778992, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.6102, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.43656207366984995, | |
| "grad_norm": 0.7832861542701721, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.6324, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.4583901773533424, | |
| "grad_norm": 1.031021237373352, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.7119, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.48021828103683495, | |
| "grad_norm": 1.0664341449737549, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.842, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.5020463847203275, | |
| "grad_norm": 0.6615095734596252, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.494, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.5238744884038199, | |
| "grad_norm": 0.605603039264679, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.4857, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5457025920873124, | |
| "grad_norm": 0.5263887643814087, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.4183, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5457025920873124, | |
| "eval_loss": 1.462013602256775, | |
| "eval_runtime": 8.8736, | |
| "eval_samples_per_second": 34.822, | |
| "eval_steps_per_second": 4.395, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.567530695770805, | |
| "grad_norm": 0.44412490725517273, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4738, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.5893587994542974, | |
| "grad_norm": 0.4294642210006714, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.4576, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.6111869031377899, | |
| "grad_norm": 0.46107932925224304, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.4545, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.6330150068212824, | |
| "grad_norm": 0.5138009786605835, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.4653, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.654843110504775, | |
| "grad_norm": 0.6419461965560913, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.5643, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.6766712141882674, | |
| "grad_norm": 0.7712287306785583, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.5594, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.6984993178717599, | |
| "grad_norm": 0.8432745337486267, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.689, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.7203274215552524, | |
| "grad_norm": 0.9621841907501221, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.7543, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.7421555252387448, | |
| "grad_norm": 0.5970948338508606, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.4379, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.7639836289222374, | |
| "grad_norm": 0.3458403944969177, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.4491, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.7858117326057299, | |
| "grad_norm": 0.3697258234024048, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.3815, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.8076398362892224, | |
| "grad_norm": 0.40853965282440186, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.4245, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.8294679399727148, | |
| "grad_norm": 0.4629148244857788, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.4196, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.8512960436562074, | |
| "grad_norm": 0.5173665881156921, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.51, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.8731241473396999, | |
| "grad_norm": 0.5273569226264954, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.4178, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.8949522510231923, | |
| "grad_norm": 0.6194100975990295, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.4843, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.9167803547066848, | |
| "grad_norm": 0.6384758353233337, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.4766, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.9386084583901774, | |
| "grad_norm": 0.7393871545791626, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.6202, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.9604365620736699, | |
| "grad_norm": 0.744990885257721, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.653, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.9822646657571623, | |
| "grad_norm": 0.9761192202568054, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.591, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.0136425648021827, | |
| "grad_norm": 0.6270838379859924, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 2.4549, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.0354706684856754, | |
| "grad_norm": 0.3342169225215912, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.3464, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.0572987721691678, | |
| "grad_norm": 0.361870139837265, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.3793, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.0791268758526602, | |
| "grad_norm": 0.413613498210907, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.4744, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.1009549795361528, | |
| "grad_norm": 0.42899948358535767, | |
| "learning_rate": 0.0, | |
| "loss": 1.4594, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.1009549795361528, | |
| "eval_loss": 1.4401788711547852, | |
| "eval_runtime": 8.8679, | |
| "eval_samples_per_second": 34.845, | |
| "eval_steps_per_second": 4.398, | |
| "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": 5.968083617316864e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |