| { | |
| "best_metric": 11.927355766296387, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.2336448598130841, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004672897196261682, | |
| "grad_norm": 0.015262666158378124, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 11.9336, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004672897196261682, | |
| "eval_loss": 11.933741569519043, | |
| "eval_runtime": 0.2661, | |
| "eval_samples_per_second": 187.865, | |
| "eval_steps_per_second": 26.301, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009345794392523364, | |
| "grad_norm": 0.010072018951177597, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 11.9349, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.014018691588785047, | |
| "grad_norm": 0.014539014548063278, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 11.9336, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.018691588785046728, | |
| "grad_norm": 0.012826521880924702, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 11.9343, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02336448598130841, | |
| "grad_norm": 0.01322372816503048, | |
| "learning_rate": 0.00015, | |
| "loss": 11.9332, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.028037383177570093, | |
| "grad_norm": 0.011686271987855434, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 11.9324, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03271028037383177, | |
| "grad_norm": 0.01585233211517334, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 11.9335, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.037383177570093455, | |
| "grad_norm": 0.011046156287193298, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 11.9347, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04205607476635514, | |
| "grad_norm": 0.01065156888216734, | |
| "learning_rate": 0.00027, | |
| "loss": 11.9333, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04672897196261682, | |
| "grad_norm": 0.00867808423936367, | |
| "learning_rate": 0.0003, | |
| "loss": 11.9356, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0514018691588785, | |
| "grad_norm": 0.011804298497736454, | |
| "learning_rate": 0.0002999794957488703, | |
| "loss": 11.933, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.056074766355140186, | |
| "grad_norm": 0.012750547379255295, | |
| "learning_rate": 0.0002999179886011389, | |
| "loss": 11.9328, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.06074766355140187, | |
| "grad_norm": 0.010166078805923462, | |
| "learning_rate": 0.0002998154953722457, | |
| "loss": 11.934, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.06542056074766354, | |
| "grad_norm": 0.008991819806396961, | |
| "learning_rate": 0.00029967204408281613, | |
| "loss": 11.9359, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.07009345794392523, | |
| "grad_norm": 0.012300461530685425, | |
| "learning_rate": 0.00029948767395100045, | |
| "loss": 11.9335, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07476635514018691, | |
| "grad_norm": 0.01353101059794426, | |
| "learning_rate": 0.0002992624353817517, | |
| "loss": 11.9321, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0794392523364486, | |
| "grad_norm": 0.011064659804105759, | |
| "learning_rate": 0.0002989963899530457, | |
| "loss": 11.9329, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.08411214953271028, | |
| "grad_norm": 0.010729066096246243, | |
| "learning_rate": 0.00029868961039904624, | |
| "loss": 11.9339, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.08878504672897196, | |
| "grad_norm": 0.012338140979409218, | |
| "learning_rate": 0.00029834218059022024, | |
| "loss": 11.933, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.09345794392523364, | |
| "grad_norm": 0.011216608807444572, | |
| "learning_rate": 0.00029795419551040833, | |
| "loss": 11.9326, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09813084112149532, | |
| "grad_norm": 0.011954426765441895, | |
| "learning_rate": 0.00029752576123085736, | |
| "loss": 11.932, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.102803738317757, | |
| "grad_norm": 0.012529377825558186, | |
| "learning_rate": 0.0002970569948812214, | |
| "loss": 11.9341, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.10747663551401869, | |
| "grad_norm": 0.013572929427027702, | |
| "learning_rate": 0.0002965480246175399, | |
| "loss": 11.9341, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.11214953271028037, | |
| "grad_norm": 0.014423901215195656, | |
| "learning_rate": 0.0002959989895872009, | |
| "loss": 11.9338, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.11682242990654206, | |
| "grad_norm": 0.01651933416724205, | |
| "learning_rate": 0.0002954100398908995, | |
| "loss": 11.9333, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11682242990654206, | |
| "eval_loss": 11.932720184326172, | |
| "eval_runtime": 0.2737, | |
| "eval_samples_per_second": 182.703, | |
| "eval_steps_per_second": 25.578, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.12149532710280374, | |
| "grad_norm": 0.01691250689327717, | |
| "learning_rate": 0.0002947813365416023, | |
| "loss": 11.9356, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.1261682242990654, | |
| "grad_norm": 0.01488806214183569, | |
| "learning_rate": 0.0002941130514205272, | |
| "loss": 11.9327, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.1308411214953271, | |
| "grad_norm": 0.011068173684179783, | |
| "learning_rate": 0.0002934053672301536, | |
| "loss": 11.9306, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.13551401869158877, | |
| "grad_norm": 0.01614326983690262, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 11.9339, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.14018691588785046, | |
| "grad_norm": 0.017582055181264877, | |
| "learning_rate": 0.00029187258625509513, | |
| "loss": 11.9326, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.14485981308411214, | |
| "grad_norm": 0.021076716482639313, | |
| "learning_rate": 0.00029104790851742417, | |
| "loss": 11.9312, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.14953271028037382, | |
| "grad_norm": 0.031267255544662476, | |
| "learning_rate": 0.0002901846696899191, | |
| "loss": 11.9309, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.1542056074766355, | |
| "grad_norm": 0.028096068650484085, | |
| "learning_rate": 0.00028928310577345606, | |
| "loss": 11.9308, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1588785046728972, | |
| "grad_norm": 0.024486729875206947, | |
| "learning_rate": 0.0002883434632466077, | |
| "loss": 11.934, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.16355140186915887, | |
| "grad_norm": 0.021672122180461884, | |
| "learning_rate": 0.00028736599899825856, | |
| "loss": 11.9301, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.16822429906542055, | |
| "grad_norm": 0.0294785276055336, | |
| "learning_rate": 0.00028635098025737434, | |
| "loss": 11.9303, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.17289719626168223, | |
| "grad_norm": 0.029576191678643227, | |
| "learning_rate": 0.00028529868451994384, | |
| "loss": 11.9298, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.17757009345794392, | |
| "grad_norm": 0.03013836406171322, | |
| "learning_rate": 0.0002842093994731145, | |
| "loss": 11.9297, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.1822429906542056, | |
| "grad_norm": 0.039979491382837296, | |
| "learning_rate": 0.00028308342291654174, | |
| "loss": 11.9309, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.18691588785046728, | |
| "grad_norm": 0.047189485281705856, | |
| "learning_rate": 0.00028192106268097334, | |
| "loss": 11.9321, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.19158878504672897, | |
| "grad_norm": 0.04108109697699547, | |
| "learning_rate": 0.00028072263654409154, | |
| "loss": 11.9305, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.19626168224299065, | |
| "grad_norm": 0.05130422115325928, | |
| "learning_rate": 0.0002794884721436361, | |
| "loss": 11.932, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.20093457943925233, | |
| "grad_norm": 0.041305627673864365, | |
| "learning_rate": 0.00027821890688783083, | |
| "loss": 11.9291, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.205607476635514, | |
| "grad_norm": 0.05282793566584587, | |
| "learning_rate": 0.0002769142878631403, | |
| "loss": 11.9339, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.2102803738317757, | |
| "grad_norm": 0.04912222549319267, | |
| "learning_rate": 0.00027557497173937923, | |
| "loss": 11.927, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.21495327102803738, | |
| "grad_norm": 0.07533613592386246, | |
| "learning_rate": 0.000274201324672203, | |
| "loss": 11.9275, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.21962616822429906, | |
| "grad_norm": 0.06588118523359299, | |
| "learning_rate": 0.00027279372220300385, | |
| "loss": 11.931, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.22429906542056074, | |
| "grad_norm": 0.07589995115995407, | |
| "learning_rate": 0.0002713525491562421, | |
| "loss": 11.928, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.22897196261682243, | |
| "grad_norm": 0.06371214240789413, | |
| "learning_rate": 0.00026987819953423867, | |
| "loss": 11.9286, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.2336448598130841, | |
| "grad_norm": 0.0883798599243164, | |
| "learning_rate": 0.00026837107640945905, | |
| "loss": 11.932, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2336448598130841, | |
| "eval_loss": 11.927355766296387, | |
| "eval_runtime": 0.2651, | |
| "eval_samples_per_second": 188.605, | |
| "eval_steps_per_second": 26.405, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 79631155200.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |