| { | |
| "best_metric": 0.9729824066162109, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.014164305949008499, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00028328611898016995, | |
| "grad_norm": 2.4837124347686768, | |
| "learning_rate": 5e-06, | |
| "loss": 1.0328, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00028328611898016995, | |
| "eval_loss": 1.364790678024292, | |
| "eval_runtime": 482.3304, | |
| "eval_samples_per_second": 12.328, | |
| "eval_steps_per_second": 6.164, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005665722379603399, | |
| "grad_norm": 0.7393561005592346, | |
| "learning_rate": 1e-05, | |
| "loss": 1.044, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008498583569405099, | |
| "grad_norm": 0.5064038038253784, | |
| "learning_rate": 1.5e-05, | |
| "loss": 1.0228, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0011331444759206798, | |
| "grad_norm": 1.1812818050384521, | |
| "learning_rate": 2e-05, | |
| "loss": 1.0907, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00141643059490085, | |
| "grad_norm": 0.7924461364746094, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.1227, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0016997167138810198, | |
| "grad_norm": 0.5778879523277283, | |
| "learning_rate": 3e-05, | |
| "loss": 1.0562, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00198300283286119, | |
| "grad_norm": 0.7456988096237183, | |
| "learning_rate": 3.5e-05, | |
| "loss": 1.0785, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0022662889518413596, | |
| "grad_norm": 0.5129983425140381, | |
| "learning_rate": 4e-05, | |
| "loss": 1.0225, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0025495750708215297, | |
| "grad_norm": 0.4113961458206177, | |
| "learning_rate": 4.5e-05, | |
| "loss": 1.0419, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0028328611898017, | |
| "grad_norm": 0.37529513239860535, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9771, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0031161473087818695, | |
| "grad_norm": 0.4042710065841675, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.9975, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0033994334277620396, | |
| "grad_norm": 0.3994333744049072, | |
| "learning_rate": 6e-05, | |
| "loss": 1.0203, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0036827195467422098, | |
| "grad_norm": 0.430587500333786, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 0.981, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.00396600566572238, | |
| "grad_norm": 0.4299090504646301, | |
| "learning_rate": 7e-05, | |
| "loss": 0.9638, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.00424929178470255, | |
| "grad_norm": 0.41372954845428467, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.9036, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004532577903682719, | |
| "grad_norm": 0.4030589163303375, | |
| "learning_rate": 8e-05, | |
| "loss": 0.8851, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004815864022662889, | |
| "grad_norm": 0.43109366297721863, | |
| "learning_rate": 8.5e-05, | |
| "loss": 0.9949, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0050991501416430595, | |
| "grad_norm": 0.4088292419910431, | |
| "learning_rate": 9e-05, | |
| "loss": 0.9794, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00538243626062323, | |
| "grad_norm": 0.3350220322608948, | |
| "learning_rate": 9.5e-05, | |
| "loss": 0.8792, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0056657223796034, | |
| "grad_norm": 0.30330002307891846, | |
| "learning_rate": 0.0001, | |
| "loss": 0.878, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00594900849858357, | |
| "grad_norm": 0.3451264500617981, | |
| "learning_rate": 9.999238475781957e-05, | |
| "loss": 0.8818, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.006232294617563739, | |
| "grad_norm": 0.3362950384616852, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 0.8614, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.006515580736543909, | |
| "grad_norm": 0.36854445934295654, | |
| "learning_rate": 9.99314767377287e-05, | |
| "loss": 0.8847, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.006798866855524079, | |
| "grad_norm": 0.3834778666496277, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.9134, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.007082152974504249, | |
| "grad_norm": 0.4009423851966858, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 0.8813, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0073654390934844195, | |
| "grad_norm": 0.32073336839675903, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 0.8641, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.00764872521246459, | |
| "grad_norm": 0.3810870051383972, | |
| "learning_rate": 9.962730758206611e-05, | |
| "loss": 0.9017, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.00793201133144476, | |
| "grad_norm": 0.40584418177604675, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 0.9204, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.00821529745042493, | |
| "grad_norm": 0.29945215582847595, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 0.8645, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0084985835694051, | |
| "grad_norm": 0.4067940413951874, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 0.9061, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.008781869688385268, | |
| "grad_norm": 0.4845235049724579, | |
| "learning_rate": 9.908135917238321e-05, | |
| "loss": 0.9485, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.009065155807365438, | |
| "grad_norm": 0.4056897461414337, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.9093, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.009348441926345609, | |
| "grad_norm": 0.43699613213539124, | |
| "learning_rate": 9.871850323926177e-05, | |
| "loss": 0.9523, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.009631728045325779, | |
| "grad_norm": 0.5528873205184937, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 0.8597, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.009915014164305949, | |
| "grad_norm": 0.5298404097557068, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.0194, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.010198300283286119, | |
| "grad_norm": 0.5607902407646179, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 0.9661, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.010481586402266289, | |
| "grad_norm": 0.6369351744651794, | |
| "learning_rate": 9.781523779815179e-05, | |
| "loss": 1.0808, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.01076487252124646, | |
| "grad_norm": 0.5015552639961243, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.9148, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.01104815864022663, | |
| "grad_norm": 0.5619277954101562, | |
| "learning_rate": 9.727592877996585e-05, | |
| "loss": 1.0133, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0113314447592068, | |
| "grad_norm": 0.7182181477546692, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.994, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01161473087818697, | |
| "grad_norm": 0.7005313634872437, | |
| "learning_rate": 9.667902132486009e-05, | |
| "loss": 1.0247, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.01189801699716714, | |
| "grad_norm": 0.771409273147583, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 1.1388, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.012181303116147308, | |
| "grad_norm": 0.6452864408493042, | |
| "learning_rate": 9.602524267262203e-05, | |
| "loss": 1.0388, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.012464589235127478, | |
| "grad_norm": 0.7697048783302307, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 1.0937, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.012747875354107648, | |
| "grad_norm": 0.8071401119232178, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 0.938, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.013031161473087818, | |
| "grad_norm": 0.9409806728363037, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 1.23, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.013314447592067988, | |
| "grad_norm": 0.9912319779396057, | |
| "learning_rate": 9.45503262094184e-05, | |
| "loss": 1.0184, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.013597733711048159, | |
| "grad_norm": 1.4439435005187988, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 1.1788, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.013881019830028329, | |
| "grad_norm": 1.5036474466323853, | |
| "learning_rate": 9.373098535696979e-05, | |
| "loss": 1.0626, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.014164305949008499, | |
| "grad_norm": 2.3197476863861084, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.0557, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.014164305949008499, | |
| "eval_loss": 0.9729824066162109, | |
| "eval_runtime": 485.1181, | |
| "eval_samples_per_second": 12.257, | |
| "eval_steps_per_second": 6.128, | |
| "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": 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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.8634147815424e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |