| { | |
| "best_metric": 0.4648851156234741, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.11417154274297131, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0022834308548594262, | |
| "grad_norm": 0.22559398412704468, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3501, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0022834308548594262, | |
| "eval_loss": 0.6596930623054504, | |
| "eval_runtime": 200.1881, | |
| "eval_samples_per_second": 14.741, | |
| "eval_steps_per_second": 1.843, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0045668617097188524, | |
| "grad_norm": 0.22919631004333496, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3151, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006850292564578279, | |
| "grad_norm": 0.2545759975910187, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 0.4304, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009133723419437705, | |
| "grad_norm": 0.23282743990421295, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.3648, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01141715427429713, | |
| "grad_norm": 0.22734428942203522, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.3844, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.013700585129156558, | |
| "grad_norm": 0.32344239950180054, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.4446, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.015984015984015984, | |
| "grad_norm": 0.25610044598579407, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.4174, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01826744683887541, | |
| "grad_norm": 0.19879823923110962, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.5232, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.020550877693734836, | |
| "grad_norm": 0.2444503903388977, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.596, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02283430854859426, | |
| "grad_norm": 0.2801436185836792, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.7173, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02511773940345369, | |
| "grad_norm": 0.29815584421157837, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.7865, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.027401170258313116, | |
| "grad_norm": 0.3620450794696808, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.9747, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.029684601113172542, | |
| "grad_norm": 0.18315419554710388, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.4203, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03196803196803197, | |
| "grad_norm": 0.17548008263111115, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.2471, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0342514628228914, | |
| "grad_norm": 0.220022052526474, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.3949, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03653489367775082, | |
| "grad_norm": 0.17819145321846008, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.3722, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.03881832453261025, | |
| "grad_norm": 0.19627267122268677, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.4137, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04110175538746967, | |
| "grad_norm": 0.15671569108963013, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.4389, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0433851862423291, | |
| "grad_norm": 0.16053399443626404, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.4783, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04566861709718852, | |
| "grad_norm": 0.16855283081531525, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.5583, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04795204795204795, | |
| "grad_norm": 0.19199872016906738, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.5753, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05023547880690738, | |
| "grad_norm": 0.22297468781471252, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.6232, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.052518909661766804, | |
| "grad_norm": 0.25045719742774963, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.6832, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.05480234051662623, | |
| "grad_norm": 0.31544703245162964, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.8324, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.057085771371485655, | |
| "grad_norm": 0.4587164521217346, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.0082, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.057085771371485655, | |
| "eval_loss": 0.47236114740371704, | |
| "eval_runtime": 200.2165, | |
| "eval_samples_per_second": 14.739, | |
| "eval_steps_per_second": 1.843, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.059369202226345084, | |
| "grad_norm": 0.11356440931558609, | |
| "learning_rate": 5e-05, | |
| "loss": 0.2328, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.06165263308120451, | |
| "grad_norm": 0.12556737661361694, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.2785, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.06393606393606394, | |
| "grad_norm": 0.13164840638637543, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.2977, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.06621949479092336, | |
| "grad_norm": 0.16159792244434357, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.4175, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0685029256457828, | |
| "grad_norm": 0.16275496780872345, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.4616, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07078635650064222, | |
| "grad_norm": 0.16565589606761932, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.4595, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.07306978735550164, | |
| "grad_norm": 0.18394418060779572, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.5079, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.07535321821036106, | |
| "grad_norm": 0.1702607125043869, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.3712, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0776366490652205, | |
| "grad_norm": 0.2136932760477066, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.6439, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.07992007992007992, | |
| "grad_norm": 0.23648518323898315, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.5586, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08220351077493934, | |
| "grad_norm": 0.27319836616516113, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.7303, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.08448694162979878, | |
| "grad_norm": 0.35524117946624756, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.9086, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0867703724846582, | |
| "grad_norm": 0.2031528353691101, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.3624, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.08905380333951762, | |
| "grad_norm": 0.0991303101181984, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.2811, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.09133723419437705, | |
| "grad_norm": 0.10457004606723785, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.3733, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09362066504923648, | |
| "grad_norm": 0.11494916677474976, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.3843, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0959040959040959, | |
| "grad_norm": 0.12473290413618088, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.434, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.09818752675895533, | |
| "grad_norm": 0.1304829865694046, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.4221, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.10047095761381476, | |
| "grad_norm": 0.1233222633600235, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.3852, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.10275438846867418, | |
| "grad_norm": 0.15903952717781067, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.5617, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.10503781932353361, | |
| "grad_norm": 0.2569705843925476, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.5424, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.10732125017839303, | |
| "grad_norm": 0.1869916319847107, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.6157, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.10960468103325247, | |
| "grad_norm": 0.23289279639720917, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.7795, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.11188811188811189, | |
| "grad_norm": 0.3144865036010742, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.8344, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.11417154274297131, | |
| "grad_norm": 0.4401632845401764, | |
| "learning_rate": 0.0, | |
| "loss": 0.9783, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.11417154274297131, | |
| "eval_loss": 0.4648851156234741, | |
| "eval_runtime": 200.2466, | |
| "eval_samples_per_second": 14.737, | |
| "eval_steps_per_second": 1.843, | |
| "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": 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 | |
| } | |