| { | |
| "best_metric": 0.7183287143707275, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.4184397163120568, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.028368794326241134, | |
| "grad_norm": 3.583650588989258, | |
| "learning_rate": 5e-05, | |
| "loss": 1.9778, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.028368794326241134, | |
| "eval_loss": 2.142423629760742, | |
| "eval_runtime": 17.2512, | |
| "eval_samples_per_second": 13.796, | |
| "eval_steps_per_second": 1.739, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05673758865248227, | |
| "grad_norm": 4.6802778244018555, | |
| "learning_rate": 0.0001, | |
| "loss": 2.0171, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0851063829787234, | |
| "grad_norm": 3.03648042678833, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.7015, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.11347517730496454, | |
| "grad_norm": 2.8811120986938477, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.4013, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.14184397163120568, | |
| "grad_norm": 2.1845221519470215, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.1624, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1702127659574468, | |
| "grad_norm": 2.2986996173858643, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.9492, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.19858156028368795, | |
| "grad_norm": 1.9965656995773315, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.7071, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.22695035460992907, | |
| "grad_norm": 1.9633533954620361, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.5672, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.2553191489361702, | |
| "grad_norm": 2.7532734870910645, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.2355, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.28368794326241137, | |
| "grad_norm": 2.8143556118011475, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.287, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3120567375886525, | |
| "grad_norm": 1.7883267402648926, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.0704, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.3404255319148936, | |
| "grad_norm": 1.5733007192611694, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.984, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.36879432624113473, | |
| "grad_norm": 2.026470899581909, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.8609, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.3971631205673759, | |
| "grad_norm": 1.6229561567306519, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.7816, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.425531914893617, | |
| "grad_norm": 1.168531894683838, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.6721, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.45390070921985815, | |
| "grad_norm": 0.882336437702179, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.5504, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.48226950354609927, | |
| "grad_norm": 1.123659610748291, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.5288, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.5106382978723404, | |
| "grad_norm": 1.6023423671722412, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.1514, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.5390070921985816, | |
| "grad_norm": 1.6665570735931396, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.1521, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.5673758865248227, | |
| "grad_norm": 1.448330283164978, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.0183, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5957446808510638, | |
| "grad_norm": 1.2645760774612427, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.8652, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.624113475177305, | |
| "grad_norm": 1.1755330562591553, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.7396, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.6524822695035462, | |
| "grad_norm": 1.072890043258667, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.6991, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.6808510638297872, | |
| "grad_norm": 0.9242495894432068, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.5401, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.7092198581560284, | |
| "grad_norm": 1.1206426620483398, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.5489, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.7092198581560284, | |
| "eval_loss": 0.7767251133918762, | |
| "eval_runtime": 7.9117, | |
| "eval_samples_per_second": 30.082, | |
| "eval_steps_per_second": 3.792, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.7375886524822695, | |
| "grad_norm": 1.975343108177185, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5047, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.7659574468085106, | |
| "grad_norm": 1.0302635431289673, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.1042, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.7943262411347518, | |
| "grad_norm": 0.9461258053779602, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.9609, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.8226950354609929, | |
| "grad_norm": 0.8858218789100647, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.894, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.851063829787234, | |
| "grad_norm": 0.8415829539299011, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.7884, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.8794326241134752, | |
| "grad_norm": 0.7886775732040405, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.7462, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.9078014184397163, | |
| "grad_norm": 0.805213212966919, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.635, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.9361702127659575, | |
| "grad_norm": 0.9563062191009521, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.5737, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.9645390070921985, | |
| "grad_norm": 1.0272057056427002, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.5183, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.9929078014184397, | |
| "grad_norm": 2.298342704772949, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.5251, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.0212765957446808, | |
| "grad_norm": 1.6830999851226807, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.5769, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.049645390070922, | |
| "grad_norm": 1.0642327070236206, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.8534, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.0780141843971631, | |
| "grad_norm": 1.0689526796340942, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.7813, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.1063829787234043, | |
| "grad_norm": 1.1304749250411987, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.7206, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.1347517730496455, | |
| "grad_norm": 1.0267786979675293, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.6546, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.1631205673758864, | |
| "grad_norm": 1.0408142805099487, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.5775, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.1914893617021276, | |
| "grad_norm": 1.1746472120285034, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.4895, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.2198581560283688, | |
| "grad_norm": 1.1773086786270142, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.4423, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.24822695035461, | |
| "grad_norm": 1.0412017107009888, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.2604, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.2765957446808511, | |
| "grad_norm": 1.3813236951828003, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.4494, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.3049645390070923, | |
| "grad_norm": 1.0576671361923218, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.8167, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 1.0873304605484009, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.755, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.3617021276595744, | |
| "grad_norm": 1.2028731107711792, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.6773, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.3900709219858156, | |
| "grad_norm": 1.0739576816558838, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.6052, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.4184397163120568, | |
| "grad_norm": 1.1737654209136963, | |
| "learning_rate": 0.0, | |
| "loss": 0.5532, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.4184397163120568, | |
| "eval_loss": 0.7183287143707275, | |
| "eval_runtime": 7.9142, | |
| "eval_samples_per_second": 30.073, | |
| "eval_steps_per_second": 3.791, | |
| "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": 6.174479344467968e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |