| { | |
| "best_metric": 2.191683053970337, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.03611412062116288, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007222824124232575, | |
| "grad_norm": 8.923365592956543, | |
| "learning_rate": 5e-05, | |
| "loss": 2.4509, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007222824124232575, | |
| "eval_loss": 2.645667314529419, | |
| "eval_runtime": 454.6187, | |
| "eval_samples_per_second": 20.516, | |
| "eval_steps_per_second": 2.565, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001444564824846515, | |
| "grad_norm": 10.0977201461792, | |
| "learning_rate": 0.0001, | |
| "loss": 2.4898, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0021668472372697724, | |
| "grad_norm": 10.266446113586426, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.4814, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00288912964969303, | |
| "grad_norm": 6.914961338043213, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.3492, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0036114120621162874, | |
| "grad_norm": 3.9817748069763184, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.3709, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004333694474539545, | |
| "grad_norm": 3.5428454875946045, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.3368, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005055976886962802, | |
| "grad_norm": 4.146511554718018, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.3464, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00577825929938606, | |
| "grad_norm": 4.333606719970703, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.3451, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0065005417118093175, | |
| "grad_norm": 4.145175457000732, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.2307, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007222824124232575, | |
| "grad_norm": 3.5478930473327637, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.389, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007945106536655833, | |
| "grad_norm": 3.7317428588867188, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.3465, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00866738894907909, | |
| "grad_norm": 4.45909309387207, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.4326, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.009389671361502348, | |
| "grad_norm": 3.515819787979126, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.4245, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.010111953773925604, | |
| "grad_norm": 3.014991283416748, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.2316, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.010834236186348862, | |
| "grad_norm": 3.000011682510376, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.2088, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01155651859877212, | |
| "grad_norm": 2.4111955165863037, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.212, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.012278801011195377, | |
| "grad_norm": 2.1892237663269043, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 2.2043, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.013001083423618635, | |
| "grad_norm": 2.0798254013061523, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.2517, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.013723365836041893, | |
| "grad_norm": 2.3925435543060303, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 2.1524, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.01444564824846515, | |
| "grad_norm": 2.400036096572876, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.1919, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.015167930660888408, | |
| "grad_norm": 2.5018272399902344, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 2.1821, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.015890213073311666, | |
| "grad_norm": 3.0887036323547363, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 2.2386, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.016612495485734922, | |
| "grad_norm": 3.3591127395629883, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 2.2291, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.01733477789815818, | |
| "grad_norm": 3.623659372329712, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 2.1639, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01805706031058144, | |
| "grad_norm": 5.142810821533203, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 2.465, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01805706031058144, | |
| "eval_loss": 2.2178146839141846, | |
| "eval_runtime": 453.616, | |
| "eval_samples_per_second": 20.561, | |
| "eval_steps_per_second": 2.57, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.018779342723004695, | |
| "grad_norm": 2.463944435119629, | |
| "learning_rate": 5e-05, | |
| "loss": 2.2202, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.01950162513542795, | |
| "grad_norm": 2.5546419620513916, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 2.2016, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.020223907547851208, | |
| "grad_norm": 3.138413429260254, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 2.236, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.020946189960274468, | |
| "grad_norm": 3.267152786254883, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 2.2221, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.021668472372697724, | |
| "grad_norm": 2.7643165588378906, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 2.1869, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02239075478512098, | |
| "grad_norm": 2.357870578765869, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 2.1428, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.02311303719754424, | |
| "grad_norm": 2.3059284687042236, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.1879, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.023835319609967497, | |
| "grad_norm": 2.3275415897369385, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 2.1146, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.024557602022390754, | |
| "grad_norm": 2.5051019191741943, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.1424, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.025279884434814014, | |
| "grad_norm": 2.978761911392212, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 2.1838, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.02600216684723727, | |
| "grad_norm": 2.9468026161193848, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 2.1519, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.026724449259660527, | |
| "grad_norm": 4.417997360229492, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 2.266, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.027446731672083786, | |
| "grad_norm": 3.7377946376800537, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.4016, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.028169014084507043, | |
| "grad_norm": 1.8437291383743286, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 2.2582, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0288912964969303, | |
| "grad_norm": 2.100909948348999, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 2.2269, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.029613578909353556, | |
| "grad_norm": 2.0871973037719727, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 2.1468, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.030335861321776816, | |
| "grad_norm": 2.019470691680908, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 2.1884, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.031058143734200072, | |
| "grad_norm": 2.251432418823242, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 2.1517, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.03178042614662333, | |
| "grad_norm": 2.1813924312591553, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.1458, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.032502708559046585, | |
| "grad_norm": 2.3104052543640137, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 2.1803, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.033224990971469845, | |
| "grad_norm": 2.5009100437164307, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 2.1618, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.033947273383893105, | |
| "grad_norm": 2.5242321491241455, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 2.1527, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.03466955579631636, | |
| "grad_norm": 2.7807717323303223, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 2.1826, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.03539183820873962, | |
| "grad_norm": 3.412902593612671, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 2.2023, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.03611412062116288, | |
| "grad_norm": 4.9823317527771, | |
| "learning_rate": 0.0, | |
| "loss": 2.3556, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03611412062116288, | |
| "eval_loss": 2.191683053970337, | |
| "eval_runtime": 453.534, | |
| "eval_samples_per_second": 20.565, | |
| "eval_steps_per_second": 2.571, | |
| "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": 2.9773479893847245e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |