| { | |
| "best_metric": 0.4216839075088501, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.5449591280653951, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.010899182561307902, | |
| "grad_norm": 48.334930419921875, | |
| "learning_rate": 5e-05, | |
| "loss": 10.5681, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010899182561307902, | |
| "eval_loss": 11.284085273742676, | |
| "eval_runtime": 32.4269, | |
| "eval_samples_per_second": 19.058, | |
| "eval_steps_per_second": 2.405, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.021798365122615803, | |
| "grad_norm": 51.34646987915039, | |
| "learning_rate": 0.0001, | |
| "loss": 10.0866, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0326975476839237, | |
| "grad_norm": 30.734779357910156, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 5.7853, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.043596730245231606, | |
| "grad_norm": 10.935500144958496, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.0325, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.05449591280653951, | |
| "grad_norm": 6.813920974731445, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.9098, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0653950953678474, | |
| "grad_norm": 3.5395240783691406, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.6013, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07629427792915532, | |
| "grad_norm": 5.146648406982422, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.575, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.08719346049046321, | |
| "grad_norm": 2.045412540435791, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.5183, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.09809264305177112, | |
| "grad_norm": 2.0153496265411377, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.5145, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.10899182561307902, | |
| "grad_norm": 1.4971418380737305, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.4488, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11989100817438691, | |
| "grad_norm": 5.10093355178833, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.5873, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1307901907356948, | |
| "grad_norm": 3.391411781311035, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.5884, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.14168937329700274, | |
| "grad_norm": 2.1817774772644043, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.591, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.15258855585831063, | |
| "grad_norm": 1.477457880973816, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.5558, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.16348773841961853, | |
| "grad_norm": 0.7660332918167114, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.5087, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.17438692098092642, | |
| "grad_norm": 1.6169441938400269, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.4857, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.18528610354223432, | |
| "grad_norm": 2.446556568145752, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.4854, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.19618528610354224, | |
| "grad_norm": 1.8394956588745117, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.4433, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.20708446866485014, | |
| "grad_norm": 2.452279567718506, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.435, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.21798365122615804, | |
| "grad_norm": 2.270860195159912, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.4276, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.22888283378746593, | |
| "grad_norm": 1.0671144723892212, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.4334, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.23978201634877383, | |
| "grad_norm": 0.8742726445198059, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.4164, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.2506811989100817, | |
| "grad_norm": 1.552753210067749, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.3616, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2615803814713896, | |
| "grad_norm": 1.963327407836914, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.4068, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2724795640326976, | |
| "grad_norm": 2.3681602478027344, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.5229, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2724795640326976, | |
| "eval_loss": 0.5041758418083191, | |
| "eval_runtime": 32.4374, | |
| "eval_samples_per_second": 19.052, | |
| "eval_steps_per_second": 2.405, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.28337874659400547, | |
| "grad_norm": 4.118583679199219, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4394, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.29427792915531337, | |
| "grad_norm": 2.555344581604004, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.4048, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.30517711171662126, | |
| "grad_norm": 2.8441410064697266, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.4419, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.31607629427792916, | |
| "grad_norm": 1.463327407836914, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.3937, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.32697547683923706, | |
| "grad_norm": 1.5427021980285645, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.4078, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.33787465940054495, | |
| "grad_norm": 1.2628159523010254, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.4284, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.34877384196185285, | |
| "grad_norm": 1.524219274520874, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.405, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.35967302452316074, | |
| "grad_norm": 1.321671962738037, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.4124, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.37057220708446864, | |
| "grad_norm": 1.3506972789764404, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.3914, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.3814713896457766, | |
| "grad_norm": 1.0806541442871094, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.3978, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3923705722070845, | |
| "grad_norm": 0.7781311869621277, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.3966, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.4032697547683924, | |
| "grad_norm": 1.2545527219772339, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.3881, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.4141689373297003, | |
| "grad_norm": 1.2499167919158936, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.4066, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.4250681198910082, | |
| "grad_norm": 1.8262399435043335, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.3859, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.4359673024523161, | |
| "grad_norm": 1.667894721031189, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.4104, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.44686648501362397, | |
| "grad_norm": 0.9992119669914246, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.3886, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.45776566757493187, | |
| "grad_norm": 1.4388220310211182, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.379, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.46866485013623976, | |
| "grad_norm": 1.5127443075180054, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.3874, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.47956403269754766, | |
| "grad_norm": 1.4673212766647339, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.3158, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.4904632152588556, | |
| "grad_norm": 1.724837064743042, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.4141, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5013623978201635, | |
| "grad_norm": 1.2674442529678345, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.3687, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.5122615803814714, | |
| "grad_norm": 2.083022356033325, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.42, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.5231607629427792, | |
| "grad_norm": 1.465240240097046, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.3703, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.5340599455040872, | |
| "grad_norm": 1.7388436794281006, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.4232, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.5449591280653951, | |
| "grad_norm": 1.4903584718704224, | |
| "learning_rate": 0.0, | |
| "loss": 0.4242, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5449591280653951, | |
| "eval_loss": 0.4216839075088501, | |
| "eval_runtime": 32.4334, | |
| "eval_samples_per_second": 19.054, | |
| "eval_steps_per_second": 2.405, | |
| "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": 6.631381723512832e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |