|
{ |
|
"best_metric": 0.6459671854972839, |
|
"best_model_checkpoint": "miner_id_24/checkpoint-50", |
|
"epoch": 0.06207806316442927, |
|
"eval_steps": 25, |
|
"global_step": 50, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0012415612632885853, |
|
"grad_norm": 0.4338114559650421, |
|
"learning_rate": 5e-05, |
|
"loss": 0.9528, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0012415612632885853, |
|
"eval_loss": 0.8670650124549866, |
|
"eval_runtime": 135.4435, |
|
"eval_samples_per_second": 40.061, |
|
"eval_steps_per_second": 5.013, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0024831225265771707, |
|
"grad_norm": 0.3199804425239563, |
|
"learning_rate": 0.0001, |
|
"loss": 0.8353, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.003724683789865756, |
|
"grad_norm": 0.34869617223739624, |
|
"learning_rate": 9.989294616193017e-05, |
|
"loss": 0.8952, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.004966245053154341, |
|
"grad_norm": 0.2707532048225403, |
|
"learning_rate": 9.957224306869053e-05, |
|
"loss": 0.8736, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.006207806316442927, |
|
"grad_norm": 0.24987579882144928, |
|
"learning_rate": 9.903926402016153e-05, |
|
"loss": 0.821, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.007449367579731512, |
|
"grad_norm": 0.2585524022579193, |
|
"learning_rate": 9.829629131445342e-05, |
|
"loss": 0.8276, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.008690928843020097, |
|
"grad_norm": 0.27001699805259705, |
|
"learning_rate": 9.73465064747553e-05, |
|
"loss": 0.794, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.009932490106308683, |
|
"grad_norm": 0.2764400839805603, |
|
"learning_rate": 9.619397662556435e-05, |
|
"loss": 0.8022, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.011174051369597269, |
|
"grad_norm": 0.2692529559135437, |
|
"learning_rate": 9.484363707663442e-05, |
|
"loss": 0.7329, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.012415612632885854, |
|
"grad_norm": 0.2532176375389099, |
|
"learning_rate": 9.330127018922194e-05, |
|
"loss": 0.6992, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.01365717389617444, |
|
"grad_norm": 0.2420653998851776, |
|
"learning_rate": 9.157348061512727e-05, |
|
"loss": 0.6047, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.014898735159463024, |
|
"grad_norm": 0.2832377552986145, |
|
"learning_rate": 8.966766701456177e-05, |
|
"loss": 0.5085, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.01614029642275161, |
|
"grad_norm": 0.5778734087944031, |
|
"learning_rate": 8.759199037394887e-05, |
|
"loss": 0.8946, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.017381857686040194, |
|
"grad_norm": 0.20259259641170502, |
|
"learning_rate": 8.535533905932738e-05, |
|
"loss": 0.6674, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.01862341894932878, |
|
"grad_norm": 0.18697814643383026, |
|
"learning_rate": 8.296729075500344e-05, |
|
"loss": 0.6915, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.019864980212617366, |
|
"grad_norm": 0.18954052031040192, |
|
"learning_rate": 8.043807145043604e-05, |
|
"loss": 0.7364, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.021106541475905953, |
|
"grad_norm": 0.17210833728313446, |
|
"learning_rate": 7.777851165098012e-05, |
|
"loss": 0.6746, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.022348102739194537, |
|
"grad_norm": 0.1925540417432785, |
|
"learning_rate": 7.500000000000001e-05, |
|
"loss": 0.7289, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.02358966400248312, |
|
"grad_norm": 0.18113888800144196, |
|
"learning_rate": 7.211443451095007e-05, |
|
"loss": 0.6931, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.02483122526577171, |
|
"grad_norm": 0.1875569373369217, |
|
"learning_rate": 6.91341716182545e-05, |
|
"loss": 0.737, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.026072786529060293, |
|
"grad_norm": 0.18100717663764954, |
|
"learning_rate": 6.607197326515808e-05, |
|
"loss": 0.7101, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.02731434779234888, |
|
"grad_norm": 0.16578786075115204, |
|
"learning_rate": 6.294095225512603e-05, |
|
"loss": 0.613, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.028555909055637464, |
|
"grad_norm": 0.1748124659061432, |
|
"learning_rate": 5.9754516100806423e-05, |
|
"loss": 0.609, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.02979747031892605, |
|
"grad_norm": 0.17466582357883453, |
|
"learning_rate": 5.6526309611002594e-05, |
|
"loss": 0.4765, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.031039031582214636, |
|
"grad_norm": 0.2356194257736206, |
|
"learning_rate": 5.327015646150716e-05, |
|
"loss": 0.3753, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.031039031582214636, |
|
"eval_loss": 0.6584460139274597, |
|
"eval_runtime": 46.7151, |
|
"eval_samples_per_second": 116.151, |
|
"eval_steps_per_second": 14.535, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.03228059284550322, |
|
"grad_norm": 0.23359929025173187, |
|
"learning_rate": 5e-05, |
|
"loss": 0.7075, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.03352215410879181, |
|
"grad_norm": 0.15845683217048645, |
|
"learning_rate": 4.6729843538492847e-05, |
|
"loss": 0.6823, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.03476371537208039, |
|
"grad_norm": 0.15037257969379425, |
|
"learning_rate": 4.347369038899744e-05, |
|
"loss": 0.6786, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.036005276635368975, |
|
"grad_norm": 0.15445923805236816, |
|
"learning_rate": 4.0245483899193595e-05, |
|
"loss": 0.7396, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 0.03724683789865756, |
|
"grad_norm": 0.15990139544010162, |
|
"learning_rate": 3.705904774487396e-05, |
|
"loss": 0.7291, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.03848839916194615, |
|
"grad_norm": 0.139845073223114, |
|
"learning_rate": 3.392802673484193e-05, |
|
"loss": 0.6508, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 0.03972996042523473, |
|
"grad_norm": 0.14541897177696228, |
|
"learning_rate": 3.086582838174551e-05, |
|
"loss": 0.679, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 0.04097152168852332, |
|
"grad_norm": 0.1448265165090561, |
|
"learning_rate": 2.7885565489049946e-05, |
|
"loss": 0.6659, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 0.042213082951811906, |
|
"grad_norm": 0.14122691750526428, |
|
"learning_rate": 2.500000000000001e-05, |
|
"loss": 0.6712, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 0.04345464421510049, |
|
"grad_norm": 0.157490074634552, |
|
"learning_rate": 2.2221488349019903e-05, |
|
"loss": 0.6074, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.044696205478389074, |
|
"grad_norm": 0.16067852079868317, |
|
"learning_rate": 1.9561928549563968e-05, |
|
"loss": 0.5234, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 0.04593776674167766, |
|
"grad_norm": 0.1827419102191925, |
|
"learning_rate": 1.703270924499656e-05, |
|
"loss": 0.4291, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 0.04717932800496624, |
|
"grad_norm": 0.4607616364955902, |
|
"learning_rate": 1.4644660940672627e-05, |
|
"loss": 0.7925, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 0.04842088926825483, |
|
"grad_norm": 0.1292809545993805, |
|
"learning_rate": 1.2408009626051137e-05, |
|
"loss": 0.6489, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 0.04966245053154342, |
|
"grad_norm": 0.13788002729415894, |
|
"learning_rate": 1.0332332985438248e-05, |
|
"loss": 0.7076, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.050904011794832, |
|
"grad_norm": 0.13166581094264984, |
|
"learning_rate": 8.426519384872733e-06, |
|
"loss": 0.7163, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 0.052145573058120585, |
|
"grad_norm": 0.13151279091835022, |
|
"learning_rate": 6.698729810778065e-06, |
|
"loss": 0.7093, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 0.05338713432140917, |
|
"grad_norm": 0.13615787029266357, |
|
"learning_rate": 5.156362923365588e-06, |
|
"loss": 0.6487, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 0.05462869558469776, |
|
"grad_norm": 0.14063283801078796, |
|
"learning_rate": 3.8060233744356633e-06, |
|
"loss": 0.6809, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 0.05587025684798634, |
|
"grad_norm": 0.13367421925067902, |
|
"learning_rate": 2.653493525244721e-06, |
|
"loss": 0.6908, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.05711181811127493, |
|
"grad_norm": 0.138374924659729, |
|
"learning_rate": 1.70370868554659e-06, |
|
"loss": 0.6654, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 0.058353379374563516, |
|
"grad_norm": 0.15195026993751526, |
|
"learning_rate": 9.607359798384785e-07, |
|
"loss": 0.6068, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 0.0595949406378521, |
|
"grad_norm": 0.15703357756137848, |
|
"learning_rate": 4.277569313094809e-07, |
|
"loss": 0.5665, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 0.060836501901140684, |
|
"grad_norm": 0.16355907917022705, |
|
"learning_rate": 1.0705383806982606e-07, |
|
"loss": 0.4578, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 0.06207806316442927, |
|
"grad_norm": 0.2248668223619461, |
|
"learning_rate": 0.0, |
|
"loss": 0.3556, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.06207806316442927, |
|
"eval_loss": 0.6459671854972839, |
|
"eval_runtime": 46.181, |
|
"eval_samples_per_second": 117.494, |
|
"eval_steps_per_second": 14.703, |
|
"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": 8.42792324479058e+16, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|