| { | |
| "best_metric": 1.0168567895889282, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.06777363605557438, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0013554727211114877, | |
| "grad_norm": 36.596012115478516, | |
| "learning_rate": 5e-05, | |
| "loss": 63.4065, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013554727211114877, | |
| "eval_loss": 3.8362667560577393, | |
| "eval_runtime": 213.6984, | |
| "eval_samples_per_second": 23.257, | |
| "eval_steps_per_second": 2.911, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0027109454422229754, | |
| "grad_norm": 38.99151611328125, | |
| "learning_rate": 0.0001, | |
| "loss": 64.8437, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004066418163334463, | |
| "grad_norm": 41.29121017456055, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 65.1126, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005421890884445951, | |
| "grad_norm": 42.77500534057617, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 60.8543, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006777363605557438, | |
| "grad_norm": 32.83053207397461, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 49.4978, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008132836326668925, | |
| "grad_norm": 38.703086853027344, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 46.339, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009488309047780414, | |
| "grad_norm": 42.6236572265625, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 41.951, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.010843781768891902, | |
| "grad_norm": 30.51891326904297, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 35.5313, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.012199254490003388, | |
| "grad_norm": 36.923702239990234, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 31.8236, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.013554727211114876, | |
| "grad_norm": 21.106178283691406, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 32.1737, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.014910199932226365, | |
| "grad_norm": 37.03933334350586, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 27.7951, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.01626567265333785, | |
| "grad_norm": 50.268577575683594, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 28.1014, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01762114537444934, | |
| "grad_norm": 61.605918884277344, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 28.6188, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.018976618095560827, | |
| "grad_norm": 214.79013061523438, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 25.8743, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.020332090816672314, | |
| "grad_norm": 451.5144348144531, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 28.1142, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.021687563537783804, | |
| "grad_norm": 292.95025634765625, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 28.5825, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.02304303625889529, | |
| "grad_norm": 254.0452880859375, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 28.3858, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.024398508980006776, | |
| "grad_norm": 75.8310775756836, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 26.6884, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.025753981701118266, | |
| "grad_norm": 60.58232116699219, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 27.6412, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.027109454422229753, | |
| "grad_norm": 39.16401290893555, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 24.6649, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02846492714334124, | |
| "grad_norm": 32.388431549072266, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 25.1232, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02982039986445273, | |
| "grad_norm": 22.858781814575195, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 21.7579, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.031175872585564215, | |
| "grad_norm": 17.251733779907227, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 21.4803, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0325313453066757, | |
| "grad_norm": 20.60053825378418, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 20.8267, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03388681802778719, | |
| "grad_norm": 22.706756591796875, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 22.8192, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03388681802778719, | |
| "eval_loss": 1.2665033340454102, | |
| "eval_runtime": 213.7001, | |
| "eval_samples_per_second": 23.257, | |
| "eval_steps_per_second": 2.911, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03524229074889868, | |
| "grad_norm": 18.225135803222656, | |
| "learning_rate": 5e-05, | |
| "loss": 20.766, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.03659776347001017, | |
| "grad_norm": 16.9871768951416, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 21.6636, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.037953236191121655, | |
| "grad_norm": 17.358606338500977, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 19.1701, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03930870891223314, | |
| "grad_norm": 17.15289306640625, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 18.1974, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.04066418163334463, | |
| "grad_norm": 13.593099594116211, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 18.8118, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.042019654354456114, | |
| "grad_norm": 15.375582695007324, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 18.5611, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.04337512707556761, | |
| "grad_norm": 15.086400985717773, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 18.7409, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.044730599796679094, | |
| "grad_norm": 20.995872497558594, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 18.5098, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.04608607251779058, | |
| "grad_norm": 33.625465393066406, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 17.3266, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.047441545238902066, | |
| "grad_norm": 16.21245574951172, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 17.6345, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04879701796001355, | |
| "grad_norm": 16.550430297851562, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 16.328, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.05015249068112504, | |
| "grad_norm": 19.983448028564453, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 18.239, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.05150796340223653, | |
| "grad_norm": 20.869291305541992, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 19.6876, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.05286343612334802, | |
| "grad_norm": 18.964210510253906, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 16.477, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.054218908844459505, | |
| "grad_norm": 15.887338638305664, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 16.8681, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05557438156557099, | |
| "grad_norm": 16.398021697998047, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 15.5168, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.05692985428668248, | |
| "grad_norm": 23.358903884887695, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 17.0795, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.058285327007793965, | |
| "grad_norm": 27.82067108154297, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 17.604, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.05964079972890546, | |
| "grad_norm": 21.790048599243164, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 17.5052, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.060996272450016945, | |
| "grad_norm": 21.848608016967773, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 17.0257, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.06235174517112843, | |
| "grad_norm": 15.1517333984375, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 16.9079, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.06370721789223992, | |
| "grad_norm": 14.538222312927246, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 15.9922, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0650626906133514, | |
| "grad_norm": 16.66765785217285, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 17.3769, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.06641816333446289, | |
| "grad_norm": 18.048357009887695, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 16.0147, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.06777363605557438, | |
| "grad_norm": 19.516748428344727, | |
| "learning_rate": 0.0, | |
| "loss": 18.572, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06777363605557438, | |
| "eval_loss": 1.0168567895889282, | |
| "eval_runtime": 213.7505, | |
| "eval_samples_per_second": 23.251, | |
| "eval_steps_per_second": 2.91, | |
| "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": 5.259156315439104e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |