| { | |
| "best_metric": 0.6260138750076294, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.10933442667760011, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002186688533552002, | |
| "grad_norm": 1.1105414628982544, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6609, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002186688533552002, | |
| "eval_loss": 1.4441356658935547, | |
| "eval_runtime": 182.5843, | |
| "eval_samples_per_second": 16.874, | |
| "eval_steps_per_second": 2.114, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004373377067104004, | |
| "grad_norm": 1.3735562562942505, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8495, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006560065600656006, | |
| "grad_norm": 1.4012031555175781, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 0.935, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.008746754134208008, | |
| "grad_norm": 0.6011267304420471, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.7601, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01093344266776001, | |
| "grad_norm": 0.5295389890670776, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.7598, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.013120131201312012, | |
| "grad_norm": 0.6502489447593689, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.7563, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.015306819734864016, | |
| "grad_norm": 0.5572352409362793, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.7585, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.017493508268416016, | |
| "grad_norm": 0.4851221740245819, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.7714, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.01968019680196802, | |
| "grad_norm": 0.406841903924942, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.7604, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02186688533552002, | |
| "grad_norm": 0.41418033838272095, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.7886, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.024053573869072024, | |
| "grad_norm": 0.4525168836116791, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.8056, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.026240262402624025, | |
| "grad_norm": 0.5825612545013428, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.8127, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.02842695093617603, | |
| "grad_norm": 0.3739285171031952, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.3493, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.030613639469728032, | |
| "grad_norm": 0.20394007861614227, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.4709, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03280032800328003, | |
| "grad_norm": 0.21499967575073242, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.5838, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03498701653683203, | |
| "grad_norm": 0.18819545209407806, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.5984, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.03717370507038404, | |
| "grad_norm": 0.21380701661109924, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.5902, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.03936039360393604, | |
| "grad_norm": 0.22303147614002228, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.6519, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04154708213748804, | |
| "grad_norm": 0.2147863209247589, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.6503, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04373377067104004, | |
| "grad_norm": 0.2406228929758072, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.6872, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04592045920459205, | |
| "grad_norm": 0.2548230290412903, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.6664, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.04810714773814405, | |
| "grad_norm": 0.30359193682670593, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.6854, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.05029383627169605, | |
| "grad_norm": 0.41962817311286926, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.7442, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.05248052480524805, | |
| "grad_norm": 0.45455101132392883, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.7666, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.05466721333880006, | |
| "grad_norm": 0.5619322061538696, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.7485, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05466721333880006, | |
| "eval_loss": 0.6429993510246277, | |
| "eval_runtime": 180.7656, | |
| "eval_samples_per_second": 17.044, | |
| "eval_steps_per_second": 2.135, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05685390187235206, | |
| "grad_norm": 0.16069209575653076, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3299, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.05904059040590406, | |
| "grad_norm": 0.17538459599018097, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.5203, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.061227278939456065, | |
| "grad_norm": 0.1931326687335968, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.5735, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.06341396747300806, | |
| "grad_norm": 0.206190824508667, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.5574, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.06560065600656007, | |
| "grad_norm": 0.20361047983169556, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.5864, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06778734454011207, | |
| "grad_norm": 0.24747894704341888, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.6423, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.06997403307366407, | |
| "grad_norm": 0.23271162807941437, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.6678, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.07216072160721607, | |
| "grad_norm": 0.24798904359340668, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.6408, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.07434741014076808, | |
| "grad_norm": 0.28206339478492737, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.6489, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.07653409867432008, | |
| "grad_norm": 0.33762359619140625, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.7041, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.07872078720787208, | |
| "grad_norm": 0.41767123341560364, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.7162, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.08090747574142408, | |
| "grad_norm": 0.4611891806125641, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.7631, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.08309416427497608, | |
| "grad_norm": 0.1755916178226471, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.3483, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.08528085280852808, | |
| "grad_norm": 0.15542787313461304, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.4641, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.08746754134208008, | |
| "grad_norm": 0.14870032668113708, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.5253, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0896542298756321, | |
| "grad_norm": 0.15303368866443634, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.5764, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0918409184091841, | |
| "grad_norm": 0.17057447135448456, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.6111, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0940276069427361, | |
| "grad_norm": 0.1693965494632721, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.6094, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0962142954762881, | |
| "grad_norm": 0.18184174597263336, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.6249, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0984009840098401, | |
| "grad_norm": 0.23067162930965424, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.654, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1005876725433921, | |
| "grad_norm": 0.25408676266670227, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.6695, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.1027743610769441, | |
| "grad_norm": 0.28090396523475647, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.6815, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.1049610496104961, | |
| "grad_norm": 0.38103654980659485, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.7202, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.10714773814404811, | |
| "grad_norm": 0.4314904510974884, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.7642, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.10933442667760011, | |
| "grad_norm": 0.5988128781318665, | |
| "learning_rate": 0.0, | |
| "loss": 0.7072, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.10933442667760011, | |
| "eval_loss": 0.6260138750076294, | |
| "eval_runtime": 181.3493, | |
| "eval_samples_per_second": 16.989, | |
| "eval_steps_per_second": 2.128, | |
| "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": 6.813744746410803e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |