{ "best_metric": 1.9395381212234497, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.32323232323232326, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.006464646464646465, "grad_norm": 0.13794121146202087, "learning_rate": 5e-05, "loss": 2.1076, "step": 1 }, { "epoch": 0.006464646464646465, "eval_loss": 2.1259307861328125, "eval_runtime": 18.9274, "eval_samples_per_second": 55.105, "eval_steps_per_second": 6.921, "step": 1 }, { "epoch": 0.01292929292929293, "grad_norm": 0.19002071022987366, "learning_rate": 0.0001, "loss": 2.1139, "step": 2 }, { "epoch": 0.019393939393939394, "grad_norm": 0.20002254843711853, "learning_rate": 9.989294616193017e-05, "loss": 2.1161, "step": 3 }, { "epoch": 0.02585858585858586, "grad_norm": 0.23847076296806335, "learning_rate": 9.957224306869053e-05, "loss": 2.0648, "step": 4 }, { "epoch": 0.03232323232323232, "grad_norm": 0.18669605255126953, "learning_rate": 9.903926402016153e-05, "loss": 2.0676, "step": 5 }, { "epoch": 0.03878787878787879, "grad_norm": 0.16979680955410004, "learning_rate": 9.829629131445342e-05, "loss": 2.0377, "step": 6 }, { "epoch": 0.04525252525252525, "grad_norm": 0.1790999323129654, "learning_rate": 9.73465064747553e-05, "loss": 2.0074, "step": 7 }, { "epoch": 0.05171717171717172, "grad_norm": 0.1701156347990036, "learning_rate": 9.619397662556435e-05, "loss": 1.9835, "step": 8 }, { "epoch": 0.05818181818181818, "grad_norm": 0.21324147284030914, "learning_rate": 9.484363707663442e-05, "loss": 1.9334, "step": 9 }, { "epoch": 0.06464646464646465, "grad_norm": 0.3143400251865387, "learning_rate": 9.330127018922194e-05, "loss": 1.8562, "step": 10 }, { "epoch": 0.07111111111111111, "grad_norm": 0.3273347318172455, "learning_rate": 9.157348061512727e-05, "loss": 1.8348, "step": 11 }, { "epoch": 0.07757575757575758, "grad_norm": 0.348003089427948, "learning_rate": 8.966766701456177e-05, "loss": 1.7444, "step": 12 }, { "epoch": 0.08404040404040404, "grad_norm": 0.34863314032554626, "learning_rate": 8.759199037394887e-05, "loss": 2.1291, "step": 13 }, { "epoch": 0.0905050505050505, "grad_norm": 0.3459385633468628, "learning_rate": 8.535533905932738e-05, "loss": 2.1046, "step": 14 }, { "epoch": 0.09696969696969697, "grad_norm": 0.2635910212993622, "learning_rate": 8.296729075500344e-05, "loss": 2.1029, "step": 15 }, { "epoch": 0.10343434343434343, "grad_norm": 0.2018289715051651, "learning_rate": 8.043807145043604e-05, "loss": 2.0579, "step": 16 }, { "epoch": 0.1098989898989899, "grad_norm": 0.15820299088954926, "learning_rate": 7.777851165098012e-05, "loss": 2.0294, "step": 17 }, { "epoch": 0.11636363636363636, "grad_norm": 0.17375575006008148, "learning_rate": 7.500000000000001e-05, "loss": 2.0248, "step": 18 }, { "epoch": 0.12282828282828283, "grad_norm": 0.16773708164691925, "learning_rate": 7.211443451095007e-05, "loss": 2.0072, "step": 19 }, { "epoch": 0.1292929292929293, "grad_norm": 0.15941676497459412, "learning_rate": 6.91341716182545e-05, "loss": 1.9344, "step": 20 }, { "epoch": 0.13575757575757577, "grad_norm": 0.16956786811351776, "learning_rate": 6.607197326515808e-05, "loss": 1.9306, "step": 21 }, { "epoch": 0.14222222222222222, "grad_norm": 0.21462693810462952, "learning_rate": 6.294095225512603e-05, "loss": 1.8964, "step": 22 }, { "epoch": 0.1486868686868687, "grad_norm": 0.3244251012802124, "learning_rate": 5.9754516100806423e-05, "loss": 1.8402, "step": 23 }, { "epoch": 0.15515151515151515, "grad_norm": 0.39707544445991516, "learning_rate": 5.6526309611002594e-05, "loss": 1.8173, "step": 24 }, { "epoch": 0.16161616161616163, "grad_norm": 0.5086701512336731, "learning_rate": 5.327015646150716e-05, "loss": 1.7137, "step": 25 }, { "epoch": 0.16161616161616163, "eval_loss": 1.9494298696517944, "eval_runtime": 18.9074, "eval_samples_per_second": 55.164, "eval_steps_per_second": 6.929, "step": 25 }, { "epoch": 0.16808080808080808, "grad_norm": 0.10119690001010895, "learning_rate": 5e-05, "loss": 2.0909, "step": 26 }, { "epoch": 0.17454545454545456, "grad_norm": 0.1081235408782959, "learning_rate": 4.6729843538492847e-05, "loss": 2.0909, "step": 27 }, { "epoch": 0.181010101010101, "grad_norm": 0.12175089120864868, "learning_rate": 4.347369038899744e-05, "loss": 2.0908, "step": 28 }, { "epoch": 0.1874747474747475, "grad_norm": 0.13839766383171082, "learning_rate": 4.0245483899193595e-05, "loss": 2.0257, "step": 29 }, { "epoch": 0.19393939393939394, "grad_norm": 0.1502249538898468, "learning_rate": 3.705904774487396e-05, "loss": 2.0209, "step": 30 }, { "epoch": 0.20040404040404042, "grad_norm": 0.16542190313339233, "learning_rate": 3.392802673484193e-05, "loss": 1.9956, "step": 31 }, { "epoch": 0.20686868686868687, "grad_norm": 0.1611490398645401, "learning_rate": 3.086582838174551e-05, "loss": 1.9543, "step": 32 }, { "epoch": 0.21333333333333335, "grad_norm": 0.1697140336036682, "learning_rate": 2.7885565489049946e-05, "loss": 1.9624, "step": 33 }, { "epoch": 0.2197979797979798, "grad_norm": 0.18247292935848236, "learning_rate": 2.500000000000001e-05, "loss": 1.8987, "step": 34 }, { "epoch": 0.22626262626262628, "grad_norm": 0.2177690714597702, "learning_rate": 2.2221488349019903e-05, "loss": 1.8438, "step": 35 }, { "epoch": 0.23272727272727273, "grad_norm": 0.2801283895969391, "learning_rate": 1.9561928549563968e-05, "loss": 1.8015, "step": 36 }, { "epoch": 0.2391919191919192, "grad_norm": 0.3550100028514862, "learning_rate": 1.703270924499656e-05, "loss": 1.7079, "step": 37 }, { "epoch": 0.24565656565656566, "grad_norm": 0.10651691257953644, "learning_rate": 1.4644660940672627e-05, "loss": 2.0448, "step": 38 }, { "epoch": 0.25212121212121213, "grad_norm": 0.10382003337144852, "learning_rate": 1.2408009626051137e-05, "loss": 2.0345, "step": 39 }, { "epoch": 0.2585858585858586, "grad_norm": 0.10816065967082977, "learning_rate": 1.0332332985438248e-05, "loss": 2.0477, "step": 40 }, { "epoch": 0.26505050505050504, "grad_norm": 0.13777312636375427, "learning_rate": 8.426519384872733e-06, "loss": 2.0325, "step": 41 }, { "epoch": 0.27151515151515154, "grad_norm": 0.12429886311292648, "learning_rate": 6.698729810778065e-06, "loss": 1.9577, "step": 42 }, { "epoch": 0.277979797979798, "grad_norm": 0.13117745518684387, "learning_rate": 5.156362923365588e-06, "loss": 2.0359, "step": 43 }, { "epoch": 0.28444444444444444, "grad_norm": 0.13389986753463745, "learning_rate": 3.8060233744356633e-06, "loss": 1.9874, "step": 44 }, { "epoch": 0.2909090909090909, "grad_norm": 0.14647652208805084, "learning_rate": 2.653493525244721e-06, "loss": 1.9679, "step": 45 }, { "epoch": 0.2973737373737374, "grad_norm": 0.1532333493232727, "learning_rate": 1.70370868554659e-06, "loss": 1.9175, "step": 46 }, { "epoch": 0.30383838383838385, "grad_norm": 0.1804121434688568, "learning_rate": 9.607359798384785e-07, "loss": 1.8934, "step": 47 }, { "epoch": 0.3103030303030303, "grad_norm": 0.23982085287570953, "learning_rate": 4.277569313094809e-07, "loss": 1.7789, "step": 48 }, { "epoch": 0.31676767676767675, "grad_norm": 0.3199950158596039, "learning_rate": 1.0705383806982606e-07, "loss": 1.7638, "step": 49 }, { "epoch": 0.32323232323232326, "grad_norm": 0.4603963792324066, "learning_rate": 0.0, "loss": 1.7108, "step": 50 }, { "epoch": 0.32323232323232326, "eval_loss": 1.9395381212234497, "eval_runtime": 18.9224, "eval_samples_per_second": 55.12, "eval_steps_per_second": 6.923, "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": 2.254995537788928e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }