| { | |
| "best_metric": 1.6392896175384521, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.6514657980456026, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.013029315960912053, | |
| "grad_norm": 4.139136791229248, | |
| "learning_rate": 5e-05, | |
| "loss": 4.4207, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013029315960912053, | |
| "eval_loss": 6.510675430297852, | |
| "eval_runtime": 15.7697, | |
| "eval_samples_per_second": 32.784, | |
| "eval_steps_per_second": 4.122, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.026058631921824105, | |
| "grad_norm": 4.689591407775879, | |
| "learning_rate": 0.0001, | |
| "loss": 4.8966, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03908794788273615, | |
| "grad_norm": 5.493028163909912, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 4.8022, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05211726384364821, | |
| "grad_norm": 4.579153537750244, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 4.1035, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06514657980456026, | |
| "grad_norm": 4.905165672302246, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.2565, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0781758957654723, | |
| "grad_norm": 3.7031538486480713, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.7356, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.09120521172638436, | |
| "grad_norm": 3.1968441009521484, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.7279, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.10423452768729642, | |
| "grad_norm": 3.473313093185425, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.4495, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.11726384364820847, | |
| "grad_norm": 3.8224689960479736, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.2317, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.13029315960912052, | |
| "grad_norm": 2.7436556816101074, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.1773, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14332247557003258, | |
| "grad_norm": 3.2410264015197754, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.8731, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1563517915309446, | |
| "grad_norm": 7.049959182739258, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.5939, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.16938110749185667, | |
| "grad_norm": 9.249019622802734, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.9236, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.18241042345276873, | |
| "grad_norm": 7.12423849105835, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.6659, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.19543973941368079, | |
| "grad_norm": 3.718914270401001, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.3087, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.20846905537459284, | |
| "grad_norm": 2.0409340858459473, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.3382, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.22149837133550487, | |
| "grad_norm": 2.006042242050171, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 2.1424, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.23452768729641693, | |
| "grad_norm": 2.1970691680908203, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.0763, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.247557003257329, | |
| "grad_norm": 2.3917160034179688, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 2.1011, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.26058631921824105, | |
| "grad_norm": 2.2477595806121826, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.0157, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2736156351791531, | |
| "grad_norm": 1.7341458797454834, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.8822, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.28664495114006516, | |
| "grad_norm": 1.9003583192825317, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.8711, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.2996742671009772, | |
| "grad_norm": 1.9300239086151123, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.4577, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3127035830618892, | |
| "grad_norm": 1.921851634979248, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.2073, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3257328990228013, | |
| "grad_norm": 9.920126914978027, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.6304, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3257328990228013, | |
| "eval_loss": 1.8528634309768677, | |
| "eval_runtime": 15.7871, | |
| "eval_samples_per_second": 32.748, | |
| "eval_steps_per_second": 4.117, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.33876221498371334, | |
| "grad_norm": 3.202028751373291, | |
| "learning_rate": 5e-05, | |
| "loss": 2.3397, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.3517915309446254, | |
| "grad_norm": 2.898632764816284, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 2.2195, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.36482084690553745, | |
| "grad_norm": 2.4346694946289062, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.9748, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.3778501628664495, | |
| "grad_norm": 2.3225157260894775, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 2.0881, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.39087947882736157, | |
| "grad_norm": 1.7192515134811401, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.7137, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.40390879478827363, | |
| "grad_norm": 1.475867509841919, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.8545, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.4169381107491857, | |
| "grad_norm": 1.7031975984573364, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.824, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.42996742671009774, | |
| "grad_norm": 1.7940890789031982, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.8246, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.44299674267100975, | |
| "grad_norm": 1.6462401151657104, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.6737, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.4560260586319218, | |
| "grad_norm": 1.8870519399642944, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.5229, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.46905537459283386, | |
| "grad_norm": 2.078465223312378, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.4339, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.4820846905537459, | |
| "grad_norm": 2.843310832977295, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.1289, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.495114006514658, | |
| "grad_norm": 1.7793502807617188, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.8975, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.50814332247557, | |
| "grad_norm": 1.516412377357483, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 2.003, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5211726384364821, | |
| "grad_norm": 1.5982497930526733, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.9499, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5342019543973942, | |
| "grad_norm": 1.562781810760498, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.8598, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5472312703583062, | |
| "grad_norm": 1.4703500270843506, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.8388, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.5602605863192183, | |
| "grad_norm": 1.4454585313796997, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.8969, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.5732899022801303, | |
| "grad_norm": 1.5187628269195557, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.7079, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.5863192182410424, | |
| "grad_norm": 1.3791704177856445, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.5546, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5993485342019544, | |
| "grad_norm": 1.5736020803451538, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.6179, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6123778501628665, | |
| "grad_norm": 1.7379757165908813, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.7742, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6254071661237784, | |
| "grad_norm": 1.689818024635315, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.352, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6384364820846905, | |
| "grad_norm": 1.7637438774108887, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.1788, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6514657980456026, | |
| "grad_norm": 2.6566402912139893, | |
| "learning_rate": 0.0, | |
| "loss": 0.5134, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6514657980456026, | |
| "eval_loss": 1.6392896175384521, | |
| "eval_runtime": 15.8031, | |
| "eval_samples_per_second": 32.715, | |
| "eval_steps_per_second": 4.113, | |
| "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": 5.968083617316864e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |