| { | |
| "best_metric": 0.6238670945167542, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 1.084010840108401, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04336043360433604, | |
| "grad_norm": 0.48692163825035095, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7452, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04336043360433604, | |
| "eval_loss": 0.8691906929016113, | |
| "eval_runtime": 3.0353, | |
| "eval_samples_per_second": 16.473, | |
| "eval_steps_per_second": 4.283, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.08672086720867209, | |
| "grad_norm": 0.5825616121292114, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7731, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.13008130081300814, | |
| "grad_norm": 0.4881550371646881, | |
| "learning_rate": 9.958086757163489e-05, | |
| "loss": 0.8063, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.17344173441734417, | |
| "grad_norm": 0.46501851081848145, | |
| "learning_rate": 9.833127793065098e-05, | |
| "loss": 0.7796, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.21680216802168023, | |
| "grad_norm": 0.3957728445529938, | |
| "learning_rate": 9.627450856774539e-05, | |
| "loss": 0.725, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2601626016260163, | |
| "grad_norm": 0.41878509521484375, | |
| "learning_rate": 9.3448873204592e-05, | |
| "loss": 0.6277, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3035230352303523, | |
| "grad_norm": 0.46268048882484436, | |
| "learning_rate": 8.990700808169889e-05, | |
| "loss": 0.6828, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.34688346883468835, | |
| "grad_norm": 0.37090781331062317, | |
| "learning_rate": 8.571489144483944e-05, | |
| "loss": 0.6465, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3902439024390244, | |
| "grad_norm": 0.3264720141887665, | |
| "learning_rate": 8.095061449516903e-05, | |
| "loss": 0.6234, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.43360433604336046, | |
| "grad_norm": 0.2802322208881378, | |
| "learning_rate": 7.570292669790186e-05, | |
| "loss": 0.6072, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.47696476964769646, | |
| "grad_norm": 0.2779908776283264, | |
| "learning_rate": 7.006958254769438e-05, | |
| "loss": 0.6124, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.5203252032520326, | |
| "grad_norm": 0.42195311188697815, | |
| "learning_rate": 6.415552058736854e-05, | |
| "loss": 0.6223, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5636856368563685, | |
| "grad_norm": 0.23575882613658905, | |
| "learning_rate": 5.80709086014102e-05, | |
| "loss": 0.6357, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.6070460704607046, | |
| "grad_norm": 0.22414590418338776, | |
| "learning_rate": 5.192909139858981e-05, | |
| "loss": 0.6305, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.6504065040650406, | |
| "grad_norm": 0.24856938421726227, | |
| "learning_rate": 4.584447941263149e-05, | |
| "loss": 0.602, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6937669376693767, | |
| "grad_norm": 0.2788071632385254, | |
| "learning_rate": 3.9930417452305626e-05, | |
| "loss": 0.5465, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.7371273712737128, | |
| "grad_norm": 0.30255916714668274, | |
| "learning_rate": 3.4297073302098156e-05, | |
| "loss": 0.5927, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.7804878048780488, | |
| "grad_norm": 0.21226972341537476, | |
| "learning_rate": 2.9049385504830985e-05, | |
| "loss": 0.6291, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.8238482384823849, | |
| "grad_norm": 0.2064390927553177, | |
| "learning_rate": 2.4285108555160577e-05, | |
| "loss": 0.6034, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.8672086720867209, | |
| "grad_norm": 0.21271000802516937, | |
| "learning_rate": 2.0092991918301108e-05, | |
| "loss": 0.6088, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.9105691056910569, | |
| "grad_norm": 0.23489035665988922, | |
| "learning_rate": 1.6551126795408016e-05, | |
| "loss": 0.5954, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.9539295392953929, | |
| "grad_norm": 0.2558073401451111, | |
| "learning_rate": 1.3725491432254624e-05, | |
| "loss": 0.605, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.997289972899729, | |
| "grad_norm": 0.28163567185401917, | |
| "learning_rate": 1.1668722069349041e-05, | |
| "loss": 0.5452, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.040650406504065, | |
| "grad_norm": 0.8378793001174927, | |
| "learning_rate": 1.0419132428365116e-05, | |
| "loss": 1.1507, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.084010840108401, | |
| "grad_norm": 0.20984496176242828, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6272, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.084010840108401, | |
| "eval_loss": 0.6238670945167542, | |
| "eval_runtime": 3.091, | |
| "eval_samples_per_second": 16.176, | |
| "eval_steps_per_second": 4.206, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 2.629553998528512e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |