| { | |
| "best_metric": 0.5023321509361267, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.2822865208186309, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.011291460832745237, | |
| "grad_norm": 0.36136147379875183, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5234, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011291460832745237, | |
| "eval_loss": 0.6947125792503357, | |
| "eval_runtime": 12.1388, | |
| "eval_samples_per_second": 4.119, | |
| "eval_steps_per_second": 4.119, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.022582921665490474, | |
| "grad_norm": 0.43794548511505127, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6383, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03387438249823571, | |
| "grad_norm": 0.4361836612224579, | |
| "learning_rate": 9.958086757163489e-05, | |
| "loss": 0.6403, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.04516584333098095, | |
| "grad_norm": 0.3344646394252777, | |
| "learning_rate": 9.833127793065098e-05, | |
| "loss": 0.5563, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.056457304163726185, | |
| "grad_norm": 0.31822192668914795, | |
| "learning_rate": 9.627450856774539e-05, | |
| "loss": 0.5234, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06774876499647142, | |
| "grad_norm": 0.32926616072654724, | |
| "learning_rate": 9.3448873204592e-05, | |
| "loss": 0.5045, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07904022582921666, | |
| "grad_norm": 0.33659106492996216, | |
| "learning_rate": 8.990700808169889e-05, | |
| "loss": 0.5373, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0903316866619619, | |
| "grad_norm": 0.3877531588077545, | |
| "learning_rate": 8.571489144483944e-05, | |
| "loss": 0.5248, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.10162314749470713, | |
| "grad_norm": 0.37099218368530273, | |
| "learning_rate": 8.095061449516903e-05, | |
| "loss": 0.5172, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.11291460832745237, | |
| "grad_norm": 0.2924746572971344, | |
| "learning_rate": 7.570292669790186e-05, | |
| "loss": 0.5064, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12420606916019761, | |
| "grad_norm": 0.31302541494369507, | |
| "learning_rate": 7.006958254769438e-05, | |
| "loss": 0.5152, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.13549752999294284, | |
| "grad_norm": 0.33571746945381165, | |
| "learning_rate": 6.415552058736854e-05, | |
| "loss": 0.5368, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.14678899082568808, | |
| "grad_norm": 0.315120130777359, | |
| "learning_rate": 5.80709086014102e-05, | |
| "loss": 0.5116, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.15808045165843332, | |
| "grad_norm": 0.25852781534194946, | |
| "learning_rate": 5.192909139858981e-05, | |
| "loss": 0.5024, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.16937191249117856, | |
| "grad_norm": 0.2634642422199249, | |
| "learning_rate": 4.584447941263149e-05, | |
| "loss": 0.5143, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1806633733239238, | |
| "grad_norm": 0.28968214988708496, | |
| "learning_rate": 3.9930417452305626e-05, | |
| "loss": 0.5071, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.19195483415666903, | |
| "grad_norm": 0.2684546709060669, | |
| "learning_rate": 3.4297073302098156e-05, | |
| "loss": 0.508, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.20324629498941427, | |
| "grad_norm": 0.274639755487442, | |
| "learning_rate": 2.9049385504830985e-05, | |
| "loss": 0.4927, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2145377558221595, | |
| "grad_norm": 0.2751311957836151, | |
| "learning_rate": 2.4285108555160577e-05, | |
| "loss": 0.5432, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.22582921665490474, | |
| "grad_norm": 0.2907402515411377, | |
| "learning_rate": 2.0092991918301108e-05, | |
| "loss": 0.5894, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.23712067748764998, | |
| "grad_norm": 0.2752492427825928, | |
| "learning_rate": 1.6551126795408016e-05, | |
| "loss": 0.4972, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.24841213832039521, | |
| "grad_norm": 0.2894921600818634, | |
| "learning_rate": 1.3725491432254624e-05, | |
| "loss": 0.5509, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.25970359915314045, | |
| "grad_norm": 0.1830475777387619, | |
| "learning_rate": 1.1668722069349041e-05, | |
| "loss": 0.416, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2709950599858857, | |
| "grad_norm": 0.23708757758140564, | |
| "learning_rate": 1.0419132428365116e-05, | |
| "loss": 0.4849, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2822865208186309, | |
| "grad_norm": 0.2340831458568573, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4941, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2822865208186309, | |
| "eval_loss": 0.5023321509361267, | |
| "eval_runtime": 12.3098, | |
| "eval_samples_per_second": 4.062, | |
| "eval_steps_per_second": 4.062, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "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": 7.46010452164608e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |