| { | |
| "best_metric": 11.931046485900879, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.1314060446780552, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005256241787122208, | |
| "grad_norm": 0.031087756156921387, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9294, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005256241787122208, | |
| "eval_loss": 11.931995391845703, | |
| "eval_runtime": 0.1797, | |
| "eval_samples_per_second": 278.18, | |
| "eval_steps_per_second": 72.327, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010512483574244415, | |
| "grad_norm": 0.021583933383226395, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9337, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01576872536136662, | |
| "grad_norm": 0.02136208303272724, | |
| "learning_rate": 9.958086757163489e-05, | |
| "loss": 11.9331, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02102496714848883, | |
| "grad_norm": 0.027043230831623077, | |
| "learning_rate": 9.833127793065098e-05, | |
| "loss": 11.9289, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.026281208935611037, | |
| "grad_norm": 0.029573684558272362, | |
| "learning_rate": 9.627450856774539e-05, | |
| "loss": 11.9309, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03153745072273324, | |
| "grad_norm": 0.029559683054685593, | |
| "learning_rate": 9.3448873204592e-05, | |
| "loss": 11.93, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03679369250985545, | |
| "grad_norm": 0.029743574559688568, | |
| "learning_rate": 8.990700808169889e-05, | |
| "loss": 11.9305, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.04204993429697766, | |
| "grad_norm": 0.025356736034154892, | |
| "learning_rate": 8.571489144483944e-05, | |
| "loss": 11.9294, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04730617608409987, | |
| "grad_norm": 0.02380228601396084, | |
| "learning_rate": 8.095061449516903e-05, | |
| "loss": 11.93, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.052562417871222074, | |
| "grad_norm": 0.022178111597895622, | |
| "learning_rate": 7.570292669790186e-05, | |
| "loss": 11.9293, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05781865965834428, | |
| "grad_norm": 0.022478066384792328, | |
| "learning_rate": 7.006958254769438e-05, | |
| "loss": 11.9324, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.06307490144546649, | |
| "grad_norm": 0.027834568172693253, | |
| "learning_rate": 6.415552058736854e-05, | |
| "loss": 11.9276, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0683311432325887, | |
| "grad_norm": 0.024634726345539093, | |
| "learning_rate": 5.80709086014102e-05, | |
| "loss": 11.9289, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0735873850197109, | |
| "grad_norm": 0.02856062725186348, | |
| "learning_rate": 5.192909139858981e-05, | |
| "loss": 11.9313, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.07884362680683311, | |
| "grad_norm": 0.027086956426501274, | |
| "learning_rate": 4.584447941263149e-05, | |
| "loss": 11.9307, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.08409986859395532, | |
| "grad_norm": 0.02562597393989563, | |
| "learning_rate": 3.9930417452305626e-05, | |
| "loss": 11.9306, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.08935611038107753, | |
| "grad_norm": 0.03616712614893913, | |
| "learning_rate": 3.4297073302098156e-05, | |
| "loss": 11.9308, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.09461235216819974, | |
| "grad_norm": 0.034863367676734924, | |
| "learning_rate": 2.9049385504830985e-05, | |
| "loss": 11.9294, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.09986859395532194, | |
| "grad_norm": 0.03076382353901863, | |
| "learning_rate": 2.4285108555160577e-05, | |
| "loss": 11.9293, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.10512483574244415, | |
| "grad_norm": 0.032090578228235245, | |
| "learning_rate": 2.0092991918301108e-05, | |
| "loss": 11.9295, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11038107752956636, | |
| "grad_norm": 0.03169110789895058, | |
| "learning_rate": 1.6551126795408016e-05, | |
| "loss": 11.9311, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.11563731931668857, | |
| "grad_norm": 0.029576878994703293, | |
| "learning_rate": 1.3725491432254624e-05, | |
| "loss": 11.9276, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.12089356110381078, | |
| "grad_norm": 0.03367379680275917, | |
| "learning_rate": 1.1668722069349041e-05, | |
| "loss": 11.9305, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.12614980289093297, | |
| "grad_norm": 0.022545788437128067, | |
| "learning_rate": 1.0419132428365116e-05, | |
| "loss": 11.931, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1314060446780552, | |
| "grad_norm": 0.03471825644373894, | |
| "learning_rate": 1e-05, | |
| "loss": 11.9286, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1314060446780552, | |
| "eval_loss": 11.931046485900879, | |
| "eval_runtime": 0.1749, | |
| "eval_samples_per_second": 285.828, | |
| "eval_steps_per_second": 74.315, | |
| "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": 521247129600.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |