|
{ |
|
"best_metric": NaN, |
|
"best_model_checkpoint": "miner_id_24/checkpoint-25", |
|
"epoch": 0.036845983787767135, |
|
"eval_steps": 25, |
|
"global_step": 50, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0007369196757553427, |
|
"grad_norm": NaN, |
|
"learning_rate": 1e-05, |
|
"loss": 0.0, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0007369196757553427, |
|
"eval_loss": NaN, |
|
"eval_runtime": 79.6152, |
|
"eval_samples_per_second": 14.357, |
|
"eval_steps_per_second": 3.592, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0014738393515106854, |
|
"grad_norm": NaN, |
|
"learning_rate": 2e-05, |
|
"loss": 0.0, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.002210759027266028, |
|
"grad_norm": NaN, |
|
"learning_rate": 3e-05, |
|
"loss": 0.0, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.0029476787030213707, |
|
"grad_norm": NaN, |
|
"learning_rate": 4e-05, |
|
"loss": 0.0, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.0036845983787767134, |
|
"grad_norm": NaN, |
|
"learning_rate": 5e-05, |
|
"loss": 0.0, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.004421518054532056, |
|
"grad_norm": NaN, |
|
"learning_rate": 6e-05, |
|
"loss": 0.0, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.005158437730287398, |
|
"grad_norm": NaN, |
|
"learning_rate": 7e-05, |
|
"loss": 0.0, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.0058953574060427415, |
|
"grad_norm": NaN, |
|
"learning_rate": 8e-05, |
|
"loss": 0.0, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.006632277081798084, |
|
"grad_norm": NaN, |
|
"learning_rate": 9e-05, |
|
"loss": 0.0, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.007369196757553427, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.008106116433308769, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.98458666866564e-05, |
|
"loss": 0.0, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.008843036109064112, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.938441702975689e-05, |
|
"loss": 0.0, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.009579955784819455, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.861849601988383e-05, |
|
"loss": 0.0, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.010316875460574797, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.755282581475769e-05, |
|
"loss": 0.0, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.01105379513633014, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.619397662556435e-05, |
|
"loss": 0.0, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.011790714812085483, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.45503262094184e-05, |
|
"loss": 0.0, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.012527634487840826, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.263200821770461e-05, |
|
"loss": 0.0, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.013264554163596167, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.045084971874738e-05, |
|
"loss": 0.0, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.01400147383935151, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.802029828000156e-05, |
|
"loss": 0.0, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.014738393515106854, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.535533905932738e-05, |
|
"loss": 0.0, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.015475313190862197, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.247240241650918e-05, |
|
"loss": 0.0, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.016212232866617538, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.938926261462366e-05, |
|
"loss": 0.0, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.01694915254237288, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.612492823579745e-05, |
|
"loss": 0.0, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.017686072218128224, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.269952498697734e-05, |
|
"loss": 0.0, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.018422991893883568, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.91341716182545e-05, |
|
"loss": 0.0, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.018422991893883568, |
|
"eval_loss": NaN, |
|
"eval_runtime": 79.1258, |
|
"eval_samples_per_second": 14.445, |
|
"eval_steps_per_second": 3.614, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.01915991156963891, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.545084971874738e-05, |
|
"loss": 0.0, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.01989683124539425, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.167226819279528e-05, |
|
"loss": 0.0, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.020633750921149593, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.782172325201155e-05, |
|
"loss": 0.0, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.021370670596904937, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.392295478639225e-05, |
|
"loss": 0.0, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 0.02210759027266028, |
|
"grad_norm": NaN, |
|
"learning_rate": 5e-05, |
|
"loss": 0.0, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.022844509948415623, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.607704521360776e-05, |
|
"loss": 0.0, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 0.023581429624170966, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.2178276747988446e-05, |
|
"loss": 0.0, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 0.02431834929992631, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.832773180720475e-05, |
|
"loss": 0.0, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 0.025055268975681652, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.4549150281252636e-05, |
|
"loss": 0.0, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 0.025792188651436992, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.086582838174551e-05, |
|
"loss": 0.0, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.026529108327192335, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.7300475013022663e-05, |
|
"loss": 0.0, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 0.027266028002947678, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.3875071764202563e-05, |
|
"loss": 0.0, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 0.02800294767870302, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.061073738537635e-05, |
|
"loss": 0.0, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 0.028739867354458364, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.7527597583490822e-05, |
|
"loss": 0.0, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 0.029476787030213707, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.4644660940672627e-05, |
|
"loss": 0.0, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.03021370670596905, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.1979701719998453e-05, |
|
"loss": 0.0, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 0.030950626381724394, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.549150281252633e-06, |
|
"loss": 0.0, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 0.03168754605747973, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.367991782295391e-06, |
|
"loss": 0.0, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 0.032424465733235076, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.449673790581611e-06, |
|
"loss": 0.0, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 0.03316138540899042, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.8060233744356633e-06, |
|
"loss": 0.0, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.03389830508474576, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.4471741852423237e-06, |
|
"loss": 0.0, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 0.034635224760501106, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.3815039801161721e-06, |
|
"loss": 0.0, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 0.03537214443625645, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.15582970243117e-07, |
|
"loss": 0.0, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 0.03610906411201179, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.5413331334360182e-07, |
|
"loss": 0.0, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 0.036845983787767135, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0, |
|
"loss": 0.0, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.036845983787767135, |
|
"eval_loss": NaN, |
|
"eval_runtime": 79.0392, |
|
"eval_samples_per_second": 14.461, |
|
"eval_steps_per_second": 3.618, |
|
"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": 1 |
|
} |
|
}, |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 7631876401397760.0, |
|
"train_batch_size": 4, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|