|
{ |
|
"best_metric": 0.3060170114040375, |
|
"best_model_checkpoint": "miner_id_24/checkpoint-30", |
|
"epoch": 0.07393715341959335, |
|
"eval_steps": 5, |
|
"global_step": 40, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0018484288354898336, |
|
"grad_norm": 7.424246311187744, |
|
"learning_rate": 2e-05, |
|
"loss": 2.2815, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0018484288354898336, |
|
"eval_loss": 0.5765224099159241, |
|
"eval_runtime": 174.6364, |
|
"eval_samples_per_second": 1.306, |
|
"eval_steps_per_second": 0.653, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0036968576709796672, |
|
"grad_norm": 8.377918243408203, |
|
"learning_rate": 4e-05, |
|
"loss": 2.6385, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.005545286506469501, |
|
"grad_norm": 6.679048538208008, |
|
"learning_rate": 6e-05, |
|
"loss": 2.1105, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.0073937153419593345, |
|
"grad_norm": 6.829878807067871, |
|
"learning_rate": 8e-05, |
|
"loss": 1.7918, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.009242144177449169, |
|
"grad_norm": 6.1202802658081055, |
|
"learning_rate": 0.0001, |
|
"loss": 1.5985, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.009242144177449169, |
|
"eval_loss": 0.44307413697242737, |
|
"eval_runtime": 175.5501, |
|
"eval_samples_per_second": 1.299, |
|
"eval_steps_per_second": 0.649, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.011090573012939002, |
|
"grad_norm": 6.970052719116211, |
|
"learning_rate": 0.00012, |
|
"loss": 2.1845, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.012939001848428836, |
|
"grad_norm": 3.6210474967956543, |
|
"learning_rate": 0.00014, |
|
"loss": 1.6165, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.014787430683918669, |
|
"grad_norm": 5.715263366699219, |
|
"learning_rate": 0.00016, |
|
"loss": 1.592, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.0166358595194085, |
|
"grad_norm": 4.726752281188965, |
|
"learning_rate": 0.00018, |
|
"loss": 1.8184, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.018484288354898338, |
|
"grad_norm": 3.724501609802246, |
|
"learning_rate": 0.0002, |
|
"loss": 1.2781, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.018484288354898338, |
|
"eval_loss": 0.38599851727485657, |
|
"eval_runtime": 174.0489, |
|
"eval_samples_per_second": 1.31, |
|
"eval_steps_per_second": 0.655, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.02033271719038817, |
|
"grad_norm": 3.8678717613220215, |
|
"learning_rate": 0.0001999979446958366, |
|
"loss": 1.6367, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.022181146025878003, |
|
"grad_norm": 3.9537124633789062, |
|
"learning_rate": 0.00019999177886783194, |
|
"loss": 1.5529, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.024029574861367836, |
|
"grad_norm": 5.052474498748779, |
|
"learning_rate": 0.00019998150276943902, |
|
"loss": 2.002, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.025878003696857672, |
|
"grad_norm": 3.856994152069092, |
|
"learning_rate": 0.000199967116823068, |
|
"loss": 1.3814, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.027726432532347505, |
|
"grad_norm": 4.525390625, |
|
"learning_rate": 0.0001999486216200688, |
|
"loss": 2.113, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.027726432532347505, |
|
"eval_loss": 0.34281158447265625, |
|
"eval_runtime": 172.8847, |
|
"eval_samples_per_second": 1.319, |
|
"eval_steps_per_second": 0.659, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.029574861367837338, |
|
"grad_norm": 2.5049190521240234, |
|
"learning_rate": 0.00019992601792070679, |
|
"loss": 1.1666, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.031423290203327174, |
|
"grad_norm": 5.2193169593811035, |
|
"learning_rate": 0.00019989930665413147, |
|
"loss": 1.5721, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.033271719038817, |
|
"grad_norm": 3.3948168754577637, |
|
"learning_rate": 0.00019986848891833845, |
|
"loss": 0.8586, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.03512014787430684, |
|
"grad_norm": 3.3094377517700195, |
|
"learning_rate": 0.0001998335659801241, |
|
"loss": 0.989, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.036968576709796676, |
|
"grad_norm": 3.9788992404937744, |
|
"learning_rate": 0.00019979453927503364, |
|
"loss": 1.4677, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.036968576709796676, |
|
"eval_loss": 0.3295012414455414, |
|
"eval_runtime": 174.1601, |
|
"eval_samples_per_second": 1.309, |
|
"eval_steps_per_second": 0.655, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.038817005545286505, |
|
"grad_norm": 4.1342549324035645, |
|
"learning_rate": 0.00019975141040730207, |
|
"loss": 1.0818, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.04066543438077634, |
|
"grad_norm": 6.201707363128662, |
|
"learning_rate": 0.0001997041811497882, |
|
"loss": 1.361, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.04251386321626617, |
|
"grad_norm": 3.2470476627349854, |
|
"learning_rate": 0.00019965285344390184, |
|
"loss": 1.5608, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.04436229205175601, |
|
"grad_norm": 3.960193157196045, |
|
"learning_rate": 0.00019959742939952392, |
|
"loss": 1.2768, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.04621072088724584, |
|
"grad_norm": 4.521762371063232, |
|
"learning_rate": 0.00019953791129491983, |
|
"loss": 1.6174, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.04621072088724584, |
|
"eval_loss": 0.3227802515029907, |
|
"eval_runtime": 174.8819, |
|
"eval_samples_per_second": 1.304, |
|
"eval_steps_per_second": 0.652, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.04805914972273567, |
|
"grad_norm": 5.535987377166748, |
|
"learning_rate": 0.00019947430157664576, |
|
"loss": 1.5342, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.04990757855822551, |
|
"grad_norm": 3.174276113510132, |
|
"learning_rate": 0.00019940660285944803, |
|
"loss": 1.3247, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.051756007393715345, |
|
"grad_norm": 2.9018266201019287, |
|
"learning_rate": 0.00019933481792615583, |
|
"loss": 1.0521, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.053604436229205174, |
|
"grad_norm": 4.290431022644043, |
|
"learning_rate": 0.0001992589497275665, |
|
"loss": 1.2776, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 0.05545286506469501, |
|
"grad_norm": 3.15394926071167, |
|
"learning_rate": 0.0001991790013823246, |
|
"loss": 1.2662, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.05545286506469501, |
|
"eval_loss": 0.3060170114040375, |
|
"eval_runtime": 173.945, |
|
"eval_samples_per_second": 1.311, |
|
"eval_steps_per_second": 0.655, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.05730129390018484, |
|
"grad_norm": 6.309504508972168, |
|
"learning_rate": 0.00019909497617679348, |
|
"loss": 1.9929, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 0.059149722735674676, |
|
"grad_norm": 3.596278190612793, |
|
"learning_rate": 0.0001990068775649202, |
|
"loss": 1.3422, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 0.06099815157116451, |
|
"grad_norm": 3.6826868057250977, |
|
"learning_rate": 0.00019891470916809362, |
|
"loss": 1.3938, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 0.06284658040665435, |
|
"grad_norm": 2.7460691928863525, |
|
"learning_rate": 0.00019881847477499557, |
|
"loss": 0.8931, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 0.06469500924214418, |
|
"grad_norm": 4.063459873199463, |
|
"learning_rate": 0.00019871817834144504, |
|
"loss": 1.4139, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.06469500924214418, |
|
"eval_loss": 0.3002864420413971, |
|
"eval_runtime": 173.4727, |
|
"eval_samples_per_second": 1.314, |
|
"eval_steps_per_second": 0.657, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.066543438077634, |
|
"grad_norm": 3.00803804397583, |
|
"learning_rate": 0.0001986138239902355, |
|
"loss": 0.9237, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 0.06839186691312385, |
|
"grad_norm": 3.4707858562469482, |
|
"learning_rate": 0.0001985054160109657, |
|
"loss": 1.6732, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 0.07024029574861368, |
|
"grad_norm": 4.129047393798828, |
|
"learning_rate": 0.00019839295885986296, |
|
"loss": 1.4183, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 0.07208872458410351, |
|
"grad_norm": 3.468799352645874, |
|
"learning_rate": 0.0001982764571596004, |
|
"loss": 1.1402, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 0.07393715341959335, |
|
"grad_norm": 2.87471079826355, |
|
"learning_rate": 0.00019815591569910654, |
|
"loss": 1.4329, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.07393715341959335, |
|
"eval_loss": 0.3075679838657379, |
|
"eval_runtime": 173.655, |
|
"eval_samples_per_second": 1.313, |
|
"eval_steps_per_second": 0.656, |
|
"step": 40 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 500, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 10, |
|
"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": 5.658027780734976e+16, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|