|
{ |
|
"best_metric": 0.64404296875, |
|
"best_model_checkpoint": "miner_id_24/checkpoint-50", |
|
"epoch": 0.5399932500843739, |
|
"eval_steps": 25, |
|
"global_step": 50, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.010799865001687479, |
|
"grad_norm": 0.21029257774353027, |
|
"learning_rate": 5e-05, |
|
"loss": 0.5895, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.010799865001687479, |
|
"eval_loss": 1.027909278869629, |
|
"eval_runtime": 2.5818, |
|
"eval_samples_per_second": 19.366, |
|
"eval_steps_per_second": 5.035, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.021599730003374958, |
|
"grad_norm": 0.29052892327308655, |
|
"learning_rate": 0.0001, |
|
"loss": 0.7084, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.03239959500506244, |
|
"grad_norm": 0.2771872878074646, |
|
"learning_rate": 9.990365154573717e-05, |
|
"loss": 0.6916, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.043199460006749915, |
|
"grad_norm": 0.27161040902137756, |
|
"learning_rate": 9.961501876182148e-05, |
|
"loss": 0.7243, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.0539993250084374, |
|
"grad_norm": 0.3536183834075928, |
|
"learning_rate": 9.913533761814537e-05, |
|
"loss": 0.7683, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.06479919001012488, |
|
"grad_norm": 0.40585237741470337, |
|
"learning_rate": 9.846666218300807e-05, |
|
"loss": 0.8005, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.07559905501181235, |
|
"grad_norm": 0.47559353709220886, |
|
"learning_rate": 9.761185582727977e-05, |
|
"loss": 0.8514, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.08639892001349983, |
|
"grad_norm": 0.5741594433784485, |
|
"learning_rate": 9.657457896300791e-05, |
|
"loss": 0.7723, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.0971987850151873, |
|
"grad_norm": 0.5773308873176575, |
|
"learning_rate": 9.535927336897098e-05, |
|
"loss": 0.8095, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.1079986500168748, |
|
"grad_norm": 0.6413544416427612, |
|
"learning_rate": 9.397114317029975e-05, |
|
"loss": 0.7646, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.11879851501856227, |
|
"grad_norm": 0.8995634913444519, |
|
"learning_rate": 9.241613255361455e-05, |
|
"loss": 0.7606, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.12959838002024976, |
|
"grad_norm": 0.7462154626846313, |
|
"learning_rate": 9.070090031310558e-05, |
|
"loss": 0.6714, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.14039824502193723, |
|
"grad_norm": 0.25571149587631226, |
|
"learning_rate": 8.883279133655399e-05, |
|
"loss": 0.5206, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.1511981100236247, |
|
"grad_norm": 0.17418192327022552, |
|
"learning_rate": 8.681980515339464e-05, |
|
"loss": 0.6207, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.16199797502531219, |
|
"grad_norm": 0.14447858929634094, |
|
"learning_rate": 8.467056167950311e-05, |
|
"loss": 0.6022, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.17279784002699966, |
|
"grad_norm": 0.33946892619132996, |
|
"learning_rate": 8.239426430539243e-05, |
|
"loss": 0.6171, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.18359770502868714, |
|
"grad_norm": 0.14791187644004822, |
|
"learning_rate": 8.000066048588211e-05, |
|
"loss": 0.6672, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.1943975700303746, |
|
"grad_norm": 0.15538538992404938, |
|
"learning_rate": 7.75e-05, |
|
"loss": 0.6587, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.2051974350320621, |
|
"grad_norm": 0.15521201491355896, |
|
"learning_rate": 7.490299105985507e-05, |
|
"loss": 0.6554, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.2159973000337496, |
|
"grad_norm": 0.16075147688388824, |
|
"learning_rate": 7.222075445642904e-05, |
|
"loss": 0.6992, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.22679716503543706, |
|
"grad_norm": 0.234422966837883, |
|
"learning_rate": 6.946477593864228e-05, |
|
"loss": 0.6868, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.23759703003712454, |
|
"grad_norm": 0.18819983303546906, |
|
"learning_rate": 6.664685702961344e-05, |
|
"loss": 0.6806, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.24839689503881202, |
|
"grad_norm": 0.21723484992980957, |
|
"learning_rate": 6.377906449072578e-05, |
|
"loss": 0.6441, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.2591967600404995, |
|
"grad_norm": 0.25310608744621277, |
|
"learning_rate": 6.087367864990233e-05, |
|
"loss": 0.712, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.26999662504218697, |
|
"grad_norm": 0.3402400314807892, |
|
"learning_rate": 5.794314081535644e-05, |
|
"loss": 0.5903, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.26999662504218697, |
|
"eval_loss": 0.6489320397377014, |
|
"eval_runtime": 2.18, |
|
"eval_samples_per_second": 22.935, |
|
"eval_steps_per_second": 5.963, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.28079649004387447, |
|
"grad_norm": 0.08643216639757156, |
|
"learning_rate": 5.500000000000001e-05, |
|
"loss": 0.509, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.2915963550455619, |
|
"grad_norm": 0.11556915938854218, |
|
"learning_rate": 5.205685918464356e-05, |
|
"loss": 0.5407, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.3023962200472494, |
|
"grad_norm": 0.13107015192508698, |
|
"learning_rate": 4.912632135009769e-05, |
|
"loss": 0.6307, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.31319608504893687, |
|
"grad_norm": 0.14084775745868683, |
|
"learning_rate": 4.6220935509274235e-05, |
|
"loss": 0.5932, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 0.32399595005062437, |
|
"grad_norm": 0.1543428748846054, |
|
"learning_rate": 4.3353142970386564e-05, |
|
"loss": 0.629, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.3347958150523119, |
|
"grad_norm": 0.15614484250545502, |
|
"learning_rate": 4.053522406135775e-05, |
|
"loss": 0.6655, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 0.3455956800539993, |
|
"grad_norm": 0.17313002049922943, |
|
"learning_rate": 3.777924554357096e-05, |
|
"loss": 0.6806, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 0.3563955450556868, |
|
"grad_norm": 0.19408182799816132, |
|
"learning_rate": 3.509700894014496e-05, |
|
"loss": 0.7165, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 0.36719541005737427, |
|
"grad_norm": 0.16677334904670715, |
|
"learning_rate": 3.250000000000001e-05, |
|
"loss": 0.6582, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 0.3779952750590618, |
|
"grad_norm": 0.18193095922470093, |
|
"learning_rate": 2.9999339514117912e-05, |
|
"loss": 0.6302, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.3887951400607492, |
|
"grad_norm": 0.20297932624816895, |
|
"learning_rate": 2.760573569460757e-05, |
|
"loss": 0.66, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 0.3995950050624367, |
|
"grad_norm": 0.23466193675994873, |
|
"learning_rate": 2.53294383204969e-05, |
|
"loss": 0.649, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 0.4103948700641242, |
|
"grad_norm": 0.09354816377162933, |
|
"learning_rate": 2.3180194846605367e-05, |
|
"loss": 0.5787, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 0.4211947350658117, |
|
"grad_norm": 0.08726412057876587, |
|
"learning_rate": 2.1167208663446025e-05, |
|
"loss": 0.5915, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 0.4319946000674992, |
|
"grad_norm": 0.10443510860204697, |
|
"learning_rate": 1.9299099686894423e-05, |
|
"loss": 0.616, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.4427944650691866, |
|
"grad_norm": 0.123623326420784, |
|
"learning_rate": 1.758386744638546e-05, |
|
"loss": 0.5388, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 0.45359433007087413, |
|
"grad_norm": 0.12465845048427582, |
|
"learning_rate": 1.602885682970026e-05, |
|
"loss": 0.6571, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 0.4643941950725616, |
|
"grad_norm": 0.12447262555360794, |
|
"learning_rate": 1.464072663102903e-05, |
|
"loss": 0.6103, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 0.4751940600742491, |
|
"grad_norm": 0.13273553550243378, |
|
"learning_rate": 1.3425421036992098e-05, |
|
"loss": 0.6815, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 0.48599392507593653, |
|
"grad_norm": 0.13501819968223572, |
|
"learning_rate": 1.2388144172720251e-05, |
|
"loss": 0.6672, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.49679379007762403, |
|
"grad_norm": 0.159222811460495, |
|
"learning_rate": 1.1533337816991932e-05, |
|
"loss": 0.6671, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 0.5075936550793115, |
|
"grad_norm": 0.1639116108417511, |
|
"learning_rate": 1.0864662381854632e-05, |
|
"loss": 0.6808, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 0.518393520080999, |
|
"grad_norm": 0.18950490653514862, |
|
"learning_rate": 1.0384981238178534e-05, |
|
"loss": 0.7195, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 0.5291933850826864, |
|
"grad_norm": 0.20681390166282654, |
|
"learning_rate": 1.0096348454262845e-05, |
|
"loss": 0.6118, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 0.5399932500843739, |
|
"grad_norm": 0.30206191539764404, |
|
"learning_rate": 1e-05, |
|
"loss": 0.5832, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.5399932500843739, |
|
"eval_loss": 0.64404296875, |
|
"eval_runtime": 2.1858, |
|
"eval_samples_per_second": 22.875, |
|
"eval_steps_per_second": 5.948, |
|
"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": 0 |
|
} |
|
}, |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 1.0601985626813235e+17, |
|
"train_batch_size": 1, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|