|
{ |
|
"best_metric": 2.0475499629974365, |
|
"best_model_checkpoint": "miner_id_24/checkpoint-50", |
|
"epoch": 1.4373881932021466, |
|
"eval_steps": 25, |
|
"global_step": 50, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.028622540250447227, |
|
"grad_norm": 5.1959147453308105, |
|
"learning_rate": 5e-05, |
|
"loss": 3.6868, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.028622540250447227, |
|
"eval_loss": 4.301292896270752, |
|
"eval_runtime": 3.1258, |
|
"eval_samples_per_second": 15.996, |
|
"eval_steps_per_second": 4.159, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.057245080500894455, |
|
"grad_norm": 5.988410472869873, |
|
"learning_rate": 0.0001, |
|
"loss": 4.0639, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.08586762075134168, |
|
"grad_norm": 6.287829875946045, |
|
"learning_rate": 9.990365154573717e-05, |
|
"loss": 4.0714, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.11449016100178891, |
|
"grad_norm": 4.875919342041016, |
|
"learning_rate": 9.961501876182148e-05, |
|
"loss": 3.9675, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.14311270125223613, |
|
"grad_norm": 5.528495788574219, |
|
"learning_rate": 9.913533761814537e-05, |
|
"loss": 3.9406, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.17173524150268335, |
|
"grad_norm": 5.681136131286621, |
|
"learning_rate": 9.846666218300807e-05, |
|
"loss": 3.7416, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.2003577817531306, |
|
"grad_norm": 3.5005509853363037, |
|
"learning_rate": 9.761185582727977e-05, |
|
"loss": 2.696, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.22898032200357782, |
|
"grad_norm": 3.4585726261138916, |
|
"learning_rate": 9.657457896300791e-05, |
|
"loss": 3.2387, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.25760286225402507, |
|
"grad_norm": 3.782135486602783, |
|
"learning_rate": 9.535927336897098e-05, |
|
"loss": 2.5966, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.28622540250447226, |
|
"grad_norm": 4.032910346984863, |
|
"learning_rate": 9.397114317029975e-05, |
|
"loss": 2.7517, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.3148479427549195, |
|
"grad_norm": 3.0664560794830322, |
|
"learning_rate": 9.241613255361455e-05, |
|
"loss": 2.5558, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.3434704830053667, |
|
"grad_norm": 2.541337490081787, |
|
"learning_rate": 9.070090031310558e-05, |
|
"loss": 2.6952, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.37209302325581395, |
|
"grad_norm": 3.1225051879882812, |
|
"learning_rate": 8.883279133655399e-05, |
|
"loss": 2.5049, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.4007155635062612, |
|
"grad_norm": 4.351744174957275, |
|
"learning_rate": 8.681980515339464e-05, |
|
"loss": 2.6004, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.4293381037567084, |
|
"grad_norm": 2.7151081562042236, |
|
"learning_rate": 8.467056167950311e-05, |
|
"loss": 2.28, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.45796064400715564, |
|
"grad_norm": 2.72318696975708, |
|
"learning_rate": 8.239426430539243e-05, |
|
"loss": 2.9666, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.4865831842576029, |
|
"grad_norm": 2.636446952819824, |
|
"learning_rate": 8.000066048588211e-05, |
|
"loss": 2.8992, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.5152057245080501, |
|
"grad_norm": 2.799785852432251, |
|
"learning_rate": 7.75e-05, |
|
"loss": 2.0822, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.5438282647584973, |
|
"grad_norm": 2.2449307441711426, |
|
"learning_rate": 7.490299105985507e-05, |
|
"loss": 2.3713, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.5724508050089445, |
|
"grad_norm": 1.7994107007980347, |
|
"learning_rate": 7.222075445642904e-05, |
|
"loss": 2.2375, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.6010733452593918, |
|
"grad_norm": 2.2747550010681152, |
|
"learning_rate": 6.946477593864228e-05, |
|
"loss": 2.0141, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.629695885509839, |
|
"grad_norm": 3.4918453693389893, |
|
"learning_rate": 6.664685702961344e-05, |
|
"loss": 2.0491, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.6583184257602862, |
|
"grad_norm": 2.9565210342407227, |
|
"learning_rate": 6.377906449072578e-05, |
|
"loss": 2.1609, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.6869409660107334, |
|
"grad_norm": 2.646497964859009, |
|
"learning_rate": 6.087367864990233e-05, |
|
"loss": 2.3189, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.7155635062611807, |
|
"grad_norm": 2.3935790061950684, |
|
"learning_rate": 5.794314081535644e-05, |
|
"loss": 2.8598, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.7155635062611807, |
|
"eval_loss": 2.2345645427703857, |
|
"eval_runtime": 2.1726, |
|
"eval_samples_per_second": 23.014, |
|
"eval_steps_per_second": 5.984, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.7441860465116279, |
|
"grad_norm": 2.2192697525024414, |
|
"learning_rate": 5.500000000000001e-05, |
|
"loss": 1.9938, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.7728085867620751, |
|
"grad_norm": 2.8937413692474365, |
|
"learning_rate": 5.205685918464356e-05, |
|
"loss": 2.2059, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.8014311270125224, |
|
"grad_norm": 2.5368123054504395, |
|
"learning_rate": 4.912632135009769e-05, |
|
"loss": 2.0859, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.8300536672629696, |
|
"grad_norm": 1.9519373178482056, |
|
"learning_rate": 4.6220935509274235e-05, |
|
"loss": 2.0092, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 0.8586762075134168, |
|
"grad_norm": 1.957302212715149, |
|
"learning_rate": 4.3353142970386564e-05, |
|
"loss": 1.954, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.8872987477638641, |
|
"grad_norm": 3.078779697418213, |
|
"learning_rate": 4.053522406135775e-05, |
|
"loss": 1.9646, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 0.9159212880143113, |
|
"grad_norm": 2.7473530769348145, |
|
"learning_rate": 3.777924554357096e-05, |
|
"loss": 1.9372, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 0.9445438282647585, |
|
"grad_norm": 2.635892152786255, |
|
"learning_rate": 3.509700894014496e-05, |
|
"loss": 2.2733, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 0.9731663685152058, |
|
"grad_norm": 2.5369815826416016, |
|
"learning_rate": 3.250000000000001e-05, |
|
"loss": 2.3486, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 1.0080500894454383, |
|
"grad_norm": 2.8737504482269287, |
|
"learning_rate": 2.9999339514117912e-05, |
|
"loss": 2.4615, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 1.0366726296958855, |
|
"grad_norm": 1.9721633195877075, |
|
"learning_rate": 2.760573569460757e-05, |
|
"loss": 1.9552, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 1.0652951699463327, |
|
"grad_norm": 1.634428858757019, |
|
"learning_rate": 2.53294383204969e-05, |
|
"loss": 1.8953, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 1.0939177101967799, |
|
"grad_norm": 1.4716153144836426, |
|
"learning_rate": 2.3180194846605367e-05, |
|
"loss": 1.9606, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 1.1225402504472273, |
|
"grad_norm": 1.6855412721633911, |
|
"learning_rate": 2.1167208663446025e-05, |
|
"loss": 1.8368, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 1.1511627906976745, |
|
"grad_norm": 2.3863978385925293, |
|
"learning_rate": 1.9299099686894423e-05, |
|
"loss": 1.8061, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 1.1797853309481217, |
|
"grad_norm": 2.4788835048675537, |
|
"learning_rate": 1.758386744638546e-05, |
|
"loss": 1.805, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 1.2084078711985689, |
|
"grad_norm": 1.9841209650039673, |
|
"learning_rate": 1.602885682970026e-05, |
|
"loss": 2.1931, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 1.237030411449016, |
|
"grad_norm": 1.788836121559143, |
|
"learning_rate": 1.464072663102903e-05, |
|
"loss": 2.2587, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 1.2656529516994635, |
|
"grad_norm": 2.320674180984497, |
|
"learning_rate": 1.3425421036992098e-05, |
|
"loss": 1.9501, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 1.2942754919499104, |
|
"grad_norm": 2.0197575092315674, |
|
"learning_rate": 1.2388144172720251e-05, |
|
"loss": 1.8906, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 1.3228980322003578, |
|
"grad_norm": 2.010979175567627, |
|
"learning_rate": 1.1533337816991932e-05, |
|
"loss": 1.8234, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 1.351520572450805, |
|
"grad_norm": 1.6593760251998901, |
|
"learning_rate": 1.0864662381854632e-05, |
|
"loss": 1.8833, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 1.3801431127012522, |
|
"grad_norm": 1.9684267044067383, |
|
"learning_rate": 1.0384981238178534e-05, |
|
"loss": 1.6469, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 1.4087656529516994, |
|
"grad_norm": 2.6509218215942383, |
|
"learning_rate": 1.0096348454262845e-05, |
|
"loss": 1.6708, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 1.4373881932021466, |
|
"grad_norm": 2.042696952819824, |
|
"learning_rate": 1e-05, |
|
"loss": 1.7957, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 1.4373881932021466, |
|
"eval_loss": 2.0475499629974365, |
|
"eval_runtime": 2.0907, |
|
"eval_samples_per_second": 23.916, |
|
"eval_steps_per_second": 6.218, |
|
"step": 50 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 50, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 2, |
|
"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": 5.002120628745011e+16, |
|
"train_batch_size": 1, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|