|
{ |
|
"best_metric": 2.79341983795166, |
|
"best_model_checkpoint": "miner_id_24/checkpoint-25", |
|
"epoch": 1.1976047904191618, |
|
"eval_steps": 25, |
|
"global_step": 25, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.04790419161676647, |
|
"grad_norm": 72.69557189941406, |
|
"learning_rate": 5e-05, |
|
"loss": 110.774, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.04790419161676647, |
|
"eval_loss": 6.629335403442383, |
|
"eval_runtime": 4.7098, |
|
"eval_samples_per_second": 10.616, |
|
"eval_steps_per_second": 2.76, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.09580838323353294, |
|
"grad_norm": 77.63043975830078, |
|
"learning_rate": 0.0001, |
|
"loss": 132.2435, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.1437125748502994, |
|
"grad_norm": 61.427513122558594, |
|
"learning_rate": 9.990365154573717e-05, |
|
"loss": 110.0578, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.19161676646706588, |
|
"grad_norm": 58.1811408996582, |
|
"learning_rate": 9.961501876182148e-05, |
|
"loss": 73.205, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.23952095808383234, |
|
"grad_norm": 49.155845642089844, |
|
"learning_rate": 9.913533761814537e-05, |
|
"loss": 69.1511, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.2874251497005988, |
|
"grad_norm": 69.05171966552734, |
|
"learning_rate": 9.846666218300807e-05, |
|
"loss": 81.67, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.33532934131736525, |
|
"grad_norm": 65.2494125366211, |
|
"learning_rate": 9.761185582727977e-05, |
|
"loss": 81.5417, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.38323353293413176, |
|
"grad_norm": 44.927223205566406, |
|
"learning_rate": 9.657457896300791e-05, |
|
"loss": 77.4983, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.4311377245508982, |
|
"grad_norm": 49.93047332763672, |
|
"learning_rate": 9.535927336897098e-05, |
|
"loss": 50.0204, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.47904191616766467, |
|
"grad_norm": 24.84800910949707, |
|
"learning_rate": 9.397114317029975e-05, |
|
"loss": 47.9566, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.5269461077844312, |
|
"grad_norm": 32.10044479370117, |
|
"learning_rate": 9.241613255361455e-05, |
|
"loss": 61.4778, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.5748502994011976, |
|
"grad_norm": 33.61887741088867, |
|
"learning_rate": 9.070090031310558e-05, |
|
"loss": 60.2869, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.6227544910179641, |
|
"grad_norm": 33.13056564331055, |
|
"learning_rate": 8.883279133655399e-05, |
|
"loss": 57.6085, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.6706586826347305, |
|
"grad_norm": 31.026601791381836, |
|
"learning_rate": 8.681980515339464e-05, |
|
"loss": 46.9569, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.718562874251497, |
|
"grad_norm": 24.52080726623535, |
|
"learning_rate": 8.467056167950311e-05, |
|
"loss": 48.4615, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.7664670658682635, |
|
"grad_norm": 22.692081451416016, |
|
"learning_rate": 8.239426430539243e-05, |
|
"loss": 51.3721, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.8143712574850299, |
|
"grad_norm": 24.40343475341797, |
|
"learning_rate": 8.000066048588211e-05, |
|
"loss": 56.1307, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.8622754491017964, |
|
"grad_norm": 18.565412521362305, |
|
"learning_rate": 7.75e-05, |
|
"loss": 49.8746, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.9101796407185628, |
|
"grad_norm": 19.204238891601562, |
|
"learning_rate": 7.490299105985507e-05, |
|
"loss": 47.3317, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.9580838323353293, |
|
"grad_norm": 15.976109504699707, |
|
"learning_rate": 7.222075445642904e-05, |
|
"loss": 48.1495, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 1.0059880239520957, |
|
"grad_norm": 14.779011726379395, |
|
"learning_rate": 6.946477593864228e-05, |
|
"loss": 47.8621, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 1.0538922155688624, |
|
"grad_norm": 15.715991973876953, |
|
"learning_rate": 6.664685702961344e-05, |
|
"loss": 46.5982, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 1.1017964071856288, |
|
"grad_norm": 18.653337478637695, |
|
"learning_rate": 6.377906449072578e-05, |
|
"loss": 48.7768, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 1.1497005988023952, |
|
"grad_norm": 16.096193313598633, |
|
"learning_rate": 6.087367864990233e-05, |
|
"loss": 49.1443, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 1.1976047904191618, |
|
"grad_norm": 12.494379043579102, |
|
"learning_rate": 5.794314081535644e-05, |
|
"loss": 41.1292, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 1.1976047904191618, |
|
"eval_loss": 2.79341983795166, |
|
"eval_runtime": 4.5515, |
|
"eval_samples_per_second": 10.985, |
|
"eval_steps_per_second": 2.856, |
|
"step": 25 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 50, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 3, |
|
"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": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 3.93611124643201e+17, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|