|
{ |
|
"best_metric": 1.6248844861984253, |
|
"best_model_checkpoint": "miner_id_24/checkpoint-25", |
|
"epoch": 0.0069270066672439175, |
|
"eval_steps": 25, |
|
"global_step": 25, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0002770802666897567, |
|
"grad_norm": 1.0172698497772217, |
|
"learning_rate": 5e-05, |
|
"loss": 2.0435, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0002770802666897567, |
|
"eval_loss": 2.6185038089752197, |
|
"eval_runtime": 440.8372, |
|
"eval_samples_per_second": 55.154, |
|
"eval_steps_per_second": 6.896, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0005541605333795133, |
|
"grad_norm": 1.3333725929260254, |
|
"learning_rate": 0.0001, |
|
"loss": 2.1851, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.0008312408000692701, |
|
"grad_norm": 1.4274028539657593, |
|
"learning_rate": 9.989294616193017e-05, |
|
"loss": 2.2284, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.0011083210667590267, |
|
"grad_norm": 1.268067479133606, |
|
"learning_rate": 9.957224306869053e-05, |
|
"loss": 2.1165, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.0013854013334487834, |
|
"grad_norm": 1.0901422500610352, |
|
"learning_rate": 9.903926402016153e-05, |
|
"loss": 2.056, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.0016624816001385402, |
|
"grad_norm": 1.1695683002471924, |
|
"learning_rate": 9.829629131445342e-05, |
|
"loss": 1.9676, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.0019395618668282969, |
|
"grad_norm": 1.228065848350525, |
|
"learning_rate": 9.73465064747553e-05, |
|
"loss": 2.0373, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.0022166421335180534, |
|
"grad_norm": 1.2500860691070557, |
|
"learning_rate": 9.619397662556435e-05, |
|
"loss": 2.0231, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.0024937224002078103, |
|
"grad_norm": 1.4088391065597534, |
|
"learning_rate": 9.484363707663442e-05, |
|
"loss": 1.9904, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.002770802666897567, |
|
"grad_norm": 1.321844220161438, |
|
"learning_rate": 9.330127018922194e-05, |
|
"loss": 1.7991, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.003047882933587324, |
|
"grad_norm": 1.5810325145721436, |
|
"learning_rate": 9.157348061512727e-05, |
|
"loss": 1.8138, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.0033249632002770803, |
|
"grad_norm": 1.3065353631973267, |
|
"learning_rate": 8.966766701456177e-05, |
|
"loss": 1.858, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.003602043466966837, |
|
"grad_norm": 1.1042661666870117, |
|
"learning_rate": 8.759199037394887e-05, |
|
"loss": 1.921, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.0038791237336565938, |
|
"grad_norm": 1.3776724338531494, |
|
"learning_rate": 8.535533905932738e-05, |
|
"loss": 1.7046, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.004156204000346351, |
|
"grad_norm": 1.3263698816299438, |
|
"learning_rate": 8.296729075500344e-05, |
|
"loss": 1.756, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.004433284267036107, |
|
"grad_norm": 1.1119990348815918, |
|
"learning_rate": 8.043807145043604e-05, |
|
"loss": 1.7557, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.004710364533725864, |
|
"grad_norm": 0.7953896522521973, |
|
"learning_rate": 7.777851165098012e-05, |
|
"loss": 1.6287, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.004987444800415621, |
|
"grad_norm": 0.8209851384162903, |
|
"learning_rate": 7.500000000000001e-05, |
|
"loss": 1.691, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.005264525067105377, |
|
"grad_norm": 1.1580805778503418, |
|
"learning_rate": 7.211443451095007e-05, |
|
"loss": 1.6265, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.005541605333795134, |
|
"grad_norm": 1.1431478261947632, |
|
"learning_rate": 6.91341716182545e-05, |
|
"loss": 1.7062, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.005818685600484891, |
|
"grad_norm": 0.8607553243637085, |
|
"learning_rate": 6.607197326515808e-05, |
|
"loss": 1.6295, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.006095765867174648, |
|
"grad_norm": 0.7982295155525208, |
|
"learning_rate": 6.294095225512603e-05, |
|
"loss": 1.5984, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.006372846133864404, |
|
"grad_norm": 0.8336132168769836, |
|
"learning_rate": 5.9754516100806423e-05, |
|
"loss": 1.6866, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.006649926400554161, |
|
"grad_norm": 0.9011556506156921, |
|
"learning_rate": 5.6526309611002594e-05, |
|
"loss": 1.6677, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.0069270066672439175, |
|
"grad_norm": 1.1473370790481567, |
|
"learning_rate": 5.327015646150716e-05, |
|
"loss": 1.8729, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.0069270066672439175, |
|
"eval_loss": 1.6248844861984253, |
|
"eval_runtime": 441.174, |
|
"eval_samples_per_second": 55.112, |
|
"eval_steps_per_second": 6.891, |
|
"step": 25 |
|
} |
|
], |
|
"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": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 1.114626154561536e+17, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|