|
{ |
|
"best_metric": NaN, |
|
"best_model_checkpoint": "miner_id_24/checkpoint-25", |
|
"epoch": 3.0375275938189845, |
|
"eval_steps": 25, |
|
"global_step": 43, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0706401766004415, |
|
"grad_norm": NaN, |
|
"learning_rate": 5e-05, |
|
"loss": 6644857.5, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0706401766004415, |
|
"eval_loss": NaN, |
|
"eval_runtime": 3.583, |
|
"eval_samples_per_second": 13.955, |
|
"eval_steps_per_second": 3.628, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.141280353200883, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.2119205298013245, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.986796105326832e-05, |
|
"loss": 0.0, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.282560706401766, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.947261907011569e-05, |
|
"loss": 0.0, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.35320088300220753, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.881629407450006e-05, |
|
"loss": 0.0, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.423841059602649, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.790283764247188e-05, |
|
"loss": 0.0, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.49448123620309054, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.673761029959427e-05, |
|
"loss": 0.0, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.565121412803532, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.53274500632475e-05, |
|
"loss": 0.0, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.6357615894039735, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.368063231442406e-05, |
|
"loss": 0.0, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.7064017660044151, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.18068212345023e-05, |
|
"loss": 0.0, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.7770419426048565, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.971701309198744e-05, |
|
"loss": 0.0, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.847682119205298, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.742347171203542e-05, |
|
"loss": 0.0, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.9183222958057395, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.493965650745043e-05, |
|
"loss": 0.0, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.9889624724061811, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.228014349349872e-05, |
|
"loss": 0.0, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 1.0596026490066226, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.946053975005496e-05, |
|
"loss": 0.0, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 1.130242825607064, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.649739183305184e-05, |
|
"loss": 0.0, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 1.2008830022075054, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.34080886727103e-05, |
|
"loss": 0.0, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 1.271523178807947, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.021075952838262e-05, |
|
"loss": 0.0, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 1.3421633554083885, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.692416759884978e-05, |
|
"loss": 0.0, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 1.4128035320088301, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.356759991241008e-05, |
|
"loss": 0.0, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 1.4834437086092715, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.016075414292803e-05, |
|
"loss": 0.0, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 1.554083885209713, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.6723623016051596e-05, |
|
"loss": 0.0, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 1.6247240618101544, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.3276376983948415e-05, |
|
"loss": 0.0, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 1.695364238410596, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.9839245857071994e-05, |
|
"loss": 0.0, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 1.7660044150110377, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.643240008758992e-05, |
|
"loss": 0.0, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 1.7660044150110377, |
|
"eval_loss": NaN, |
|
"eval_runtime": 3.6192, |
|
"eval_samples_per_second": 13.815, |
|
"eval_steps_per_second": 3.592, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 1.836644591611479, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.307583240115024e-05, |
|
"loss": 0.0, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 1.9072847682119205, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.9789240471617385e-05, |
|
"loss": 0.0, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 1.977924944812362, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.659191132728971e-05, |
|
"loss": 0.0, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 2.0485651214128033, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.350260816694816e-05, |
|
"loss": 0.0, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 2.119205298013245, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.0539460249945056e-05, |
|
"loss": 0.0, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 2.1898454746136866, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.7719856506501306e-05, |
|
"loss": 0.0, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 2.260485651214128, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.5060343492549566e-05, |
|
"loss": 0.0, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 2.3311258278145695, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.257652828796459e-05, |
|
"loss": 0.0, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 2.401766004415011, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.0282986908012567e-05, |
|
"loss": 0.0, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 2.4724061810154527, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.819317876549771e-05, |
|
"loss": 0.0, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 2.543046357615894, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.631936768557596e-05, |
|
"loss": 0.0, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 2.6136865342163356, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.4672549936752506e-05, |
|
"loss": 0.0, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 2.684326710816777, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.3262389700405744e-05, |
|
"loss": 0.0, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 2.7549668874172184, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.2097162357528127e-05, |
|
"loss": 0.0, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 2.8256070640176603, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.1183705925499948e-05, |
|
"loss": 0.0, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 2.8962472406181017, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.0527380929884324e-05, |
|
"loss": 0.0, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 2.966887417218543, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.013203894673168e-05, |
|
"loss": 0.0, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 3.0375275938189845, |
|
"grad_norm": NaN, |
|
"learning_rate": 1e-05, |
|
"loss": 0.0, |
|
"step": 43 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 43, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 4, |
|
"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": 5.2513569876895334e+17, |
|
"train_batch_size": 1, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|