|
{ |
|
"best_metric": NaN, |
|
"best_model_checkpoint": "miner_id_24/checkpoint-50", |
|
"epoch": 0.436046511627907, |
|
"eval_steps": 50, |
|
"global_step": 150, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0029069767441860465, |
|
"eval_loss": NaN, |
|
"eval_runtime": 9.3266, |
|
"eval_samples_per_second": 15.547, |
|
"eval_steps_per_second": 3.967, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.029069767441860465, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.05e-06, |
|
"loss": 0.0, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.05813953488372093, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.01e-05, |
|
"loss": 0.0, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.0872093023255814, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.323076923076924e-06, |
|
"loss": 0.0, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.11627906976744186, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.546153846153847e-06, |
|
"loss": 0.0, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.14534883720930233, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.76923076923077e-06, |
|
"loss": 0.0, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.14534883720930233, |
|
"eval_loss": NaN, |
|
"eval_runtime": 7.7414, |
|
"eval_samples_per_second": 18.731, |
|
"eval_steps_per_second": 4.78, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.1744186046511628, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.992307692307692e-06, |
|
"loss": 0.0, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.20348837209302326, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.215384615384615e-06, |
|
"loss": 0.0, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.23255813953488372, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.438461538461538e-06, |
|
"loss": 0.0, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.2616279069767442, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.661538461538462e-06, |
|
"loss": 0.0, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.29069767441860467, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.884615384615385e-06, |
|
"loss": 0.0, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.29069767441860467, |
|
"eval_loss": NaN, |
|
"eval_runtime": 7.7387, |
|
"eval_samples_per_second": 18.737, |
|
"eval_steps_per_second": 4.781, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.31976744186046513, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.1076923076923076e-06, |
|
"loss": 0.0, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.3488372093023256, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.330769230769231e-06, |
|
"loss": 0.0, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.37790697674418605, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.5538461538461538e-06, |
|
"loss": 0.0, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 0.4069767441860465, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.769230769230769e-07, |
|
"loss": 0.0, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.436046511627907, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0, |
|
"loss": 0.0, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.436046511627907, |
|
"eval_loss": NaN, |
|
"eval_runtime": 7.7414, |
|
"eval_samples_per_second": 18.73, |
|
"eval_steps_per_second": 4.779, |
|
"step": 150 |
|
} |
|
], |
|
"logging_steps": 10, |
|
"max_steps": 150, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 50, |
|
"stateful_callbacks": { |
|
"EarlyStoppingCallback": { |
|
"args": { |
|
"early_stopping_patience": 3, |
|
"early_stopping_threshold": 0.0 |
|
}, |
|
"attributes": { |
|
"early_stopping_patience_counter": 2 |
|
} |
|
}, |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 5.437798554481459e+16, |
|
"train_batch_size": 8, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|