|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.0267379679144386, |
|
"eval_steps": 8, |
|
"global_step": 36, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0285204991087344, |
|
"eval_loss": 10.387872695922852, |
|
"eval_runtime": 0.3496, |
|
"eval_samples_per_second": 677.9, |
|
"eval_steps_per_second": 85.81, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.2281639928698752, |
|
"eval_loss": 10.38524341583252, |
|
"eval_runtime": 0.3665, |
|
"eval_samples_per_second": 646.628, |
|
"eval_steps_per_second": 81.852, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.28520499108734404, |
|
"grad_norm": 2.7896149158477783, |
|
"learning_rate": 8.695044586103296e-05, |
|
"loss": 166.1243, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.4563279857397504, |
|
"eval_loss": 10.382363319396973, |
|
"eval_runtime": 0.3689, |
|
"eval_samples_per_second": 642.384, |
|
"eval_steps_per_second": 81.314, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.5704099821746881, |
|
"grad_norm": 2.8436527252197266, |
|
"learning_rate": 4.5386582026834906e-05, |
|
"loss": 166.0674, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.6844919786096256, |
|
"eval_loss": 10.380404472351074, |
|
"eval_runtime": 0.4054, |
|
"eval_samples_per_second": 584.597, |
|
"eval_steps_per_second": 74.0, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.8556149732620321, |
|
"grad_norm": 2.942018985748291, |
|
"learning_rate": 7.489143213519301e-06, |
|
"loss": 166.0386, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.9126559714795008, |
|
"eval_loss": 10.379790306091309, |
|
"eval_runtime": 0.3913, |
|
"eval_samples_per_second": 605.612, |
|
"eval_steps_per_second": 76.66, |
|
"step": 32 |
|
} |
|
], |
|
"logging_steps": 10, |
|
"max_steps": 36, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 2, |
|
"save_steps": 9, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 14904841371648.0, |
|
"train_batch_size": 8, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|