|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.0, |
|
"eval_steps": 1000, |
|
"global_step": 834, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.11990407673860912, |
|
"grad_norm": 33.553314208984375, |
|
"learning_rate": 1.929887378670186e-05, |
|
"loss": 0.7732, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.23980815347721823, |
|
"grad_norm": 5.416075706481934, |
|
"learning_rate": 1.729381074020218e-05, |
|
"loss": 0.7018, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.3597122302158273, |
|
"grad_norm": 5.061486721038818, |
|
"learning_rate": 1.4265971312744252e-05, |
|
"loss": 0.7014, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.47961630695443647, |
|
"grad_norm": 3.992720603942871, |
|
"learning_rate": 1.0639935022777741e-05, |
|
"loss": 0.6841, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.5995203836930456, |
|
"grad_norm": 4.914097785949707, |
|
"learning_rate": 6.924163688955825e-06, |
|
"loss": 0.7251, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.7194244604316546, |
|
"grad_norm": 4.0411577224731445, |
|
"learning_rate": 3.6397022482313804e-06, |
|
"loss": 0.6829, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 0.8393285371702638, |
|
"grad_norm": 5.131595611572266, |
|
"learning_rate": 1.2471151031361795e-06, |
|
"loss": 0.6744, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 0.9592326139088729, |
|
"grad_norm": 12.620176315307617, |
|
"learning_rate": 8.190336667550869e-08, |
|
"loss": 0.6864, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"step": 834, |
|
"total_flos": 0.0, |
|
"train_loss": 0.7041080118083268, |
|
"train_runtime": 641.2149, |
|
"train_samples_per_second": 10.396, |
|
"train_steps_per_second": 1.301 |
|
} |
|
], |
|
"logging_steps": 100, |
|
"max_steps": 834, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 500, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": false, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 0.0, |
|
"train_batch_size": 1, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|