|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.0, |
|
"eval_steps": 500, |
|
"global_step": 3125, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.16, |
|
"grad_norm": 1.690698266029358, |
|
"learning_rate": 8.400000000000001e-06, |
|
"loss": 2.8846, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"grad_norm": 1.4871172904968262, |
|
"learning_rate": 6.800000000000001e-06, |
|
"loss": 2.8373, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"grad_norm": 1.6461397409439087, |
|
"learning_rate": 5.2e-06, |
|
"loss": 2.8337, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"grad_norm": 1.5715138912200928, |
|
"learning_rate": 3.6000000000000003e-06, |
|
"loss": 2.8235, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"grad_norm": 1.6057703495025635, |
|
"learning_rate": 2.0000000000000003e-06, |
|
"loss": 2.812, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"grad_norm": 1.9721179008483887, |
|
"learning_rate": 4.0000000000000003e-07, |
|
"loss": 2.8048, |
|
"step": 3000 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 3125, |
|
"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": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 1.6964438675398656e+16, |
|
"train_batch_size": 8, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|