|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.0006846457493126798, |
|
"eval_steps": 2, |
|
"global_step": 4, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.00017116143732816996, |
|
"grad_norm": 1.6291395425796509, |
|
"learning_rate": 1e-05, |
|
"loss": 18.7764, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.00017116143732816996, |
|
"eval_loss": 1.2689241170883179, |
|
"eval_runtime": 2311.164, |
|
"eval_samples_per_second": 4.258, |
|
"eval_steps_per_second": 2.129, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0003423228746563399, |
|
"grad_norm": 1.7882574796676636, |
|
"learning_rate": 2e-05, |
|
"loss": 21.083, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.0003423228746563399, |
|
"eval_loss": 1.2670626640319824, |
|
"eval_runtime": 1488.254, |
|
"eval_samples_per_second": 6.612, |
|
"eval_steps_per_second": 3.306, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.0005134843119845099, |
|
"grad_norm": 1.3665907382965088, |
|
"learning_rate": 3e-05, |
|
"loss": 21.4357, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.0006846457493126798, |
|
"grad_norm": 1.379157304763794, |
|
"learning_rate": 4e-05, |
|
"loss": 18.5128, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.0006846457493126798, |
|
"eval_loss": 1.2652815580368042, |
|
"eval_runtime": 1165.1585, |
|
"eval_samples_per_second": 8.445, |
|
"eval_steps_per_second": 4.223, |
|
"step": 4 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 5, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 2, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 1.013185335263232e+16, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|