|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.0029209872937052722, |
|
"eval_steps": 3, |
|
"global_step": 10, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0002920987293705272, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0, |
|
"loss": 10.0112, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0002920987293705272, |
|
"eval_loss": 2.4118621349334717, |
|
"eval_runtime": 141.9333, |
|
"eval_samples_per_second": 5.08, |
|
"eval_steps_per_second": 5.08, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0005841974587410544, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0, |
|
"loss": 7.7777, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.0008762961881115817, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0, |
|
"loss": 4.3251, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.0008762961881115817, |
|
"eval_loss": 2.4118621349334717, |
|
"eval_runtime": 181.165, |
|
"eval_samples_per_second": 3.98, |
|
"eval_steps_per_second": 3.98, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.0011683949174821088, |
|
"grad_norm": 106.46147918701172, |
|
"learning_rate": 2e-05, |
|
"loss": 10.6612, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.0014604936468526361, |
|
"grad_norm": 46.043792724609375, |
|
"learning_rate": 4e-05, |
|
"loss": 9.5607, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.0017525923762231634, |
|
"grad_norm": 42.20634841918945, |
|
"learning_rate": 6e-05, |
|
"loss": 8.2951, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.0017525923762231634, |
|
"eval_loss": 2.274749994277954, |
|
"eval_runtime": 304.0635, |
|
"eval_samples_per_second": 2.371, |
|
"eval_steps_per_second": 2.371, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.002044691105593691, |
|
"grad_norm": 72.1349105834961, |
|
"learning_rate": 8e-05, |
|
"loss": 7.8116, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.0023367898349642177, |
|
"grad_norm": 44.42057800292969, |
|
"learning_rate": 0.0001, |
|
"loss": 7.5031, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.002628888564334745, |
|
"grad_norm": 57.80799102783203, |
|
"learning_rate": 0.00012, |
|
"loss": 9.857, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.002628888564334745, |
|
"eval_loss": 1.883453607559204, |
|
"eval_runtime": 303.9552, |
|
"eval_samples_per_second": 2.372, |
|
"eval_steps_per_second": 2.372, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.0029209872937052722, |
|
"grad_norm": 47.45390701293945, |
|
"learning_rate": 0.00014, |
|
"loss": 6.6697, |
|
"step": 10 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 10, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 3, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 7031294986813440.0, |
|
"train_batch_size": 1, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|