65 lines
1.5 KiB
JSON
65 lines
1.5 KiB
JSON
|
{
|
||
|
|
"best_global_step": null,
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 0.40634920634920635,
|
||
|
|
"eval_steps": 500,
|
||
|
|
"global_step": 32,
|
||
|
|
"is_hyper_param_search": false,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"epoch": 0.12698412698412698,
|
||
|
|
"grad_norm": 11.0625,
|
||
|
|
"learning_rate": 3.800175567920295e-07,
|
||
|
|
"loss": 2.188013458251953,
|
||
|
|
"step": 10
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.25396825396825395,
|
||
|
|
"grad_norm": 11.1875,
|
||
|
|
"learning_rate": 1.6860318024178784e-07,
|
||
|
|
"loss": 2.155006980895996,
|
||
|
|
"step": 20
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.38095238095238093,
|
||
|
|
"grad_norm": 13.4375,
|
||
|
|
"learning_rate": 1.0318667309989016e-08,
|
||
|
|
"loss": 2.011971282958984,
|
||
|
|
"step": 30
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.40634920634920635,
|
||
|
|
"step": 32,
|
||
|
|
"total_flos": 1.5185329017526272e+16,
|
||
|
|
"train_loss": 2.147665500640869,
|
||
|
|
"train_runtime": 258.8642,
|
||
|
|
"train_samples_per_second": 0.487,
|
||
|
|
"train_steps_per_second": 0.124
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 10,
|
||
|
|
"max_steps": 32,
|
||
|
|
"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": 1.5185329017526272e+16,
|
||
|
|
"train_batch_size": 1,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|