64 lines
1.5 KiB
JSON
64 lines
1.5 KiB
JSON
|
{
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 0.010036130068245684,
|
||
|
|
"eval_steps": 500,
|
||
|
|
"global_step": 75,
|
||
|
|
"is_hyper_param_search": false,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"epoch": 0.0026763013515321826,
|
||
|
|
"grad_norm": 31.0827693939209,
|
||
|
|
"learning_rate": 1.706666666666667e-05,
|
||
|
|
"loss": 1.0433,
|
||
|
|
"step": 20
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.005352602703064365,
|
||
|
|
"grad_norm": 21.620622634887695,
|
||
|
|
"learning_rate": 1.1733333333333335e-05,
|
||
|
|
"loss": 0.7188,
|
||
|
|
"step": 40
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.008028904054596548,
|
||
|
|
"grad_norm": 15.680758476257324,
|
||
|
|
"learning_rate": 6.4000000000000006e-06,
|
||
|
|
"loss": 0.5472,
|
||
|
|
"step": 60
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.010036130068245684,
|
||
|
|
"step": 75,
|
||
|
|
"total_flos": 7253655552.0,
|
||
|
|
"train_loss": 0.732325553894043,
|
||
|
|
"train_runtime": 290.3797,
|
||
|
|
"train_samples_per_second": 0.257,
|
||
|
|
"train_steps_per_second": 0.258
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 20,
|
||
|
|
"max_steps": 75,
|
||
|
|
"num_input_tokens_seen": 0,
|
||
|
|
"num_train_epochs": 1,
|
||
|
|
"save_steps": 5000,
|
||
|
|
"stateful_callbacks": {
|
||
|
|
"TrainerControl": {
|
||
|
|
"args": {
|
||
|
|
"should_epoch_stop": false,
|
||
|
|
"should_evaluate": false,
|
||
|
|
"should_log": false,
|
||
|
|
"should_save": true,
|
||
|
|
"should_training_stop": true
|
||
|
|
},
|
||
|
|
"attributes": {}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"total_flos": 7253655552.0,
|
||
|
|
"train_batch_size": 1,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|