86 lines
2.0 KiB
JSON
86 lines
2.0 KiB
JSON
|
{
|
||
|
|
"best_global_step": null,
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 0.4528301886792453,
|
||
|
|
"eval_steps": 500,
|
||
|
|
"global_step": 60,
|
||
|
|
"is_hyper_param_search": false,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"epoch": 0.07547169811320754,
|
||
|
|
"grad_norm": 22.5,
|
||
|
|
"learning_rate": 4.822441799541978e-07,
|
||
|
|
"loss": 1.7780149459838868,
|
||
|
|
"step": 10
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.1509433962264151,
|
||
|
|
"grad_norm": 6.90625,
|
||
|
|
"learning_rate": 4.012935537984413e-07,
|
||
|
|
"loss": 1.7199886322021485,
|
||
|
|
"step": 20
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.22641509433962265,
|
||
|
|
"grad_norm": 15.875,
|
||
|
|
"learning_rate": 2.770297546059854e-07,
|
||
|
|
"loss": 1.736968994140625,
|
||
|
|
"step": 30
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.3018867924528302,
|
||
|
|
"grad_norm": 9.0625,
|
||
|
|
"learning_rate": 1.4502772460993384e-07,
|
||
|
|
"loss": 1.7296815872192384,
|
||
|
|
"step": 40
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.37735849056603776,
|
||
|
|
"grad_norm": 9.9375,
|
||
|
|
"learning_rate": 4.3077750460777384e-08,
|
||
|
|
"loss": 1.7874759674072265,
|
||
|
|
"step": 50
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.4528301886792453,
|
||
|
|
"grad_norm": 20.875,
|
||
|
|
"learning_rate": 3.6664653721904526e-10,
|
||
|
|
"loss": 1.9149166107177735,
|
||
|
|
"step": 60
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.4528301886792453,
|
||
|
|
"step": 60,
|
||
|
|
"total_flos": 2.894445141093581e+16,
|
||
|
|
"train_loss": 1.7778411229451498,
|
||
|
|
"train_runtime": 516.0579,
|
||
|
|
"train_samples_per_second": 0.462,
|
||
|
|
"train_steps_per_second": 0.116
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 10,
|
||
|
|
"max_steps": 60,
|
||
|
|
"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": 2.894445141093581e+16,
|
||
|
|
"train_batch_size": 1,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|