127 lines
3.0 KiB
JSON
127 lines
3.0 KiB
JSON
{
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 2.9397590361445785,
|
|
"eval_steps": 500,
|
|
"global_step": 123,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"epoch": 0.24096385542168675,
|
|
"grad_norm": 3.629333972930908,
|
|
"learning_rate": 7.692307692307694e-06,
|
|
"loss": 1.081,
|
|
"step": 10
|
|
},
|
|
{
|
|
"epoch": 0.4819277108433735,
|
|
"grad_norm": 2.5671825408935547,
|
|
"learning_rate": 9.900412805461968e-06,
|
|
"loss": 0.8009,
|
|
"step": 20
|
|
},
|
|
{
|
|
"epoch": 0.7228915662650602,
|
|
"grad_norm": 2.330085277557373,
|
|
"learning_rate": 9.422164654989073e-06,
|
|
"loss": 0.7773,
|
|
"step": 30
|
|
},
|
|
{
|
|
"epoch": 0.963855421686747,
|
|
"grad_norm": 2.4446911811828613,
|
|
"learning_rate": 8.585659023794818e-06,
|
|
"loss": 0.7559,
|
|
"step": 40
|
|
},
|
|
{
|
|
"epoch": 1.1927710843373494,
|
|
"grad_norm": 2.232125997543335,
|
|
"learning_rate": 7.45866462322802e-06,
|
|
"loss": 0.5987,
|
|
"step": 50
|
|
},
|
|
{
|
|
"epoch": 1.4337349397590362,
|
|
"grad_norm": 2.0914366245269775,
|
|
"learning_rate": 6.132483837128823e-06,
|
|
"loss": 0.5907,
|
|
"step": 60
|
|
},
|
|
{
|
|
"epoch": 1.6746987951807228,
|
|
"grad_norm": 1.837985873222351,
|
|
"learning_rate": 4.71455594568616e-06,
|
|
"loss": 0.5766,
|
|
"step": 70
|
|
},
|
|
{
|
|
"epoch": 1.9156626506024095,
|
|
"grad_norm": 2.1364665031433105,
|
|
"learning_rate": 3.319753033922849e-06,
|
|
"loss": 0.5707,
|
|
"step": 80
|
|
},
|
|
{
|
|
"epoch": 2.144578313253012,
|
|
"grad_norm": 1.9006352424621582,
|
|
"learning_rate": 2.061073738537635e-06,
|
|
"loss": 0.4834,
|
|
"step": 90
|
|
},
|
|
{
|
|
"epoch": 2.3855421686746987,
|
|
"grad_norm": 1.8541189432144165,
|
|
"learning_rate": 1.0404887703886252e-06,
|
|
"loss": 0.4311,
|
|
"step": 100
|
|
},
|
|
{
|
|
"epoch": 2.6265060240963853,
|
|
"grad_norm": 1.9577722549438477,
|
|
"learning_rate": 3.406798539427386e-07,
|
|
"loss": 0.441,
|
|
"step": 110
|
|
},
|
|
{
|
|
"epoch": 2.8674698795180724,
|
|
"grad_norm": 1.6799449920654297,
|
|
"learning_rate": 1.834134568654333e-08,
|
|
"loss": 0.4362,
|
|
"step": 120
|
|
},
|
|
{
|
|
"epoch": 2.9397590361445785,
|
|
"step": 123,
|
|
"total_flos": 4.737549008539484e+17,
|
|
"train_loss": 0.6231146188286262,
|
|
"train_runtime": 2388.9222,
|
|
"train_samples_per_second": 3.327,
|
|
"train_steps_per_second": 0.051
|
|
}
|
|
],
|
|
"logging_steps": 10,
|
|
"max_steps": 123,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 3,
|
|
"save_steps": 1000,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": true
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 4.737549008539484e+17,
|
|
"train_batch_size": 4,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|