91 lines
2.3 KiB
JSON
91 lines
2.3 KiB
JSON
|
{
|
||
|
|
"best_global_step": null,
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 0.13300083125519535,
|
||
|
|
"eval_steps": 500,
|
||
|
|
"global_step": 16000,
|
||
|
|
"is_hyper_param_search": false,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"epoch": 0.01662510390689942,
|
||
|
|
"grad_norm": 0.3965451121330261,
|
||
|
|
"learning_rate": 0.0002998152804565647,
|
||
|
|
"loss": 1.22260986328125,
|
||
|
|
"step": 2000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.03325020781379884,
|
||
|
|
"grad_norm": 0.6959030628204346,
|
||
|
|
"learning_rate": 0.00029922181532551095,
|
||
|
|
"loss": 1.2375645751953126,
|
||
|
|
"step": 4000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.04987531172069826,
|
||
|
|
"grad_norm": 0.3597497344017029,
|
||
|
|
"learning_rate": 0.0002982207032158324,
|
||
|
|
"loss": 1.223258056640625,
|
||
|
|
"step": 6000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.06650041562759768,
|
||
|
|
"grad_norm": 0.4819546043872833,
|
||
|
|
"learning_rate": 0.0002968146789845327,
|
||
|
|
"loss": 1.228044677734375,
|
||
|
|
"step": 8000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.0831255195344971,
|
||
|
|
"grad_norm": 0.49163299798965454,
|
||
|
|
"learning_rate": 0.00029500758363521147,
|
||
|
|
"loss": 1.233032958984375,
|
||
|
|
"step": 10000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.09975062344139651,
|
||
|
|
"grad_norm": 0.4779888391494751,
|
||
|
|
"learning_rate": 0.0002928043538251369,
|
||
|
|
"loss": 1.226021728515625,
|
||
|
|
"step": 12000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.11637572734829593,
|
||
|
|
"grad_norm": 0.5528192520141602,
|
||
|
|
"learning_rate": 0.0002902110083791929,
|
||
|
|
"loss": 1.218211181640625,
|
||
|
|
"step": 14000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.13300083125519535,
|
||
|
|
"grad_norm": 0.5382248163223267,
|
||
|
|
"learning_rate": 0.0002872346318475391,
|
||
|
|
"loss": 1.2194925537109376,
|
||
|
|
"step": 16000
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 2000,
|
||
|
|
"max_steps": 120300,
|
||
|
|
"num_input_tokens_seen": 0,
|
||
|
|
"num_train_epochs": 9223372036854775807,
|
||
|
|
"save_steps": 2000,
|
||
|
|
"stateful_callbacks": {
|
||
|
|
"TrainerControl": {
|
||
|
|
"args": {
|
||
|
|
"should_epoch_stop": false,
|
||
|
|
"should_evaluate": false,
|
||
|
|
"should_log": false,
|
||
|
|
"should_save": true,
|
||
|
|
"should_training_stop": false
|
||
|
|
},
|
||
|
|
"attributes": {}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"total_flos": 4.3730249711616e+16,
|
||
|
|
"train_batch_size": 2,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|