qwenfi / checkpoint-308 /trainer_state.json
verz's picture
Upload checkpoint-308/trainer_state.json
df424f0 verified
Raw
History Blame
2.29 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 308,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.16260162601626016,
"grad_norm": 0.37675046920776367,
"learning_rate": 0.0001681818181818182,
"loss": 1.7515,
"mean_token_accuracy": 0.6049755607545376,
"num_tokens": 204800.0,
"step": 50
},
{
"epoch": 0.3252032520325203,
"grad_norm": 0.3089984357357025,
"learning_rate": 0.00013571428571428572,
"loss": 1.3323,
"mean_token_accuracy": 0.6925122183561325,
"num_tokens": 409600.0,
"step": 100
},
{
"epoch": 0.4878048780487805,
"grad_norm": 0.3363010883331299,
"learning_rate": 0.00010324675324675325,
"loss": 1.2756,
"mean_token_accuracy": 0.7040957960486413,
"num_tokens": 614400.0,
"step": 150
},
{
"epoch": 0.6504065040650406,
"grad_norm": 0.335611492395401,
"learning_rate": 7.077922077922077e-05,
"loss": 1.2833,
"mean_token_accuracy": 0.7033577680587768,
"num_tokens": 819200.0,
"step": 200
},
{
"epoch": 0.8130081300813008,
"grad_norm": 0.3524633049964905,
"learning_rate": 3.831168831168831e-05,
"loss": 1.2286,
"mean_token_accuracy": 0.7145161288976669,
"num_tokens": 1024000.0,
"step": 250
},
{
"epoch": 0.975609756097561,
"grad_norm": 0.34292736649513245,
"learning_rate": 5.844155844155844e-06,
"loss": 1.2549,
"mean_token_accuracy": 0.7073900297284126,
"num_tokens": 1228800.0,
"step": 300
}
],
"logging_steps": 50,
"max_steps": 308,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 200,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 2.09971568443392e+16,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}