yueqis's picture
Upload trainer_state.json with huggingface_hub
3ad0854 verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.9759229534510432,
"eval_steps": 1000,
"global_step": 76,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.2568218298555377,
"grad_norm": 0.6396063311539051,
"learning_rate": 9.881480035599667e-06,
"loss": 0.4811,
"step": 10
},
{
"epoch": 0.5136436597110754,
"grad_norm": 0.3654983268045694,
"learning_rate": 8.966766701456177e-06,
"loss": 0.2451,
"step": 20
},
{
"epoch": 0.7704654895666132,
"grad_norm": 0.28676240172292244,
"learning_rate": 7.308743066175172e-06,
"loss": 0.2084,
"step": 30
},
{
"epoch": 1.0513643659711076,
"grad_norm": 0.26759225032608386,
"learning_rate": 5.218096936826681e-06,
"loss": 0.2115,
"step": 40
},
{
"epoch": 1.3081861958266452,
"grad_norm": 0.2861632997496441,
"learning_rate": 3.0865828381745515e-06,
"loss": 0.1767,
"step": 50
},
{
"epoch": 1.565008025682183,
"grad_norm": 0.2683730583281023,
"learning_rate": 1.3136133159493803e-06,
"loss": 0.1714,
"step": 60
},
{
"epoch": 1.8218298555377208,
"grad_norm": 0.2705392147351614,
"learning_rate": 2.314152462588659e-07,
"loss": 0.1742,
"step": 70
},
{
"epoch": 1.9759229534510432,
"step": 76,
"total_flos": 283081697132544.0,
"train_loss": 0.23416273531160856,
"train_runtime": 4543.5593,
"train_samples_per_second": 2.194,
"train_steps_per_second": 0.017
}
],
"logging_steps": 10,
"max_steps": 76,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 100,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 283081697132544.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}