zephyr-7b-sft-qlora / trainer_state.json
yycsu's picture
Model save
a5b6b2a verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9836065573770492,
"eval_steps": 500,
"global_step": 30,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.5,
"grad_norm": 0.33984375,
"learning_rate": 0.0002,
"loss": 1.0737,
"step": 1
},
{
"epoch": 0.16393442622950818,
"grad_norm": 0.294921875,
"learning_rate": 0.00019730448705798239,
"loss": 0.9378,
"step": 5
},
{
"epoch": 0.32786885245901637,
"grad_norm": 0.28125,
"learning_rate": 0.0001686241637868734,
"loss": 0.7471,
"step": 10
},
{
"epoch": 0.4918032786885246,
"grad_norm": 0.283203125,
"learning_rate": 0.00011736481776669306,
"loss": 0.723,
"step": 15
},
{
"epoch": 0.6557377049180327,
"grad_norm": 0.25390625,
"learning_rate": 6.039202339608432e-05,
"loss": 0.806,
"step": 20
},
{
"epoch": 0.819672131147541,
"grad_norm": 0.294921875,
"learning_rate": 1.6451218858706374e-05,
"loss": 0.6992,
"step": 25
},
{
"epoch": 0.9836065573770492,
"grad_norm": 0.228515625,
"learning_rate": 0.0,
"loss": 0.7609,
"step": 30
},
{
"epoch": 0.9836065573770492,
"step": 30,
"total_flos": 2.0918103256858624e+16,
"train_loss": 0.0,
"train_runtime": 0.1548,
"train_samples_per_second": 1576.031,
"train_steps_per_second": 193.774
}
],
"logging_steps": 5,
"max_steps": 30,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"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": 2.0918103256858624e+16,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}