flan-t5-large-5-6-cnndm / trainer_state.json
spacemanidol's picture
Upload 12 files
70d5fbf
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.9999442741710785,
"global_step": 13458,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.11,
"learning_rate": 0.0001,
"loss": 1.2872,
"step": 500
},
{
"epoch": 0.22,
"learning_rate": 0.0001,
"loss": 1.2805,
"step": 1000
},
{
"epoch": 0.33,
"learning_rate": 0.0001,
"loss": 1.2781,
"step": 1500
},
{
"epoch": 0.45,
"learning_rate": 0.0001,
"loss": 1.2817,
"step": 2000
},
{
"epoch": 0.56,
"learning_rate": 0.0001,
"loss": 1.2829,
"step": 2500
},
{
"epoch": 0.67,
"learning_rate": 0.0001,
"loss": 1.2811,
"step": 3000
},
{
"epoch": 0.78,
"learning_rate": 0.0001,
"loss": 1.2803,
"step": 3500
},
{
"epoch": 0.89,
"learning_rate": 0.0001,
"loss": 1.2811,
"step": 4000
},
{
"epoch": 1.0,
"learning_rate": 0.0001,
"loss": 1.2769,
"step": 4500
},
{
"epoch": 1.11,
"learning_rate": 0.0001,
"loss": 1.2204,
"step": 5000
},
{
"epoch": 1.23,
"learning_rate": 0.0001,
"loss": 1.224,
"step": 5500
},
{
"epoch": 1.34,
"learning_rate": 0.0001,
"loss": 1.224,
"step": 6000
},
{
"epoch": 1.45,
"learning_rate": 0.0001,
"loss": 1.2275,
"step": 6500
},
{
"epoch": 1.56,
"learning_rate": 0.0001,
"loss": 1.2296,
"step": 7000
},
{
"epoch": 1.67,
"learning_rate": 0.0001,
"loss": 1.2289,
"step": 7500
},
{
"epoch": 1.78,
"learning_rate": 0.0001,
"loss": 1.2322,
"step": 8000
},
{
"epoch": 1.89,
"learning_rate": 0.0001,
"loss": 1.234,
"step": 8500
},
{
"epoch": 2.01,
"learning_rate": 0.0001,
"loss": 1.2293,
"step": 9000
},
{
"epoch": 2.12,
"learning_rate": 0.0001,
"loss": 1.1723,
"step": 9500
},
{
"epoch": 2.23,
"learning_rate": 0.0001,
"loss": 1.1786,
"step": 10000
},
{
"epoch": 2.34,
"learning_rate": 0.0001,
"loss": 1.1791,
"step": 10500
},
{
"epoch": 2.45,
"learning_rate": 0.0001,
"loss": 1.179,
"step": 11000
},
{
"epoch": 2.56,
"learning_rate": 0.0001,
"loss": 1.1853,
"step": 11500
},
{
"epoch": 2.67,
"learning_rate": 0.0001,
"loss": 1.1855,
"step": 12000
},
{
"epoch": 2.79,
"learning_rate": 0.0001,
"loss": 1.1931,
"step": 12500
},
{
"epoch": 2.9,
"learning_rate": 0.0001,
"loss": 1.1914,
"step": 13000
},
{
"epoch": 3.0,
"step": 13458,
"total_flos": 3.692914410132136e+18,
"train_loss": 1.2309965376585372,
"train_runtime": 86494.2022,
"train_samples_per_second": 9.958,
"train_steps_per_second": 0.156
}
],
"max_steps": 13458,
"num_train_epochs": 3,
"total_flos": 3.692914410132136e+18,
"trial_name": null,
"trial_params": null
}