flan-t5-small-cnndm / trainer_state.json
spacemanidol's picture
Upload 13 files
8508a84
raw
history blame
3.38 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.999958205046044,
"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": 2.1118,
"step": 500
},
{
"epoch": 0.22,
"learning_rate": 0.0001,
"loss": 2.0683,
"step": 1000
},
{
"epoch": 0.33,
"learning_rate": 0.0001,
"loss": 2.0434,
"step": 1500
},
{
"epoch": 0.45,
"learning_rate": 0.0001,
"loss": 2.0363,
"step": 2000
},
{
"epoch": 0.56,
"learning_rate": 0.0001,
"loss": 2.0274,
"step": 2500
},
{
"epoch": 0.67,
"learning_rate": 0.0001,
"loss": 2.0182,
"step": 3000
},
{
"epoch": 0.78,
"learning_rate": 0.0001,
"loss": 2.0065,
"step": 3500
},
{
"epoch": 0.89,
"learning_rate": 0.0001,
"loss": 2.0014,
"step": 4000
},
{
"epoch": 1.0,
"learning_rate": 0.0001,
"loss": 1.9923,
"step": 4500
},
{
"epoch": 1.11,
"learning_rate": 0.0001,
"loss": 1.9702,
"step": 5000
},
{
"epoch": 1.23,
"learning_rate": 0.0001,
"loss": 1.9662,
"step": 5500
},
{
"epoch": 1.34,
"learning_rate": 0.0001,
"loss": 1.9603,
"step": 6000
},
{
"epoch": 1.45,
"learning_rate": 0.0001,
"loss": 1.9585,
"step": 6500
},
{
"epoch": 1.56,
"learning_rate": 0.0001,
"loss": 1.9539,
"step": 7000
},
{
"epoch": 1.67,
"learning_rate": 0.0001,
"loss": 1.9485,
"step": 7500
},
{
"epoch": 1.78,
"learning_rate": 0.0001,
"loss": 1.9465,
"step": 8000
},
{
"epoch": 1.89,
"learning_rate": 0.0001,
"loss": 1.9444,
"step": 8500
},
{
"epoch": 2.01,
"learning_rate": 0.0001,
"loss": 1.9368,
"step": 9000
},
{
"epoch": 2.12,
"learning_rate": 0.0001,
"loss": 1.9224,
"step": 9500
},
{
"epoch": 2.23,
"learning_rate": 0.0001,
"loss": 1.9213,
"step": 10000
},
{
"epoch": 2.34,
"learning_rate": 0.0001,
"loss": 1.9162,
"step": 10500
},
{
"epoch": 2.45,
"learning_rate": 0.0001,
"loss": 1.9076,
"step": 11000
},
{
"epoch": 2.56,
"learning_rate": 0.0001,
"loss": 1.914,
"step": 11500
},
{
"epoch": 2.67,
"learning_rate": 0.0001,
"loss": 1.9095,
"step": 12000
},
{
"epoch": 2.79,
"learning_rate": 0.0001,
"loss": 1.9144,
"step": 12500
},
{
"epoch": 2.9,
"learning_rate": 0.0001,
"loss": 1.9083,
"step": 13000
},
{
"epoch": 3.0,
"step": 13458,
"total_flos": 3.1433009883806515e+17,
"train_loss": 1.96707555141894,
"train_runtime": 39189.7752,
"train_samples_per_second": 21.979,
"train_steps_per_second": 0.343
}
],
"max_steps": 13458,
"num_train_epochs": 3,
"total_flos": 3.1433009883806515e+17,
"trial_name": null,
"trial_params": null
}