falcon-testing / last-checkpoint /trainer_state.json
bwebs's picture
Training in progress, step 17
1d42776
raw
history blame
2.1 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 4.25,
"global_step": 17,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.25,
"learning_rate": 0.0002,
"loss": 1.7413,
"step": 1
},
{
"epoch": 0.5,
"learning_rate": 0.0002,
"loss": 1.7187,
"step": 2
},
{
"epoch": 0.75,
"learning_rate": 0.0002,
"loss": 1.7006,
"step": 3
},
{
"epoch": 1.0,
"learning_rate": 0.0002,
"loss": 1.5806,
"step": 4
},
{
"epoch": 1.25,
"learning_rate": 0.0002,
"loss": 1.5316,
"step": 5
},
{
"epoch": 1.5,
"learning_rate": 0.0002,
"loss": 1.4856,
"step": 6
},
{
"epoch": 1.75,
"learning_rate": 0.0002,
"loss": 1.3389,
"step": 7
},
{
"epoch": 2.0,
"learning_rate": 0.0002,
"loss": 1.2343,
"step": 8
},
{
"epoch": 2.25,
"learning_rate": 0.0002,
"loss": 1.1174,
"step": 9
},
{
"epoch": 2.5,
"learning_rate": 0.0002,
"loss": 0.9802,
"step": 10
},
{
"epoch": 2.75,
"learning_rate": 0.0002,
"loss": 0.8965,
"step": 11
},
{
"epoch": 3.0,
"learning_rate": 0.0002,
"loss": 0.7951,
"step": 12
},
{
"epoch": 3.25,
"learning_rate": 0.0002,
"loss": 0.6422,
"step": 13
},
{
"epoch": 3.5,
"learning_rate": 0.0002,
"loss": 0.6023,
"step": 14
},
{
"epoch": 3.75,
"learning_rate": 0.0002,
"loss": 0.5078,
"step": 15
},
{
"epoch": 4.0,
"learning_rate": 0.0002,
"loss": 0.5033,
"step": 16
},
{
"epoch": 4.25,
"learning_rate": 0.0002,
"loss": 0.4317,
"step": 17
}
],
"max_steps": 500,
"num_train_epochs": 125,
"total_flos": 2835286102376448.0,
"trial_name": null,
"trial_params": null
}