cwaud's picture
Training in progress, step 10, checkpoint
6bdecce verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.007993605115907274,
"eval_steps": 3,
"global_step": 10,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0007993605115907274,
"grad_norm": NaN,
"learning_rate": 2e-05,
"loss": 0.0,
"step": 1
},
{
"epoch": 0.0007993605115907274,
"eval_loss": NaN,
"eval_runtime": 46.7095,
"eval_samples_per_second": 11.282,
"eval_steps_per_second": 5.652,
"step": 1
},
{
"epoch": 0.0015987210231814548,
"grad_norm": NaN,
"learning_rate": 4e-05,
"loss": 0.0,
"step": 2
},
{
"epoch": 0.002398081534772182,
"grad_norm": NaN,
"learning_rate": 6e-05,
"loss": 0.0,
"step": 3
},
{
"epoch": 0.002398081534772182,
"eval_loss": NaN,
"eval_runtime": 46.6654,
"eval_samples_per_second": 11.293,
"eval_steps_per_second": 5.657,
"step": 3
},
{
"epoch": 0.0031974420463629096,
"grad_norm": NaN,
"learning_rate": 8e-05,
"loss": 0.0,
"step": 4
},
{
"epoch": 0.003996802557953637,
"grad_norm": NaN,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 5
},
{
"epoch": 0.004796163069544364,
"grad_norm": NaN,
"learning_rate": 0.00012,
"loss": 0.0,
"step": 6
},
{
"epoch": 0.004796163069544364,
"eval_loss": NaN,
"eval_runtime": 46.9003,
"eval_samples_per_second": 11.237,
"eval_steps_per_second": 5.629,
"step": 6
},
{
"epoch": 0.005595523581135092,
"grad_norm": NaN,
"learning_rate": 0.00014,
"loss": 0.0,
"step": 7
},
{
"epoch": 0.006394884092725819,
"grad_norm": NaN,
"learning_rate": 0.00016,
"loss": 0.0,
"step": 8
},
{
"epoch": 0.007194244604316547,
"grad_norm": NaN,
"learning_rate": 0.00018,
"loss": 0.0,
"step": 9
},
{
"epoch": 0.007194244604316547,
"eval_loss": NaN,
"eval_runtime": 47.0125,
"eval_samples_per_second": 11.21,
"eval_steps_per_second": 5.616,
"step": 9
},
{
"epoch": 0.007993605115907274,
"grad_norm": NaN,
"learning_rate": 0.0002,
"loss": 0.0,
"step": 10
}
],
"logging_steps": 1,
"max_steps": 10,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 3,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1630396427010048.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}