lesso's picture
Training in progress, step 10, checkpoint
7cb5203 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.8333333333333334,
"eval_steps": 3,
"global_step": 10,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.08333333333333333,
"grad_norm": NaN,
"learning_rate": 0.0,
"loss": 1.4927,
"step": 1
},
{
"epoch": 0.08333333333333333,
"eval_loss": 1.4977792501449585,
"eval_runtime": 0.2209,
"eval_samples_per_second": 13.579,
"eval_steps_per_second": 13.579,
"step": 1
},
{
"epoch": 0.16666666666666666,
"grad_norm": 4.962691783905029,
"learning_rate": 2e-05,
"loss": 1.307,
"step": 2
},
{
"epoch": 0.25,
"grad_norm": 5.919677734375,
"learning_rate": 4e-05,
"loss": 1.5735,
"step": 3
},
{
"epoch": 0.25,
"eval_loss": 1.4450377225875854,
"eval_runtime": 0.2257,
"eval_samples_per_second": 13.291,
"eval_steps_per_second": 13.291,
"step": 3
},
{
"epoch": 0.3333333333333333,
"grad_norm": 4.771228313446045,
"learning_rate": 6e-05,
"loss": 1.2789,
"step": 4
},
{
"epoch": 0.4166666666666667,
"grad_norm": 3.510233163833618,
"learning_rate": 8e-05,
"loss": 1.3015,
"step": 5
},
{
"epoch": 0.5,
"grad_norm": 2.8811535835266113,
"learning_rate": 0.0001,
"loss": 1.0788,
"step": 6
},
{
"epoch": 0.5,
"eval_loss": 0.8092367053031921,
"eval_runtime": 0.2418,
"eval_samples_per_second": 12.405,
"eval_steps_per_second": 12.405,
"step": 6
},
{
"epoch": 0.5833333333333334,
"grad_norm": 2.4136533737182617,
"learning_rate": 0.00012,
"loss": 0.8223,
"step": 7
},
{
"epoch": 0.6666666666666666,
"grad_norm": 2.6814074516296387,
"learning_rate": 0.00014,
"loss": 0.5264,
"step": 8
},
{
"epoch": 0.75,
"grad_norm": 2.8438990116119385,
"learning_rate": 0.00016,
"loss": 0.2195,
"step": 9
},
{
"epoch": 0.75,
"eval_loss": 0.0419984795153141,
"eval_runtime": 0.227,
"eval_samples_per_second": 13.215,
"eval_steps_per_second": 13.215,
"step": 9
},
{
"epoch": 0.8333333333333334,
"grad_norm": 2.2577595710754395,
"learning_rate": 0.00018,
"loss": 0.1396,
"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": 1849564248145920.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}