lesso's picture
Training in progress, step 10, checkpoint
4e8e0bb verified
raw
history blame
3.05 kB
{
"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": 0.3019,
"eval_samples_per_second": 9.937,
"eval_steps_per_second": 9.937,
"step": 1
},
{
"epoch": 0.16666666666666666,
"grad_norm": 4.949731349945068,
"learning_rate": 2e-05,
"loss": 1.307,
"step": 2
},
{
"epoch": 0.25,
"grad_norm": 5.8763322830200195,
"learning_rate": 4e-05,
"loss": 1.5735,
"step": 3
},
{
"epoch": 0.25,
"eval_loss": 1.4451128244400024,
"eval_runtime": 0.4158,
"eval_samples_per_second": 7.215,
"eval_steps_per_second": 7.215,
"step": 3
},
{
"epoch": 0.3333333333333333,
"grad_norm": 4.730646133422852,
"learning_rate": 6e-05,
"loss": 1.2767,
"step": 4
},
{
"epoch": 0.4166666666666667,
"grad_norm": 3.4440248012542725,
"learning_rate": 8e-05,
"loss": 1.3011,
"step": 5
},
{
"epoch": 0.5,
"grad_norm": 2.8259096145629883,
"learning_rate": 0.0001,
"loss": 1.0815,
"step": 6
},
{
"epoch": 0.5,
"eval_loss": 0.816199779510498,
"eval_runtime": 0.4516,
"eval_samples_per_second": 6.643,
"eval_steps_per_second": 6.643,
"step": 6
},
{
"epoch": 0.5833333333333334,
"grad_norm": 2.387253522872925,
"learning_rate": 0.00012,
"loss": 0.8264,
"step": 7
},
{
"epoch": 0.6666666666666666,
"grad_norm": 2.6841723918914795,
"learning_rate": 0.00014,
"loss": 0.5359,
"step": 8
},
{
"epoch": 0.75,
"grad_norm": 2.8740291595458984,
"learning_rate": 0.00016,
"loss": 0.229,
"step": 9
},
{
"epoch": 0.75,
"eval_loss": 0.04347331449389458,
"eval_runtime": 0.4018,
"eval_samples_per_second": 7.467,
"eval_steps_per_second": 7.467,
"step": 9
},
{
"epoch": 0.8333333333333334,
"grad_norm": 2.354649782180786,
"learning_rate": 0.00018,
"loss": 0.1454,
"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
}