VERSIL91's picture
Training in progress, step 5, checkpoint
7028e91 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.01416179854841565,
"eval_steps": 2,
"global_step": 5,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0028323597096831295,
"grad_norm": 9.473759651184082,
"learning_rate": 1e-05,
"loss": 13.477,
"step": 1
},
{
"epoch": 0.0028323597096831295,
"eval_loss": 13.491250991821289,
"eval_runtime": 508.8556,
"eval_samples_per_second": 1.169,
"eval_steps_per_second": 0.586,
"step": 1
},
{
"epoch": 0.005664719419366259,
"grad_norm": 9.305607795715332,
"learning_rate": 2e-05,
"loss": 13.4128,
"step": 2
},
{
"epoch": 0.005664719419366259,
"eval_loss": 13.201850891113281,
"eval_runtime": 255.8922,
"eval_samples_per_second": 2.325,
"eval_steps_per_second": 1.165,
"step": 2
},
{
"epoch": 0.008497079129049389,
"grad_norm": 9.665515899658203,
"learning_rate": 3e-05,
"loss": 13.235,
"step": 3
},
{
"epoch": 0.011329438838732518,
"grad_norm": 8.425497055053711,
"learning_rate": 4e-05,
"loss": 12.9052,
"step": 4
},
{
"epoch": 0.011329438838732518,
"eval_loss": 12.784314155578613,
"eval_runtime": 229.8044,
"eval_samples_per_second": 2.589,
"eval_steps_per_second": 1.297,
"step": 4
},
{
"epoch": 0.01416179854841565,
"grad_norm": 9.428298950195312,
"learning_rate": 5e-05,
"loss": 13.0804,
"step": 5
}
],
"logging_steps": 1,
"max_steps": 5,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 2,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 7398256992583680.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}