joboffer's picture
Training in progress, step 10, checkpoint
3e91e7e verified
{
"best_metric": NaN,
"best_model_checkpoint": "miner_id_24/checkpoint-10",
"epoch": 0.026917900403768506,
"eval_steps": 5,
"global_step": 10,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0026917900403768506,
"eval_loss": NaN,
"eval_runtime": 13.4825,
"eval_samples_per_second": 11.645,
"eval_steps_per_second": 5.859,
"step": 1
},
{
"epoch": 0.008075370121130552,
"grad_norm": NaN,
"learning_rate": 6e-05,
"loss": 0.0,
"step": 3
},
{
"epoch": 0.013458950201884253,
"eval_loss": NaN,
"eval_runtime": 12.9621,
"eval_samples_per_second": 12.112,
"eval_steps_per_second": 6.095,
"step": 5
},
{
"epoch": 0.016150740242261104,
"grad_norm": NaN,
"learning_rate": 9.96057350657239e-05,
"loss": 0.0,
"step": 6
},
{
"epoch": 0.024226110363391656,
"grad_norm": NaN,
"learning_rate": 9.381533400219318e-05,
"loss": 0.0,
"step": 9
},
{
"epoch": 0.026917900403768506,
"eval_loss": NaN,
"eval_runtime": 13.091,
"eval_samples_per_second": 11.993,
"eval_steps_per_second": 6.035,
"step": 10
}
],
"logging_steps": 3,
"max_steps": 30,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 10,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 1,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1306268836823040.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}