vmpsergio's picture
Training in progress, step 10, checkpoint
83170df verified
{
"best_metric": NaN,
"best_model_checkpoint": "miner_id_24/checkpoint-10",
"epoch": 0.03714020427112349,
"eval_steps": 5,
"global_step": 10,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.003714020427112349,
"eval_loss": NaN,
"eval_runtime": 20.5895,
"eval_samples_per_second": 5.537,
"eval_steps_per_second": 2.768,
"step": 1
},
{
"epoch": 0.011142061281337047,
"grad_norm": NaN,
"learning_rate": 6e-05,
"loss": 0.0,
"step": 3
},
{
"epoch": 0.018570102135561744,
"eval_loss": NaN,
"eval_runtime": 20.8187,
"eval_samples_per_second": 5.476,
"eval_steps_per_second": 2.738,
"step": 5
},
{
"epoch": 0.022284122562674095,
"grad_norm": NaN,
"learning_rate": 0.00012,
"loss": 0.0,
"step": 6
},
{
"epoch": 0.033426183844011144,
"grad_norm": NaN,
"learning_rate": 0.00018,
"loss": 0.0,
"step": 9
},
{
"epoch": 0.03714020427112349,
"eval_loss": NaN,
"eval_runtime": 20.8697,
"eval_samples_per_second": 5.462,
"eval_steps_per_second": 2.731,
"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": 6361963089100800.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}