vermoney's picture
Training in progress, step 10, checkpoint
9c2a2e9 verified
raw
history blame
2.12 kB
{
"best_metric": 3.928494930267334,
"best_model_checkpoint": "miner_id_24/checkpoint-10",
"epoch": 0.001732051615138131,
"eval_steps": 5,
"global_step": 10,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0001732051615138131,
"eval_loss": 6.304304599761963,
"eval_runtime": 591.6269,
"eval_samples_per_second": 4.109,
"eval_steps_per_second": 2.055,
"step": 1
},
{
"epoch": 0.0005196154845414394,
"grad_norm": 10.378375053405762,
"learning_rate": 3e-05,
"loss": 4.644,
"step": 3
},
{
"epoch": 0.0008660258075690655,
"eval_loss": 5.5202250480651855,
"eval_runtime": 620.0845,
"eval_samples_per_second": 3.92,
"eval_steps_per_second": 1.961,
"step": 5
},
{
"epoch": 0.0010392309690828788,
"grad_norm": 7.568704605102539,
"learning_rate": 6e-05,
"loss": 4.6156,
"step": 6
},
{
"epoch": 0.001558846453624318,
"grad_norm": 13.759147644042969,
"learning_rate": 9e-05,
"loss": 4.5151,
"step": 9
},
{
"epoch": 0.001732051615138131,
"eval_loss": 3.928494930267334,
"eval_runtime": 618.5461,
"eval_samples_per_second": 3.93,
"eval_steps_per_second": 1.966,
"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": 3834471807713280.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}