vermoney's picture
Training in progress, step 10, checkpoint
1be6ce5 verified
raw
history blame
2.16 kB
{
"best_metric": 1.317108392715454,
"best_model_checkpoint": "miner_id_24/checkpoint-10",
"epoch": 0.0005015862665680214,
"eval_steps": 5,
"global_step": 10,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 5.0158626656802136e-05,
"eval_loss": 1.8039422035217285,
"eval_runtime": 812.9865,
"eval_samples_per_second": 10.326,
"eval_steps_per_second": 5.164,
"step": 1
},
{
"epoch": 0.00015047587997040642,
"grad_norm": 0.5721948146820068,
"learning_rate": 6e-05,
"loss": 1.7091,
"step": 3
},
{
"epoch": 0.0002507931332840107,
"eval_loss": 1.6594451665878296,
"eval_runtime": 843.2851,
"eval_samples_per_second": 9.955,
"eval_steps_per_second": 4.978,
"step": 5
},
{
"epoch": 0.00030095175994081285,
"grad_norm": 1.1099064350128174,
"learning_rate": 9.96057350657239e-05,
"loss": 1.7172,
"step": 6
},
{
"epoch": 0.00045142763991121924,
"grad_norm": 0.8487201929092407,
"learning_rate": 9.381533400219318e-05,
"loss": 1.4969,
"step": 9
},
{
"epoch": 0.0005015862665680214,
"eval_loss": 1.317108392715454,
"eval_runtime": 843.8013,
"eval_samples_per_second": 9.949,
"eval_steps_per_second": 4.975,
"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": 1378569745858560.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}