imaditya123's picture
Training in progress, step 2500
c587c59 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.1446540880503147,
"eval_steps": 500,
"global_step": 1000,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_accuracy": 0.6680645161290323,
"eval_loss": 0.4126000702381134,
"eval_runtime": 5.3541,
"eval_samples_per_second": 578.999,
"eval_steps_per_second": 12.14,
"step": 318
},
{
"epoch": 1.5723270440251573,
"grad_norm": 0.9286167621612549,
"learning_rate": 1.606918238993711e-05,
"loss": 0.6457,
"step": 500
},
{
"epoch": 2.0,
"eval_accuracy": 0.8387096774193549,
"eval_loss": 0.14377787709236145,
"eval_runtime": 5.7959,
"eval_samples_per_second": 534.861,
"eval_steps_per_second": 11.215,
"step": 636
},
{
"epoch": 3.0,
"eval_accuracy": 0.8964516129032258,
"eval_loss": 0.0756388008594513,
"eval_runtime": 5.5995,
"eval_samples_per_second": 553.618,
"eval_steps_per_second": 11.608,
"step": 954
},
{
"epoch": 3.1446540880503147,
"grad_norm": 0.782314121723175,
"learning_rate": 1.2138364779874214e-05,
"loss": 0.1679,
"step": 1000
}
],
"logging_steps": 500,
"max_steps": 2544,
"num_input_tokens_seen": 0,
"num_train_epochs": 8,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 462935763122448.0,
"train_batch_size": 48,
"trial_name": null,
"trial_params": {
"alpha": 0.0171008380469381,
"num_train_epochs": 8,
"temperature": 2
}
}