VERSIL91's picture
Training in progress, step 5, checkpoint
6e977ac verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.07804878048780488,
"eval_steps": 2,
"global_step": 5,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.015609756097560976,
"grad_norm": 0.6015342473983765,
"learning_rate": 1e-05,
"loss": 6.8893,
"step": 1
},
{
"epoch": 0.015609756097560976,
"eval_loss": 6.875264644622803,
"eval_runtime": 11.2183,
"eval_samples_per_second": 9.627,
"eval_steps_per_second": 4.814,
"step": 1
},
{
"epoch": 0.03121951219512195,
"grad_norm": 0.6219642162322998,
"learning_rate": 2e-05,
"loss": 6.877,
"step": 2
},
{
"epoch": 0.03121951219512195,
"eval_loss": 6.875111103057861,
"eval_runtime": 0.1733,
"eval_samples_per_second": 623.041,
"eval_steps_per_second": 311.52,
"step": 2
},
{
"epoch": 0.04682926829268293,
"grad_norm": 0.595236599445343,
"learning_rate": 3e-05,
"loss": 6.8781,
"step": 3
},
{
"epoch": 0.0624390243902439,
"grad_norm": 0.6043254733085632,
"learning_rate": 4e-05,
"loss": 6.8834,
"step": 4
},
{
"epoch": 0.0624390243902439,
"eval_loss": 6.87425422668457,
"eval_runtime": 0.1762,
"eval_samples_per_second": 613.036,
"eval_steps_per_second": 306.518,
"step": 4
},
{
"epoch": 0.07804878048780488,
"grad_norm": 0.5619105696678162,
"learning_rate": 5e-05,
"loss": 6.8799,
"step": 5
}
],
"logging_steps": 1,
"max_steps": 5,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 2,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 29662433280.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}