| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.007552157084867365, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0015104314169734731, | |
| "grad_norm": 0.27795398235321045, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5891, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015104314169734731, | |
| "eval_loss": 0.6050078272819519, | |
| "eval_runtime": 222.9293, | |
| "eval_samples_per_second": 5.002, | |
| "eval_steps_per_second": 2.503, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0030208628339469462, | |
| "grad_norm": 0.24203497171401978, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5053, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0030208628339469462, | |
| "eval_loss": 0.5993300676345825, | |
| "eval_runtime": 79.8504, | |
| "eval_samples_per_second": 13.964, | |
| "eval_steps_per_second": 6.988, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004531294250920419, | |
| "grad_norm": 0.2544724643230438, | |
| "learning_rate": 3e-05, | |
| "loss": 0.493, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0060417256678938925, | |
| "grad_norm": 0.2703111171722412, | |
| "learning_rate": 4e-05, | |
| "loss": 0.5334, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0060417256678938925, | |
| "eval_loss": 0.5920233726501465, | |
| "eval_runtime": 79.7003, | |
| "eval_samples_per_second": 13.99, | |
| "eval_steps_per_second": 7.001, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.007552157084867365, | |
| "grad_norm": 0.292390912771225, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5946, | |
| "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": 5595029292711936.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |