| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00565171317555634, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011303426351112682, | |
| "grad_norm": 0.693830668926239, | |
| "learning_rate": 1e-05, | |
| "loss": 1.1385, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011303426351112682, | |
| "eval_loss": 1.1293458938598633, | |
| "eval_runtime": 48.1681, | |
| "eval_samples_per_second": 30.933, | |
| "eval_steps_per_second": 15.467, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0022606852702225363, | |
| "grad_norm": 0.7315422892570496, | |
| "learning_rate": 2e-05, | |
| "loss": 1.1501, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0022606852702225363, | |
| "eval_loss": 1.1152327060699463, | |
| "eval_runtime": 19.2856, | |
| "eval_samples_per_second": 77.26, | |
| "eval_steps_per_second": 38.63, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0033910279053338045, | |
| "grad_norm": 0.6873337626457214, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1193, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004521370540445073, | |
| "grad_norm": 0.6715127825737, | |
| "learning_rate": 4e-05, | |
| "loss": 1.0917, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004521370540445073, | |
| "eval_loss": 1.0981663465499878, | |
| "eval_runtime": 19.3332, | |
| "eval_samples_per_second": 77.069, | |
| "eval_steps_per_second": 38.535, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00565171317555634, | |
| "grad_norm": 0.6725367307662964, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1052, | |
| "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": 1023167913000960.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |