| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0012195307855302673, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00024390615710605343, | |
| "grad_norm": 3.2885518074035645, | |
| "learning_rate": 1e-05, | |
| "loss": 3.476, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00024390615710605343, | |
| "eval_loss": 3.9984519481658936, | |
| "eval_runtime": 321.8554, | |
| "eval_samples_per_second": 21.457, | |
| "eval_steps_per_second": 10.728, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00048781231421210687, | |
| "grad_norm": 3.737687587738037, | |
| "learning_rate": 2e-05, | |
| "loss": 4.0163, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00048781231421210687, | |
| "eval_loss": 3.9769108295440674, | |
| "eval_runtime": 241.4971, | |
| "eval_samples_per_second": 28.597, | |
| "eval_steps_per_second": 14.298, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0007317184713181603, | |
| "grad_norm": 3.2360386848449707, | |
| "learning_rate": 3e-05, | |
| "loss": 3.602, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0009756246284242137, | |
| "grad_norm": 3.2537007331848145, | |
| "learning_rate": 4e-05, | |
| "loss": 3.311, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0009756246284242137, | |
| "eval_loss": 3.8624930381774902, | |
| "eval_runtime": 132.9812, | |
| "eval_samples_per_second": 51.932, | |
| "eval_steps_per_second": 25.966, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0012195307855302673, | |
| "grad_norm": 2.600978374481201, | |
| "learning_rate": 5e-05, | |
| "loss": 3.0447, | |
| "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": 1012697094684672.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |