| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04174573055028463, | |
| "eval_steps": 14, | |
| "global_step": 55, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007590132827324478, | |
| "eval_loss": 3.6194629669189453, | |
| "eval_runtime": 6.1291, | |
| "eval_samples_per_second": 45.357, | |
| "eval_steps_per_second": 22.679, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007590132827324478, | |
| "grad_norm": 11.131251335144043, | |
| "learning_rate": 0.0002, | |
| "loss": 2.5841, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01062618595825427, | |
| "eval_loss": 1.3193589448928833, | |
| "eval_runtime": 5.6114, | |
| "eval_samples_per_second": 49.542, | |
| "eval_steps_per_second": 24.771, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.015180265654648957, | |
| "grad_norm": 4.966372489929199, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2173, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02125237191650854, | |
| "eval_loss": 1.1263376474380493, | |
| "eval_runtime": 5.716, | |
| "eval_samples_per_second": 48.635, | |
| "eval_steps_per_second": 24.318, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.022770398481973434, | |
| "grad_norm": 4.151969909667969, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1996, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.030360531309297913, | |
| "grad_norm": 13.053388595581055, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1524, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.031878557874762806, | |
| "eval_loss": 1.0414668321609497, | |
| "eval_runtime": 5.6278, | |
| "eval_samples_per_second": 49.397, | |
| "eval_steps_per_second": 24.699, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.03795066413662239, | |
| "grad_norm": 3.2989048957824707, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1103, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 55, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 14, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 910539054120960.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |