| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 27, | |
| "global_step": 81, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.48148148148148145, | |
| "grad_norm": 2.997140884399414, | |
| "learning_rate": 1.8755582313020912e-05, | |
| "loss": 0.7448, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.9629629629629629, | |
| "grad_norm": 2.6168112754821777, | |
| "learning_rate": 1.5332044328016916e-05, | |
| "loss": 0.6217, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.5140408277511597, | |
| "eval_runtime": 0.8057, | |
| "eval_samples_per_second": 16.135, | |
| "eval_steps_per_second": 2.482, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.4444444444444444, | |
| "grad_norm": 2.0166800022125244, | |
| "learning_rate": 1.0581448289104759e-05, | |
| "loss": 0.3648, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.925925925925926, | |
| "grad_norm": 1.8459001779556274, | |
| "learning_rate": 5.686139343187468e-06, | |
| "loss": 0.3082, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.5627971291542053, | |
| "eval_runtime": 0.7989, | |
| "eval_samples_per_second": 16.271, | |
| "eval_steps_per_second": 2.503, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.4074074074074074, | |
| "grad_norm": 1.6898136138916016, | |
| "learning_rate": 1.8644792973703252e-06, | |
| "loss": 0.1852, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.888888888888889, | |
| "grad_norm": 1.3877729177474976, | |
| "learning_rate": 6.761642258056977e-08, | |
| "loss": 0.1499, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.6246976852416992, | |
| "eval_runtime": 0.8326, | |
| "eval_samples_per_second": 15.613, | |
| "eval_steps_per_second": 2.402, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 81, | |
| "total_flos": 34595577790464.0, | |
| "train_loss": 0.3884385390046202, | |
| "train_runtime": 2965.0449, | |
| "train_samples_per_second": 2.617, | |
| "train_steps_per_second": 0.027 | |
| } | |
| ], | |
| "logging_steps": 13, | |
| "max_steps": 81, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 27, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 34595577790464.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |