| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0056409533211112676, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005640953321111268, | |
| "grad_norm": 3.863463878631592, | |
| "learning_rate": 2e-05, | |
| "loss": 13.8423, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005640953321111268, | |
| "eval_loss": 3.3676869869232178, | |
| "eval_runtime": 25.5492, | |
| "eval_samples_per_second": 29.238, | |
| "eval_steps_per_second": 14.638, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011281906642222536, | |
| "grad_norm": 5.888922214508057, | |
| "learning_rate": 4e-05, | |
| "loss": 14.5699, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0016922859963333804, | |
| "grad_norm": 4.284083843231201, | |
| "learning_rate": 6e-05, | |
| "loss": 14.3218, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0016922859963333804, | |
| "eval_loss": 3.3628196716308594, | |
| "eval_runtime": 25.5206, | |
| "eval_samples_per_second": 29.271, | |
| "eval_steps_per_second": 14.655, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0022563813284445073, | |
| "grad_norm": 3.8727877140045166, | |
| "learning_rate": 8e-05, | |
| "loss": 13.6571, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0028204766605556338, | |
| "grad_norm": 4.041762351989746, | |
| "learning_rate": 0.0001, | |
| "loss": 12.1829, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0033845719926667607, | |
| "grad_norm": 5.419154167175293, | |
| "learning_rate": 0.00012, | |
| "loss": 13.0971, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0033845719926667607, | |
| "eval_loss": 3.3201839923858643, | |
| "eval_runtime": 25.7789, | |
| "eval_samples_per_second": 28.977, | |
| "eval_steps_per_second": 14.508, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003948667324777887, | |
| "grad_norm": 7.6508989334106445, | |
| "learning_rate": 0.00014, | |
| "loss": 14.0988, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0045127626568890146, | |
| "grad_norm": 4.7432169914245605, | |
| "learning_rate": 0.00016, | |
| "loss": 13.5879, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005076857989000141, | |
| "grad_norm": 8.729517936706543, | |
| "learning_rate": 0.00018, | |
| "loss": 14.2015, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005076857989000141, | |
| "eval_loss": 3.165574789047241, | |
| "eval_runtime": 25.7311, | |
| "eval_samples_per_second": 29.031, | |
| "eval_steps_per_second": 14.535, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0056409533211112676, | |
| "grad_norm": 8.815227508544922, | |
| "learning_rate": 0.0002, | |
| "loss": 12.8984, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1628733135912960.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |