| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.07648183556405354, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0076481835564053535, | |
| "grad_norm": 21.02690315246582, | |
| "learning_rate": 2e-05, | |
| "loss": 9.822, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0076481835564053535, | |
| "eval_loss": 2.890343189239502, | |
| "eval_runtime": 1.8517, | |
| "eval_samples_per_second": 29.703, | |
| "eval_steps_per_second": 15.122, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.015296367112810707, | |
| "grad_norm": 20.047754287719727, | |
| "learning_rate": 4e-05, | |
| "loss": 12.9937, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.022944550669216062, | |
| "grad_norm": 22.70226287841797, | |
| "learning_rate": 6e-05, | |
| "loss": 11.7915, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.022944550669216062, | |
| "eval_loss": 2.828831434249878, | |
| "eval_runtime": 0.91, | |
| "eval_samples_per_second": 60.437, | |
| "eval_steps_per_second": 30.768, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.030592734225621414, | |
| "grad_norm": 29.1671085357666, | |
| "learning_rate": 8e-05, | |
| "loss": 11.1711, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03824091778202677, | |
| "grad_norm": 15.751770973205566, | |
| "learning_rate": 0.0001, | |
| "loss": 9.6744, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.045889101338432124, | |
| "grad_norm": 18.53544807434082, | |
| "learning_rate": 0.00012, | |
| "loss": 11.195, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.045889101338432124, | |
| "eval_loss": 2.4405295848846436, | |
| "eval_runtime": 1.0267, | |
| "eval_samples_per_second": 53.572, | |
| "eval_steps_per_second": 27.273, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.05353728489483748, | |
| "grad_norm": 13.921692848205566, | |
| "learning_rate": 0.00014, | |
| "loss": 8.334, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.06118546845124283, | |
| "grad_norm": 21.811330795288086, | |
| "learning_rate": 0.00016, | |
| "loss": 9.1286, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.06883365200764818, | |
| "grad_norm": 17.255428314208984, | |
| "learning_rate": 0.00018, | |
| "loss": 6.7562, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06883365200764818, | |
| "eval_loss": 1.9071483612060547, | |
| "eval_runtime": 0.9102, | |
| "eval_samples_per_second": 60.427, | |
| "eval_steps_per_second": 30.763, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.07648183556405354, | |
| "grad_norm": 23.9243106842041, | |
| "learning_rate": 0.0002, | |
| "loss": 7.9559, | |
| "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": 298765642629120.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |