| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.036596523330283626, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0036596523330283625, | |
| "grad_norm": 0.3861056864261627, | |
| "learning_rate": 2e-05, | |
| "loss": 2.3027, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0036596523330283625, | |
| "eval_loss": 2.259103298187256, | |
| "eval_runtime": 9.5141, | |
| "eval_samples_per_second": 12.087, | |
| "eval_steps_per_second": 6.096, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007319304666056725, | |
| "grad_norm": 0.5979791879653931, | |
| "learning_rate": 4e-05, | |
| "loss": 1.9536, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.010978956999085087, | |
| "grad_norm": 0.39298292994499207, | |
| "learning_rate": 6e-05, | |
| "loss": 2.0999, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010978956999085087, | |
| "eval_loss": 2.255657196044922, | |
| "eval_runtime": 7.7834, | |
| "eval_samples_per_second": 14.775, | |
| "eval_steps_per_second": 7.452, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01463860933211345, | |
| "grad_norm": 0.4520469307899475, | |
| "learning_rate": 8e-05, | |
| "loss": 2.1588, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.018298261665141813, | |
| "grad_norm": 0.4833182692527771, | |
| "learning_rate": 0.0001, | |
| "loss": 2.01, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.021957913998170174, | |
| "grad_norm": 0.5507794618606567, | |
| "learning_rate": 0.00012, | |
| "loss": 2.1838, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.021957913998170174, | |
| "eval_loss": 2.1994447708129883, | |
| "eval_runtime": 7.8005, | |
| "eval_samples_per_second": 14.743, | |
| "eval_steps_per_second": 7.435, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.025617566331198535, | |
| "grad_norm": 0.4981963634490967, | |
| "learning_rate": 0.00014, | |
| "loss": 1.9151, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0292772186642269, | |
| "grad_norm": 0.6484657526016235, | |
| "learning_rate": 0.00016, | |
| "loss": 2.16, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03293687099725526, | |
| "grad_norm": 0.5292857885360718, | |
| "learning_rate": 0.00018, | |
| "loss": 1.8135, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03293687099725526, | |
| "eval_loss": 1.9987196922302246, | |
| "eval_runtime": 7.7857, | |
| "eval_samples_per_second": 14.771, | |
| "eval_steps_per_second": 7.45, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.036596523330283626, | |
| "grad_norm": 0.4609442949295044, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7845, | |
| "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": 4195222196060160.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |