| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0004947127574052315, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.947127574052316e-05, | |
| "grad_norm": 6.565613269805908, | |
| "learning_rate": 2e-05, | |
| "loss": 9.6628, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.947127574052316e-05, | |
| "eval_loss": 9.460563659667969, | |
| "eval_runtime": 48.1705, | |
| "eval_samples_per_second": 176.685, | |
| "eval_steps_per_second": 88.353, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 9.894255148104632e-05, | |
| "grad_norm": 6.578593730926514, | |
| "learning_rate": 4e-05, | |
| "loss": 9.2307, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00014841382722156947, | |
| "grad_norm": 7.637526512145996, | |
| "learning_rate": 6e-05, | |
| "loss": 9.5831, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00014841382722156947, | |
| "eval_loss": 9.451005935668945, | |
| "eval_runtime": 47.696, | |
| "eval_samples_per_second": 178.443, | |
| "eval_steps_per_second": 89.232, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00019788510296209265, | |
| "grad_norm": 6.049842834472656, | |
| "learning_rate": 8e-05, | |
| "loss": 9.5229, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00024735637870261577, | |
| "grad_norm": 6.059463024139404, | |
| "learning_rate": 0.0001, | |
| "loss": 9.6265, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00029682765444313895, | |
| "grad_norm": 6.40576696395874, | |
| "learning_rate": 0.00012, | |
| "loss": 9.4738, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00029682765444313895, | |
| "eval_loss": 9.306656837463379, | |
| "eval_runtime": 47.9088, | |
| "eval_samples_per_second": 177.65, | |
| "eval_steps_per_second": 88.835, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0003462989301836621, | |
| "grad_norm": 6.363209247589111, | |
| "learning_rate": 0.00014, | |
| "loss": 9.1041, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0003957702059241853, | |
| "grad_norm": 7.665739059448242, | |
| "learning_rate": 0.00016, | |
| "loss": 9.2728, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0004452414816647084, | |
| "grad_norm": 7.9968414306640625, | |
| "learning_rate": 0.00018, | |
| "loss": 9.0876, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0004452414816647084, | |
| "eval_loss": 8.97900104522705, | |
| "eval_runtime": 47.6991, | |
| "eval_samples_per_second": 178.431, | |
| "eval_steps_per_second": 89.226, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0004947127574052315, | |
| "grad_norm": 7.241934776306152, | |
| "learning_rate": 0.0002, | |
| "loss": 9.1593, | |
| "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": 655585443840.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |