| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.5006134969325153, | |
| "eval_steps": 51, | |
| "global_step": 51, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05889570552147239, | |
| "grad_norm": 0.17814360558986664, | |
| "learning_rate": 9.803921568627451e-06, | |
| "loss": 0.1429, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.11779141104294479, | |
| "grad_norm": 0.19341157376766205, | |
| "learning_rate": 2.1568627450980395e-05, | |
| "loss": 0.1421, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.17668711656441718, | |
| "grad_norm": 0.21557286381721497, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.1137, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.23558282208588957, | |
| "grad_norm": 0.0923461839556694, | |
| "learning_rate": 4.5098039215686275e-05, | |
| "loss": 0.0903, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.294478527607362, | |
| "grad_norm": 0.0747547447681427, | |
| "learning_rate": 5.6862745098039215e-05, | |
| "loss": 0.0541, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.35337423312883437, | |
| "grad_norm": 0.06449007987976074, | |
| "learning_rate": 6.862745098039216e-05, | |
| "loss": 0.056, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.41226993865030676, | |
| "grad_norm": 0.06695199757814407, | |
| "learning_rate": 8.039215686274511e-05, | |
| "loss": 0.0378, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.47116564417177914, | |
| "grad_norm": 0.057652052491903305, | |
| "learning_rate": 9.215686274509804e-05, | |
| "loss": 0.0333, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.5006134969325153, | |
| "eval_loss": 0.04454955831170082, | |
| "eval_runtime": 99.1976, | |
| "eval_samples_per_second": 0.917, | |
| "eval_steps_per_second": 0.917, | |
| "step": 51 | |
| } | |
| ], | |
| "logging_steps": 6, | |
| "max_steps": 505, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 51, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9.592202840113152e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |