| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004265574679548702, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.531149359097404e-05, | |
| "eval_loss": 3.899817705154419, | |
| "eval_runtime": 66.4454, | |
| "eval_samples_per_second": 74.287, | |
| "eval_steps_per_second": 37.143, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008531149359097404, | |
| "grad_norm": 11.559722900390625, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 14.6898, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0011090494166826625, | |
| "eval_loss": 3.0394980907440186, | |
| "eval_runtime": 64.5588, | |
| "eval_samples_per_second": 76.457, | |
| "eval_steps_per_second": 38.229, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0017062298718194808, | |
| "grad_norm": 19.72844886779785, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 12.6422, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002218098833365325, | |
| "eval_loss": 2.8474488258361816, | |
| "eval_runtime": 64.7263, | |
| "eval_samples_per_second": 76.26, | |
| "eval_steps_per_second": 38.13, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0025593448077292215, | |
| "grad_norm": 13.219390869140625, | |
| "learning_rate": 8.263518223330697e-05, | |
| "loss": 11.7934, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0033271482500479878, | |
| "eval_loss": 2.7936599254608154, | |
| "eval_runtime": 65.006, | |
| "eval_samples_per_second": 75.931, | |
| "eval_steps_per_second": 37.966, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0034124597436389617, | |
| "grad_norm": 10.538164138793945, | |
| "learning_rate": 2.339555568810221e-05, | |
| "loss": 10.8896, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.004265574679548702, | |
| "grad_norm": 13.128223419189453, | |
| "learning_rate": 0.0, | |
| "loss": 11.2783, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1949445818155008.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |