| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9523809523809523, | |
| "eval_steps": 500, | |
| "global_step": 4000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11904761904761904, | |
| "eval_loss": 1.185745358467102, | |
| "eval_runtime": 511.386, | |
| "eval_samples_per_second": 20.532, | |
| "eval_steps_per_second": 10.266, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.23809523809523808, | |
| "grad_norm": 6.73046875, | |
| "learning_rate": 3.809523809523809e-05, | |
| "loss": 1.4021, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.23809523809523808, | |
| "eval_loss": 1.1710022687911987, | |
| "eval_runtime": 511.3541, | |
| "eval_samples_per_second": 20.534, | |
| "eval_steps_per_second": 10.267, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.35714285714285715, | |
| "eval_loss": 1.1692695617675781, | |
| "eval_runtime": 534.0354, | |
| "eval_samples_per_second": 19.662, | |
| "eval_steps_per_second": 9.831, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.47619047619047616, | |
| "grad_norm": 6.9140625, | |
| "learning_rate": 2.6190476190476192e-05, | |
| "loss": 1.2, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.47619047619047616, | |
| "eval_loss": 1.1674636602401733, | |
| "eval_runtime": 510.2022, | |
| "eval_samples_per_second": 20.58, | |
| "eval_steps_per_second": 10.29, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.5952380952380952, | |
| "eval_loss": 1.165112018585205, | |
| "eval_runtime": 510.1211, | |
| "eval_samples_per_second": 20.583, | |
| "eval_steps_per_second": 10.292, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.7142857142857143, | |
| "grad_norm": 11.3671875, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 1.1956, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.7142857142857143, | |
| "eval_loss": 1.1650755405426025, | |
| "eval_runtime": 510.062, | |
| "eval_samples_per_second": 20.586, | |
| "eval_steps_per_second": 10.293, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.8333333333333334, | |
| "eval_loss": 1.1639403104782104, | |
| "eval_runtime": 510.1097, | |
| "eval_samples_per_second": 20.584, | |
| "eval_steps_per_second": 10.292, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.9523809523809523, | |
| "grad_norm": 7.4921875, | |
| "learning_rate": 2.3809523809523808e-06, | |
| "loss": 1.1869, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.9523809523809523, | |
| "eval_loss": 1.163933277130127, | |
| "eval_runtime": 509.9381, | |
| "eval_samples_per_second": 20.591, | |
| "eval_steps_per_second": 10.295, | |
| "step": 4000 | |
| } | |
| ], | |
| "logging_steps": 1000, | |
| "max_steps": 4200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.401220896300237e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |