| { | |
| "best_metric": 1.3450770378112793, | |
| "best_model_checkpoint": "../llama2-9439-21sept/checkpoint-200", | |
| "epoch": 0.3473227206946454, | |
| "eval_steps": 200, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 3.4609, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 2.8346, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 1.7597, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 1.542, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0003, | |
| "loss": 1.4567, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0002963076923076923, | |
| "loss": 1.4081, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0002926153846153846, | |
| "loss": 1.3805, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0002889230769230769, | |
| "loss": 1.3605, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00028523076923076923, | |
| "loss": 1.3329, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0002815384615384615, | |
| "loss": 1.3367, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": 1.3450770378112793, | |
| "eval_runtime": 6.306, | |
| "eval_samples_per_second": 47.574, | |
| "eval_steps_per_second": 1.269, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 1725, | |
| "num_train_epochs": 3, | |
| "save_steps": 200, | |
| "total_flos": 4.784156340073267e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |