| { | |
| "best_metric": 8.360694885253906, | |
| "best_model_checkpoint": "checkpoints-mistral-300M-FA2/checkpoint-100", | |
| "epoch": 2.8667413213885777, | |
| "eval_steps": 100, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 5.999999999999999e-06, | |
| "loss": 10.9345, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 1.1999999999999999e-05, | |
| "loss": 10.5058, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 1.7999999999999997e-05, | |
| "loss": 9.9277, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 2.3999999999999997e-05, | |
| "loss": 9.5263, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 9.3038, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 3.5999999999999994e-05, | |
| "loss": 9.1594, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 4.2e-05, | |
| "loss": 9.0196, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 4.7999999999999994e-05, | |
| "loss": 8.8448, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 5.399999999999999e-05, | |
| "loss": 8.5947, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 8.361, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "eval_loss": 8.360694885253906, | |
| "eval_runtime": 47.6223, | |
| "eval_samples_per_second": 183.779, | |
| "eval_steps_per_second": 11.486, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 100, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "total_flos": 3.1758312754538086e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |