| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 36, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.5e-05, | |
| "loss": 3.9206, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 2.25e-05, | |
| "loss": 3.7181, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 2.90625e-05, | |
| "loss": 2.8356, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 2.71875e-05, | |
| "loss": 4.5522, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 2.5312500000000002e-05, | |
| "loss": 3.1933, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 2.34375e-05, | |
| "loss": 3.5613, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 2.15625e-05, | |
| "loss": 3.1014, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 2.0625e-05, | |
| "loss": 3.4517, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 1.8750000000000002e-05, | |
| "loss": 4.0346, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 1.6875e-05, | |
| "loss": 2.8067, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 1.5e-05, | |
| "loss": 3.4686, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.3125e-05, | |
| "loss": 3.5438, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 1.125e-05, | |
| "loss": 3.5073, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 9.375000000000001e-06, | |
| "loss": 2.7377, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 7.5e-06, | |
| "loss": 2.8966, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 5.625e-06, | |
| "loss": 4.2557, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 3.75e-06, | |
| "loss": 2.3242, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 1.875e-06, | |
| "loss": 3.8503, | |
| "step": 36 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 36, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 91455882264576.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |