| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.776119402985074, | |
| "eval_steps": 500, | |
| "global_step": 80, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 5e-05, | |
| "loss": 0.8672, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 5e-05, | |
| "loss": 0.8051, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6955, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6879, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6785, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6584, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 5e-05, | |
| "loss": 0.646, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6585, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5556, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4459, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4237, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4039, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3943, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3858, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 5e-05, | |
| "loss": 0.402, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4071, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3372, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 5e-05, | |
| "loss": 0.2406, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1945, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1935, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1866, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1739, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1708, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1808, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1847, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1019, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0741, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 5e-05, | |
| "loss": 0.073, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0748, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 5e-05, | |
| "loss": 0.07, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0692, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 5e-05, | |
| "loss": 0.079, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0835, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0533, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 4.18, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0356, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0326, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 4.42, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0417, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 4.54, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0352, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "learning_rate": 5e-05, | |
| "loss": 0.042, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 4.78, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0359, | |
| "step": 80 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 80, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 20, | |
| "total_flos": 58433383956480.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |