| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9944064636420137, | |
| "eval_steps": 500, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4575, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0002, | |
| "loss": 2.2028, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0002, | |
| "loss": 2.2306, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0002, | |
| "loss": 2.2154, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1778, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1734, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0091, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1055, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8893, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0398, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9298, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9687, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7748, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0527, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0485, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9685, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0669, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0416, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0002, | |
| "loss": 1.92, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9969, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8663, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9247, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9624, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8684, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9118, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9122, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9483, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9967, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0291, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0156, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8287, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8032, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0124, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8951, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7415, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8676, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9817, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9221, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9439, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0937, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0001, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0092, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0165, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8853, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8469, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9119, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8086, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9036, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.0002, | |
| "loss": 1.859, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9257, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "total_flos": 1.3407179920195584e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |