| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 435.0, | |
| "eval_steps": 500, | |
| "global_step": 3480, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 12.5, | |
| "learning_rate": 1.9515000000000002e-05, | |
| "loss": 4.8504, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 1.9015e-05, | |
| "loss": 2.1747, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 37.5, | |
| "learning_rate": 1.8520000000000002e-05, | |
| "loss": 1.3085, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "learning_rate": 1.802e-05, | |
| "loss": 0.6752, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 62.5, | |
| "learning_rate": 1.752e-05, | |
| "loss": 0.314, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "learning_rate": 1.702e-05, | |
| "loss": 0.1608, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 87.5, | |
| "learning_rate": 1.652e-05, | |
| "loss": 0.0914, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "learning_rate": 1.6020000000000002e-05, | |
| "loss": 0.0514, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 112.5, | |
| "learning_rate": 1.552e-05, | |
| "loss": 0.0383, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 125.0, | |
| "learning_rate": 1.5020000000000002e-05, | |
| "loss": 0.0342, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 137.5, | |
| "learning_rate": 1.4520000000000002e-05, | |
| "loss": 0.0284, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 150.0, | |
| "learning_rate": 1.402e-05, | |
| "loss": 0.0214, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 162.5, | |
| "learning_rate": 1.3520000000000003e-05, | |
| "loss": 0.0146, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 175.0, | |
| "learning_rate": 1.302e-05, | |
| "loss": 0.0115, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 187.5, | |
| "learning_rate": 1.252e-05, | |
| "loss": 0.0144, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 200.0, | |
| "learning_rate": 1.202e-05, | |
| "loss": 0.0097, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 212.5, | |
| "learning_rate": 1.152e-05, | |
| "loss": 0.0079, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 225.0, | |
| "learning_rate": 1.1020000000000001e-05, | |
| "loss": 0.0055, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 237.5, | |
| "learning_rate": 1.0520000000000001e-05, | |
| "loss": 0.0075, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 250.0, | |
| "learning_rate": 1.002e-05, | |
| "loss": 0.0081, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 262.5, | |
| "learning_rate": 9.52e-06, | |
| "loss": 0.0045, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 275.0, | |
| "learning_rate": 9.020000000000002e-06, | |
| "loss": 0.0083, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 287.5, | |
| "learning_rate": 8.525e-06, | |
| "loss": 0.012, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 300.0, | |
| "learning_rate": 8.025e-06, | |
| "loss": 0.0113, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 312.5, | |
| "learning_rate": 7.525e-06, | |
| "loss": 0.0113, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 325.0, | |
| "learning_rate": 7.0250000000000005e-06, | |
| "loss": 0.0066, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 337.5, | |
| "learning_rate": 6.525e-06, | |
| "loss": 0.0074, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 350.0, | |
| "learning_rate": 6.025000000000001e-06, | |
| "loss": 0.0053, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 362.5, | |
| "learning_rate": 5.5250000000000005e-06, | |
| "loss": 0.0043, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 375.0, | |
| "learning_rate": 5.025e-06, | |
| "loss": 0.0054, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 387.5, | |
| "learning_rate": 4.525000000000001e-06, | |
| "loss": 0.0028, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 400.0, | |
| "learning_rate": 4.0250000000000004e-06, | |
| "loss": 0.0028, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 412.5, | |
| "learning_rate": 3.525e-06, | |
| "loss": 0.0097, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 425.0, | |
| "learning_rate": 3.0250000000000003e-06, | |
| "loss": 0.0117, | |
| "step": 3400 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 4000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 500, | |
| "save_steps": 500, | |
| "total_flos": 5.440826272776192e+19, | |
| "train_batch_size": 5, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |