| { | |
| "best_metric": 6.997350215911865, | |
| "best_model_checkpoint": "controlled-food-recipe-generation/checkpoint-15", | |
| "epoch": 17.0, | |
| "eval_steps": 1, | |
| "global_step": 17, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 5e-05, | |
| "loss": 78.014, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 76.51811981201172, | |
| "eval_runtime": 0.0422, | |
| "eval_samples_per_second": 23.686, | |
| "eval_steps_per_second": 23.686, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 5e-05, | |
| "loss": 78.2388, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 76.51811981201172, | |
| "eval_runtime": 0.0201, | |
| "eval_samples_per_second": 49.811, | |
| "eval_steps_per_second": 49.811, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 5e-05, | |
| "loss": 77.0195, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 76.51811981201172, | |
| "eval_runtime": 0.0202, | |
| "eval_samples_per_second": 49.475, | |
| "eval_steps_per_second": 49.475, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 5e-05, | |
| "loss": 77.6197, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 76.51811981201172, | |
| "eval_runtime": 0.0199, | |
| "eval_samples_per_second": 50.171, | |
| "eval_steps_per_second": 50.171, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 5e-05, | |
| "loss": 77.8364, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 76.51811981201172, | |
| "eval_runtime": 0.02, | |
| "eval_samples_per_second": 50.05, | |
| "eval_steps_per_second": 50.05, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 5e-05, | |
| "loss": 77.9326, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 76.51811981201172, | |
| "eval_runtime": 0.02, | |
| "eval_samples_per_second": 49.998, | |
| "eval_steps_per_second": 49.998, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 5e-05, | |
| "loss": 77.1428, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 76.51811981201172, | |
| "eval_runtime": 0.0203, | |
| "eval_samples_per_second": 49.376, | |
| "eval_steps_per_second": 49.376, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 5e-05, | |
| "loss": 77.9131, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 76.51811981201172, | |
| "eval_runtime": 0.0197, | |
| "eval_samples_per_second": 50.657, | |
| "eval_steps_per_second": 50.657, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 4.9500000000000004e-05, | |
| "loss": 77.8046, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 46.12736129760742, | |
| "eval_runtime": 0.0203, | |
| "eval_samples_per_second": 49.335, | |
| "eval_steps_per_second": 49.335, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 4.9e-05, | |
| "loss": 35.9262, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 42.20186233520508, | |
| "eval_runtime": 0.0212, | |
| "eval_samples_per_second": 47.156, | |
| "eval_steps_per_second": 47.156, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 4.85e-05, | |
| "loss": 24.7783, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 21.848590850830078, | |
| "eval_runtime": 0.0209, | |
| "eval_samples_per_second": 47.862, | |
| "eval_steps_per_second": 47.862, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 4.8e-05, | |
| "loss": 11.8436, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 10.201495170593262, | |
| "eval_runtime": 0.0205, | |
| "eval_samples_per_second": 48.692, | |
| "eval_steps_per_second": 48.692, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 4.75e-05, | |
| "loss": 8.908, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 11.220573425292969, | |
| "eval_runtime": 0.0213, | |
| "eval_samples_per_second": 46.959, | |
| "eval_steps_per_second": 46.959, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 4.7e-05, | |
| "loss": 7.022, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 9.170014381408691, | |
| "eval_runtime": 0.0227, | |
| "eval_samples_per_second": 44.006, | |
| "eval_steps_per_second": 44.006, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 4.6500000000000005e-05, | |
| "loss": 6.3525, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 6.997350215911865, | |
| "eval_runtime": 0.0211, | |
| "eval_samples_per_second": 47.457, | |
| "eval_steps_per_second": 47.457, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 4.600000000000001e-05, | |
| "loss": 5.6621, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 4.715316295623779, | |
| "eval_runtime": 0.0208, | |
| "eval_samples_per_second": 48.084, | |
| "eval_steps_per_second": 48.084, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "learning_rate": 5e-05, | |
| "loss": 5.8038, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 4.024607181549072, | |
| "eval_runtime": 0.0201, | |
| "eval_samples_per_second": 49.72, | |
| "eval_steps_per_second": 49.72, | |
| "step": 17 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 100, | |
| "save_steps": 1, | |
| "total_flos": 9994420224000.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |