| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.6699507389162561, | |
| "eval_steps": 500, | |
| "global_step": 68, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.999516282291988e-05, | |
| "loss": 1.1267, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.987930439740757e-05, | |
| "loss": 1.8565, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.95201310753273e-05, | |
| "loss": 1.1471, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.8931150161867917e-05, | |
| "loss": 1.0745, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.8126579138282502e-05, | |
| "loss": 1.0317, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.7125839641475074e-05, | |
| "loss": 1.0106, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.595308864276666e-05, | |
| "loss": 1.0005, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.4636635319853274e-05, | |
| "loss": 0.9906, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.3208257698153677e-05, | |
| "loss": 0.9749, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.1702435557223988e-05, | |
| "loss": 0.9738, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.0155518119203511e-05, | |
| "loss": 0.9724, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 8.604846610560771e-06, | |
| "loss": 0.969, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 7.0878528777274814e-06, | |
| "loss": 0.9684, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 5.64115581524629e-06, | |
| "loss": 0.9644, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 0.965281069278717, | |
| "eval_runtime": 824.4812, | |
| "eval_samples_per_second": 28.03, | |
| "eval_steps_per_second": 0.439, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "step": 68, | |
| "total_flos": 455937286471680.0, | |
| "train_loss": 1.057758885271409, | |
| "train_runtime": 30153.6478, | |
| "train_samples_per_second": 6.894, | |
| "train_steps_per_second": 0.003 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 101, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "total_flos": 455937286471680.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |