| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0365296803652968, | |
| "global_step": 400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 5e-05, | |
| "loss": 2.6714, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.0001, | |
| "loss": 2.5361, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 2.3465, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0844, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.0001999145758387301, | |
| "loss": 2.0421, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.000199658449300667, | |
| "loss": 1.9894, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0001992320579737045, | |
| "loss": 1.9617, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019863613034027224, | |
| "loss": 2.0536, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019787168453273544, | |
| "loss": 1.9324, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019694002659393305, | |
| "loss": 1.985, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0001958427482458253, | |
| "loss": 1.9952, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019458172417006347, | |
| "loss": 2.007, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0001931591088051279, | |
| "loss": 1.983, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019157733266550575, | |
| "loss": 1.9472, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0001898390981891979, | |
| "loss": 2.0466, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0001879473751206489, | |
| "loss": 2.008, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00018590539543698854, | |
| "loss": 2.0157, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00018371664782625287, | |
| "loss": 1.9199, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0001813848717270195, | |
| "loss": 2.04, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00017891405093963938, | |
| "loss": 1.9081, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00017630840681998066, | |
| "loss": 1.9743, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00017357239106731317, | |
| "loss": 1.9165, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.9622, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00016772815716257412, | |
| "loss": 1.9589, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00016462992378609407, | |
| "loss": 1.9725, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0001614212712689668, | |
| "loss": 1.9992, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00015810768154019385, | |
| "loss": 1.9791, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00015469481581224272, | |
| "loss": 1.9638, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00015118850490896012, | |
| "loss": 1.9842, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00014759473930370736, | |
| "loss": 1.9316, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00014391965888473703, | |
| "loss": 1.9995, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00014016954246529696, | |
| "loss": 1.9569, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00013635079705638298, | |
| "loss": 1.9623, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00013246994692046836, | |
| "loss": 1.9055, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00012853362242491053, | |
| "loss": 1.9084, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00012454854871407994, | |
| "loss": 2.0149, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00012052153421956342, | |
| "loss": 1.953, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00011645945902807341, | |
| "loss": 2.0303, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00011236926312693479, | |
| "loss": 1.9762, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00010825793454723325, | |
| "loss": 1.9585, | |
| "step": 400 | |
| } | |
| ], | |
| "max_steps": 800, | |
| "num_train_epochs": 1, | |
| "total_flos": 1.637251048912128e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |