| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.25773554939466975, | |
| "global_step": 18500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.965170871703423e-05, | |
| "loss": 3.2187, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.9303417434068464e-05, | |
| "loss": 3.2319, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.8955126151102695e-05, | |
| "loss": 3.2003, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.8606834868136925e-05, | |
| "loss": 3.2206, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.825854358517115e-05, | |
| "loss": 3.2168, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.791025230220538e-05, | |
| "loss": 3.2134, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.756196101923962e-05, | |
| "loss": 3.2317, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.721366973627384e-05, | |
| "loss": 3.2235, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.686537845330807e-05, | |
| "loss": 3.2294, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.65170871703423e-05, | |
| "loss": 3.225, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.6168795887376534e-05, | |
| "loss": 3.2082, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.5820504604410765e-05, | |
| "loss": 3.2202, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.5472213321444996e-05, | |
| "loss": 3.221, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.512392203847922e-05, | |
| "loss": 3.2042, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.477563075551345e-05, | |
| "loss": 3.1977, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.442733947254769e-05, | |
| "loss": 3.1891, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.407904818958191e-05, | |
| "loss": 3.2053, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.373075690661614e-05, | |
| "loss": 3.2168, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.3382465623650374e-05, | |
| "loss": 3.2138, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.3034174340684604e-05, | |
| "loss": 3.1905, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.2685883057718835e-05, | |
| "loss": 3.1923, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.2337591774753066e-05, | |
| "loss": 3.1953, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.198930049178729e-05, | |
| "loss": 3.1958, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.164100920882153e-05, | |
| "loss": 3.1885, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.129271792585576e-05, | |
| "loss": 3.1701, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.094442664288998e-05, | |
| "loss": 3.1908, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.059613535992421e-05, | |
| "loss": 3.1618, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.0247844076958444e-05, | |
| "loss": 3.1917, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 3.9899552793992674e-05, | |
| "loss": 3.1812, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3.9551261511026905e-05, | |
| "loss": 3.1794, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.9202970228061136e-05, | |
| "loss": 3.1902, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.885467894509536e-05, | |
| "loss": 3.18, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 3.85063876621296e-05, | |
| "loss": 3.1849, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 3.815809637916383e-05, | |
| "loss": 3.1857, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 3.780980509619805e-05, | |
| "loss": 3.1577, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 3.746151381323228e-05, | |
| "loss": 3.1878, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 3.7113222530266514e-05, | |
| "loss": 3.1512, | |
| "step": 18500 | |
| } | |
| ], | |
| "max_steps": 71779, | |
| "num_train_epochs": 1, | |
| "total_flos": 3.912747299426304e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |