| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 14.619883040935672, | |
| "global_step": 10000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0002966863033873343, | |
| "loss": 0.6757, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.00029116347569955813, | |
| "loss": 0.516, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.00028564064801178197, | |
| "loss": 0.4685, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 0.00028011782032400586, | |
| "loss": 0.4306, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 0.0002745949926362297, | |
| "loss": 0.4228, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 0.0002690721649484536, | |
| "loss": 0.3927, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 0.0002635493372606774, | |
| "loss": 0.3716, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 0.0002580265095729013, | |
| "loss": 0.3724, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 0.00025250368188512514, | |
| "loss": 0.3353, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "learning_rate": 0.000246980854197349, | |
| "loss": 0.3312, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 0.0002414580265095729, | |
| "loss": 0.3317, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "learning_rate": 0.00023593519882179672, | |
| "loss": 0.2892, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "learning_rate": 0.0002304123711340206, | |
| "loss": 0.2968, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 0.00022488954344624445, | |
| "loss": 0.2817, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 5.48, | |
| "learning_rate": 0.0002193667157584683, | |
| "loss": 0.2557, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 5.85, | |
| "learning_rate": 0.00021384388807069217, | |
| "loss": 0.2622, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 6.21, | |
| "learning_rate": 0.00020832106038291603, | |
| "loss": 0.234, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 6.58, | |
| "learning_rate": 0.0002027982326951399, | |
| "loss": 0.2228, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 6.94, | |
| "learning_rate": 0.00019727540500736376, | |
| "loss": 0.2292, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 7.31, | |
| "learning_rate": 0.0001917525773195876, | |
| "loss": 0.1906, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 7.68, | |
| "learning_rate": 0.00018622974963181148, | |
| "loss": 0.19, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 8.04, | |
| "learning_rate": 0.00018070692194403532, | |
| "loss": 0.1914, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 8.41, | |
| "learning_rate": 0.0001751840942562592, | |
| "loss": 0.1542, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 8.77, | |
| "learning_rate": 0.00016966126656848304, | |
| "loss": 0.1615, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 9.14, | |
| "learning_rate": 0.00016413843888070693, | |
| "loss": 0.1495, | |
| "step": 6250 | |
| }, | |
| { | |
| "epoch": 9.5, | |
| "learning_rate": 0.00015861561119293076, | |
| "loss": 0.1286, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 9.87, | |
| "learning_rate": 0.00015309278350515463, | |
| "loss": 0.1343, | |
| "step": 6750 | |
| }, | |
| { | |
| "epoch": 10.23, | |
| "learning_rate": 0.0001475699558173785, | |
| "loss": 0.1151, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 10.6, | |
| "learning_rate": 0.00014204712812960235, | |
| "loss": 0.1071, | |
| "step": 7250 | |
| }, | |
| { | |
| "epoch": 10.96, | |
| "learning_rate": 0.0001365243004418262, | |
| "loss": 0.1114, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 11.33, | |
| "learning_rate": 0.00013100147275405007, | |
| "loss": 0.0887, | |
| "step": 7750 | |
| }, | |
| { | |
| "epoch": 11.7, | |
| "learning_rate": 0.00012547864506627394, | |
| "loss": 0.0901, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 12.06, | |
| "learning_rate": 0.00011995581737849778, | |
| "loss": 0.0898, | |
| "step": 8250 | |
| }, | |
| { | |
| "epoch": 12.43, | |
| "learning_rate": 0.00011443298969072163, | |
| "loss": 0.0745, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 12.79, | |
| "learning_rate": 0.0001089101620029455, | |
| "loss": 0.0778, | |
| "step": 8750 | |
| }, | |
| { | |
| "epoch": 13.16, | |
| "learning_rate": 0.00010338733431516936, | |
| "loss": 0.073, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 13.52, | |
| "learning_rate": 9.786450662739322e-05, | |
| "loss": 0.067, | |
| "step": 9250 | |
| }, | |
| { | |
| "epoch": 13.89, | |
| "learning_rate": 9.234167893961708e-05, | |
| "loss": 0.069, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 14.25, | |
| "learning_rate": 8.681885125184094e-05, | |
| "loss": 0.0628, | |
| "step": 9750 | |
| }, | |
| { | |
| "epoch": 14.62, | |
| "learning_rate": 8.129602356406479e-05, | |
| "loss": 0.0616, | |
| "step": 10000 | |
| } | |
| ], | |
| "max_steps": 13680, | |
| "num_train_epochs": 20, | |
| "total_flos": 8.358078580103578e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |