| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 15.968063872255488, | |
| "global_step": 32000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 9.916833000665336e-05, | |
| "loss": 7.7087, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 9.833666001330672e-05, | |
| "loss": 7.4465, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 9.750499001996009e-05, | |
| "loss": 7.1976, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 9.667332002661345e-05, | |
| "loss": 6.9445, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 9.58416500332668e-05, | |
| "loss": 6.6812, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 9.500998003992016e-05, | |
| "loss": 6.2449, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 9.417831004657353e-05, | |
| "loss": 5.6326, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 9.334664005322689e-05, | |
| "loss": 4.9326, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 9.251497005988024e-05, | |
| "loss": 4.4854, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 9.16833000665336e-05, | |
| "loss": 4.1808, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 9.085163007318697e-05, | |
| "loss": 3.9169, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 9.001996007984033e-05, | |
| "loss": 3.7161, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 8.918829008649369e-05, | |
| "loss": 3.5102, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 8.835662009314704e-05, | |
| "loss": 3.3782, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 8.752495009980041e-05, | |
| "loss": 3.246, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 8.669328010645377e-05, | |
| "loss": 3.1532, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 4.24, | |
| "learning_rate": 8.586161011310713e-05, | |
| "loss": 3.0313, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "learning_rate": 8.502994011976048e-05, | |
| "loss": 2.9563, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 8.419827012641384e-05, | |
| "loss": 2.8741, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "learning_rate": 8.336660013306721e-05, | |
| "loss": 2.816, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "learning_rate": 8.253493013972057e-05, | |
| "loss": 2.7435, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 5.49, | |
| "learning_rate": 8.170326014637393e-05, | |
| "loss": 2.6801, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 5.74, | |
| "learning_rate": 8.087159015302728e-05, | |
| "loss": 2.6325, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 5.99, | |
| "learning_rate": 8.003992015968065e-05, | |
| "loss": 2.5931, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 6.24, | |
| "learning_rate": 7.9208250166334e-05, | |
| "loss": 2.525, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 6.49, | |
| "learning_rate": 7.837658017298735e-05, | |
| "loss": 2.4914, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 6.74, | |
| "learning_rate": 7.754491017964072e-05, | |
| "loss": 2.4559, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "learning_rate": 7.671324018629408e-05, | |
| "loss": 2.4176, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 7.24, | |
| "learning_rate": 7.588157019294744e-05, | |
| "loss": 2.3771, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 7.49, | |
| "learning_rate": 7.50499001996008e-05, | |
| "loss": 2.3386, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 7.73, | |
| "learning_rate": 7.421823020625415e-05, | |
| "loss": 2.3137, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 7.98, | |
| "learning_rate": 7.338656021290752e-05, | |
| "loss": 2.2792, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 8.23, | |
| "learning_rate": 7.255489021956088e-05, | |
| "loss": 2.235, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 8.48, | |
| "learning_rate": 7.172322022621424e-05, | |
| "loss": 2.2126, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 8.73, | |
| "learning_rate": 7.089155023286759e-05, | |
| "loss": 2.1985, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 8.98, | |
| "learning_rate": 7.005988023952096e-05, | |
| "loss": 2.1803, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 9.23, | |
| "learning_rate": 6.922821024617432e-05, | |
| "loss": 2.1363, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 9.48, | |
| "learning_rate": 6.839654025282768e-05, | |
| "loss": 2.1104, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 9.73, | |
| "learning_rate": 6.756487025948103e-05, | |
| "loss": 2.0954, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 9.98, | |
| "learning_rate": 6.67332002661344e-05, | |
| "loss": 2.0818, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 10.23, | |
| "learning_rate": 6.590153027278776e-05, | |
| "loss": 2.0576, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 10.48, | |
| "learning_rate": 6.506986027944112e-05, | |
| "loss": 2.0304, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 10.73, | |
| "learning_rate": 6.423819028609448e-05, | |
| "loss": 2.0079, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 10.98, | |
| "learning_rate": 6.340652029274785e-05, | |
| "loss": 2.0089, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 11.23, | |
| "learning_rate": 6.25748502994012e-05, | |
| "loss": 1.971, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 11.48, | |
| "learning_rate": 6.174318030605456e-05, | |
| "loss": 1.9458, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 11.73, | |
| "learning_rate": 6.091151031270792e-05, | |
| "loss": 1.9479, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 11.98, | |
| "learning_rate": 6.007984031936128e-05, | |
| "loss": 1.9332, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 12.23, | |
| "learning_rate": 5.924817032601464e-05, | |
| "loss": 1.9048, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 12.48, | |
| "learning_rate": 5.8416500332668e-05, | |
| "loss": 1.8943, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 12.72, | |
| "learning_rate": 5.758483033932136e-05, | |
| "loss": 1.8837, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 12.97, | |
| "learning_rate": 5.675316034597472e-05, | |
| "loss": 1.8606, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 13.22, | |
| "learning_rate": 5.592149035262808e-05, | |
| "loss": 1.8289, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 13.47, | |
| "learning_rate": 5.508982035928144e-05, | |
| "loss": 1.8209, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 13.72, | |
| "learning_rate": 5.42581503659348e-05, | |
| "loss": 1.8284, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 13.97, | |
| "learning_rate": 5.342648037258816e-05, | |
| "loss": 1.814, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 14.22, | |
| "learning_rate": 5.259481037924152e-05, | |
| "loss": 1.7909, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 14.47, | |
| "learning_rate": 5.1763140385894884e-05, | |
| "loss": 1.7712, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 14.72, | |
| "learning_rate": 5.093147039254824e-05, | |
| "loss": 1.7695, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 14.97, | |
| "learning_rate": 5.0099800399201604e-05, | |
| "loss": 1.7594, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 15.22, | |
| "learning_rate": 4.9268130405854955e-05, | |
| "loss": 1.7413, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 15.47, | |
| "learning_rate": 4.843646041250832e-05, | |
| "loss": 1.7254, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 15.72, | |
| "learning_rate": 4.7604790419161675e-05, | |
| "loss": 1.7287, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 15.97, | |
| "learning_rate": 4.677312042581504e-05, | |
| "loss": 1.7078, | |
| "step": 32000 | |
| } | |
| ], | |
| "max_steps": 60120, | |
| "num_train_epochs": 30, | |
| "total_flos": 3.3697979301888e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |