| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.25, | |
| "global_step": 50000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1e-05, | |
| "loss": 6.6141, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 2e-05, | |
| "loss": 4.8749, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 3e-05, | |
| "loss": 4.3313, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4e-05, | |
| "loss": 3.8037, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 5e-05, | |
| "loss": 3.546, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 6e-05, | |
| "loss": 2.278, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 7e-05, | |
| "loss": 1.966, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 8e-05, | |
| "loss": 1.675, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9e-05, | |
| "loss": 1.6046, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5251, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.999316524962345e-05, | |
| "loss": 1.4243, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 1.4579, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.993849845741524e-05, | |
| "loss": 1.26, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 1.3691, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 1.2561, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 1.2829, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.966546331768191e-05, | |
| "loss": 1.2622, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 1.2034, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.944739353007344e-05, | |
| "loss": 1.2684, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 1.1202, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 1.2468, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 1.1417, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.884934153917997e-05, | |
| "loss": 1.1873, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 1.1425, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 1.1133, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 1.1921, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 1.0537, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 1.1778, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 1.0729, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 1.1123, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.701596950580806e-05, | |
| "loss": 1.0753, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 1.0802, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 1.1432, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 1.0214, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 1.1205, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 1.0126, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.509956150664796e-05, | |
| "loss": 1.0801, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 1.0347, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 1.0509, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 1.0974, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.357421218136386e-05, | |
| "loss": 0.9812, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 1.081, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.273963562927695e-05, | |
| "loss": 0.9772, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 1.0695, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 1.0044, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 1.0309, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 9.093124073433463e-05, | |
| "loss": 1.0289, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.9732, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 8.995939984474624e-05, | |
| "loss": 1.068, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 0.9538, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 0.7697387337684631, | |
| "eval_runtime": 17.2413, | |
| "eval_samples_per_second": 290.001, | |
| "eval_steps_per_second": 2.32, | |
| "step": 50000 | |
| } | |
| ], | |
| "max_steps": 200000, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 8.422699302912e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |