| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 9.019195, | |
| "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": 6.5159, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 2e-05, | |
| "loss": 4.7939, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 3e-05, | |
| "loss": 4.1435, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4e-05, | |
| "loss": 3.9199, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 5e-05, | |
| "loss": 3.3094, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 6e-05, | |
| "loss": 2.3907, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 7e-05, | |
| "loss": 2.0078, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 8e-05, | |
| "loss": 1.7064, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 9e-05, | |
| "loss": 1.6833, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.0001, | |
| "loss": 1.4878, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 9.999316524962345e-05, | |
| "loss": 1.4635, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 1.4416, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 9.993849845741524e-05, | |
| "loss": 1.3392, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 1.3889, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 1.2742, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 1.2841, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 9.966546331768191e-05, | |
| "loss": 1.2706, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 1.2599, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 9.944739353007344e-05, | |
| "loss": 1.2441, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 1.1784, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 1.2054, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 1.1766, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 9.884934153917997e-05, | |
| "loss": 1.2071, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 1.1654, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 1.1619, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 1.1389, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 1.0962, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 1.1754, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 1.1028, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 1.1469, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 9.701596950580806e-05, | |
| "loss": 1.078, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 1.0601, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 1.1506, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 1.0549, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 1.1374, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 1.0301, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 9.509956150664796e-05, | |
| "loss": 1.0283, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 1.1236, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 1.0206, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 1.1147, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 7.03, | |
| "learning_rate": 9.357421218136386e-05, | |
| "loss": 1.0182, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 1.0063, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 9.273963562927695e-05, | |
| "loss": 1.0877, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 0.9996, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 1.0898, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 0.9928, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 9.093124073433463e-05, | |
| "loss": 1.0028, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.0667, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 8.995939984474624e-05, | |
| "loss": 0.9789, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 1.0668, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "eval_loss": 0.7346000671386719, | |
| "eval_runtime": 17.1312, | |
| "eval_samples_per_second": 291.864, | |
| "eval_steps_per_second": 2.335, | |
| "step": 50000 | |
| } | |
| ], | |
| "max_steps": 200000, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 8.423836367317893e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |