| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 8.0, | |
| "global_step": 10768, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 2.8620913818722143e-05, | |
| "loss": 0.0869, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 2.7227897473997028e-05, | |
| "loss": 0.071, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 2.583488112927192e-05, | |
| "loss": 0.0672, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 2.4441864784546807e-05, | |
| "loss": 0.0553, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 2.3051634472511147e-05, | |
| "loss": 0.0634, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 2.1658618127786032e-05, | |
| "loss": 0.0578, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 2.0265601783060923e-05, | |
| "loss": 0.0567, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 1.8872585438335808e-05, | |
| "loss": 0.0485, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 1.74795690936107e-05, | |
| "loss": 0.0376, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "learning_rate": 1.6086552748885588e-05, | |
| "loss": 0.0392, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 1.4693536404160476e-05, | |
| "loss": 0.0388, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "learning_rate": 1.3300520059435364e-05, | |
| "loss": 0.0289, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 1.1910289747399702e-05, | |
| "loss": 0.0329, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 5.2, | |
| "learning_rate": 1.051727340267459e-05, | |
| "loss": 0.0275, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 5.57, | |
| "learning_rate": 9.124257057949479e-06, | |
| "loss": 0.0222, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 5.94, | |
| "learning_rate": 7.734026745913819e-06, | |
| "loss": 0.0238, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 6.32, | |
| "learning_rate": 6.341010401188708e-06, | |
| "loss": 0.0173, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 6.69, | |
| "learning_rate": 4.947994056463596e-06, | |
| "loss": 0.0172, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 7.06, | |
| "learning_rate": 3.5549777117384844e-06, | |
| "loss": 0.0137, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 7.43, | |
| "learning_rate": 2.161961367013373e-06, | |
| "loss": 0.0123, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 7.8, | |
| "learning_rate": 7.717310549777118e-07, | |
| "loss": 0.0121, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "step": 10768, | |
| "total_flos": 1.8659637466025165e+17, | |
| "train_loss": 0.0387608133931748, | |
| "train_runtime": 15676.2621, | |
| "train_samples_per_second": 5.493, | |
| "train_steps_per_second": 0.687 | |
| } | |
| ], | |
| "max_steps": 10768, | |
| "num_train_epochs": 8, | |
| "total_flos": 1.8659637466025165e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |