| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 15.4608, | |
| "global_step": 1500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 4.800000000000001e-06, | |
| "loss": 10.7159, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": 7.062511920928955, | |
| "eval_runtime": 16.5468, | |
| "eval_samples_per_second": 604.347, | |
| "eval_steps_per_second": 37.772, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 9.65e-06, | |
| "loss": 5.0371, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_loss": 2.8384995460510254, | |
| "eval_runtime": 16.0338, | |
| "eval_samples_per_second": 623.684, | |
| "eval_steps_per_second": 38.98, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 1.4449999999999999e-05, | |
| "loss": 2.4865, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_loss": 1.1602892875671387, | |
| "eval_runtime": 16.2241, | |
| "eval_samples_per_second": 616.367, | |
| "eval_steps_per_second": 38.523, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 1.93e-05, | |
| "loss": 1.0806, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "eval_loss": 0.7614782452583313, | |
| "eval_runtime": 16.2665, | |
| "eval_samples_per_second": 614.761, | |
| "eval_steps_per_second": 38.423, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "learning_rate": 2.415e-05, | |
| "loss": 0.8412, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_loss": 0.726601243019104, | |
| "eval_runtime": 16.7852, | |
| "eval_samples_per_second": 595.764, | |
| "eval_steps_per_second": 37.235, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 5.99, | |
| "learning_rate": 2.9e-05, | |
| "loss": 0.802, | |
| "step": 582 | |
| }, | |
| { | |
| "epoch": 5.99, | |
| "eval_loss": 0.7105833292007446, | |
| "eval_runtime": 16.763, | |
| "eval_samples_per_second": 596.553, | |
| "eval_steps_per_second": 37.285, | |
| "step": 582 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "learning_rate": 3.385e-05, | |
| "loss": 0.7776, | |
| "step": 679 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "eval_loss": 0.6986653804779053, | |
| "eval_runtime": 16.7875, | |
| "eval_samples_per_second": 595.68, | |
| "eval_steps_per_second": 37.23, | |
| "step": 679 | |
| }, | |
| { | |
| "epoch": 7.99, | |
| "learning_rate": 3.8700000000000006e-05, | |
| "loss": 0.7568, | |
| "step": 776 | |
| }, | |
| { | |
| "epoch": 7.99, | |
| "eval_loss": 0.687833309173584, | |
| "eval_runtime": 16.4861, | |
| "eval_samples_per_second": 606.571, | |
| "eval_steps_per_second": 37.911, | |
| "step": 776 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "learning_rate": 4.355e-05, | |
| "loss": 0.7382, | |
| "step": 873 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "eval_loss": 0.6793721914291382, | |
| "eval_runtime": 16.6577, | |
| "eval_samples_per_second": 600.323, | |
| "eval_steps_per_second": 37.52, | |
| "step": 873 | |
| }, | |
| { | |
| "epoch": 9.99, | |
| "learning_rate": 4.8400000000000004e-05, | |
| "loss": 0.7202, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 9.99, | |
| "eval_loss": 0.6695303320884705, | |
| "eval_runtime": 16.3181, | |
| "eval_samples_per_second": 612.817, | |
| "eval_steps_per_second": 38.301, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 10.99, | |
| "learning_rate": 4.6542553191489364e-05, | |
| "loss": 0.7022, | |
| "step": 1067 | |
| }, | |
| { | |
| "epoch": 10.99, | |
| "eval_loss": 0.6605609059333801, | |
| "eval_runtime": 16.748, | |
| "eval_samples_per_second": 597.086, | |
| "eval_steps_per_second": 37.318, | |
| "step": 1067 | |
| }, | |
| { | |
| "epoch": 11.99, | |
| "learning_rate": 4.138297872340426e-05, | |
| "loss": 0.6844, | |
| "step": 1164 | |
| }, | |
| { | |
| "epoch": 11.99, | |
| "eval_loss": 0.6539720892906189, | |
| "eval_runtime": 16.7037, | |
| "eval_samples_per_second": 598.671, | |
| "eval_steps_per_second": 37.417, | |
| "step": 1164 | |
| }, | |
| { | |
| "epoch": 12.99, | |
| "learning_rate": 3.622340425531915e-05, | |
| "loss": 0.669, | |
| "step": 1261 | |
| }, | |
| { | |
| "epoch": 12.99, | |
| "eval_loss": 0.6471053957939148, | |
| "eval_runtime": 16.5172, | |
| "eval_samples_per_second": 605.43, | |
| "eval_steps_per_second": 37.839, | |
| "step": 1261 | |
| }, | |
| { | |
| "epoch": 13.99, | |
| "learning_rate": 3.1063829787234046e-05, | |
| "loss": 0.6562, | |
| "step": 1358 | |
| }, | |
| { | |
| "epoch": 13.99, | |
| "eval_loss": 0.6417160034179688, | |
| "eval_runtime": 16.0822, | |
| "eval_samples_per_second": 621.804, | |
| "eval_steps_per_second": 38.863, | |
| "step": 1358 | |
| }, | |
| { | |
| "epoch": 14.99, | |
| "learning_rate": 2.590425531914894e-05, | |
| "loss": 0.6453, | |
| "step": 1455 | |
| }, | |
| { | |
| "epoch": 14.99, | |
| "eval_loss": 0.6380994915962219, | |
| "eval_runtime": 16.4132, | |
| "eval_samples_per_second": 609.265, | |
| "eval_steps_per_second": 38.079, | |
| "step": 1455 | |
| } | |
| ], | |
| "max_steps": 1940, | |
| "num_train_epochs": 20, | |
| "total_flos": 5.89188339597312e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |