| { | |
| "best_metric": 0.5469470024108887, | |
| "best_model_checkpoint": "bart_lora_outputs\\checkpoint-500", | |
| "epoch": 0.8156606851549756, | |
| "eval_steps": 100, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 2e-05, | |
| "loss": 2.9281, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4e-05, | |
| "loss": 2.8201, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 6e-05, | |
| "loss": 2.579, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 8e-05, | |
| "loss": 2.4427, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0001, | |
| "loss": 2.1681, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00012, | |
| "loss": 1.7104, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00014000000000000001, | |
| "loss": 1.4177, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00016, | |
| "loss": 1.2515, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 1.1238, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0489, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 0.8469381928443909, | |
| "eval_runtime": 5.9601, | |
| "eval_samples_per_second": 196.474, | |
| "eval_steps_per_second": 24.664, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00022, | |
| "loss": 1.0079, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00024, | |
| "loss": 1.0077, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00026000000000000003, | |
| "loss": 0.9416, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00028000000000000003, | |
| "loss": 0.8882, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8595, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00032, | |
| "loss": 0.8853, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00034, | |
| "loss": 0.7678, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00035999999999999997, | |
| "loss": 0.8595, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00038, | |
| "loss": 0.8514, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0004, | |
| "loss": 0.8128, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 0.6850531697273254, | |
| "eval_runtime": 6.0279, | |
| "eval_samples_per_second": 194.264, | |
| "eval_steps_per_second": 24.387, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00042, | |
| "loss": 0.7782, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00044, | |
| "loss": 0.8064, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00046, | |
| "loss": 0.7627, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00048, | |
| "loss": 0.7447, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0005, | |
| "loss": 0.7652, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.0005200000000000001, | |
| "loss": 0.7568, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00054, | |
| "loss": 0.7291, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0005600000000000001, | |
| "loss": 0.7118, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00058, | |
| "loss": 0.7462, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.0006, | |
| "loss": 0.6866, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 0.629724383354187, | |
| "eval_runtime": 6.0378, | |
| "eval_samples_per_second": 193.943, | |
| "eval_steps_per_second": 24.346, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00062, | |
| "loss": 0.6995, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00064, | |
| "loss": 0.724, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.00066, | |
| "loss": 0.6698, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00068, | |
| "loss": 0.6516, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0007, | |
| "loss": 0.6657, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.0007199999999999999, | |
| "loss": 0.6765, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00074, | |
| "loss": 0.6596, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00076, | |
| "loss": 0.6884, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.0007800000000000001, | |
| "loss": 0.647, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.0008, | |
| "loss": 0.713, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 0.5541791319847107, | |
| "eval_runtime": 6.0716, | |
| "eval_samples_per_second": 192.864, | |
| "eval_steps_per_second": 24.211, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00082, | |
| "loss": 0.6593, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.00084, | |
| "loss": 0.62, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.00086, | |
| "loss": 0.6912, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.00088, | |
| "loss": 0.6407, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.0009000000000000001, | |
| "loss": 0.6444, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.00092, | |
| "loss": 0.6591, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.00094, | |
| "loss": 0.6329, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.00096, | |
| "loss": 0.6097, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.00098, | |
| "loss": 0.6444, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.001, | |
| "loss": 0.6106, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_loss": 0.5469470024108887, | |
| "eval_runtime": 6.1353, | |
| "eval_samples_per_second": 190.861, | |
| "eval_steps_per_second": 23.96, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 6130, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 939361765588992.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |