| { | |
| "best_metric": 1.0294359922409058, | |
| "best_model_checkpoint": "output/Baichuan-13B-Chat_lora_wqs_jiansuo/checkpoint-400", | |
| "epoch": 1.9939795304033714, | |
| "global_step": 414, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.9928054992195985e-05, | |
| "loss": 1.3488, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.971263405551576e-05, | |
| "loss": 1.2097, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.9354977066836986e-05, | |
| "loss": 1.1719, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.885714255694698e-05, | |
| "loss": 1.145, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.822199586246168e-05, | |
| "loss": 1.1203, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 1.11279296875, | |
| "eval_runtime": 10.7965, | |
| "eval_samples_per_second": 18.71, | |
| "eval_steps_per_second": 1.575, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.74531926340924e-05, | |
| "loss": 1.1036, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.6555157796180335e-05, | |
| "loss": 1.0904, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 4.5533060078599226e-05, | |
| "loss": 1.0818, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 4.43927822676105e-05, | |
| "loss": 1.0829, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 4.3140887346894974e-05, | |
| "loss": 1.0744, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 1.065435767173767, | |
| "eval_runtime": 7.9424, | |
| "eval_samples_per_second": 25.433, | |
| "eval_steps_per_second": 2.14, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.1784580723639923e-05, | |
| "loss": 1.0629, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.033166875709291e-05, | |
| "loss": 1.0659, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.8790513828275683e-05, | |
| "loss": 1.0523, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.716998620945871e-05, | |
| "loss": 1.0397, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 3.547941301041661e-05, | |
| "loss": 1.0435, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 1.048127293586731, | |
| "eval_runtime": 8.0034, | |
| "eval_samples_per_second": 25.239, | |
| "eval_steps_per_second": 2.124, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 3.372852449530922e-05, | |
| "loss": 1.0563, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 3.1927398079167226e-05, | |
| "loss": 1.0376, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 3.008640032631585e-05, | |
| "loss": 1.0436, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 2.821612728457078e-05, | |
| "loss": 1.0301, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 2.632734349861874e-05, | |
| "loss": 1.0338, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 1.0388035774230957, | |
| "eval_runtime": 7.9339, | |
| "eval_samples_per_second": 25.46, | |
| "eval_steps_per_second": 2.143, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 2.4430920053597356e-05, | |
| "loss": 1.033, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 2.2537772005470782e-05, | |
| "loss": 1.0399, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 2.0658795558326743e-05, | |
| "loss": 1.0277, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 1.8804805350177505e-05, | |
| "loss": 1.0325, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 1.6986472208222576e-05, | |
| "loss": 1.0322, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_loss": 1.0336002111434937, | |
| "eval_runtime": 7.9742, | |
| "eval_samples_per_second": 25.332, | |
| "eval_steps_per_second": 2.132, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 1.5214261731829022e-05, | |
| "loss": 1.0248, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 1.3498374056721197e-05, | |
| "loss": 1.0235, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 1.1848685147073222e-05, | |
| "loss": 1.0446, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 1.0274689953403407e-05, | |
| "loss": 1.0271, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 8.785447763431101e-06, | |
| "loss": 1.0351, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "eval_loss": 1.031198263168335, | |
| "eval_runtime": 7.9378, | |
| "eval_samples_per_second": 25.448, | |
| "eval_steps_per_second": 2.142, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 7.389530060434696e-06, | |
| "loss": 1.0341, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 6.094971189217042e-06, | |
| "loss": 1.0267, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 4.9092221136255444e-06, | |
| "loss": 1.0122, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 3.839107531779978e-06, | |
| "loss": 1.0197, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 2.890786595835693e-06, | |
| "loss": 1.0193, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "eval_loss": 1.0297337770462036, | |
| "eval_runtime": 7.9869, | |
| "eval_samples_per_second": 25.292, | |
| "eval_steps_per_second": 2.128, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 2.0697174623636794e-06, | |
| "loss": 1.0231, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 1.3806258773811476e-06, | |
| "loss": 1.0233, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 8.274779768448482e-07, | |
| "loss": 1.0224, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 4.134574591564494e-07, | |
| "loss": 1.0181, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 1.4094726106603505e-07, | |
| "loss": 1.0189, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "eval_loss": 1.0294359922409058, | |
| "eval_runtime": 7.9102, | |
| "eval_samples_per_second": 25.537, | |
| "eval_steps_per_second": 2.149, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 1.1515842439871472e-08, | |
| "loss": 1.0244, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "step": 414, | |
| "total_flos": 3.076881712207102e+18, | |
| "train_loss": 1.0595260426618052, | |
| "train_runtime": 5379.5583, | |
| "train_samples_per_second": 7.407, | |
| "train_steps_per_second": 0.077 | |
| } | |
| ], | |
| "max_steps": 414, | |
| "num_train_epochs": 2, | |
| "total_flos": 3.076881712207102e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |