| { | |
| "best_metric": 0.6302221417427063, | |
| "best_model_checkpoint": "./lora-alpaca/checkpoint-400", | |
| "epoch": 0.9411764705882353, | |
| "global_step": 400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 2.0163, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 1.9284, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 1.77, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 1.3452, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00015, | |
| "loss": 0.9243, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 0.8385, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 0.7986, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 0.7786, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00027, | |
| "loss": 0.75, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0003, | |
| "loss": 0.7389, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00029076923076923073, | |
| "loss": 0.7248, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0002815384615384615, | |
| "loss": 0.7199, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0002723076923076923, | |
| "loss": 0.7159, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00026307692307692306, | |
| "loss": 0.7029, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0002538461538461538, | |
| "loss": 0.6851, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0002446153846153846, | |
| "loss": 0.6935, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00023538461538461536, | |
| "loss": 0.6737, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00022615384615384614, | |
| "loss": 0.682, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.0002169230769230769, | |
| "loss": 0.667, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00020769230769230766, | |
| "loss": 0.6731, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 0.6641973853111267, | |
| "eval_runtime": 178.902, | |
| "eval_samples_per_second": 11.179, | |
| "eval_steps_per_second": 0.699, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00019846153846153844, | |
| "loss": 0.6631, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.0001892307692307692, | |
| "loss": 0.6652, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 0.6591, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.00017076923076923074, | |
| "loss": 0.6605, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00016153846153846153, | |
| "loss": 0.653, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00015230769230769228, | |
| "loss": 0.6574, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00014307692307692307, | |
| "loss": 0.6545, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00013384615384615385, | |
| "loss": 0.6328, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.0001246153846153846, | |
| "loss": 0.6485, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.00011538461538461538, | |
| "loss": 0.6477, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.00010615384615384615, | |
| "loss": 0.639, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 9.692307692307692e-05, | |
| "loss": 0.6384, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 8.76923076923077e-05, | |
| "loss": 0.6338, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 7.846153846153845e-05, | |
| "loss": 0.6394, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 6.923076923076922e-05, | |
| "loss": 0.6345, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 0.6424, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 5.0769230769230766e-05, | |
| "loss": 0.6271, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 4.153846153846154e-05, | |
| "loss": 0.6267, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 3.230769230769231e-05, | |
| "loss": 0.642, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 2.3076923076923076e-05, | |
| "loss": 0.6389, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_loss": 0.6302221417427063, | |
| "eval_runtime": 177.453, | |
| "eval_samples_per_second": 11.271, | |
| "eval_steps_per_second": 0.704, | |
| "step": 400 | |
| } | |
| ], | |
| "max_steps": 425, | |
| "num_train_epochs": 1, | |
| "total_flos": 5.199525204249805e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |