| { | |
| "best_metric": 5.976424694061279, | |
| "best_model_checkpoint": "saved_models/narrativeqa_adaptertune/checkpoint-4092", | |
| "epoch": 1.9996335654085746, | |
| "global_step": 4092, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.968067774519389e-05, | |
| "loss": 10.6425, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.935483870967742e-05, | |
| "loss": 6.447, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.902899967416097e-05, | |
| "loss": 6.2146, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.870316063864451e-05, | |
| "loss": 6.1529, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 9.837732160312806e-05, | |
| "loss": 6.1086, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 9.80514825676116e-05, | |
| "loss": 6.0845, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 9.772564353209514e-05, | |
| "loss": 6.065, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 9.73998044965787e-05, | |
| "loss": 6.0532, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 9.707396546106225e-05, | |
| "loss": 6.0406, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 9.674812642554578e-05, | |
| "loss": 6.0327, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.642228739002933e-05, | |
| "loss": 6.023, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 9.609644835451288e-05, | |
| "loss": 6.0156, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 9.577060931899642e-05, | |
| "loss": 6.0196, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 9.544477028347996e-05, | |
| "loss": 6.0088, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 9.51189312479635e-05, | |
| "loss": 6.0029, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 9.479309221244705e-05, | |
| "loss": 6.0015, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 9.446725317693061e-05, | |
| "loss": 6.0022, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 9.414141414141415e-05, | |
| "loss": 5.9995, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 9.381557510589769e-05, | |
| "loss": 5.9931, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 9.348973607038124e-05, | |
| "loss": 5.9961, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 5.981632232666016, | |
| "eval_rouge1": 0.4942, | |
| "eval_rouge2": 0.2497, | |
| "eval_rougeL": 0.489, | |
| "eval_runtime": 642.0603, | |
| "eval_samples_per_second": 10.781, | |
| "eval_steps_per_second": 2.696, | |
| "step": 2046 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 9.316389703486478e-05, | |
| "loss": 6.0409, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 9.283805799934833e-05, | |
| "loss": 5.9926, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 9.251221896383187e-05, | |
| "loss": 5.9925, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 9.218963831867058e-05, | |
| "loss": 5.9883, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 9.186379928315413e-05, | |
| "loss": 5.9822, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 9.153796024763767e-05, | |
| "loss": 5.9871, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 9.121212121212121e-05, | |
| "loss": 5.9836, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 9.088628217660477e-05, | |
| "loss": 5.9832, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 9.05604431410883e-05, | |
| "loss": 5.9885, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 9.023460410557186e-05, | |
| "loss": 5.9866, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 8.99087650700554e-05, | |
| "loss": 5.9802, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 8.958292603453894e-05, | |
| "loss": 5.9789, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 8.925708699902249e-05, | |
| "loss": 5.9857, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 8.893124796350603e-05, | |
| "loss": 5.9781, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 8.860540892798957e-05, | |
| "loss": 5.9747, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 8.827956989247312e-05, | |
| "loss": 5.9757, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 8.795373085695668e-05, | |
| "loss": 5.9775, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 8.762789182144022e-05, | |
| "loss": 5.9787, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 8.730205278592376e-05, | |
| "loss": 5.9827, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 8.69762137504073e-05, | |
| "loss": 5.9755, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 5.976424694061279, | |
| "eval_rouge1": 0.5089, | |
| "eval_rouge2": 0.2563, | |
| "eval_rougeL": 0.5034, | |
| "eval_runtime": 639.6582, | |
| "eval_samples_per_second": 10.821, | |
| "eval_steps_per_second": 2.706, | |
| "step": 4092 | |
| } | |
| ], | |
| "max_steps": 30690, | |
| "num_train_epochs": 15, | |
| "total_flos": 1.727047442376622e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |