| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.006615506747816882, |
| "eval_steps": 756, |
| "global_step": 50, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0, |
| "learning_rate": 0.0, |
| "loss": 0.929, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.0, |
| "eval_loss": 0.9224275946617126, |
| "eval_runtime": 2.17, |
| "eval_samples_per_second": 79.724, |
| "eval_steps_per_second": 3.687, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.0, |
| "eval_bench_accuracy_agieval": 0.288135593220339, |
| "eval_bench_accuracy_arc_challenge": 0.8148148148148148, |
| "eval_bench_accuracy_arc_easy": 0.9074074074074074, |
| "eval_bench_accuracy_bigbench": 0.3442622950819672, |
| "eval_bench_accuracy_boolq": 0.5185185185185185, |
| "eval_bench_accuracy_mmlu": 0.48148148148148145, |
| "eval_bench_accuracy_openbookqa": 0.14814814814814814, |
| "eval_bench_accuracy_truthful_qa": 0.37735849056603776, |
| "eval_bench_accuracy_winogrande": 0.4074074074074074, |
| "eval_bench_average_accuracy": 0.4763926840717912, |
| "eval_bench_loss": 5.786159653261484, |
| "eval_bench_total_accuracy": 0.47283702213279677, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.0, |
| "learning_rate": 6.000000000000001e-07, |
| "loss": 0.8533, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.0, |
| "learning_rate": 1.2000000000000002e-06, |
| "loss": 0.9641, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.0, |
| "learning_rate": 1.8e-06, |
| "loss": 0.8488, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.0, |
| "learning_rate": 2.4000000000000003e-06, |
| "loss": 0.8863, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.0, |
| "learning_rate": 3e-06, |
| "loss": 0.7988, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.0, |
| "learning_rate": 3.6e-06, |
| "loss": 0.7789, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.0, |
| "learning_rate": 4.2e-06, |
| "loss": 0.7144, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.0, |
| "learning_rate": 4.800000000000001e-06, |
| "loss": 0.8322, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.0, |
| "learning_rate": 5.4e-06, |
| "loss": 0.734, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.0, |
| "learning_rate": 6e-06, |
| "loss": 0.7861, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.0, |
| "learning_rate": 5.999602806831722e-06, |
| "loss": 0.6733, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.0, |
| "learning_rate": 5.999205613663445e-06, |
| "loss": 0.7019, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.0, |
| "learning_rate": 5.9988084204951675e-06, |
| "loss": 0.7096, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.0, |
| "learning_rate": 5.99841122732689e-06, |
| "loss": 0.6745, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.0, |
| "learning_rate": 5.998014034158613e-06, |
| "loss": 0.8022, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.0, |
| "learning_rate": 5.997616840990336e-06, |
| "loss": 0.7753, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.0, |
| "learning_rate": 5.997219647822058e-06, |
| "loss": 0.6939, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.0, |
| "learning_rate": 5.99682245465378e-06, |
| "loss": 0.689, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.0, |
| "learning_rate": 5.996425261485502e-06, |
| "loss": 0.7419, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.0, |
| "learning_rate": 5.996028068317225e-06, |
| "loss": 0.6975, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.0, |
| "learning_rate": 5.9956308751489475e-06, |
| "loss": 0.686, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.0, |
| "learning_rate": 5.99523368198067e-06, |
| "loss": 0.7576, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.0, |
| "learning_rate": 5.994836488812393e-06, |
| "loss": 0.6802, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.0, |
| "learning_rate": 5.994439295644115e-06, |
| "loss": 0.711, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.0, |
| "learning_rate": 5.994042102475838e-06, |
| "loss": 0.6658, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.0, |
| "learning_rate": 5.99364490930756e-06, |
| "loss": 0.685, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.0, |
| "learning_rate": 5.993247716139283e-06, |
| "loss": 0.6881, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.0, |
| "learning_rate": 5.992850522971005e-06, |
| "loss": 0.7066, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.0, |
| "learning_rate": 5.992453329802727e-06, |
| "loss": 0.6993, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.0, |
| "learning_rate": 5.99205613663445e-06, |
| "loss": 0.6429, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.0, |
| "learning_rate": 5.991658943466173e-06, |
| "loss": 0.7205, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.0, |
| "learning_rate": 5.991261750297895e-06, |
| "loss": 0.703, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.0, |
| "learning_rate": 5.990864557129617e-06, |
| "loss": 0.6512, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.0, |
| "learning_rate": 5.99046736396134e-06, |
| "loss": 0.6583, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.0, |
| "learning_rate": 5.990070170793063e-06, |
| "loss": 0.6904, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.0, |
| "learning_rate": 5.989672977624785e-06, |
| "loss": 0.6619, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.01, |
| "learning_rate": 5.989275784456507e-06, |
| "loss": 0.7033, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.01, |
| "learning_rate": 5.98887859128823e-06, |
| "loss": 0.6522, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.01, |
| "learning_rate": 5.9884813981199526e-06, |
| "loss": 0.6365, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.01, |
| "learning_rate": 5.988084204951675e-06, |
| "loss": 0.6422, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.01, |
| "learning_rate": 5.987687011783397e-06, |
| "loss": 0.625, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.01, |
| "learning_rate": 5.98728981861512e-06, |
| "loss": 0.6148, |
| "step": 43 |
| }, |
| { |
| "epoch": 0.01, |
| "learning_rate": 5.986892625446843e-06, |
| "loss": 0.7089, |
| "step": 44 |
| }, |
| { |
| "epoch": 0.01, |
| "learning_rate": 5.986495432278565e-06, |
| "loss": 0.681, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.01, |
| "learning_rate": 5.986098239110287e-06, |
| "loss": 0.6505, |
| "step": 46 |
| }, |
| { |
| "epoch": 0.01, |
| "learning_rate": 5.98570104594201e-06, |
| "loss": 0.6531, |
| "step": 47 |
| }, |
| { |
| "epoch": 0.01, |
| "learning_rate": 5.9853038527737325e-06, |
| "loss": 0.6683, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.01, |
| "learning_rate": 5.984906659605455e-06, |
| "loss": 0.6967, |
| "step": 49 |
| }, |
| { |
| "epoch": 0.01, |
| "learning_rate": 5.984509466437178e-06, |
| "loss": 0.6514, |
| "step": 50 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 15116, |
| "num_train_epochs": 2, |
| "save_steps": 50, |
| "total_flos": 2.097021406150656e+17, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
