| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9999576791231114, | |
| "global_step": 11814, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 8.460236886632826e-06, | |
| "loss": 0.4255, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.6920473773265652e-05, | |
| "loss": 0.3691, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.940180586907449e-05, | |
| "loss": 0.3549, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.8461249059443193e-05, | |
| "loss": 0.3573, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.752069224981189e-05, | |
| "loss": 0.3383, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.658013544018059e-05, | |
| "loss": 0.2995, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.5639578630549285e-05, | |
| "loss": 0.3225, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.4699021820917985e-05, | |
| "loss": 0.3038, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1.3758465011286683e-05, | |
| "loss": 0.2974, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.281790820165538e-05, | |
| "loss": 0.28, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.1877351392024078e-05, | |
| "loss": 0.2854, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1.0936794582392779e-05, | |
| "loss": 0.2989, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.996237772761475e-06, | |
| "loss": 0.264, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 9.055680963130174e-06, | |
| "loss": 0.2623, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 8.115124153498872e-06, | |
| "loss": 0.2778, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 7.17456734386757e-06, | |
| "loss": 0.2785, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 6.234010534236269e-06, | |
| "loss": 0.2563, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 5.293453724604967e-06, | |
| "loss": 0.2891, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.352896914973665e-06, | |
| "loss": 0.2653, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 3.4123401053423627e-06, | |
| "loss": 0.2413, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 2.471783295711061e-06, | |
| "loss": 0.2601, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.5312264860797594e-06, | |
| "loss": 0.2534, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 5.906696764484576e-07, | |
| "loss": 0.236, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.35328546166419983, | |
| "eval_runtime": 25.6194, | |
| "eval_samples_per_second": 50.47, | |
| "step": 11814 | |
| } | |
| ], | |
| "max_steps": 11814, | |
| "num_train_epochs": 1, | |
| "total_flos": 5.402804106210509e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |