| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 15.998864926220204, | |
| "global_step": 3520, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7795322956613279, | |
| "eval_loss": 1.5038145780563354, | |
| "eval_runtime": 5.9639, | |
| "eval_samples_per_second": 15.258, | |
| "eval_steps_per_second": 7.713, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7964938287518932, | |
| "eval_loss": 1.3765002489089966, | |
| "eval_runtime": 5.973, | |
| "eval_samples_per_second": 15.235, | |
| "eval_steps_per_second": 7.701, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 8.579545454545455e-06, | |
| "loss": 1.5308, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8075258075258075, | |
| "eval_loss": 1.2920387983322144, | |
| "eval_runtime": 5.9722, | |
| "eval_samples_per_second": 15.237, | |
| "eval_steps_per_second": 7.702, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8155607833027188, | |
| "eval_loss": 1.230821967124939, | |
| "eval_runtime": 5.6615, | |
| "eval_samples_per_second": 16.073, | |
| "eval_steps_per_second": 8.125, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 4.54, | |
| "learning_rate": 7.161931818181819e-06, | |
| "loss": 1.2695, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.8225860161344032, | |
| "eval_loss": 1.1788371801376343, | |
| "eval_runtime": 5.9852, | |
| "eval_samples_per_second": 15.204, | |
| "eval_steps_per_second": 7.686, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.8278817956237311, | |
| "eval_loss": 1.136326789855957, | |
| "eval_runtime": 5.9723, | |
| "eval_samples_per_second": 15.237, | |
| "eval_steps_per_second": 7.702, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 6.82, | |
| "learning_rate": 5.741477272727272e-06, | |
| "loss": 1.1353, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.8323826710923485, | |
| "eval_loss": 1.102668285369873, | |
| "eval_runtime": 5.9851, | |
| "eval_samples_per_second": 15.204, | |
| "eval_steps_per_second": 7.686, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.8373239663562244, | |
| "eval_loss": 1.072572112083435, | |
| "eval_runtime": 5.9939, | |
| "eval_samples_per_second": 15.182, | |
| "eval_steps_per_second": 7.674, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.8404928404928405, | |
| "eval_loss": 1.0481319427490234, | |
| "eval_runtime": 5.9927, | |
| "eval_samples_per_second": 15.185, | |
| "eval_steps_per_second": 7.676, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 9.09, | |
| "learning_rate": 4.321022727272728e-06, | |
| "loss": 1.0713, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.8432642626191014, | |
| "eval_loss": 1.0299291610717773, | |
| "eval_runtime": 5.6745, | |
| "eval_samples_per_second": 16.037, | |
| "eval_steps_per_second": 8.106, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.8455415552189746, | |
| "eval_loss": 1.0174473524093628, | |
| "eval_runtime": 5.9763, | |
| "eval_samples_per_second": 15.227, | |
| "eval_steps_per_second": 7.697, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 11.36, | |
| "learning_rate": 2.900568181818182e-06, | |
| "loss": 1.0233, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.8477006864103638, | |
| "eval_loss": 1.0027512311935425, | |
| "eval_runtime": 5.9881, | |
| "eval_samples_per_second": 15.197, | |
| "eval_steps_per_second": 7.682, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.8488178488178488, | |
| "eval_loss": 0.9938735961914062, | |
| "eval_runtime": 5.9759, | |
| "eval_samples_per_second": 15.228, | |
| "eval_steps_per_second": 7.698, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 13.64, | |
| "learning_rate": 1.4829545454545454e-06, | |
| "loss": 0.9811, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.8496772045159142, | |
| "eval_loss": 0.9889363646507263, | |
| "eval_runtime": 5.9819, | |
| "eval_samples_per_second": 15.213, | |
| "eval_steps_per_second": 7.69, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.8499779790102371, | |
| "eval_loss": 0.9854440093040466, | |
| "eval_runtime": 5.9887, | |
| "eval_samples_per_second": 15.195, | |
| "eval_steps_per_second": 7.681, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 15.91, | |
| "learning_rate": 6.250000000000001e-08, | |
| "loss": 0.9696, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.8501928179347534, | |
| "eval_loss": 0.9834597110748291, | |
| "eval_runtime": 5.978, | |
| "eval_samples_per_second": 15.223, | |
| "eval_steps_per_second": 7.695, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "step": 3520, | |
| "total_flos": 1.2269276173959168e+17, | |
| "train_loss": 1.138753395730799, | |
| "train_runtime": 5180.444, | |
| "train_samples_per_second": 5.442, | |
| "train_steps_per_second": 0.679 | |
| } | |
| ], | |
| "max_steps": 3520, | |
| "num_train_epochs": 16, | |
| "total_flos": 1.2269276173959168e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |