| { | |
| "best_metric": 1.653587818145752, | |
| "best_model_checkpoint": "./pippa-sharegpt-13b-qlora/checkpoint-50", | |
| "epoch": 0.5277044854881267, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 2e-05, | |
| "loss": 1.9036, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4e-05, | |
| "loss": 1.9209, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 6e-05, | |
| "loss": 1.9161, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 8e-05, | |
| "loss": 1.8722, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0001, | |
| "loss": 1.866, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00012, | |
| "loss": 1.872, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00014, | |
| "loss": 1.9138, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00016, | |
| "loss": 1.8785, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00018, | |
| "loss": 1.8013, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7859, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00019999332998034514, | |
| "loss": 1.7805, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00019997332081116373, | |
| "loss": 1.7716, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00019993997516168689, | |
| "loss": 1.7453, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00019989329748023725, | |
| "loss": 1.7306, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00019983329399363598, | |
| "loss": 1.7535, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0001997599727063717, | |
| "loss": 1.7811, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.000199673343399533, | |
| "loss": 1.7455, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00019957341762950344, | |
| "loss": 1.748, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0001994602087264201, | |
| "loss": 1.723, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00019933373179239502, | |
| "loss": 1.7539, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.000199194003699501, | |
| "loss": 1.7293, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0001990410430875205, | |
| "loss": 1.6857, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0001988748703614594, | |
| "loss": 1.7209, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00019869550768882455, | |
| "loss": 1.7127, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0001985029789966671, | |
| "loss": 1.7024, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0001982973099683902, | |
| "loss": 1.6927, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 1.6584, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0001978466623980609, | |
| "loss": 1.7149, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00019760174397257156, | |
| "loss": 1.6815, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0001973438054360693, | |
| "loss": 1.7067, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00019707288119765623, | |
| "loss": 1.6799, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00019678900739873226, | |
| "loss": 1.7206, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0001964922219081738, | |
| "loss": 1.6458, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00019618256431728194, | |
| "loss": 1.6649, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.00019586007593450097, | |
| "loss": 1.6684, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.000195524799779908, | |
| "loss": 1.7411, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00019517678057947384, | |
| "loss": 1.6678, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0001948160647590966, | |
| "loss": 1.6738, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00019444270043840852, | |
| "loss": 1.6804, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00019405673742435678, | |
| "loss": 1.6728, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00019365822720455916, | |
| "loss": 1.6941, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00019324722294043558, | |
| "loss": 1.6861, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00019282377946011652, | |
| "loss": 1.6751, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 1.7175, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00019193980245285966, | |
| "loss": 1.6454, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.0001914793868488021, | |
| "loss": 1.6934, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0001910067678585786, | |
| "loss": 1.6534, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00019052200852974819, | |
| "loss": 1.6797, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00019002517352939598, | |
| "loss": 1.6566, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00018951632913550626, | |
| "loss": 1.657, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 1.653587818145752, | |
| "eval_runtime": 200.2473, | |
| "eval_samples_per_second": 6.672, | |
| "eval_steps_per_second": 0.21, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 282, | |
| "num_train_epochs": 3, | |
| "save_steps": 50, | |
| "total_flos": 5.1673281053956506e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |