| { | |
| "best_metric": 1.1750015020370483, | |
| "best_model_checkpoint": "/mnt/bn/qingyi-bn-lq/llama/saved_llamainstinwild/checkpoint-132", | |
| "epoch": 2.6921606118546846, | |
| "global_step": 132, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 1.39645254611969, | |
| "eval_runtime": 37.7333, | |
| "eval_samples_per_second": 53.004, | |
| "eval_steps_per_second": 0.848, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 1.2984137535095215, | |
| "eval_runtime": 37.7164, | |
| "eval_samples_per_second": 53.027, | |
| "eval_steps_per_second": 0.848, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 1.2540132999420166, | |
| "eval_runtime": 37.6847, | |
| "eval_samples_per_second": 53.072, | |
| "eval_steps_per_second": 0.849, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 1.2342448234558105, | |
| "eval_runtime": 37.6879, | |
| "eval_samples_per_second": 53.067, | |
| "eval_steps_per_second": 0.849, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0002664335664335664, | |
| "loss": 1.3125, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 1.2209277153015137, | |
| "eval_runtime": 37.7168, | |
| "eval_samples_per_second": 53.027, | |
| "eval_steps_per_second": 0.848, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 1.2117934226989746, | |
| "eval_runtime": 37.6897, | |
| "eval_samples_per_second": 53.065, | |
| "eval_steps_per_second": 0.849, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": 1.2057584524154663, | |
| "eval_runtime": 37.7691, | |
| "eval_samples_per_second": 52.953, | |
| "eval_steps_per_second": 0.847, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 1.2009178400039673, | |
| "eval_runtime": 37.7026, | |
| "eval_samples_per_second": 53.047, | |
| "eval_steps_per_second": 0.849, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": 1.197250485420227, | |
| "eval_runtime": 37.6765, | |
| "eval_samples_per_second": 53.084, | |
| "eval_steps_per_second": 0.849, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.00022447552447552445, | |
| "loss": 1.2095, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_loss": 1.1943359375, | |
| "eval_runtime": 37.6881, | |
| "eval_samples_per_second": 53.067, | |
| "eval_steps_per_second": 0.849, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_loss": 1.1920316219329834, | |
| "eval_runtime": 37.694, | |
| "eval_samples_per_second": 53.059, | |
| "eval_steps_per_second": 0.849, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_loss": 1.1898770332336426, | |
| "eval_runtime": 37.7089, | |
| "eval_samples_per_second": 53.038, | |
| "eval_steps_per_second": 0.849, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "eval_loss": 1.1879488229751587, | |
| "eval_runtime": 37.6975, | |
| "eval_samples_per_second": 53.054, | |
| "eval_steps_per_second": 0.849, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "eval_loss": 1.1864111423492432, | |
| "eval_runtime": 37.7188, | |
| "eval_samples_per_second": 53.024, | |
| "eval_steps_per_second": 0.848, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.00018251748251748253, | |
| "loss": 1.188, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "eval_loss": 1.1849411725997925, | |
| "eval_runtime": 37.7686, | |
| "eval_samples_per_second": 52.954, | |
| "eval_steps_per_second": 0.847, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "eval_loss": 1.1838239431381226, | |
| "eval_runtime": 37.6945, | |
| "eval_samples_per_second": 53.058, | |
| "eval_steps_per_second": 0.849, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "eval_loss": 1.182841181755066, | |
| "eval_runtime": 37.6624, | |
| "eval_samples_per_second": 53.103, | |
| "eval_steps_per_second": 0.85, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "eval_loss": 1.1818122863769531, | |
| "eval_runtime": 37.7233, | |
| "eval_samples_per_second": 53.018, | |
| "eval_steps_per_second": 0.848, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "eval_loss": 1.1808911561965942, | |
| "eval_runtime": 37.7038, | |
| "eval_samples_per_second": 53.045, | |
| "eval_steps_per_second": 0.849, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 0.00014055944055944055, | |
| "loss": 1.1876, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "eval_loss": 1.1801403760910034, | |
| "eval_runtime": 37.7277, | |
| "eval_samples_per_second": 53.011, | |
| "eval_steps_per_second": 0.848, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "eval_loss": 1.1793811321258545, | |
| "eval_runtime": 37.6641, | |
| "eval_samples_per_second": 53.101, | |
| "eval_steps_per_second": 0.85, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "eval_loss": 1.1788283586502075, | |
| "eval_runtime": 37.7097, | |
| "eval_samples_per_second": 53.037, | |
| "eval_steps_per_second": 0.849, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "eval_loss": 1.1783016920089722, | |
| "eval_runtime": 37.7104, | |
| "eval_samples_per_second": 53.036, | |
| "eval_steps_per_second": 0.849, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "eval_loss": 1.177699327468872, | |
| "eval_runtime": 37.6884, | |
| "eval_samples_per_second": 53.067, | |
| "eval_steps_per_second": 0.849, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 9.860139860139858e-05, | |
| "loss": 1.182, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "eval_loss": 1.1773412227630615, | |
| "eval_runtime": 37.7134, | |
| "eval_samples_per_second": 53.032, | |
| "eval_steps_per_second": 0.849, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "eval_loss": 1.176965594291687, | |
| "eval_runtime": 37.6735, | |
| "eval_samples_per_second": 53.088, | |
| "eval_steps_per_second": 0.849, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "eval_loss": 1.1765486001968384, | |
| "eval_runtime": 37.7771, | |
| "eval_samples_per_second": 52.942, | |
| "eval_steps_per_second": 0.847, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "eval_loss": 1.1761963367462158, | |
| "eval_runtime": 37.7211, | |
| "eval_samples_per_second": 53.021, | |
| "eval_steps_per_second": 0.848, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "eval_loss": 1.1757991313934326, | |
| "eval_runtime": 37.7438, | |
| "eval_samples_per_second": 52.989, | |
| "eval_steps_per_second": 0.848, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 5.664335664335664e-05, | |
| "loss": 1.1785, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "eval_loss": 1.1754933595657349, | |
| "eval_runtime": 37.7128, | |
| "eval_samples_per_second": 53.032, | |
| "eval_steps_per_second": 0.849, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "eval_loss": 1.1753153800964355, | |
| "eval_runtime": 37.6929, | |
| "eval_samples_per_second": 53.06, | |
| "eval_steps_per_second": 0.849, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "eval_loss": 1.1751618385314941, | |
| "eval_runtime": 37.6913, | |
| "eval_samples_per_second": 53.063, | |
| "eval_steps_per_second": 0.849, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "eval_loss": 1.1750015020370483, | |
| "eval_runtime": 37.7589, | |
| "eval_samples_per_second": 52.968, | |
| "eval_steps_per_second": 0.847, | |
| "step": 132 | |
| } | |
| ], | |
| "max_steps": 147, | |
| "num_train_epochs": 3, | |
| "total_flos": 1.5383482920421294e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |