| { | |
| "best_metric": 1.5729879140853882, | |
| "best_model_checkpoint": "./lora-outB/checkpoint-50", | |
| "epoch": 1.4970059880239521, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 1.866, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 1.7383, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 6e-06, | |
| "loss": 1.8306, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 1.9213, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1e-05, | |
| "loss": 1.9524, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.2e-05, | |
| "loss": 1.7308, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.4e-05, | |
| "loss": 1.7334, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 1.6749, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.8e-05, | |
| "loss": 1.805, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 2e-05, | |
| "loss": 1.778, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.9997946042345128e-05, | |
| "loss": 1.7804, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.9991785013128922e-05, | |
| "loss": 1.8191, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.998151944325001e-05, | |
| "loss": 1.7089, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.996715354971755e-05, | |
| "loss": 1.7131, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.994869323391895e-05, | |
| "loss": 1.917, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.9926146079195597e-05, | |
| "loss": 1.6701, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1.989952134772769e-05, | |
| "loss": 1.7119, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 1.9868829976729444e-05, | |
| "loss": 1.7037, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 1.983408457395613e-05, | |
| "loss": 1.7314, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 1.9795299412524948e-05, | |
| "loss": 1.6771, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1.975249042505174e-05, | |
| "loss": 1.6734, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1.970567519710602e-05, | |
| "loss": 1.689, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.9654872959986936e-05, | |
| "loss": 1.7452, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.960010458282326e-05, | |
| "loss": 1.7126, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.954139256400049e-05, | |
| "loss": 1.5629, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 1.6511253118515015, | |
| "eval_runtime": 5.4427, | |
| "eval_samples_per_second": 5.145, | |
| "eval_steps_per_second": 0.735, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.947876102191873e-05, | |
| "loss": 1.6948, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.9412235685085034e-05, | |
| "loss": 1.5969, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1.9341843881544372e-05, | |
| "loss": 1.5367, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 1.926761452765349e-05, | |
| "loss": 1.463, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 1.918957811620231e-05, | |
| "loss": 1.4575, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.9107766703887764e-05, | |
| "loss": 1.5928, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.9022213898145176e-05, | |
| "loss": 1.5604, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 1.893295484334259e-05, | |
| "loss": 1.6508, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 1.8840026206343786e-05, | |
| "loss": 1.4583, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 1.8743466161445823e-05, | |
| "loss": 1.7124, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 1.8643314374697377e-05, | |
| "loss": 1.462, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 1.853961198760426e-05, | |
| "loss": 1.6664, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 1.8432401600228823e-05, | |
| "loss": 1.6264, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 1.832172725369024e-05, | |
| "loss": 1.6704, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 1.8207634412072765e-05, | |
| "loss": 1.5221, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 1.8090169943749477e-05, | |
| "loss": 1.5411, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 1.7969382102129153e-05, | |
| "loss": 1.4493, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 1.7845320505834176e-05, | |
| "loss": 1.4783, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 1.771803611831762e-05, | |
| "loss": 1.5882, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 1.758758122692791e-05, | |
| "loss": 1.5848, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 1.74540094214296e-05, | |
| "loss": 1.4439, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 1.7317375571989158e-05, | |
| "loss": 1.5398, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 1.717773580663479e-05, | |
| "loss": 1.3689, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 1.703514748819948e-05, | |
| "loss": 1.5311, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 1.688966919075687e-05, | |
| "loss": 1.5253, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "eval_loss": 1.5729879140853882, | |
| "eval_runtime": 5.4053, | |
| "eval_samples_per_second": 5.18, | |
| "eval_steps_per_second": 0.74, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 165, | |
| "num_train_epochs": 5, | |
| "save_steps": 50, | |
| "total_flos": 5.618042316364186e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |