| { | |
| "best_metric": 1.570174217224121, | |
| "best_model_checkpoint": "./pippa-sharegpt-13b-qlora/checkpoint-100", | |
| "epoch": 0.6756756756756757, | |
| "eval_steps": 50, | |
| "global_step": 100, | |
| "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": 2.0773, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4e-05, | |
| "loss": 2.0879, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 6e-05, | |
| "loss": 2.0647, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 8e-05, | |
| "loss": 1.9962, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0001, | |
| "loss": 1.9106, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00012, | |
| "loss": 1.8651, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00014, | |
| "loss": 1.8169, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00016, | |
| "loss": 1.8535, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00018, | |
| "loss": 1.8226, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7774, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019999738007780348, | |
| "loss": 1.7297, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019998952044849376, | |
| "loss": 1.7607, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00019997642152390314, | |
| "loss": 1.7323, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00019995808399039496, | |
| "loss": 1.6993, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00019993450880882735, | |
| "loss": 1.7053, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00019990569721450326, | |
| "loss": 1.7207, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00019987165071710527, | |
| "loss": 1.667, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00019983237110061697, | |
| "loss": 1.7375, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0001997878604232291, | |
| "loss": 1.725, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00019973812101723188, | |
| "loss": 1.658, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0001996831554888928, | |
| "loss": 1.6804, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00019962296671832003, | |
| "loss": 1.7273, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00019955755785931145, | |
| "loss": 1.6712, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00019948693233918952, | |
| "loss": 1.6261, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0001994110938586216, | |
| "loss": 1.673, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00019933004639142605, | |
| "loss": 1.6796, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00019924379418436404, | |
| "loss": 1.6701, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.000199152341756917, | |
| "loss": 1.6619, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00019905569390104986, | |
| "loss": 1.6282, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00019895385568095982, | |
| "loss": 1.7152, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00019884683243281116, | |
| "loss": 1.6431, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00019873462976445553, | |
| "loss": 1.7584, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00019861725355513823, | |
| "loss": 1.6342, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00019849470995518992, | |
| "loss": 1.652, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00019836700538570457, | |
| "loss": 1.6472, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0001982341465382029, | |
| "loss": 1.6961, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00019809614037428176, | |
| "loss": 1.6556, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00019795299412524945, | |
| "loss": 1.6386, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00019780471529174664, | |
| "loss": 1.6692, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00019765131164335345, | |
| "loss": 1.5955, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00019749279121818235, | |
| "loss": 1.6292, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.000197329162322457, | |
| "loss": 1.648, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00019716043353007693, | |
| "loss": 1.7011, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00019698661368216817, | |
| "loss": 1.6319, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00019680771188662044, | |
| "loss": 1.6143, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00019662373751760934, | |
| "loss": 1.6526, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0001964347002151056, | |
| "loss": 1.5946, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00019624060988436966, | |
| "loss": 1.6474, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00019604147669543282, | |
| "loss": 1.6756, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0001958373110825644, | |
| "loss": 1.6447, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 1.6321444511413574, | |
| "eval_runtime": 311.9756, | |
| "eval_samples_per_second": 4.795, | |
| "eval_steps_per_second": 1.199, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00019562812374372473, | |
| "loss": 1.6902, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00019541392564000488, | |
| "loss": 1.6152, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0001951947279950522, | |
| "loss": 1.631, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00019497054229448223, | |
| "loss": 1.6445, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.00019474138028527675, | |
| "loss": 1.6278, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0001945072539751685, | |
| "loss": 1.6202, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00019426817563201177, | |
| "loss": 1.6196, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00019402415778313977, | |
| "loss": 1.6062, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00019377521321470805, | |
| "loss": 1.5883, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00019352135497102463, | |
| "loss": 1.6769, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00019326259635386644, | |
| "loss": 1.6134, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.0001929989509217824, | |
| "loss": 1.5884, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00019273043248938288, | |
| "loss": 1.6232, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.0001924570551266159, | |
| "loss": 1.6303, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00019217883315802991, | |
| "loss": 1.6585, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00019189578116202307, | |
| "loss": 1.6264, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00019160791397007957, | |
| "loss": 1.5944, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00019131524666599233, | |
| "loss": 1.6371, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00019101779458507263, | |
| "loss": 1.592, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00019071557331334669, | |
| "loss": 1.6369, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00019040859868673887, | |
| "loss": 1.6355, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.0001900968867902419, | |
| "loss": 1.6435, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00018978045395707418, | |
| "loss": 1.6074, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00018945931676782373, | |
| "loss": 1.5909, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0001891334920495795, | |
| "loss": 1.6151, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0001888029968750498, | |
| "loss": 1.5976, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.0001884678485616675, | |
| "loss": 1.5716, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00018812806467068268, | |
| "loss": 1.5879, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00018778366300624245, | |
| "loss": 1.5664, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.00018743466161445823, | |
| "loss": 1.6096, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00018708107878245977, | |
| "loss": 1.603, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00018672293303743738, | |
| "loss": 1.6123, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.00018636024314567067, | |
| "loss": 1.6197, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.00018599302811154572, | |
| "loss": 1.5905, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.00018562130717655878, | |
| "loss": 1.6175, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.00018524509981830852, | |
| "loss": 1.5753, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00018486442574947511, | |
| "loss": 1.6248, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00018447930491678733, | |
| "loss": 1.5616, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00018408975749997759, | |
| "loss": 1.596, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00018369580391072433, | |
| "loss": 1.5591, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00018329746479158265, | |
| "loss": 1.6116, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00018289476101490256, | |
| "loss": 1.5883, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00018248771368173524, | |
| "loss": 1.6456, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00018207634412072764, | |
| "loss": 1.5663, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.0001816606738870046, | |
| "loss": 1.6058, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00018124072476103956, | |
| "loss": 1.5659, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00018081651874751327, | |
| "loss": 1.5531, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00018038807807416068, | |
| "loss": 1.5899, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00017995542519060647, | |
| "loss": 1.5176, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.00017951858276718844, | |
| "loss": 1.6243, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 1.570174217224121, | |
| "eval_runtime": 311.9281, | |
| "eval_samples_per_second": 4.796, | |
| "eval_steps_per_second": 1.199, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 444, | |
| "num_train_epochs": 3, | |
| "save_steps": 50, | |
| "total_flos": 7.922919280261202e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |