| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.8547008547008547, | |
| "eval_steps": 500, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008547008547008548, | |
| "grad_norm": 45.01607894897461, | |
| "learning_rate": 5e-06, | |
| "loss": 1.9033, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.017094017094017096, | |
| "grad_norm": 28.609533309936523, | |
| "learning_rate": 1e-05, | |
| "loss": 1.8163, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02564102564102564, | |
| "grad_norm": 58.36526870727539, | |
| "learning_rate": 9.89795918367347e-06, | |
| "loss": 2.5933, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03418803418803419, | |
| "grad_norm": 39.587982177734375, | |
| "learning_rate": 9.795918367346939e-06, | |
| "loss": 1.7991, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.042735042735042736, | |
| "grad_norm": 90.51757049560547, | |
| "learning_rate": 9.693877551020408e-06, | |
| "loss": 2.6511, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05128205128205128, | |
| "grad_norm": 33.15379333496094, | |
| "learning_rate": 9.591836734693878e-06, | |
| "loss": 2.0931, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.05982905982905983, | |
| "grad_norm": 45.139949798583984, | |
| "learning_rate": 9.489795918367348e-06, | |
| "loss": 2.0398, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.06837606837606838, | |
| "grad_norm": 63.17831039428711, | |
| "learning_rate": 9.387755102040818e-06, | |
| "loss": 2.0816, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.07692307692307693, | |
| "grad_norm": 24.13720703125, | |
| "learning_rate": 9.285714285714288e-06, | |
| "loss": 1.3469, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08547008547008547, | |
| "grad_norm": 130.69837951660156, | |
| "learning_rate": 9.183673469387756e-06, | |
| "loss": 1.8606, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09401709401709402, | |
| "grad_norm": 41.71373748779297, | |
| "learning_rate": 9.081632653061225e-06, | |
| "loss": 2.0109, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.10256410256410256, | |
| "grad_norm": 41.24937438964844, | |
| "learning_rate": 8.979591836734695e-06, | |
| "loss": 1.929, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1111111111111111, | |
| "grad_norm": 51.960426330566406, | |
| "learning_rate": 8.877551020408163e-06, | |
| "loss": 1.866, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.11965811965811966, | |
| "grad_norm": 42.9802360534668, | |
| "learning_rate": 8.775510204081633e-06, | |
| "loss": 1.8252, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.1282051282051282, | |
| "grad_norm": 50.58588409423828, | |
| "learning_rate": 8.673469387755103e-06, | |
| "loss": 2.1206, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.13675213675213677, | |
| "grad_norm": 98.52228546142578, | |
| "learning_rate": 8.571428571428571e-06, | |
| "loss": 2.1851, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.1452991452991453, | |
| "grad_norm": 187.91094970703125, | |
| "learning_rate": 8.469387755102042e-06, | |
| "loss": 2.2665, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.15384615384615385, | |
| "grad_norm": 44.042022705078125, | |
| "learning_rate": 8.36734693877551e-06, | |
| "loss": 2.1688, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1623931623931624, | |
| "grad_norm": 36.91716766357422, | |
| "learning_rate": 8.26530612244898e-06, | |
| "loss": 2.0421, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.17094017094017094, | |
| "grad_norm": 27.246334075927734, | |
| "learning_rate": 8.16326530612245e-06, | |
| "loss": 1.9751, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1794871794871795, | |
| "grad_norm": 32.8808479309082, | |
| "learning_rate": 8.06122448979592e-06, | |
| "loss": 2.1734, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.18803418803418803, | |
| "grad_norm": 33.08450698852539, | |
| "learning_rate": 7.959183673469388e-06, | |
| "loss": 2.3046, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.19658119658119658, | |
| "grad_norm": 34.17445373535156, | |
| "learning_rate": 7.857142857142858e-06, | |
| "loss": 2.122, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.20512820512820512, | |
| "grad_norm": 55.36966323852539, | |
| "learning_rate": 7.755102040816327e-06, | |
| "loss": 1.6824, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.21367521367521367, | |
| "grad_norm": 50.512596130371094, | |
| "learning_rate": 7.653061224489796e-06, | |
| "loss": 2.1274, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "grad_norm": 32.29758834838867, | |
| "learning_rate": 7.551020408163265e-06, | |
| "loss": 1.8956, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.23076923076923078, | |
| "grad_norm": 26.03915786743164, | |
| "learning_rate": 7.448979591836736e-06, | |
| "loss": 1.8013, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.23931623931623933, | |
| "grad_norm": 29.17389678955078, | |
| "learning_rate": 7.346938775510205e-06, | |
| "loss": 2.0998, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.24786324786324787, | |
| "grad_norm": 25.569332122802734, | |
| "learning_rate": 7.244897959183675e-06, | |
| "loss": 0.8649, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.2564102564102564, | |
| "grad_norm": 24.709575653076172, | |
| "learning_rate": 7.1428571428571436e-06, | |
| "loss": 1.4284, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.26495726495726496, | |
| "grad_norm": 40.75468063354492, | |
| "learning_rate": 7.0408163265306125e-06, | |
| "loss": 2.4333, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.27350427350427353, | |
| "grad_norm": 28.9516544342041, | |
| "learning_rate": 6.938775510204082e-06, | |
| "loss": 1.8231, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.28205128205128205, | |
| "grad_norm": 31.57037925720215, | |
| "learning_rate": 6.836734693877551e-06, | |
| "loss": 1.9139, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.2905982905982906, | |
| "grad_norm": 28.325578689575195, | |
| "learning_rate": 6.734693877551021e-06, | |
| "loss": 2.2195, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.29914529914529914, | |
| "grad_norm": 39.064449310302734, | |
| "learning_rate": 6.63265306122449e-06, | |
| "loss": 2.1197, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3076923076923077, | |
| "grad_norm": 26.608673095703125, | |
| "learning_rate": 6.530612244897959e-06, | |
| "loss": 1.6402, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.3162393162393162, | |
| "grad_norm": 24.13069725036621, | |
| "learning_rate": 6.4285714285714295e-06, | |
| "loss": 2.3671, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.3247863247863248, | |
| "grad_norm": 25.87238311767578, | |
| "learning_rate": 6.326530612244899e-06, | |
| "loss": 1.5874, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": 29.62607765197754, | |
| "learning_rate": 6.224489795918368e-06, | |
| "loss": 1.6643, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.3418803418803419, | |
| "grad_norm": 30.726987838745117, | |
| "learning_rate": 6.122448979591837e-06, | |
| "loss": 1.583, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3504273504273504, | |
| "grad_norm": 26.581026077270508, | |
| "learning_rate": 6.020408163265307e-06, | |
| "loss": 2.0036, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.358974358974359, | |
| "grad_norm": 26.827810287475586, | |
| "learning_rate": 5.918367346938776e-06, | |
| "loss": 1.4689, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.36752136752136755, | |
| "grad_norm": 25.676605224609375, | |
| "learning_rate": 5.816326530612246e-06, | |
| "loss": 1.875, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.37606837606837606, | |
| "grad_norm": 29.468841552734375, | |
| "learning_rate": 5.7142857142857145e-06, | |
| "loss": 1.5171, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.38461538461538464, | |
| "grad_norm": 23.370439529418945, | |
| "learning_rate": 5.6122448979591834e-06, | |
| "loss": 1.1047, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.39316239316239315, | |
| "grad_norm": 24.33774757385254, | |
| "learning_rate": 5.510204081632653e-06, | |
| "loss": 1.6296, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.4017094017094017, | |
| "grad_norm": 30.425437927246094, | |
| "learning_rate": 5.408163265306123e-06, | |
| "loss": 1.478, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.41025641025641024, | |
| "grad_norm": 19.86203956604004, | |
| "learning_rate": 5.306122448979593e-06, | |
| "loss": 1.846, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.4188034188034188, | |
| "grad_norm": 31.836505889892578, | |
| "learning_rate": 5.204081632653062e-06, | |
| "loss": 2.0027, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.42735042735042733, | |
| "grad_norm": 30.679075241088867, | |
| "learning_rate": 5.1020408163265315e-06, | |
| "loss": 1.6028, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4358974358974359, | |
| "grad_norm": 25.78423309326172, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2363, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 27.172372817993164, | |
| "learning_rate": 4.897959183673469e-06, | |
| "loss": 1.6288, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.452991452991453, | |
| "grad_norm": 28.951725006103516, | |
| "learning_rate": 4.795918367346939e-06, | |
| "loss": 1.8334, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.46153846153846156, | |
| "grad_norm": 46.81833267211914, | |
| "learning_rate": 4.693877551020409e-06, | |
| "loss": 1.1823, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.4700854700854701, | |
| "grad_norm": 26.226045608520508, | |
| "learning_rate": 4.591836734693878e-06, | |
| "loss": 1.8236, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.47863247863247865, | |
| "grad_norm": 22.57502555847168, | |
| "learning_rate": 4.489795918367348e-06, | |
| "loss": 1.7485, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.48717948717948717, | |
| "grad_norm": 38.75823974609375, | |
| "learning_rate": 4.3877551020408165e-06, | |
| "loss": 2.315, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.49572649572649574, | |
| "grad_norm": 30.443164825439453, | |
| "learning_rate": 4.2857142857142855e-06, | |
| "loss": 1.4465, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.5042735042735043, | |
| "grad_norm": 30.137744903564453, | |
| "learning_rate": 4.183673469387755e-06, | |
| "loss": 1.8649, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.5128205128205128, | |
| "grad_norm": 30.10780143737793, | |
| "learning_rate": 4.081632653061225e-06, | |
| "loss": 1.2203, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5213675213675214, | |
| "grad_norm": 30.356447219848633, | |
| "learning_rate": 3.979591836734694e-06, | |
| "loss": 1.5023, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.5299145299145299, | |
| "grad_norm": 23.183887481689453, | |
| "learning_rate": 3.877551020408164e-06, | |
| "loss": 2.1429, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.5384615384615384, | |
| "grad_norm": 23.465574264526367, | |
| "learning_rate": 3.7755102040816327e-06, | |
| "loss": 2.482, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.5470085470085471, | |
| "grad_norm": 27.807279586791992, | |
| "learning_rate": 3.6734693877551024e-06, | |
| "loss": 1.5094, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.5555555555555556, | |
| "grad_norm": 24.647205352783203, | |
| "learning_rate": 3.5714285714285718e-06, | |
| "loss": 1.3724, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.5641025641025641, | |
| "grad_norm": 23.685543060302734, | |
| "learning_rate": 3.469387755102041e-06, | |
| "loss": 1.5686, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.5726495726495726, | |
| "grad_norm": 44.072669982910156, | |
| "learning_rate": 3.3673469387755105e-06, | |
| "loss": 2.7541, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.5811965811965812, | |
| "grad_norm": 29.146209716796875, | |
| "learning_rate": 3.2653061224489794e-06, | |
| "loss": 1.6415, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.5897435897435898, | |
| "grad_norm": 31.696557998657227, | |
| "learning_rate": 3.1632653061224496e-06, | |
| "loss": 1.7669, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.5982905982905983, | |
| "grad_norm": 18.153284072875977, | |
| "learning_rate": 3.0612244897959185e-06, | |
| "loss": 1.763, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6068376068376068, | |
| "grad_norm": 17.51633644104004, | |
| "learning_rate": 2.959183673469388e-06, | |
| "loss": 1.7882, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": 21.281356811523438, | |
| "learning_rate": 2.8571428571428573e-06, | |
| "loss": 1.2255, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.6239316239316239, | |
| "grad_norm": 30.624502182006836, | |
| "learning_rate": 2.7551020408163266e-06, | |
| "loss": 1.2902, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.6324786324786325, | |
| "grad_norm": 32.38172149658203, | |
| "learning_rate": 2.6530612244897964e-06, | |
| "loss": 1.8834, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.6410256410256411, | |
| "grad_norm": 29.069534301757812, | |
| "learning_rate": 2.5510204081632657e-06, | |
| "loss": 1.7467, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.6495726495726496, | |
| "grad_norm": 56.46368408203125, | |
| "learning_rate": 2.4489795918367347e-06, | |
| "loss": 1.6087, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.6581196581196581, | |
| "grad_norm": 29.552095413208008, | |
| "learning_rate": 2.3469387755102044e-06, | |
| "loss": 1.4008, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 30.940513610839844, | |
| "learning_rate": 2.244897959183674e-06, | |
| "loss": 1.1384, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.6752136752136753, | |
| "grad_norm": 26.42818832397461, | |
| "learning_rate": 2.1428571428571427e-06, | |
| "loss": 1.6209, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.6837606837606838, | |
| "grad_norm": 23.604707717895508, | |
| "learning_rate": 2.0408163265306125e-06, | |
| "loss": 1.2335, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.6923076923076923, | |
| "grad_norm": 33.276771545410156, | |
| "learning_rate": 1.938775510204082e-06, | |
| "loss": 1.8955, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.7008547008547008, | |
| "grad_norm": 17.27667808532715, | |
| "learning_rate": 1.8367346938775512e-06, | |
| "loss": 1.8708, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.7094017094017094, | |
| "grad_norm": 34.4437255859375, | |
| "learning_rate": 1.7346938775510206e-06, | |
| "loss": 1.8406, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.717948717948718, | |
| "grad_norm": 27.164016723632812, | |
| "learning_rate": 1.6326530612244897e-06, | |
| "loss": 1.6318, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.7264957264957265, | |
| "grad_norm": 30.789165496826172, | |
| "learning_rate": 1.5306122448979593e-06, | |
| "loss": 2.1226, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.7350427350427351, | |
| "grad_norm": 24.16193962097168, | |
| "learning_rate": 1.4285714285714286e-06, | |
| "loss": 0.8153, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.7435897435897436, | |
| "grad_norm": 19.538379669189453, | |
| "learning_rate": 1.3265306122448982e-06, | |
| "loss": 1.9163, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.7521367521367521, | |
| "grad_norm": 26.798044204711914, | |
| "learning_rate": 1.2244897959183673e-06, | |
| "loss": 1.7253, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.7606837606837606, | |
| "grad_norm": 26.220504760742188, | |
| "learning_rate": 1.122448979591837e-06, | |
| "loss": 1.2386, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.7692307692307693, | |
| "grad_norm": 27.829275131225586, | |
| "learning_rate": 1.0204081632653063e-06, | |
| "loss": 2.0316, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.7777777777777778, | |
| "grad_norm": 19.041147232055664, | |
| "learning_rate": 9.183673469387756e-07, | |
| "loss": 1.8049, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.7863247863247863, | |
| "grad_norm": 18.105703353881836, | |
| "learning_rate": 8.163265306122449e-07, | |
| "loss": 1.5467, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.7948717948717948, | |
| "grad_norm": 25.5799560546875, | |
| "learning_rate": 7.142857142857143e-07, | |
| "loss": 1.5628, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.8034188034188035, | |
| "grad_norm": 24.031326293945312, | |
| "learning_rate": 6.122448979591837e-07, | |
| "loss": 1.8895, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.811965811965812, | |
| "grad_norm": 14.778085708618164, | |
| "learning_rate": 5.102040816326531e-07, | |
| "loss": 1.4871, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.8205128205128205, | |
| "grad_norm": 24.120147705078125, | |
| "learning_rate": 4.0816326530612243e-07, | |
| "loss": 1.507, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.8290598290598291, | |
| "grad_norm": 19.402923583984375, | |
| "learning_rate": 3.0612244897959183e-07, | |
| "loss": 1.2183, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.8376068376068376, | |
| "grad_norm": 26.27826499938965, | |
| "learning_rate": 2.0408163265306121e-07, | |
| "loss": 1.7308, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.8461538461538461, | |
| "grad_norm": 23.33223533630371, | |
| "learning_rate": 1.0204081632653061e-07, | |
| "loss": 1.3037, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.8547008547008547, | |
| "grad_norm": 24.819562911987305, | |
| "learning_rate": 0.0, | |
| "loss": 1.2484, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.8547008547008547, | |
| "step": 100, | |
| "total_flos": 2305515375820800.0, | |
| "train_loss": 1.7708107882738113, | |
| "train_runtime": 5686.4644, | |
| "train_samples_per_second": 0.018, | |
| "train_steps_per_second": 0.018 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2305515375820800.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |