| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 117, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008547008547008548, | |
| "grad_norm": 0.475104957818985, | |
| "learning_rate": 2e-05, | |
| "loss": 0.9491, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.017094017094017096, | |
| "grad_norm": 0.3602507710456848, | |
| "learning_rate": 4e-05, | |
| "loss": 0.7401, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02564102564102564, | |
| "grad_norm": 0.49503466486930847, | |
| "learning_rate": 6e-05, | |
| "loss": 0.9861, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03418803418803419, | |
| "grad_norm": 0.3425951898097992, | |
| "learning_rate": 8e-05, | |
| "loss": 1.3363, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.042735042735042736, | |
| "grad_norm": 0.5006900429725647, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8529, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05128205128205128, | |
| "grad_norm": 0.414726585149765, | |
| "learning_rate": 0.00012, | |
| "loss": 1.2524, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.05982905982905983, | |
| "grad_norm": 0.3771184980869293, | |
| "learning_rate": 0.00014, | |
| "loss": 0.8486, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.06837606837606838, | |
| "grad_norm": 0.3893500566482544, | |
| "learning_rate": 0.00016, | |
| "loss": 0.8931, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.07692307692307693, | |
| "grad_norm": 0.33733996748924255, | |
| "learning_rate": 0.00018, | |
| "loss": 0.7253, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08547008547008547, | |
| "grad_norm": 0.6951685547828674, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9938, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09401709401709402, | |
| "grad_norm": 0.6600769758224487, | |
| "learning_rate": 0.0001999976474595967, | |
| "loss": 0.9379, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.10256410256410256, | |
| "grad_norm": 0.3751288056373596, | |
| "learning_rate": 0.00019999058994907564, | |
| "loss": 0.7716, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1111111111111111, | |
| "grad_norm": 0.4716266393661499, | |
| "learning_rate": 0.00019997882780049847, | |
| "loss": 0.8637, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.11965811965811966, | |
| "grad_norm": 0.5008829832077026, | |
| "learning_rate": 0.0001999623615672837, | |
| "loss": 0.9545, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.1282051282051282, | |
| "grad_norm": 0.46447134017944336, | |
| "learning_rate": 0.00019994119202418098, | |
| "loss": 1.0945, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.13675213675213677, | |
| "grad_norm": 0.5583352446556091, | |
| "learning_rate": 0.00019991532016723439, | |
| "loss": 0.7752, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.1452991452991453, | |
| "grad_norm": 0.4787881076335907, | |
| "learning_rate": 0.00019988474721373568, | |
| "loss": 1.1693, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.15384615384615385, | |
| "grad_norm": 0.4033676087856293, | |
| "learning_rate": 0.00019984947460216707, | |
| "loss": 0.6522, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1623931623931624, | |
| "grad_norm": 0.5240854620933533, | |
| "learning_rate": 0.00019980950399213344, | |
| "loss": 0.7717, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.17094017094017094, | |
| "grad_norm": 0.41608908772468567, | |
| "learning_rate": 0.00019976483726428422, | |
| "loss": 0.6719, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1794871794871795, | |
| "grad_norm": 0.48278939723968506, | |
| "learning_rate": 0.0001997154765202251, | |
| "loss": 0.6905, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.18803418803418803, | |
| "grad_norm": 0.445468544960022, | |
| "learning_rate": 0.00019966142408241901, | |
| "loss": 0.7572, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.19658119658119658, | |
| "grad_norm": 0.4958309233188629, | |
| "learning_rate": 0.00019960268249407675, | |
| "loss": 0.8273, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.20512820512820512, | |
| "grad_norm": 0.46474188566207886, | |
| "learning_rate": 0.00019953925451903756, | |
| "loss": 0.776, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.21367521367521367, | |
| "grad_norm": 0.3750772774219513, | |
| "learning_rate": 0.0001994711431416389, | |
| "loss": 1.4004, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "grad_norm": 0.4821198284626007, | |
| "learning_rate": 0.00019939835156657616, | |
| "loss": 1.2073, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.23076923076923078, | |
| "grad_norm": 0.5062704682350159, | |
| "learning_rate": 0.00019932088321875172, | |
| "loss": 0.7346, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.23931623931623933, | |
| "grad_norm": 0.5169610977172852, | |
| "learning_rate": 0.00019923874174311394, | |
| "loss": 0.6212, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.24786324786324787, | |
| "grad_norm": 0.4412098526954651, | |
| "learning_rate": 0.0001991519310044857, | |
| "loss": 1.0973, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.2564102564102564, | |
| "grad_norm": 0.49315598607063293, | |
| "learning_rate": 0.00019906045508738228, | |
| "loss": 0.9767, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.26495726495726496, | |
| "grad_norm": 0.4327487647533417, | |
| "learning_rate": 0.0001989643182958196, | |
| "loss": 0.682, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.27350427350427353, | |
| "grad_norm": 0.45163172483444214, | |
| "learning_rate": 0.00019886352515311134, | |
| "loss": 0.7315, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.28205128205128205, | |
| "grad_norm": 0.45258256793022156, | |
| "learning_rate": 0.0001987580804016563, | |
| "loss": 0.9502, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.2905982905982906, | |
| "grad_norm": 0.4901167154312134, | |
| "learning_rate": 0.00019864798900271532, | |
| "loss": 0.8431, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.29914529914529914, | |
| "grad_norm": 0.4742427170276642, | |
| "learning_rate": 0.0001985332561361776, | |
| "loss": 0.658, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3076923076923077, | |
| "grad_norm": 0.4435608983039856, | |
| "learning_rate": 0.00019841388720031727, | |
| "loss": 0.6167, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.3162393162393162, | |
| "grad_norm": 0.49269428849220276, | |
| "learning_rate": 0.00019828988781153917, | |
| "loss": 0.7105, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.3247863247863248, | |
| "grad_norm": 0.47239962220191956, | |
| "learning_rate": 0.00019816126380411476, | |
| "loss": 0.7264, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": 0.4605489671230316, | |
| "learning_rate": 0.00019802802122990758, | |
| "loss": 0.744, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.3418803418803419, | |
| "grad_norm": 0.5027369260787964, | |
| "learning_rate": 0.00019789016635808837, | |
| "loss": 0.7997, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3504273504273504, | |
| "grad_norm": 0.4595533311367035, | |
| "learning_rate": 0.00019774770567484022, | |
| "loss": 0.9184, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.358974358974359, | |
| "grad_norm": 0.4321463108062744, | |
| "learning_rate": 0.00019760064588305345, | |
| "loss": 0.6633, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.36752136752136755, | |
| "grad_norm": 0.4019186198711395, | |
| "learning_rate": 0.00019744899390201006, | |
| "loss": 0.7046, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.37606837606837606, | |
| "grad_norm": 0.4053269326686859, | |
| "learning_rate": 0.0001972927568670583, | |
| "loss": 1.0849, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.38461538461538464, | |
| "grad_norm": 0.4526562988758087, | |
| "learning_rate": 0.00019713194212927696, | |
| "loss": 0.7877, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.39316239316239315, | |
| "grad_norm": 0.47216200828552246, | |
| "learning_rate": 0.00019696655725512933, | |
| "loss": 0.7337, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.4017094017094017, | |
| "grad_norm": 0.469186395406723, | |
| "learning_rate": 0.00019679661002610743, | |
| "loss": 0.8048, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.41025641025641024, | |
| "grad_norm": 0.40787142515182495, | |
| "learning_rate": 0.00019662210843836574, | |
| "loss": 0.7041, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.4188034188034188, | |
| "grad_norm": 0.4881182610988617, | |
| "learning_rate": 0.0001964430607023449, | |
| "loss": 0.7163, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.42735042735042733, | |
| "grad_norm": 0.5976874828338623, | |
| "learning_rate": 0.00019625947524238563, | |
| "loss": 1.0021, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4358974358974359, | |
| "grad_norm": 0.49746468663215637, | |
| "learning_rate": 0.00019607136069633212, | |
| "loss": 0.6709, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 0.43088001012802124, | |
| "learning_rate": 0.0001958787259151258, | |
| "loss": 0.6773, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.452991452991453, | |
| "grad_norm": 0.5117547512054443, | |
| "learning_rate": 0.00019568157996238884, | |
| "loss": 0.6801, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.46153846153846156, | |
| "grad_norm": 0.39666032791137695, | |
| "learning_rate": 0.0001954799321139975, | |
| "loss": 0.9736, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.4700854700854701, | |
| "grad_norm": 0.4586123526096344, | |
| "learning_rate": 0.00019527379185764612, | |
| "loss": 0.6431, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.47863247863247865, | |
| "grad_norm": 0.5679425001144409, | |
| "learning_rate": 0.00019506316889240027, | |
| "loss": 1.1387, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.48717948717948717, | |
| "grad_norm": 0.4713611304759979, | |
| "learning_rate": 0.00019484807312824067, | |
| "loss": 0.5671, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.49572649572649574, | |
| "grad_norm": 0.5581649541854858, | |
| "learning_rate": 0.0001946285146855968, | |
| "loss": 0.7273, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.5042735042735043, | |
| "grad_norm": 0.4809207320213318, | |
| "learning_rate": 0.0001944045038948709, | |
| "loss": 0.7237, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.5128205128205128, | |
| "grad_norm": 0.4750754237174988, | |
| "learning_rate": 0.00019417605129595157, | |
| "loss": 0.6509, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5213675213675214, | |
| "grad_norm": 0.4904468059539795, | |
| "learning_rate": 0.0001939431676377183, | |
| "loss": 0.6897, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.5299145299145299, | |
| "grad_norm": 0.4743252396583557, | |
| "learning_rate": 0.0001937058638775353, | |
| "loss": 0.6232, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.5384615384615384, | |
| "grad_norm": 0.38650548458099365, | |
| "learning_rate": 0.00019346415118073632, | |
| "loss": 1.2282, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.5470085470085471, | |
| "grad_norm": 0.5221203565597534, | |
| "learning_rate": 0.00019321804092009906, | |
| "loss": 0.6979, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.5555555555555556, | |
| "grad_norm": 0.4398798644542694, | |
| "learning_rate": 0.00019296754467531014, | |
| "loss": 0.6671, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.5641025641025641, | |
| "grad_norm": 0.5590323209762573, | |
| "learning_rate": 0.00019271267423242024, | |
| "loss": 0.6642, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.5726495726495726, | |
| "grad_norm": 0.512601912021637, | |
| "learning_rate": 0.00019245344158328972, | |
| "loss": 0.7476, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.5811965811965812, | |
| "grad_norm": 0.49666309356689453, | |
| "learning_rate": 0.0001921898589250242, | |
| "loss": 0.6581, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.5897435897435898, | |
| "grad_norm": 0.48546653985977173, | |
| "learning_rate": 0.0001919219386594007, | |
| "loss": 0.7066, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.5982905982905983, | |
| "grad_norm": 0.46102452278137207, | |
| "learning_rate": 0.00019164969339228422, | |
| "loss": 0.7214, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6068376068376068, | |
| "grad_norm": 0.5350074768066406, | |
| "learning_rate": 0.00019137313593303463, | |
| "loss": 0.7814, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": 0.4764799177646637, | |
| "learning_rate": 0.00019109227929390378, | |
| "loss": 1.3498, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.6239316239316239, | |
| "grad_norm": 0.4472093880176544, | |
| "learning_rate": 0.00019080713668942356, | |
| "loss": 0.6558, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.6324786324786325, | |
| "grad_norm": 0.4892171025276184, | |
| "learning_rate": 0.00019051772153578389, | |
| "loss": 0.663, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.6410256410256411, | |
| "grad_norm": 0.46784690022468567, | |
| "learning_rate": 0.00019022404745020163, | |
| "loss": 0.6452, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.6495726495726496, | |
| "grad_norm": 0.4115755558013916, | |
| "learning_rate": 0.00018992612825027976, | |
| "loss": 0.6968, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.6581196581196581, | |
| "grad_norm": 0.5248686075210571, | |
| "learning_rate": 0.0001896239779533575, | |
| "loss": 0.8097, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 0.4202110171318054, | |
| "learning_rate": 0.00018931761077585035, | |
| "loss": 0.6617, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.6752136752136753, | |
| "grad_norm": 0.418204128742218, | |
| "learning_rate": 0.00018900704113258165, | |
| "loss": 0.6448, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.6837606837606838, | |
| "grad_norm": 0.43573886156082153, | |
| "learning_rate": 0.00018869228363610404, | |
| "loss": 0.6327, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.6923076923076923, | |
| "grad_norm": 0.48871275782585144, | |
| "learning_rate": 0.00018837335309601213, | |
| "loss": 0.7072, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.7008547008547008, | |
| "grad_norm": 0.4110111892223358, | |
| "learning_rate": 0.00018805026451824546, | |
| "loss": 1.2326, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.7094017094017094, | |
| "grad_norm": 0.40106821060180664, | |
| "learning_rate": 0.00018772303310438275, | |
| "loss": 1.1263, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.717948717948718, | |
| "grad_norm": 0.4688105583190918, | |
| "learning_rate": 0.00018739167425092644, | |
| "loss": 1.1007, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.7264957264957265, | |
| "grad_norm": 0.4649762809276581, | |
| "learning_rate": 0.00018705620354857833, | |
| "loss": 0.5994, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.7350427350427351, | |
| "grad_norm": 0.46150311827659607, | |
| "learning_rate": 0.00018671663678150607, | |
| "loss": 0.5989, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.7435897435897436, | |
| "grad_norm": 0.46822255849838257, | |
| "learning_rate": 0.0001863729899266004, | |
| "loss": 0.6286, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.7521367521367521, | |
| "grad_norm": 0.5017993450164795, | |
| "learning_rate": 0.0001860252791527236, | |
| "loss": 1.0247, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.7606837606837606, | |
| "grad_norm": 0.3973097801208496, | |
| "learning_rate": 0.00018567352081994852, | |
| "loss": 1.1795, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.7692307692307693, | |
| "grad_norm": 0.410843163728714, | |
| "learning_rate": 0.00018531773147878895, | |
| "loss": 1.0421, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.7777777777777778, | |
| "grad_norm": 0.4612373113632202, | |
| "learning_rate": 0.0001849579278694209, | |
| "loss": 0.6935, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.7863247863247863, | |
| "grad_norm": 0.46664804220199585, | |
| "learning_rate": 0.00018459412692089494, | |
| "loss": 0.6416, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.7948717948717948, | |
| "grad_norm": 0.4491286277770996, | |
| "learning_rate": 0.0001842263457503397, | |
| "loss": 0.5875, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.8034188034188035, | |
| "grad_norm": 0.5161553621292114, | |
| "learning_rate": 0.00018385460166215638, | |
| "loss": 0.8172, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.811965811965812, | |
| "grad_norm": 0.500079870223999, | |
| "learning_rate": 0.00018347891214720477, | |
| "loss": 0.6465, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.8205128205128205, | |
| "grad_norm": 0.3862932622432709, | |
| "learning_rate": 0.00018309929488198012, | |
| "loss": 1.1162, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.8290598290598291, | |
| "grad_norm": 0.44776979088783264, | |
| "learning_rate": 0.00018271576772778154, | |
| "loss": 0.6599, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.8376068376068376, | |
| "grad_norm": 0.4439445734024048, | |
| "learning_rate": 0.00018232834872987147, | |
| "loss": 1.1616, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.8461538461538461, | |
| "grad_norm": 0.491223007440567, | |
| "learning_rate": 0.00018193705611662696, | |
| "loss": 0.7391, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.8547008547008547, | |
| "grad_norm": 0.5422267913818359, | |
| "learning_rate": 0.0001815419082986815, | |
| "loss": 0.7363, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.8632478632478633, | |
| "grad_norm": 0.4128502905368805, | |
| "learning_rate": 0.00018114292386805936, | |
| "loss": 1.0206, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.8717948717948718, | |
| "grad_norm": 0.3821941316127777, | |
| "learning_rate": 0.00018074012159730032, | |
| "loss": 1.1002, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.8803418803418803, | |
| "grad_norm": 0.46259158849716187, | |
| "learning_rate": 0.00018033352043857675, | |
| "loss": 0.9668, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 0.42356961965560913, | |
| "learning_rate": 0.00017992313952280172, | |
| "loss": 1.0531, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.8974358974358975, | |
| "grad_norm": 0.45854252576828003, | |
| "learning_rate": 0.00017950899815872892, | |
| "loss": 1.1803, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.905982905982906, | |
| "grad_norm": 0.5974142551422119, | |
| "learning_rate": 0.00017909111583204422, | |
| "loss": 1.0416, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.9145299145299145, | |
| "grad_norm": 0.6633700728416443, | |
| "learning_rate": 0.0001786695122044487, | |
| "loss": 0.8394, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.9230769230769231, | |
| "grad_norm": 0.4408910274505615, | |
| "learning_rate": 0.0001782442071127338, | |
| "loss": 1.0641, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.9316239316239316, | |
| "grad_norm": 0.6098408699035645, | |
| "learning_rate": 0.0001778152205678477, | |
| "loss": 1.0964, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.9401709401709402, | |
| "grad_norm": 0.5177589654922485, | |
| "learning_rate": 0.00017738257275395404, | |
| "loss": 0.767, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.9487179487179487, | |
| "grad_norm": 0.46795642375946045, | |
| "learning_rate": 0.00017694628402748202, | |
| "loss": 0.6871, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.9572649572649573, | |
| "grad_norm": 0.5054307579994202, | |
| "learning_rate": 0.0001765063749161688, | |
| "loss": 0.7332, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.9658119658119658, | |
| "grad_norm": 0.4986553490161896, | |
| "learning_rate": 0.00017606286611809353, | |
| "loss": 0.7099, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.9743589743589743, | |
| "grad_norm": 0.5066249966621399, | |
| "learning_rate": 0.00017561577850070355, | |
| "loss": 0.8318, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.9829059829059829, | |
| "grad_norm": 0.4113486707210541, | |
| "learning_rate": 0.00017516513309983253, | |
| "loss": 0.6118, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.9914529914529915, | |
| "grad_norm": 0.5578283667564392, | |
| "learning_rate": 0.00017471095111871074, | |
| "loss": 0.7386, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.4336143732070923, | |
| "learning_rate": 0.0001742532539269674, | |
| "loss": 0.631, | |
| "step": 117 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 468, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 117, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.223421236707328e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |