| { | |
| "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": 0.6336084008216858, | |
| "learning_rate": 2e-05, | |
| "loss": 1.2928, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.017094017094017096, | |
| "grad_norm": 0.6126894950866699, | |
| "learning_rate": 4e-05, | |
| "loss": 1.1179, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02564102564102564, | |
| "grad_norm": 0.6590365171432495, | |
| "learning_rate": 6e-05, | |
| "loss": 1.2546, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03418803418803419, | |
| "grad_norm": 0.3842516839504242, | |
| "learning_rate": 8e-05, | |
| "loss": 1.402, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.042735042735042736, | |
| "grad_norm": 0.7100726962089539, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1523, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05128205128205128, | |
| "grad_norm": 0.4285312592983246, | |
| "learning_rate": 0.00012, | |
| "loss": 1.4567, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.05982905982905983, | |
| "grad_norm": 0.5057687163352966, | |
| "learning_rate": 0.00014, | |
| "loss": 1.2153, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.06837606837606838, | |
| "grad_norm": 0.3327566683292389, | |
| "learning_rate": 0.00016, | |
| "loss": 1.1503, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.07692307692307693, | |
| "grad_norm": 0.29217734932899475, | |
| "learning_rate": 0.00018, | |
| "loss": 0.9723, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08547008547008547, | |
| "grad_norm": 0.5076949000358582, | |
| "learning_rate": 0.0002, | |
| "loss": 1.5848, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09401709401709402, | |
| "grad_norm": 0.40562769770622253, | |
| "learning_rate": 0.0001999976474595967, | |
| "loss": 1.3397, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.10256410256410256, | |
| "grad_norm": 0.33129796385765076, | |
| "learning_rate": 0.00019999058994907564, | |
| "loss": 1.0107, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1111111111111111, | |
| "grad_norm": 0.39453431963920593, | |
| "learning_rate": 0.00019997882780049847, | |
| "loss": 1.1293, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.11965811965811966, | |
| "grad_norm": 0.3235519826412201, | |
| "learning_rate": 0.0001999623615672837, | |
| "loss": 1.259, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.1282051282051282, | |
| "grad_norm": 0.2598688006401062, | |
| "learning_rate": 0.00019994119202418098, | |
| "loss": 1.2164, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.13675213675213677, | |
| "grad_norm": 0.2793278992176056, | |
| "learning_rate": 0.00019991532016723439, | |
| "loss": 1.0104, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.1452991452991453, | |
| "grad_norm": 0.24649402499198914, | |
| "learning_rate": 0.00019988474721373568, | |
| "loss": 1.2559, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.15384615384615385, | |
| "grad_norm": 0.23192395269870758, | |
| "learning_rate": 0.00019984947460216707, | |
| "loss": 0.8831, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1623931623931624, | |
| "grad_norm": 0.2821623384952545, | |
| "learning_rate": 0.00019980950399213344, | |
| "loss": 0.9643, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.17094017094017094, | |
| "grad_norm": 0.2398855984210968, | |
| "learning_rate": 0.00019976483726428422, | |
| "loss": 0.9148, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1794871794871795, | |
| "grad_norm": 0.2592308819293976, | |
| "learning_rate": 0.0001997154765202251, | |
| "loss": 0.8939, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.18803418803418803, | |
| "grad_norm": 0.25392013788223267, | |
| "learning_rate": 0.00019966142408241901, | |
| "loss": 0.9752, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.19658119658119658, | |
| "grad_norm": 0.2928493022918701, | |
| "learning_rate": 0.00019960268249407675, | |
| "loss": 1.0981, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.20512820512820512, | |
| "grad_norm": 0.2692890763282776, | |
| "learning_rate": 0.00019953925451903756, | |
| "loss": 0.9699, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.21367521367521367, | |
| "grad_norm": 0.23414169251918793, | |
| "learning_rate": 0.0001994711431416389, | |
| "loss": 1.3802, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "grad_norm": 0.32594603300094604, | |
| "learning_rate": 0.00019939835156657616, | |
| "loss": 1.3705, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.23076923076923078, | |
| "grad_norm": 0.27903756499290466, | |
| "learning_rate": 0.00019932088321875172, | |
| "loss": 0.9765, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.23931623931623933, | |
| "grad_norm": 0.27631697058677673, | |
| "learning_rate": 0.00019923874174311394, | |
| "loss": 0.7924, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.24786324786324787, | |
| "grad_norm": 0.28414595127105713, | |
| "learning_rate": 0.0001991519310044857, | |
| "loss": 1.2446, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.2564102564102564, | |
| "grad_norm": 0.280527800321579, | |
| "learning_rate": 0.00019906045508738228, | |
| "loss": 1.1986, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.26495726495726496, | |
| "grad_norm": 0.25973978638648987, | |
| "learning_rate": 0.0001989643182958196, | |
| "loss": 0.9276, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.27350427350427353, | |
| "grad_norm": 0.2691807448863983, | |
| "learning_rate": 0.00019886352515311134, | |
| "loss": 0.9007, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.28205128205128205, | |
| "grad_norm": 0.260856032371521, | |
| "learning_rate": 0.0001987580804016563, | |
| "loss": 1.1973, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.2905982905982906, | |
| "grad_norm": 0.28188374638557434, | |
| "learning_rate": 0.00019864798900271532, | |
| "loss": 1.1079, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.29914529914529914, | |
| "grad_norm": 0.25889885425567627, | |
| "learning_rate": 0.0001985332561361776, | |
| "loss": 0.8755, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3076923076923077, | |
| "grad_norm": 0.2496309131383896, | |
| "learning_rate": 0.00019841388720031727, | |
| "loss": 0.8361, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.3162393162393162, | |
| "grad_norm": 0.276593416929245, | |
| "learning_rate": 0.00019828988781153917, | |
| "loss": 0.9342, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.3247863247863248, | |
| "grad_norm": 0.24598534405231476, | |
| "learning_rate": 0.00019816126380411476, | |
| "loss": 0.9002, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": 0.25998443365097046, | |
| "learning_rate": 0.00019802802122990758, | |
| "loss": 1.0115, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.3418803418803419, | |
| "grad_norm": 0.2910752594470978, | |
| "learning_rate": 0.00019789016635808837, | |
| "loss": 1.1122, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3504273504273504, | |
| "grad_norm": 0.23144645988941193, | |
| "learning_rate": 0.00019774770567484022, | |
| "loss": 1.0541, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.358974358974359, | |
| "grad_norm": 0.23637208342552185, | |
| "learning_rate": 0.00019760064588305345, | |
| "loss": 0.9, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.36752136752136755, | |
| "grad_norm": 0.24016380310058594, | |
| "learning_rate": 0.00019744899390201006, | |
| "loss": 0.9473, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.37606837606837606, | |
| "grad_norm": 0.23975665867328644, | |
| "learning_rate": 0.0001972927568670583, | |
| "loss": 1.361, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.38461538461538464, | |
| "grad_norm": 0.2693803310394287, | |
| "learning_rate": 0.00019713194212927696, | |
| "loss": 1.1029, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.39316239316239315, | |
| "grad_norm": 0.2764308452606201, | |
| "learning_rate": 0.00019696655725512933, | |
| "loss": 0.9312, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.4017094017094017, | |
| "grad_norm": 0.25453776121139526, | |
| "learning_rate": 0.00019679661002610743, | |
| "loss": 0.9677, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.41025641025641024, | |
| "grad_norm": 0.26758676767349243, | |
| "learning_rate": 0.00019662210843836574, | |
| "loss": 0.9591, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.4188034188034188, | |
| "grad_norm": 0.27530986070632935, | |
| "learning_rate": 0.0001964430607023449, | |
| "loss": 0.9504, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.42735042735042733, | |
| "grad_norm": 0.2969217896461487, | |
| "learning_rate": 0.00019625947524238563, | |
| "loss": 1.11, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4358974358974359, | |
| "grad_norm": 0.26885175704956055, | |
| "learning_rate": 0.00019607136069633212, | |
| "loss": 0.8923, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 0.255889892578125, | |
| "learning_rate": 0.0001958787259151258, | |
| "loss": 0.9118, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.452991452991453, | |
| "grad_norm": 0.2702856659889221, | |
| "learning_rate": 0.00019568157996238884, | |
| "loss": 0.9143, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.46153846153846156, | |
| "grad_norm": 0.2267722338438034, | |
| "learning_rate": 0.0001954799321139975, | |
| "loss": 1.1196, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.4700854700854701, | |
| "grad_norm": 0.23851439356803894, | |
| "learning_rate": 0.00019527379185764612, | |
| "loss": 0.8702, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.47863247863247865, | |
| "grad_norm": 0.30145585536956787, | |
| "learning_rate": 0.00019506316889240027, | |
| "loss": 1.4398, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.48717948717948717, | |
| "grad_norm": 0.2665199339389801, | |
| "learning_rate": 0.00019484807312824067, | |
| "loss": 0.8006, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.49572649572649574, | |
| "grad_norm": 0.3289227783679962, | |
| "learning_rate": 0.0001946285146855968, | |
| "loss": 0.9466, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.5042735042735043, | |
| "grad_norm": 0.2549362778663635, | |
| "learning_rate": 0.0001944045038948709, | |
| "loss": 0.8871, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.5128205128205128, | |
| "grad_norm": 0.289874792098999, | |
| "learning_rate": 0.00019417605129595157, | |
| "loss": 0.8717, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5213675213675214, | |
| "grad_norm": 0.32114192843437195, | |
| "learning_rate": 0.0001939431676377183, | |
| "loss": 0.9448, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.5299145299145299, | |
| "grad_norm": 0.2595084309577942, | |
| "learning_rate": 0.0001937058638775353, | |
| "loss": 0.8295, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.5384615384615384, | |
| "grad_norm": 0.22089529037475586, | |
| "learning_rate": 0.00019346415118073632, | |
| "loss": 1.2068, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.5470085470085471, | |
| "grad_norm": 0.3057108223438263, | |
| "learning_rate": 0.00019321804092009906, | |
| "loss": 0.9483, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.5555555555555556, | |
| "grad_norm": 0.2628245949745178, | |
| "learning_rate": 0.00019296754467531014, | |
| "loss": 0.928, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.5641025641025641, | |
| "grad_norm": 0.31952518224716187, | |
| "learning_rate": 0.00019271267423242024, | |
| "loss": 0.9064, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.5726495726495726, | |
| "grad_norm": 0.2862078845500946, | |
| "learning_rate": 0.00019245344158328972, | |
| "loss": 1.0335, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.5811965811965812, | |
| "grad_norm": 0.27666571736335754, | |
| "learning_rate": 0.0001921898589250242, | |
| "loss": 0.8877, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.5897435897435898, | |
| "grad_norm": 0.24311263859272003, | |
| "learning_rate": 0.0001919219386594007, | |
| "loss": 0.8868, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.5982905982905983, | |
| "grad_norm": 0.2716294825077057, | |
| "learning_rate": 0.00019164969339228422, | |
| "loss": 0.9431, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6068376068376068, | |
| "grad_norm": 0.3183337152004242, | |
| "learning_rate": 0.00019137313593303463, | |
| "loss": 1.0538, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": 0.2670356333255768, | |
| "learning_rate": 0.00019109227929390378, | |
| "loss": 1.3404, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.6239316239316239, | |
| "grad_norm": 0.26112431287765503, | |
| "learning_rate": 0.00019080713668942356, | |
| "loss": 0.8849, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.6324786324786325, | |
| "grad_norm": 0.3271474838256836, | |
| "learning_rate": 0.00019051772153578389, | |
| "loss": 1.0236, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.6410256410256411, | |
| "grad_norm": 0.32266974449157715, | |
| "learning_rate": 0.00019022404745020163, | |
| "loss": 0.8979, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.6495726495726496, | |
| "grad_norm": 0.2465939223766327, | |
| "learning_rate": 0.00018992612825027976, | |
| "loss": 0.891, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.6581196581196581, | |
| "grad_norm": 0.31744077801704407, | |
| "learning_rate": 0.0001896239779533575, | |
| "loss": 1.0727, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 0.2582801878452301, | |
| "learning_rate": 0.00018931761077585035, | |
| "loss": 0.9047, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.6752136752136753, | |
| "grad_norm": 0.25554949045181274, | |
| "learning_rate": 0.00018900704113258165, | |
| "loss": 0.8029, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.6837606837606838, | |
| "grad_norm": 0.2558218836784363, | |
| "learning_rate": 0.00018869228363610404, | |
| "loss": 0.8504, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.6923076923076923, | |
| "grad_norm": 0.3036883771419525, | |
| "learning_rate": 0.00018837335309601213, | |
| "loss": 0.9286, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.7008547008547008, | |
| "grad_norm": 0.24368591606616974, | |
| "learning_rate": 0.00018805026451824546, | |
| "loss": 1.4037, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.7094017094017094, | |
| "grad_norm": 0.22905252873897552, | |
| "learning_rate": 0.00018772303310438275, | |
| "loss": 1.2179, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.717948717948718, | |
| "grad_norm": 0.3644798696041107, | |
| "learning_rate": 0.00018739167425092644, | |
| "loss": 1.3658, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.7264957264957265, | |
| "grad_norm": 0.25496625900268555, | |
| "learning_rate": 0.00018705620354857833, | |
| "loss": 0.7991, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.7350427350427351, | |
| "grad_norm": 0.2917548418045044, | |
| "learning_rate": 0.00018671663678150607, | |
| "loss": 0.7979, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.7435897435897436, | |
| "grad_norm": 0.2509627342224121, | |
| "learning_rate": 0.0001863729899266004, | |
| "loss": 0.8439, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.7521367521367521, | |
| "grad_norm": 0.26703646779060364, | |
| "learning_rate": 0.0001860252791527236, | |
| "loss": 1.1359, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.7606837606837606, | |
| "grad_norm": 0.2911994159221649, | |
| "learning_rate": 0.00018567352081994852, | |
| "loss": 1.378, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.7692307692307693, | |
| "grad_norm": 0.24897685647010803, | |
| "learning_rate": 0.00018531773147878895, | |
| "loss": 1.1141, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.7777777777777778, | |
| "grad_norm": 0.28840702772140503, | |
| "learning_rate": 0.0001849579278694209, | |
| "loss": 0.9043, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.7863247863247863, | |
| "grad_norm": 0.2617591619491577, | |
| "learning_rate": 0.00018459412692089494, | |
| "loss": 0.7995, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.7948717948717948, | |
| "grad_norm": 0.2502082586288452, | |
| "learning_rate": 0.0001842263457503397, | |
| "loss": 0.789, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.8034188034188035, | |
| "grad_norm": 0.30928075313568115, | |
| "learning_rate": 0.00018385460166215638, | |
| "loss": 0.9983, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.811965811965812, | |
| "grad_norm": 0.33725544810295105, | |
| "learning_rate": 0.00018347891214720477, | |
| "loss": 0.955, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.8205128205128205, | |
| "grad_norm": 0.24872225522994995, | |
| "learning_rate": 0.00018309929488198012, | |
| "loss": 1.1854, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.8290598290598291, | |
| "grad_norm": 0.2822365462779999, | |
| "learning_rate": 0.00018271576772778154, | |
| "loss": 0.8358, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.8376068376068376, | |
| "grad_norm": 0.2920995056629181, | |
| "learning_rate": 0.00018232834872987147, | |
| "loss": 1.3358, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.8461538461538461, | |
| "grad_norm": 0.303602397441864, | |
| "learning_rate": 0.00018193705611662696, | |
| "loss": 0.9797, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.8547008547008547, | |
| "grad_norm": 0.3406928479671478, | |
| "learning_rate": 0.0001815419082986815, | |
| "loss": 0.9816, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.8632478632478633, | |
| "grad_norm": 0.22692528367042542, | |
| "learning_rate": 0.00018114292386805936, | |
| "loss": 1.221, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.8717948717948718, | |
| "grad_norm": 0.22570784389972687, | |
| "learning_rate": 0.00018074012159730032, | |
| "loss": 1.1856, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.8803418803418803, | |
| "grad_norm": 0.2517668306827545, | |
| "learning_rate": 0.00018033352043857675, | |
| "loss": 1.1498, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 0.27244430780410767, | |
| "learning_rate": 0.00017992313952280172, | |
| "loss": 1.1015, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.8974358974358975, | |
| "grad_norm": 0.3242965638637543, | |
| "learning_rate": 0.00017950899815872892, | |
| "loss": 1.2942, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.905982905982906, | |
| "grad_norm": 0.32707729935646057, | |
| "learning_rate": 0.00017909111583204422, | |
| "loss": 1.2383, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.9145299145299145, | |
| "grad_norm": 0.37845203280448914, | |
| "learning_rate": 0.0001786695122044487, | |
| "loss": 0.9584, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.9230769230769231, | |
| "grad_norm": 0.26341512799263, | |
| "learning_rate": 0.0001782442071127338, | |
| "loss": 1.1443, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.9316239316239316, | |
| "grad_norm": 0.3688293397426605, | |
| "learning_rate": 0.0001778152205678477, | |
| "loss": 1.5414, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.9401709401709402, | |
| "grad_norm": 0.3266530930995941, | |
| "learning_rate": 0.00017738257275395404, | |
| "loss": 1.0778, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.9487179487179487, | |
| "grad_norm": 0.4219954311847687, | |
| "learning_rate": 0.00017694628402748202, | |
| "loss": 1.1903, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.9572649572649573, | |
| "grad_norm": 0.28938961029052734, | |
| "learning_rate": 0.0001765063749161688, | |
| "loss": 0.8998, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.9658119658119658, | |
| "grad_norm": 0.3432457745075226, | |
| "learning_rate": 0.00017606286611809353, | |
| "loss": 0.9684, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.9743589743589743, | |
| "grad_norm": 0.26857873797416687, | |
| "learning_rate": 0.00017561577850070355, | |
| "loss": 1.0045, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.9829059829059829, | |
| "grad_norm": 0.24974624812602997, | |
| "learning_rate": 0.00017516513309983253, | |
| "loss": 0.7979, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.9914529914529915, | |
| "grad_norm": 0.343883752822876, | |
| "learning_rate": 0.00017471095111871074, | |
| "loss": 1.0162, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.29970595240592957, | |
| "learning_rate": 0.0001742532539269674, | |
| "loss": 0.8354, | |
| "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": 2.287953380376576e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |