v0.8w-adapter / checkpoint-550 /trainer_state.json
gotzmann's picture
..
7361bb3
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9784300644874361,
"eval_steps": 500,
"global_step": 550,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"grad_norm": 0.45256540179252625,
"learning_rate": 2.366863905325444e-07,
"loss": 1.4569,
"step": 1
},
{
"epoch": 0.0,
"grad_norm": 0.4529481828212738,
"learning_rate": 4.733727810650888e-07,
"loss": 1.3644,
"step": 2
},
{
"epoch": 0.01,
"grad_norm": 0.6197301149368286,
"learning_rate": 7.100591715976332e-07,
"loss": 1.4401,
"step": 3
},
{
"epoch": 0.01,
"grad_norm": 0.4604271352291107,
"learning_rate": 9.467455621301776e-07,
"loss": 1.4268,
"step": 4
},
{
"epoch": 0.01,
"grad_norm": 0.43845024704933167,
"learning_rate": 1.183431952662722e-06,
"loss": 1.3566,
"step": 5
},
{
"epoch": 0.01,
"grad_norm": 0.411244660615921,
"learning_rate": 1.4201183431952664e-06,
"loss": 1.3928,
"step": 6
},
{
"epoch": 0.01,
"grad_norm": 0.44185420870780945,
"learning_rate": 1.656804733727811e-06,
"loss": 1.3219,
"step": 7
},
{
"epoch": 0.01,
"grad_norm": 0.35254159569740295,
"learning_rate": 1.8934911242603552e-06,
"loss": 1.2633,
"step": 8
},
{
"epoch": 0.02,
"grad_norm": 0.6924590468406677,
"learning_rate": 2.1301775147929e-06,
"loss": 1.3981,
"step": 9
},
{
"epoch": 0.02,
"grad_norm": 0.35222283005714417,
"learning_rate": 2.366863905325444e-06,
"loss": 1.3974,
"step": 10
},
{
"epoch": 0.02,
"grad_norm": 0.30887699127197266,
"learning_rate": 2.603550295857988e-06,
"loss": 1.3804,
"step": 11
},
{
"epoch": 0.02,
"grad_norm": 0.2868764102458954,
"learning_rate": 2.840236686390533e-06,
"loss": 1.3667,
"step": 12
},
{
"epoch": 0.02,
"grad_norm": 0.266529381275177,
"learning_rate": 3.0769230769230774e-06,
"loss": 1.3539,
"step": 13
},
{
"epoch": 0.02,
"grad_norm": 0.2709053158760071,
"learning_rate": 3.313609467455622e-06,
"loss": 1.3328,
"step": 14
},
{
"epoch": 0.03,
"grad_norm": 0.2658722698688507,
"learning_rate": 3.550295857988166e-06,
"loss": 1.3057,
"step": 15
},
{
"epoch": 0.03,
"grad_norm": 0.25174638628959656,
"learning_rate": 3.7869822485207104e-06,
"loss": 1.3251,
"step": 16
},
{
"epoch": 0.03,
"grad_norm": 0.3282093405723572,
"learning_rate": 4.023668639053255e-06,
"loss": 1.3731,
"step": 17
},
{
"epoch": 0.03,
"grad_norm": 0.2421874701976776,
"learning_rate": 4.2603550295858e-06,
"loss": 1.3182,
"step": 18
},
{
"epoch": 0.03,
"grad_norm": 0.2390267550945282,
"learning_rate": 4.497041420118343e-06,
"loss": 1.3427,
"step": 19
},
{
"epoch": 0.04,
"grad_norm": 0.2561015486717224,
"learning_rate": 4.733727810650888e-06,
"loss": 1.2169,
"step": 20
},
{
"epoch": 0.04,
"grad_norm": 0.2676621079444885,
"learning_rate": 4.970414201183432e-06,
"loss": 1.281,
"step": 21
},
{
"epoch": 0.04,
"grad_norm": 0.26723212003707886,
"learning_rate": 5.207100591715976e-06,
"loss": 1.315,
"step": 22
},
{
"epoch": 0.04,
"grad_norm": 0.25090569257736206,
"learning_rate": 5.443786982248521e-06,
"loss": 1.3735,
"step": 23
},
{
"epoch": 0.04,
"grad_norm": 0.23309403657913208,
"learning_rate": 5.680473372781066e-06,
"loss": 1.4455,
"step": 24
},
{
"epoch": 0.04,
"grad_norm": 0.22344529628753662,
"learning_rate": 5.91715976331361e-06,
"loss": 1.2653,
"step": 25
},
{
"epoch": 0.05,
"grad_norm": 0.2396487593650818,
"learning_rate": 6.153846153846155e-06,
"loss": 1.2975,
"step": 26
},
{
"epoch": 0.05,
"grad_norm": 0.20989473164081573,
"learning_rate": 6.3905325443786995e-06,
"loss": 1.2818,
"step": 27
},
{
"epoch": 0.05,
"grad_norm": 0.25289615988731384,
"learning_rate": 6.627218934911244e-06,
"loss": 1.3461,
"step": 28
},
{
"epoch": 0.05,
"grad_norm": 0.21861045062541962,
"learning_rate": 6.863905325443787e-06,
"loss": 1.2251,
"step": 29
},
{
"epoch": 0.05,
"grad_norm": 0.34595948457717896,
"learning_rate": 7.100591715976332e-06,
"loss": 1.3674,
"step": 30
},
{
"epoch": 0.06,
"grad_norm": 0.22662296891212463,
"learning_rate": 7.337278106508876e-06,
"loss": 1.3098,
"step": 31
},
{
"epoch": 0.06,
"grad_norm": 0.23772552609443665,
"learning_rate": 7.573964497041421e-06,
"loss": 1.3131,
"step": 32
},
{
"epoch": 0.06,
"grad_norm": 0.2229236513376236,
"learning_rate": 7.810650887573965e-06,
"loss": 1.2146,
"step": 33
},
{
"epoch": 0.06,
"grad_norm": 0.2346654236316681,
"learning_rate": 8.04733727810651e-06,
"loss": 1.2461,
"step": 34
},
{
"epoch": 0.06,
"grad_norm": 0.239919513463974,
"learning_rate": 8.284023668639054e-06,
"loss": 1.3061,
"step": 35
},
{
"epoch": 0.06,
"grad_norm": 0.28290900588035583,
"learning_rate": 8.5207100591716e-06,
"loss": 1.3061,
"step": 36
},
{
"epoch": 0.07,
"grad_norm": 0.24613362550735474,
"learning_rate": 8.757396449704143e-06,
"loss": 1.3081,
"step": 37
},
{
"epoch": 0.07,
"grad_norm": 0.2197539210319519,
"learning_rate": 8.994082840236687e-06,
"loss": 1.314,
"step": 38
},
{
"epoch": 0.07,
"grad_norm": 0.22429563105106354,
"learning_rate": 9.230769230769232e-06,
"loss": 1.3043,
"step": 39
},
{
"epoch": 0.07,
"grad_norm": 0.22450979053974152,
"learning_rate": 9.467455621301776e-06,
"loss": 1.2923,
"step": 40
},
{
"epoch": 0.07,
"grad_norm": 0.27412596344947815,
"learning_rate": 9.70414201183432e-06,
"loss": 1.3158,
"step": 41
},
{
"epoch": 0.07,
"grad_norm": 0.23781456053256989,
"learning_rate": 9.940828402366864e-06,
"loss": 1.2986,
"step": 42
},
{
"epoch": 0.08,
"grad_norm": 0.21080109477043152,
"learning_rate": 1.017751479289941e-05,
"loss": 1.309,
"step": 43
},
{
"epoch": 0.08,
"grad_norm": 0.22735567390918732,
"learning_rate": 1.0414201183431953e-05,
"loss": 1.2832,
"step": 44
},
{
"epoch": 0.08,
"grad_norm": 0.22945533692836761,
"learning_rate": 1.0650887573964498e-05,
"loss": 1.277,
"step": 45
},
{
"epoch": 0.08,
"grad_norm": 0.22165744006633759,
"learning_rate": 1.0887573964497042e-05,
"loss": 1.2381,
"step": 46
},
{
"epoch": 0.08,
"grad_norm": 0.23516800999641418,
"learning_rate": 1.1124260355029586e-05,
"loss": 1.2913,
"step": 47
},
{
"epoch": 0.09,
"grad_norm": 0.19824980199337006,
"learning_rate": 1.1360946745562131e-05,
"loss": 1.1926,
"step": 48
},
{
"epoch": 0.09,
"grad_norm": 0.3040119707584381,
"learning_rate": 1.1597633136094675e-05,
"loss": 1.3153,
"step": 49
},
{
"epoch": 0.09,
"grad_norm": 0.2223094254732132,
"learning_rate": 1.183431952662722e-05,
"loss": 1.2184,
"step": 50
},
{
"epoch": 0.09,
"grad_norm": 0.2515048682689667,
"learning_rate": 1.2071005917159764e-05,
"loss": 1.336,
"step": 51
},
{
"epoch": 0.09,
"grad_norm": 0.23539452254772186,
"learning_rate": 1.230769230769231e-05,
"loss": 1.4118,
"step": 52
},
{
"epoch": 0.09,
"grad_norm": 0.23905791342258453,
"learning_rate": 1.2544378698224854e-05,
"loss": 1.331,
"step": 53
},
{
"epoch": 0.1,
"grad_norm": 0.2439602166414261,
"learning_rate": 1.2781065088757399e-05,
"loss": 1.3149,
"step": 54
},
{
"epoch": 0.1,
"grad_norm": 0.22920997440814972,
"learning_rate": 1.3017751479289941e-05,
"loss": 1.2606,
"step": 55
},
{
"epoch": 0.1,
"grad_norm": 0.2133115828037262,
"learning_rate": 1.3254437869822488e-05,
"loss": 1.3365,
"step": 56
},
{
"epoch": 0.1,
"grad_norm": 0.2142357975244522,
"learning_rate": 1.349112426035503e-05,
"loss": 1.3224,
"step": 57
},
{
"epoch": 0.1,
"grad_norm": 0.20909257233142853,
"learning_rate": 1.3727810650887574e-05,
"loss": 1.2912,
"step": 58
},
{
"epoch": 0.1,
"grad_norm": 0.23404663801193237,
"learning_rate": 1.396449704142012e-05,
"loss": 1.3027,
"step": 59
},
{
"epoch": 0.11,
"grad_norm": 0.21893072128295898,
"learning_rate": 1.4201183431952663e-05,
"loss": 1.2553,
"step": 60
},
{
"epoch": 0.11,
"grad_norm": 0.22096726298332214,
"learning_rate": 1.4437869822485209e-05,
"loss": 1.281,
"step": 61
},
{
"epoch": 0.11,
"grad_norm": 1.081170916557312,
"learning_rate": 1.4674556213017752e-05,
"loss": 1.2884,
"step": 62
},
{
"epoch": 0.11,
"grad_norm": 0.22385230660438538,
"learning_rate": 1.4911242603550298e-05,
"loss": 1.2623,
"step": 63
},
{
"epoch": 0.11,
"grad_norm": 0.23298712074756622,
"learning_rate": 1.5147928994082842e-05,
"loss": 1.2821,
"step": 64
},
{
"epoch": 0.12,
"grad_norm": 0.3878341615200043,
"learning_rate": 1.5384615384615387e-05,
"loss": 1.2506,
"step": 65
},
{
"epoch": 0.12,
"grad_norm": 0.22243380546569824,
"learning_rate": 1.562130177514793e-05,
"loss": 1.2227,
"step": 66
},
{
"epoch": 0.12,
"grad_norm": 0.2637002468109131,
"learning_rate": 1.5857988165680475e-05,
"loss": 1.2881,
"step": 67
},
{
"epoch": 0.12,
"grad_norm": 0.2298763245344162,
"learning_rate": 1.609467455621302e-05,
"loss": 1.3599,
"step": 68
},
{
"epoch": 0.12,
"grad_norm": 0.2115241140127182,
"learning_rate": 1.6331360946745562e-05,
"loss": 1.1884,
"step": 69
},
{
"epoch": 0.12,
"grad_norm": 0.2874203026294708,
"learning_rate": 1.6568047337278108e-05,
"loss": 1.3397,
"step": 70
},
{
"epoch": 0.13,
"grad_norm": 0.22124260663986206,
"learning_rate": 1.6804733727810653e-05,
"loss": 1.3417,
"step": 71
},
{
"epoch": 0.13,
"grad_norm": 0.2512863874435425,
"learning_rate": 1.70414201183432e-05,
"loss": 1.2949,
"step": 72
},
{
"epoch": 0.13,
"grad_norm": 0.3238716423511505,
"learning_rate": 1.727810650887574e-05,
"loss": 1.2081,
"step": 73
},
{
"epoch": 0.13,
"grad_norm": 0.20584481954574585,
"learning_rate": 1.7514792899408286e-05,
"loss": 1.2029,
"step": 74
},
{
"epoch": 0.13,
"grad_norm": 0.21194683015346527,
"learning_rate": 1.7751479289940828e-05,
"loss": 1.2889,
"step": 75
},
{
"epoch": 0.14,
"grad_norm": 0.21375629305839539,
"learning_rate": 1.7988165680473374e-05,
"loss": 1.1978,
"step": 76
},
{
"epoch": 0.14,
"grad_norm": 0.3396347463130951,
"learning_rate": 1.822485207100592e-05,
"loss": 1.2245,
"step": 77
},
{
"epoch": 0.14,
"grad_norm": 0.22037793695926666,
"learning_rate": 1.8461538461538465e-05,
"loss": 1.2168,
"step": 78
},
{
"epoch": 0.14,
"grad_norm": 0.20697161555290222,
"learning_rate": 1.8698224852071007e-05,
"loss": 1.28,
"step": 79
},
{
"epoch": 0.14,
"grad_norm": 0.22741861641407013,
"learning_rate": 1.8934911242603552e-05,
"loss": 1.2906,
"step": 80
},
{
"epoch": 0.14,
"grad_norm": 0.22307828068733215,
"learning_rate": 1.9171597633136098e-05,
"loss": 1.2696,
"step": 81
},
{
"epoch": 0.15,
"grad_norm": 0.20539595186710358,
"learning_rate": 1.940828402366864e-05,
"loss": 1.2793,
"step": 82
},
{
"epoch": 0.15,
"grad_norm": 0.35372307896614075,
"learning_rate": 1.9644970414201185e-05,
"loss": 1.2929,
"step": 83
},
{
"epoch": 0.15,
"grad_norm": 0.22638989984989166,
"learning_rate": 1.9881656804733727e-05,
"loss": 1.3448,
"step": 84
},
{
"epoch": 0.15,
"grad_norm": 0.23473680019378662,
"learning_rate": 2.0118343195266276e-05,
"loss": 1.4049,
"step": 85
},
{
"epoch": 0.15,
"grad_norm": 0.40462109446525574,
"learning_rate": 2.035502958579882e-05,
"loss": 1.2063,
"step": 86
},
{
"epoch": 0.15,
"grad_norm": 0.5088987946510315,
"learning_rate": 2.059171597633136e-05,
"loss": 1.3173,
"step": 87
},
{
"epoch": 0.16,
"grad_norm": 0.2960086464881897,
"learning_rate": 2.0828402366863906e-05,
"loss": 1.1658,
"step": 88
},
{
"epoch": 0.16,
"grad_norm": 0.18364708125591278,
"learning_rate": 2.106508875739645e-05,
"loss": 1.2131,
"step": 89
},
{
"epoch": 0.16,
"grad_norm": 0.20984740555286407,
"learning_rate": 2.1301775147928997e-05,
"loss": 1.2959,
"step": 90
},
{
"epoch": 0.16,
"grad_norm": 0.23264534771442413,
"learning_rate": 2.153846153846154e-05,
"loss": 1.3718,
"step": 91
},
{
"epoch": 0.16,
"grad_norm": 0.18781857192516327,
"learning_rate": 2.1775147928994084e-05,
"loss": 1.2442,
"step": 92
},
{
"epoch": 0.17,
"grad_norm": 0.21347913146018982,
"learning_rate": 2.201183431952663e-05,
"loss": 1.2354,
"step": 93
},
{
"epoch": 0.17,
"grad_norm": 0.19755306839942932,
"learning_rate": 2.224852071005917e-05,
"loss": 1.21,
"step": 94
},
{
"epoch": 0.17,
"grad_norm": 0.6877259612083435,
"learning_rate": 2.2485207100591717e-05,
"loss": 1.2694,
"step": 95
},
{
"epoch": 0.17,
"grad_norm": 0.21010373532772064,
"learning_rate": 2.2721893491124263e-05,
"loss": 1.2075,
"step": 96
},
{
"epoch": 0.17,
"grad_norm": 0.18228934705257416,
"learning_rate": 2.2958579881656808e-05,
"loss": 1.2062,
"step": 97
},
{
"epoch": 0.17,
"grad_norm": 0.2007497102022171,
"learning_rate": 2.319526627218935e-05,
"loss": 1.2616,
"step": 98
},
{
"epoch": 0.18,
"grad_norm": 0.21043969690799713,
"learning_rate": 2.3431952662721896e-05,
"loss": 1.2297,
"step": 99
},
{
"epoch": 0.18,
"grad_norm": 0.19528649747371674,
"learning_rate": 2.366863905325444e-05,
"loss": 1.2951,
"step": 100
},
{
"epoch": 0.18,
"grad_norm": 0.2004949301481247,
"learning_rate": 2.3905325443786986e-05,
"loss": 1.3297,
"step": 101
},
{
"epoch": 0.18,
"grad_norm": 0.18860860168933868,
"learning_rate": 2.414201183431953e-05,
"loss": 1.2922,
"step": 102
},
{
"epoch": 0.18,
"grad_norm": 0.19460582733154297,
"learning_rate": 2.4378698224852074e-05,
"loss": 1.2539,
"step": 103
},
{
"epoch": 0.19,
"grad_norm": 0.23081618547439575,
"learning_rate": 2.461538461538462e-05,
"loss": 1.3242,
"step": 104
},
{
"epoch": 0.19,
"grad_norm": 0.18269965052604675,
"learning_rate": 2.485207100591716e-05,
"loss": 1.2574,
"step": 105
},
{
"epoch": 0.19,
"grad_norm": 0.1838914453983307,
"learning_rate": 2.5088757396449707e-05,
"loss": 1.282,
"step": 106
},
{
"epoch": 0.19,
"grad_norm": 0.19195106625556946,
"learning_rate": 2.5325443786982252e-05,
"loss": 1.3306,
"step": 107
},
{
"epoch": 0.19,
"grad_norm": 0.18179951608181,
"learning_rate": 2.5562130177514798e-05,
"loss": 1.2826,
"step": 108
},
{
"epoch": 0.19,
"grad_norm": 0.18123595416545868,
"learning_rate": 2.5798816568047337e-05,
"loss": 1.1557,
"step": 109
},
{
"epoch": 0.2,
"grad_norm": 0.17565734684467316,
"learning_rate": 2.6035502958579882e-05,
"loss": 1.2967,
"step": 110
},
{
"epoch": 0.2,
"grad_norm": 0.17343786358833313,
"learning_rate": 2.6272189349112428e-05,
"loss": 1.2091,
"step": 111
},
{
"epoch": 0.2,
"grad_norm": 0.18770839273929596,
"learning_rate": 2.6508875739644976e-05,
"loss": 1.2598,
"step": 112
},
{
"epoch": 0.2,
"grad_norm": 0.18156233429908752,
"learning_rate": 2.6745562130177515e-05,
"loss": 1.4203,
"step": 113
},
{
"epoch": 0.2,
"grad_norm": 0.17836841940879822,
"learning_rate": 2.698224852071006e-05,
"loss": 1.3028,
"step": 114
},
{
"epoch": 0.2,
"grad_norm": 0.18834306299686432,
"learning_rate": 2.7218934911242606e-05,
"loss": 1.3476,
"step": 115
},
{
"epoch": 0.21,
"grad_norm": 0.17323559522628784,
"learning_rate": 2.7455621301775148e-05,
"loss": 1.2906,
"step": 116
},
{
"epoch": 0.21,
"grad_norm": 0.17727844417095184,
"learning_rate": 2.7692307692307694e-05,
"loss": 1.2975,
"step": 117
},
{
"epoch": 0.21,
"grad_norm": 0.17880651354789734,
"learning_rate": 2.792899408284024e-05,
"loss": 1.2702,
"step": 118
},
{
"epoch": 0.21,
"grad_norm": 0.16582255065441132,
"learning_rate": 2.8165680473372784e-05,
"loss": 1.1503,
"step": 119
},
{
"epoch": 0.21,
"grad_norm": 0.17850655317306519,
"learning_rate": 2.8402366863905327e-05,
"loss": 1.2997,
"step": 120
},
{
"epoch": 0.22,
"grad_norm": 0.18331943452358246,
"learning_rate": 2.8639053254437872e-05,
"loss": 1.3637,
"step": 121
},
{
"epoch": 0.22,
"grad_norm": 0.1787254512310028,
"learning_rate": 2.8875739644970417e-05,
"loss": 1.3294,
"step": 122
},
{
"epoch": 0.22,
"grad_norm": 0.1663455218076706,
"learning_rate": 2.9112426035502963e-05,
"loss": 1.2493,
"step": 123
},
{
"epoch": 0.22,
"grad_norm": 0.18791569769382477,
"learning_rate": 2.9349112426035505e-05,
"loss": 1.3098,
"step": 124
},
{
"epoch": 0.22,
"grad_norm": 0.20719879865646362,
"learning_rate": 2.958579881656805e-05,
"loss": 1.2525,
"step": 125
},
{
"epoch": 0.22,
"grad_norm": 0.18029142916202545,
"learning_rate": 2.9822485207100596e-05,
"loss": 1.2253,
"step": 126
},
{
"epoch": 0.23,
"grad_norm": 0.1783473640680313,
"learning_rate": 3.0059171597633138e-05,
"loss": 1.2442,
"step": 127
},
{
"epoch": 0.23,
"grad_norm": 0.17132772505283356,
"learning_rate": 3.0295857988165683e-05,
"loss": 1.2608,
"step": 128
},
{
"epoch": 0.23,
"grad_norm": 0.18309135735034943,
"learning_rate": 3.0532544378698226e-05,
"loss": 1.2042,
"step": 129
},
{
"epoch": 0.23,
"grad_norm": 0.16952255368232727,
"learning_rate": 3.0769230769230774e-05,
"loss": 1.1857,
"step": 130
},
{
"epoch": 0.23,
"grad_norm": 0.17200875282287598,
"learning_rate": 3.1005917159763316e-05,
"loss": 1.3099,
"step": 131
},
{
"epoch": 0.23,
"grad_norm": 0.1655825823545456,
"learning_rate": 3.124260355029586e-05,
"loss": 1.1104,
"step": 132
},
{
"epoch": 0.24,
"grad_norm": 1.1321977376937866,
"learning_rate": 3.147928994082841e-05,
"loss": 1.2752,
"step": 133
},
{
"epoch": 0.24,
"grad_norm": 0.17164289951324463,
"learning_rate": 3.171597633136095e-05,
"loss": 1.3419,
"step": 134
},
{
"epoch": 0.24,
"grad_norm": 0.1645852029323578,
"learning_rate": 3.195266272189349e-05,
"loss": 1.277,
"step": 135
},
{
"epoch": 0.24,
"grad_norm": 0.18138067424297333,
"learning_rate": 3.218934911242604e-05,
"loss": 1.3829,
"step": 136
},
{
"epoch": 0.24,
"grad_norm": 0.17257159948349,
"learning_rate": 3.242603550295858e-05,
"loss": 1.2158,
"step": 137
},
{
"epoch": 0.25,
"grad_norm": 0.17873308062553406,
"learning_rate": 3.2662721893491124e-05,
"loss": 1.3722,
"step": 138
},
{
"epoch": 0.25,
"grad_norm": 0.18967239558696747,
"learning_rate": 3.289940828402367e-05,
"loss": 1.3189,
"step": 139
},
{
"epoch": 0.25,
"grad_norm": 0.17044439911842346,
"learning_rate": 3.3136094674556215e-05,
"loss": 1.2405,
"step": 140
},
{
"epoch": 0.25,
"grad_norm": 0.17479783296585083,
"learning_rate": 3.3372781065088764e-05,
"loss": 1.2111,
"step": 141
},
{
"epoch": 0.25,
"grad_norm": 0.17302677035331726,
"learning_rate": 3.3609467455621306e-05,
"loss": 1.2284,
"step": 142
},
{
"epoch": 0.25,
"grad_norm": 0.195891872048378,
"learning_rate": 3.384615384615385e-05,
"loss": 1.2887,
"step": 143
},
{
"epoch": 0.26,
"grad_norm": 0.18167690932750702,
"learning_rate": 3.40828402366864e-05,
"loss": 1.2402,
"step": 144
},
{
"epoch": 0.26,
"grad_norm": 0.17309151589870453,
"learning_rate": 3.431952662721894e-05,
"loss": 1.2908,
"step": 145
},
{
"epoch": 0.26,
"grad_norm": 0.16847188770771027,
"learning_rate": 3.455621301775148e-05,
"loss": 1.232,
"step": 146
},
{
"epoch": 0.26,
"grad_norm": 0.15291230380535126,
"learning_rate": 3.4792899408284023e-05,
"loss": 1.2175,
"step": 147
},
{
"epoch": 0.26,
"grad_norm": 0.17138057947158813,
"learning_rate": 3.502958579881657e-05,
"loss": 1.2425,
"step": 148
},
{
"epoch": 0.27,
"grad_norm": 0.1690928041934967,
"learning_rate": 3.5266272189349114e-05,
"loss": 1.2559,
"step": 149
},
{
"epoch": 0.27,
"grad_norm": 0.16478750109672546,
"learning_rate": 3.5502958579881656e-05,
"loss": 1.2275,
"step": 150
},
{
"epoch": 0.27,
"grad_norm": 0.16980737447738647,
"learning_rate": 3.5739644970414205e-05,
"loss": 1.2615,
"step": 151
},
{
"epoch": 0.27,
"grad_norm": 0.18318678438663483,
"learning_rate": 3.597633136094675e-05,
"loss": 1.1944,
"step": 152
},
{
"epoch": 0.27,
"grad_norm": 0.16001984477043152,
"learning_rate": 3.621301775147929e-05,
"loss": 1.2195,
"step": 153
},
{
"epoch": 0.27,
"grad_norm": 0.16806018352508545,
"learning_rate": 3.644970414201184e-05,
"loss": 1.2447,
"step": 154
},
{
"epoch": 0.28,
"grad_norm": 0.165884330868721,
"learning_rate": 3.668639053254438e-05,
"loss": 1.2678,
"step": 155
},
{
"epoch": 0.28,
"grad_norm": 0.1888454109430313,
"learning_rate": 3.692307692307693e-05,
"loss": 1.1565,
"step": 156
},
{
"epoch": 0.28,
"grad_norm": 0.17629367113113403,
"learning_rate": 3.715976331360947e-05,
"loss": 1.2655,
"step": 157
},
{
"epoch": 0.28,
"grad_norm": 0.15656840801239014,
"learning_rate": 3.739644970414201e-05,
"loss": 1.255,
"step": 158
},
{
"epoch": 0.28,
"grad_norm": 0.1642792522907257,
"learning_rate": 3.763313609467456e-05,
"loss": 1.2761,
"step": 159
},
{
"epoch": 0.28,
"grad_norm": 0.1748429834842682,
"learning_rate": 3.7869822485207104e-05,
"loss": 1.2886,
"step": 160
},
{
"epoch": 0.29,
"grad_norm": 0.18779656291007996,
"learning_rate": 3.8106508875739646e-05,
"loss": 1.329,
"step": 161
},
{
"epoch": 0.29,
"grad_norm": 0.1711338311433792,
"learning_rate": 3.8343195266272195e-05,
"loss": 1.217,
"step": 162
},
{
"epoch": 0.29,
"grad_norm": 0.2066163867712021,
"learning_rate": 3.857988165680474e-05,
"loss": 1.2237,
"step": 163
},
{
"epoch": 0.29,
"grad_norm": 0.1761993169784546,
"learning_rate": 3.881656804733728e-05,
"loss": 1.3078,
"step": 164
},
{
"epoch": 0.29,
"grad_norm": 0.1665651649236679,
"learning_rate": 3.905325443786983e-05,
"loss": 1.282,
"step": 165
},
{
"epoch": 0.3,
"grad_norm": 0.16825369000434875,
"learning_rate": 3.928994082840237e-05,
"loss": 1.2816,
"step": 166
},
{
"epoch": 0.3,
"grad_norm": 0.1534135639667511,
"learning_rate": 3.952662721893492e-05,
"loss": 1.1642,
"step": 167
},
{
"epoch": 0.3,
"grad_norm": 0.16484308242797852,
"learning_rate": 3.9763313609467454e-05,
"loss": 1.2835,
"step": 168
},
{
"epoch": 0.3,
"grad_norm": 0.1610719859600067,
"learning_rate": 4e-05,
"loss": 1.3346,
"step": 169
},
{
"epoch": 0.3,
"grad_norm": 0.1510305106639862,
"learning_rate": 3.999995711272738e-05,
"loss": 1.2378,
"step": 170
},
{
"epoch": 0.3,
"grad_norm": 0.15529176592826843,
"learning_rate": 3.9999828451093426e-05,
"loss": 1.2229,
"step": 171
},
{
"epoch": 0.31,
"grad_norm": 0.1719708889722824,
"learning_rate": 3.999961401564995e-05,
"loss": 1.384,
"step": 172
},
{
"epoch": 0.31,
"grad_norm": 0.1716768890619278,
"learning_rate": 3.999931380731659e-05,
"loss": 1.2835,
"step": 173
},
{
"epoch": 0.31,
"grad_norm": 0.174550399184227,
"learning_rate": 3.999892782738088e-05,
"loss": 1.271,
"step": 174
},
{
"epoch": 0.31,
"grad_norm": 0.15711328387260437,
"learning_rate": 3.999845607749817e-05,
"loss": 1.2114,
"step": 175
},
{
"epoch": 0.31,
"grad_norm": 0.15875279903411865,
"learning_rate": 3.999789855969166e-05,
"loss": 1.2691,
"step": 176
},
{
"epoch": 0.31,
"grad_norm": 0.15693986415863037,
"learning_rate": 3.999725527635241e-05,
"loss": 1.2357,
"step": 177
},
{
"epoch": 0.32,
"grad_norm": 0.16238917410373688,
"learning_rate": 3.999652623023927e-05,
"loss": 1.1509,
"step": 178
},
{
"epoch": 0.32,
"grad_norm": 0.1467331349849701,
"learning_rate": 3.9995711424478924e-05,
"loss": 1.1546,
"step": 179
},
{
"epoch": 0.32,
"grad_norm": 0.16689354181289673,
"learning_rate": 3.999481086256586e-05,
"loss": 1.3141,
"step": 180
},
{
"epoch": 0.32,
"grad_norm": 0.16529196500778198,
"learning_rate": 3.999382454836233e-05,
"loss": 1.2067,
"step": 181
},
{
"epoch": 0.32,
"grad_norm": 0.15258309245109558,
"learning_rate": 3.999275248609838e-05,
"loss": 1.155,
"step": 182
},
{
"epoch": 0.33,
"grad_norm": 0.1617356687784195,
"learning_rate": 3.9991594680371777e-05,
"loss": 1.2189,
"step": 183
},
{
"epoch": 0.33,
"grad_norm": 0.15302208065986633,
"learning_rate": 3.999035113614805e-05,
"loss": 1.1984,
"step": 184
},
{
"epoch": 0.33,
"grad_norm": 0.20816399157047272,
"learning_rate": 3.998902185876041e-05,
"loss": 1.2542,
"step": 185
},
{
"epoch": 0.33,
"grad_norm": 0.16472405195236206,
"learning_rate": 3.998760685390977e-05,
"loss": 1.2054,
"step": 186
},
{
"epoch": 0.33,
"grad_norm": 0.1601923108100891,
"learning_rate": 3.9986106127664694e-05,
"loss": 1.2957,
"step": 187
},
{
"epoch": 0.33,
"grad_norm": 0.15352420508861542,
"learning_rate": 3.99845196864614e-05,
"loss": 1.2051,
"step": 188
},
{
"epoch": 0.34,
"grad_norm": 0.17676082253456116,
"learning_rate": 3.998284753710369e-05,
"loss": 1.2261,
"step": 189
},
{
"epoch": 0.34,
"grad_norm": 0.1508205682039261,
"learning_rate": 3.998108968676296e-05,
"loss": 1.2634,
"step": 190
},
{
"epoch": 0.34,
"grad_norm": 0.1601751744747162,
"learning_rate": 3.997924614297815e-05,
"loss": 1.2006,
"step": 191
},
{
"epoch": 0.34,
"grad_norm": 0.2529548108577728,
"learning_rate": 3.997731691365572e-05,
"loss": 1.3508,
"step": 192
},
{
"epoch": 0.34,
"grad_norm": 0.17672798037528992,
"learning_rate": 3.99753020070696e-05,
"loss": 1.2879,
"step": 193
},
{
"epoch": 0.35,
"grad_norm": 0.15853144228458405,
"learning_rate": 3.997320143186119e-05,
"loss": 1.2504,
"step": 194
},
{
"epoch": 0.35,
"grad_norm": 0.14928783476352692,
"learning_rate": 3.997101519703927e-05,
"loss": 1.1055,
"step": 195
},
{
"epoch": 0.35,
"grad_norm": 0.17145495116710663,
"learning_rate": 3.9968743311980015e-05,
"loss": 1.2717,
"step": 196
},
{
"epoch": 0.35,
"grad_norm": 0.15577386319637299,
"learning_rate": 3.996638578642691e-05,
"loss": 1.2165,
"step": 197
},
{
"epoch": 0.35,
"grad_norm": 0.18255503475666046,
"learning_rate": 3.996394263049074e-05,
"loss": 1.2062,
"step": 198
},
{
"epoch": 0.35,
"grad_norm": 0.17394264042377472,
"learning_rate": 3.996141385464955e-05,
"loss": 1.2499,
"step": 199
},
{
"epoch": 0.36,
"grad_norm": 0.20845308899879456,
"learning_rate": 3.9958799469748547e-05,
"loss": 1.353,
"step": 200
},
{
"epoch": 0.36,
"grad_norm": 0.16469226777553558,
"learning_rate": 3.9956099487000135e-05,
"loss": 1.2376,
"step": 201
},
{
"epoch": 0.36,
"grad_norm": 0.16727469861507416,
"learning_rate": 3.995331391798379e-05,
"loss": 1.2536,
"step": 202
},
{
"epoch": 0.36,
"grad_norm": 0.1603512018918991,
"learning_rate": 3.9950442774646065e-05,
"loss": 1.2753,
"step": 203
},
{
"epoch": 0.36,
"grad_norm": 0.18711543083190918,
"learning_rate": 3.994748606930051e-05,
"loss": 1.2629,
"step": 204
},
{
"epoch": 0.36,
"grad_norm": 0.1531892865896225,
"learning_rate": 3.994444381462763e-05,
"loss": 1.2333,
"step": 205
},
{
"epoch": 0.37,
"grad_norm": 0.17141614854335785,
"learning_rate": 3.994131602367481e-05,
"loss": 1.2556,
"step": 206
},
{
"epoch": 0.37,
"grad_norm": 0.17776872217655182,
"learning_rate": 3.9938102709856316e-05,
"loss": 1.1875,
"step": 207
},
{
"epoch": 0.37,
"grad_norm": 0.15654616057872772,
"learning_rate": 3.9934803886953153e-05,
"loss": 1.281,
"step": 208
},
{
"epoch": 0.37,
"grad_norm": 0.16635853052139282,
"learning_rate": 3.993141956911309e-05,
"loss": 1.1977,
"step": 209
},
{
"epoch": 0.37,
"grad_norm": 0.1581771969795227,
"learning_rate": 3.9927949770850535e-05,
"loss": 1.2556,
"step": 210
},
{
"epoch": 0.38,
"grad_norm": 0.19136467576026917,
"learning_rate": 3.99243945070465e-05,
"loss": 1.2549,
"step": 211
},
{
"epoch": 0.38,
"grad_norm": 0.18221412599086761,
"learning_rate": 3.992075379294856e-05,
"loss": 1.2468,
"step": 212
},
{
"epoch": 0.38,
"grad_norm": 0.1619117110967636,
"learning_rate": 3.991702764417073e-05,
"loss": 1.2866,
"step": 213
},
{
"epoch": 0.38,
"grad_norm": 0.1579107940196991,
"learning_rate": 3.9913216076693446e-05,
"loss": 1.2815,
"step": 214
},
{
"epoch": 0.38,
"grad_norm": 0.15225648880004883,
"learning_rate": 3.9909319106863485e-05,
"loss": 1.1889,
"step": 215
},
{
"epoch": 0.38,
"grad_norm": 0.16033805906772614,
"learning_rate": 3.990533675139389e-05,
"loss": 1.2241,
"step": 216
},
{
"epoch": 0.39,
"grad_norm": 0.1602856069803238,
"learning_rate": 3.990126902736389e-05,
"loss": 1.2266,
"step": 217
},
{
"epoch": 0.39,
"grad_norm": 0.1666950285434723,
"learning_rate": 3.989711595221886e-05,
"loss": 1.2292,
"step": 218
},
{
"epoch": 0.39,
"grad_norm": 0.1629578322172165,
"learning_rate": 3.989287754377019e-05,
"loss": 1.2544,
"step": 219
},
{
"epoch": 0.39,
"grad_norm": 0.15922550857067108,
"learning_rate": 3.988855382019526e-05,
"loss": 1.2395,
"step": 220
},
{
"epoch": 0.39,
"grad_norm": 0.1633135825395584,
"learning_rate": 3.988414480003735e-05,
"loss": 1.3399,
"step": 221
},
{
"epoch": 0.39,
"grad_norm": 0.16409821808338165,
"learning_rate": 3.9879650502205537e-05,
"loss": 1.1643,
"step": 222
},
{
"epoch": 0.4,
"grad_norm": 0.1624230146408081,
"learning_rate": 3.987507094597464e-05,
"loss": 1.3067,
"step": 223
},
{
"epoch": 0.4,
"grad_norm": 0.16975589096546173,
"learning_rate": 3.9870406150985134e-05,
"loss": 1.1727,
"step": 224
},
{
"epoch": 0.4,
"grad_norm": 0.1849404126405716,
"learning_rate": 3.986565613724304e-05,
"loss": 1.3096,
"step": 225
},
{
"epoch": 0.4,
"grad_norm": 0.18090464174747467,
"learning_rate": 3.986082092511988e-05,
"loss": 1.2235,
"step": 226
},
{
"epoch": 0.4,
"grad_norm": 0.1610763967037201,
"learning_rate": 3.985590053535256e-05,
"loss": 1.2425,
"step": 227
},
{
"epoch": 0.41,
"grad_norm": 0.1640045940876007,
"learning_rate": 3.9850894989043284e-05,
"loss": 1.3407,
"step": 228
},
{
"epoch": 0.41,
"grad_norm": 0.16807672381401062,
"learning_rate": 3.9845804307659485e-05,
"loss": 1.3529,
"step": 229
},
{
"epoch": 0.41,
"grad_norm": 0.16140711307525635,
"learning_rate": 3.984062851303369e-05,
"loss": 1.3073,
"step": 230
},
{
"epoch": 0.41,
"grad_norm": 0.15345898270606995,
"learning_rate": 3.983536762736349e-05,
"loss": 1.2497,
"step": 231
},
{
"epoch": 0.41,
"grad_norm": 0.1554725468158722,
"learning_rate": 3.983002167321138e-05,
"loss": 1.2908,
"step": 232
},
{
"epoch": 0.41,
"grad_norm": 0.16261020302772522,
"learning_rate": 3.98245906735047e-05,
"loss": 1.1978,
"step": 233
},
{
"epoch": 0.42,
"grad_norm": 0.15362827479839325,
"learning_rate": 3.981907465153552e-05,
"loss": 1.1768,
"step": 234
},
{
"epoch": 0.42,
"grad_norm": 0.15314264595508575,
"learning_rate": 3.981347363096056e-05,
"loss": 1.1572,
"step": 235
},
{
"epoch": 0.42,
"grad_norm": 0.1712978333234787,
"learning_rate": 3.980778763580108e-05,
"loss": 1.3071,
"step": 236
},
{
"epoch": 0.42,
"grad_norm": 0.15101170539855957,
"learning_rate": 3.980201669044274e-05,
"loss": 1.1953,
"step": 237
},
{
"epoch": 0.42,
"grad_norm": 0.16669559478759766,
"learning_rate": 3.9796160819635566e-05,
"loss": 1.3362,
"step": 238
},
{
"epoch": 0.43,
"grad_norm": 0.23853600025177002,
"learning_rate": 3.979022004849379e-05,
"loss": 1.2309,
"step": 239
},
{
"epoch": 0.43,
"grad_norm": 0.15961961448192596,
"learning_rate": 3.9784194402495746e-05,
"loss": 1.2157,
"step": 240
},
{
"epoch": 0.43,
"grad_norm": 0.16380910575389862,
"learning_rate": 3.977808390748381e-05,
"loss": 1.1569,
"step": 241
},
{
"epoch": 0.43,
"grad_norm": 0.17208293080329895,
"learning_rate": 3.977188858966421e-05,
"loss": 1.349,
"step": 242
},
{
"epoch": 0.43,
"grad_norm": 0.1566724181175232,
"learning_rate": 3.976560847560697e-05,
"loss": 1.2158,
"step": 243
},
{
"epoch": 0.43,
"grad_norm": 0.1605634242296219,
"learning_rate": 3.975924359224581e-05,
"loss": 1.167,
"step": 244
},
{
"epoch": 0.44,
"grad_norm": 0.21259568631649017,
"learning_rate": 3.9752793966877956e-05,
"loss": 1.2877,
"step": 245
},
{
"epoch": 0.44,
"grad_norm": 0.1743762195110321,
"learning_rate": 3.97462596271641e-05,
"loss": 1.3,
"step": 246
},
{
"epoch": 0.44,
"grad_norm": 0.1705716997385025,
"learning_rate": 3.9739640601128255e-05,
"loss": 1.2658,
"step": 247
},
{
"epoch": 0.44,
"grad_norm": 0.1837138682603836,
"learning_rate": 3.97329369171576e-05,
"loss": 1.2626,
"step": 248
},
{
"epoch": 0.44,
"grad_norm": 0.22162184119224548,
"learning_rate": 3.9726148604002414e-05,
"loss": 1.1911,
"step": 249
},
{
"epoch": 0.44,
"grad_norm": 0.16128268837928772,
"learning_rate": 3.9719275690775924e-05,
"loss": 1.2447,
"step": 250
},
{
"epoch": 0.45,
"grad_norm": 0.16500110924243927,
"learning_rate": 3.971231820695417e-05,
"loss": 1.2036,
"step": 251
},
{
"epoch": 0.45,
"grad_norm": 0.16154707968235016,
"learning_rate": 3.970527618237592e-05,
"loss": 1.1957,
"step": 252
},
{
"epoch": 0.45,
"grad_norm": 0.16126224398612976,
"learning_rate": 3.969814964724248e-05,
"loss": 1.2647,
"step": 253
},
{
"epoch": 0.45,
"grad_norm": 0.16112996637821198,
"learning_rate": 3.969093863211762e-05,
"loss": 1.2127,
"step": 254
},
{
"epoch": 0.45,
"grad_norm": 0.1538519561290741,
"learning_rate": 3.968364316792743e-05,
"loss": 1.1234,
"step": 255
},
{
"epoch": 0.46,
"grad_norm": 0.16396304965019226,
"learning_rate": 3.967626328596015e-05,
"loss": 1.2309,
"step": 256
},
{
"epoch": 0.46,
"grad_norm": 0.18015865981578827,
"learning_rate": 3.966879901786608e-05,
"loss": 1.1613,
"step": 257
},
{
"epoch": 0.46,
"grad_norm": 0.16599513590335846,
"learning_rate": 3.966125039565745e-05,
"loss": 1.2543,
"step": 258
},
{
"epoch": 0.46,
"grad_norm": 0.19396306574344635,
"learning_rate": 3.965361745170821e-05,
"loss": 1.2597,
"step": 259
},
{
"epoch": 0.46,
"grad_norm": 0.1652296930551529,
"learning_rate": 3.964590021875401e-05,
"loss": 1.2601,
"step": 260
},
{
"epoch": 0.46,
"grad_norm": 0.15919215977191925,
"learning_rate": 3.963809872989193e-05,
"loss": 1.1675,
"step": 261
},
{
"epoch": 0.47,
"grad_norm": 0.16900300979614258,
"learning_rate": 3.963021301858045e-05,
"loss": 1.295,
"step": 262
},
{
"epoch": 0.47,
"grad_norm": 0.18816988170146942,
"learning_rate": 3.9622243118639215e-05,
"loss": 1.3135,
"step": 263
},
{
"epoch": 0.47,
"grad_norm": 0.17363770306110382,
"learning_rate": 3.961418906424897e-05,
"loss": 1.3225,
"step": 264
},
{
"epoch": 0.47,
"grad_norm": 0.1609456092119217,
"learning_rate": 3.960605088995134e-05,
"loss": 1.2022,
"step": 265
},
{
"epoch": 0.47,
"grad_norm": 0.1848209649324417,
"learning_rate": 3.959782863064874e-05,
"loss": 1.2134,
"step": 266
},
{
"epoch": 0.47,
"grad_norm": 0.1635885089635849,
"learning_rate": 3.9589522321604205e-05,
"loss": 1.2537,
"step": 267
},
{
"epoch": 0.48,
"grad_norm": 0.21050697565078735,
"learning_rate": 3.958113199844123e-05,
"loss": 1.3015,
"step": 268
},
{
"epoch": 0.48,
"grad_norm": 0.1821780800819397,
"learning_rate": 3.9572657697143614e-05,
"loss": 1.1287,
"step": 269
},
{
"epoch": 0.48,
"grad_norm": 0.16301009058952332,
"learning_rate": 3.9564099454055325e-05,
"loss": 1.2451,
"step": 270
},
{
"epoch": 0.48,
"grad_norm": 0.17613324522972107,
"learning_rate": 3.955545730588034e-05,
"loss": 1.3656,
"step": 271
},
{
"epoch": 0.48,
"grad_norm": 0.16889138519763947,
"learning_rate": 3.954673128968247e-05,
"loss": 1.3678,
"step": 272
},
{
"epoch": 0.49,
"grad_norm": 0.16508743166923523,
"learning_rate": 3.953792144288523e-05,
"loss": 1.3248,
"step": 273
},
{
"epoch": 0.49,
"grad_norm": 0.16305625438690186,
"learning_rate": 3.952902780327163e-05,
"loss": 1.2358,
"step": 274
},
{
"epoch": 0.49,
"grad_norm": 0.1744881272315979,
"learning_rate": 3.9520050408984076e-05,
"loss": 1.2405,
"step": 275
},
{
"epoch": 0.49,
"grad_norm": 0.16882789134979248,
"learning_rate": 3.951098929852417e-05,
"loss": 1.2694,
"step": 276
},
{
"epoch": 0.49,
"grad_norm": 0.15946689248085022,
"learning_rate": 3.950184451075252e-05,
"loss": 1.2312,
"step": 277
},
{
"epoch": 0.49,
"grad_norm": 0.16837111115455627,
"learning_rate": 3.949261608488866e-05,
"loss": 1.2121,
"step": 278
},
{
"epoch": 0.5,
"grad_norm": 0.16055358946323395,
"learning_rate": 3.948330406051077e-05,
"loss": 1.251,
"step": 279
},
{
"epoch": 0.5,
"grad_norm": 0.16870392858982086,
"learning_rate": 3.947390847755559e-05,
"loss": 1.2926,
"step": 280
},
{
"epoch": 0.5,
"grad_norm": 0.1582109034061432,
"learning_rate": 3.94644293763182e-05,
"loss": 1.2649,
"step": 281
},
{
"epoch": 0.5,
"grad_norm": 0.19230706989765167,
"learning_rate": 3.9454866797451895e-05,
"loss": 1.2991,
"step": 282
},
{
"epoch": 0.5,
"grad_norm": 0.15807847678661346,
"learning_rate": 3.9445220781967963e-05,
"loss": 1.1764,
"step": 283
},
{
"epoch": 0.51,
"grad_norm": 0.1773795485496521,
"learning_rate": 3.9435491371235534e-05,
"loss": 1.3195,
"step": 284
},
{
"epoch": 0.51,
"grad_norm": 0.16266267001628876,
"learning_rate": 3.94256786069814e-05,
"loss": 1.2765,
"step": 285
},
{
"epoch": 0.51,
"grad_norm": 0.1656751185655594,
"learning_rate": 3.941578253128982e-05,
"loss": 1.2727,
"step": 286
},
{
"epoch": 0.51,
"grad_norm": 0.15894421935081482,
"learning_rate": 3.940580318660238e-05,
"loss": 1.2083,
"step": 287
},
{
"epoch": 0.51,
"grad_norm": 0.16084228456020355,
"learning_rate": 3.939574061571775e-05,
"loss": 1.232,
"step": 288
},
{
"epoch": 0.51,
"grad_norm": 0.16208983957767487,
"learning_rate": 3.938559486179156e-05,
"loss": 1.2277,
"step": 289
},
{
"epoch": 0.52,
"grad_norm": 0.16037632524967194,
"learning_rate": 3.937536596833618e-05,
"loss": 1.1273,
"step": 290
},
{
"epoch": 0.52,
"grad_norm": 0.2040693312883377,
"learning_rate": 3.9365053979220555e-05,
"loss": 1.2405,
"step": 291
},
{
"epoch": 0.52,
"grad_norm": 0.1898617446422577,
"learning_rate": 3.935465893866998e-05,
"loss": 1.222,
"step": 292
},
{
"epoch": 0.52,
"grad_norm": 0.16039510071277618,
"learning_rate": 3.934418089126595e-05,
"loss": 1.2946,
"step": 293
},
{
"epoch": 0.52,
"grad_norm": 0.21441307663917542,
"learning_rate": 3.933361988194596e-05,
"loss": 1.2268,
"step": 294
},
{
"epoch": 0.52,
"grad_norm": 0.15417777001857758,
"learning_rate": 3.9322975956003297e-05,
"loss": 1.145,
"step": 295
},
{
"epoch": 0.53,
"grad_norm": 0.16220960021018982,
"learning_rate": 3.9312249159086855e-05,
"loss": 1.3189,
"step": 296
},
{
"epoch": 0.53,
"grad_norm": 0.1598338782787323,
"learning_rate": 3.9301439537200936e-05,
"loss": 1.2083,
"step": 297
},
{
"epoch": 0.53,
"grad_norm": 0.18459190428256989,
"learning_rate": 3.929054713670506e-05,
"loss": 1.2136,
"step": 298
},
{
"epoch": 0.53,
"grad_norm": 0.15777897834777832,
"learning_rate": 3.927957200431377e-05,
"loss": 1.2017,
"step": 299
},
{
"epoch": 0.53,
"grad_norm": 0.177915558218956,
"learning_rate": 3.926851418709641e-05,
"loss": 1.3244,
"step": 300
},
{
"epoch": 0.54,
"grad_norm": 0.1588701456785202,
"learning_rate": 3.925737373247694e-05,
"loss": 1.3037,
"step": 301
},
{
"epoch": 0.54,
"grad_norm": 0.1676599532365799,
"learning_rate": 3.9246150688233745e-05,
"loss": 1.2729,
"step": 302
},
{
"epoch": 0.54,
"grad_norm": 0.20505991578102112,
"learning_rate": 3.923484510249938e-05,
"loss": 1.241,
"step": 303
},
{
"epoch": 0.54,
"grad_norm": 0.15723706781864166,
"learning_rate": 3.922345702376044e-05,
"loss": 1.2241,
"step": 304
},
{
"epoch": 0.54,
"grad_norm": 0.18037424981594086,
"learning_rate": 3.921198650085726e-05,
"loss": 1.2395,
"step": 305
},
{
"epoch": 0.54,
"grad_norm": 0.16490055620670319,
"learning_rate": 3.9200433582983825e-05,
"loss": 1.2515,
"step": 306
},
{
"epoch": 0.55,
"grad_norm": 0.16806964576244354,
"learning_rate": 3.9188798319687406e-05,
"loss": 1.2211,
"step": 307
},
{
"epoch": 0.55,
"grad_norm": 0.1634434014558792,
"learning_rate": 3.917708076086851e-05,
"loss": 1.298,
"step": 308
},
{
"epoch": 0.55,
"grad_norm": 0.16614285111427307,
"learning_rate": 3.916528095678053e-05,
"loss": 1.3037,
"step": 309
},
{
"epoch": 0.55,
"grad_norm": 0.18700821697711945,
"learning_rate": 3.9153398958029606e-05,
"loss": 1.2613,
"step": 310
},
{
"epoch": 0.55,
"grad_norm": 0.16272488236427307,
"learning_rate": 3.91414348155744e-05,
"loss": 1.2064,
"step": 311
},
{
"epoch": 0.56,
"grad_norm": 0.16149508953094482,
"learning_rate": 3.9129388580725855e-05,
"loss": 1.2886,
"step": 312
},
{
"epoch": 0.56,
"grad_norm": 0.1734437793493271,
"learning_rate": 3.911726030514698e-05,
"loss": 1.2709,
"step": 313
},
{
"epoch": 0.56,
"grad_norm": 0.16677477955818176,
"learning_rate": 3.9105050040852646e-05,
"loss": 1.2614,
"step": 314
},
{
"epoch": 0.56,
"grad_norm": 0.17172600328922272,
"learning_rate": 3.9092757840209347e-05,
"loss": 1.184,
"step": 315
},
{
"epoch": 0.56,
"grad_norm": 0.15502072870731354,
"learning_rate": 3.908038375593498e-05,
"loss": 1.1066,
"step": 316
},
{
"epoch": 0.56,
"grad_norm": 0.16084939241409302,
"learning_rate": 3.9067927841098614e-05,
"loss": 1.2861,
"step": 317
},
{
"epoch": 0.57,
"grad_norm": 0.16080649197101593,
"learning_rate": 3.905539014912027e-05,
"loss": 1.2096,
"step": 318
},
{
"epoch": 0.57,
"grad_norm": 0.16113747656345367,
"learning_rate": 3.90427707337707e-05,
"loss": 1.1859,
"step": 319
},
{
"epoch": 0.57,
"grad_norm": 0.1573685258626938,
"learning_rate": 3.903006964917111e-05,
"loss": 1.1895,
"step": 320
},
{
"epoch": 0.57,
"grad_norm": 0.1588548868894577,
"learning_rate": 3.901728694979301e-05,
"loss": 1.2548,
"step": 321
},
{
"epoch": 0.57,
"grad_norm": 0.15512435138225555,
"learning_rate": 3.900442269045791e-05,
"loss": 1.2825,
"step": 322
},
{
"epoch": 0.57,
"grad_norm": 0.17400631308555603,
"learning_rate": 3.899147692633711e-05,
"loss": 1.3224,
"step": 323
},
{
"epoch": 0.58,
"grad_norm": 0.19142161309719086,
"learning_rate": 3.897844971295144e-05,
"loss": 1.1845,
"step": 324
},
{
"epoch": 0.58,
"grad_norm": 0.18297170102596283,
"learning_rate": 3.89653411061711e-05,
"loss": 1.198,
"step": 325
},
{
"epoch": 0.58,
"grad_norm": 0.17008209228515625,
"learning_rate": 3.895215116221529e-05,
"loss": 1.2946,
"step": 326
},
{
"epoch": 0.58,
"grad_norm": 0.16479219496250153,
"learning_rate": 3.893887993765211e-05,
"loss": 1.2793,
"step": 327
},
{
"epoch": 0.58,
"grad_norm": 0.16869719326496124,
"learning_rate": 3.892552748939823e-05,
"loss": 1.3061,
"step": 328
},
{
"epoch": 0.59,
"grad_norm": 0.16528654098510742,
"learning_rate": 3.891209387471863e-05,
"loss": 1.2766,
"step": 329
},
{
"epoch": 0.59,
"grad_norm": 0.1654234379529953,
"learning_rate": 3.889857915122644e-05,
"loss": 1.1604,
"step": 330
},
{
"epoch": 0.59,
"grad_norm": 0.1730952113866806,
"learning_rate": 3.888498337688261e-05,
"loss": 1.2526,
"step": 331
},
{
"epoch": 0.59,
"grad_norm": 0.16318488121032715,
"learning_rate": 3.8871306609995715e-05,
"loss": 1.2352,
"step": 332
},
{
"epoch": 0.59,
"grad_norm": 0.17201673984527588,
"learning_rate": 3.885754890922169e-05,
"loss": 1.331,
"step": 333
},
{
"epoch": 0.59,
"grad_norm": 0.1656893938779831,
"learning_rate": 3.8843710333563536e-05,
"loss": 1.2122,
"step": 334
},
{
"epoch": 0.6,
"grad_norm": 0.15819483995437622,
"learning_rate": 3.882979094237115e-05,
"loss": 1.1374,
"step": 335
},
{
"epoch": 0.6,
"grad_norm": 0.17912957072257996,
"learning_rate": 3.8815790795341e-05,
"loss": 1.1865,
"step": 336
},
{
"epoch": 0.6,
"grad_norm": 0.17538312077522278,
"learning_rate": 3.8801709952515894e-05,
"loss": 1.2847,
"step": 337
},
{
"epoch": 0.6,
"grad_norm": 0.16031011939048767,
"learning_rate": 3.878754847428473e-05,
"loss": 1.1983,
"step": 338
},
{
"epoch": 0.6,
"grad_norm": 0.15993796288967133,
"learning_rate": 3.8773306421382215e-05,
"loss": 1.2416,
"step": 339
},
{
"epoch": 0.6,
"grad_norm": 0.16199611127376556,
"learning_rate": 3.875898385488864e-05,
"loss": 1.2562,
"step": 340
},
{
"epoch": 0.61,
"grad_norm": 0.159291073679924,
"learning_rate": 3.87445808362296e-05,
"loss": 1.2262,
"step": 341
},
{
"epoch": 0.61,
"grad_norm": 0.15733957290649414,
"learning_rate": 3.8730097427175685e-05,
"loss": 1.1643,
"step": 342
},
{
"epoch": 0.61,
"grad_norm": 0.16530875861644745,
"learning_rate": 3.8715533689842303e-05,
"loss": 1.2809,
"step": 343
},
{
"epoch": 0.61,
"grad_norm": 0.31174418330192566,
"learning_rate": 3.870088968668936e-05,
"loss": 1.3185,
"step": 344
},
{
"epoch": 0.61,
"grad_norm": 0.1655522733926773,
"learning_rate": 3.8686165480520964e-05,
"loss": 1.3158,
"step": 345
},
{
"epoch": 0.62,
"grad_norm": 0.17282016575336456,
"learning_rate": 3.867136113448524e-05,
"loss": 1.3052,
"step": 346
},
{
"epoch": 0.62,
"grad_norm": 0.16425450146198273,
"learning_rate": 3.865647671207399e-05,
"loss": 1.3419,
"step": 347
},
{
"epoch": 0.62,
"grad_norm": 0.15989594161510468,
"learning_rate": 3.864151227712244e-05,
"loss": 1.1391,
"step": 348
},
{
"epoch": 0.62,
"grad_norm": 0.1693430244922638,
"learning_rate": 3.8626467893808956e-05,
"loss": 1.1643,
"step": 349
},
{
"epoch": 0.62,
"grad_norm": 0.15857893228530884,
"learning_rate": 3.861134362665482e-05,
"loss": 1.172,
"step": 350
},
{
"epoch": 0.62,
"grad_norm": 0.1693955510854721,
"learning_rate": 3.859613954052387e-05,
"loss": 1.3536,
"step": 351
},
{
"epoch": 0.63,
"grad_norm": 0.1622908115386963,
"learning_rate": 3.85808557006223e-05,
"loss": 1.2033,
"step": 352
},
{
"epoch": 0.63,
"grad_norm": 0.17406344413757324,
"learning_rate": 3.8565492172498314e-05,
"loss": 1.3955,
"step": 353
},
{
"epoch": 0.63,
"grad_norm": 0.17219895124435425,
"learning_rate": 3.85500490220419e-05,
"loss": 1.2801,
"step": 354
},
{
"epoch": 0.63,
"grad_norm": 0.25802117586135864,
"learning_rate": 3.853452631548452e-05,
"loss": 1.2639,
"step": 355
},
{
"epoch": 0.63,
"grad_norm": 0.16231444478034973,
"learning_rate": 3.851892411939883e-05,
"loss": 1.263,
"step": 356
},
{
"epoch": 0.64,
"grad_norm": 0.16031944751739502,
"learning_rate": 3.8503242500698396e-05,
"loss": 1.2532,
"step": 357
},
{
"epoch": 0.64,
"grad_norm": 0.15626895427703857,
"learning_rate": 3.848748152663739e-05,
"loss": 1.2321,
"step": 358
},
{
"epoch": 0.64,
"grad_norm": 0.15723131597042084,
"learning_rate": 3.847164126481035e-05,
"loss": 1.16,
"step": 359
},
{
"epoch": 0.64,
"grad_norm": 0.16541031002998352,
"learning_rate": 3.845572178315183e-05,
"loss": 1.2644,
"step": 360
},
{
"epoch": 0.64,
"grad_norm": 0.17055818438529968,
"learning_rate": 3.843972314993614e-05,
"loss": 1.2573,
"step": 361
},
{
"epoch": 0.64,
"grad_norm": 0.16403935849666595,
"learning_rate": 3.8423645433777064e-05,
"loss": 1.2026,
"step": 362
},
{
"epoch": 0.65,
"grad_norm": 0.157577782869339,
"learning_rate": 3.840748870362753e-05,
"loss": 1.2497,
"step": 363
},
{
"epoch": 0.65,
"grad_norm": 0.17598943412303925,
"learning_rate": 3.8391253028779365e-05,
"loss": 1.2226,
"step": 364
},
{
"epoch": 0.65,
"grad_norm": 0.15772323310375214,
"learning_rate": 3.8374938478862936e-05,
"loss": 1.1726,
"step": 365
},
{
"epoch": 0.65,
"grad_norm": 0.18102790415287018,
"learning_rate": 3.83585451238469e-05,
"loss": 1.2938,
"step": 366
},
{
"epoch": 0.65,
"grad_norm": 0.17216327786445618,
"learning_rate": 3.834207303403789e-05,
"loss": 1.3421,
"step": 367
},
{
"epoch": 0.65,
"grad_norm": 0.16786645352840424,
"learning_rate": 3.83255222800802e-05,
"loss": 1.2734,
"step": 368
},
{
"epoch": 0.66,
"grad_norm": 0.15548373758792877,
"learning_rate": 3.83088929329555e-05,
"loss": 1.2656,
"step": 369
},
{
"epoch": 0.66,
"grad_norm": 0.16076824069023132,
"learning_rate": 3.8292185063982536e-05,
"loss": 1.1429,
"step": 370
},
{
"epoch": 0.66,
"grad_norm": 0.16665169596672058,
"learning_rate": 3.827539874481678e-05,
"loss": 1.2775,
"step": 371
},
{
"epoch": 0.66,
"grad_norm": 0.1681457906961441,
"learning_rate": 3.82585340474502e-05,
"loss": 1.267,
"step": 372
},
{
"epoch": 0.66,
"grad_norm": 0.16220974922180176,
"learning_rate": 3.824159104421087e-05,
"loss": 1.2049,
"step": 373
},
{
"epoch": 0.67,
"grad_norm": 0.1736627221107483,
"learning_rate": 3.822456980776272e-05,
"loss": 1.2997,
"step": 374
},
{
"epoch": 0.67,
"grad_norm": 0.17877478897571564,
"learning_rate": 3.820747041110517e-05,
"loss": 1.2733,
"step": 375
},
{
"epoch": 0.67,
"grad_norm": 0.17471949756145477,
"learning_rate": 3.8190292927572896e-05,
"loss": 1.2488,
"step": 376
},
{
"epoch": 0.67,
"grad_norm": 0.1678047776222229,
"learning_rate": 3.817303743083542e-05,
"loss": 1.2193,
"step": 377
},
{
"epoch": 0.67,
"grad_norm": 0.18162204325199127,
"learning_rate": 3.8155703994896866e-05,
"loss": 1.1816,
"step": 378
},
{
"epoch": 0.67,
"grad_norm": 0.1719117909669876,
"learning_rate": 3.813829269409562e-05,
"loss": 1.3535,
"step": 379
},
{
"epoch": 0.68,
"grad_norm": 0.19797664880752563,
"learning_rate": 3.812080360310399e-05,
"loss": 1.3568,
"step": 380
},
{
"epoch": 0.68,
"grad_norm": 0.17989763617515564,
"learning_rate": 3.810323679692793e-05,
"loss": 1.3152,
"step": 381
},
{
"epoch": 0.68,
"grad_norm": 0.1681927740573883,
"learning_rate": 3.808559235090667e-05,
"loss": 1.2814,
"step": 382
},
{
"epoch": 0.68,
"grad_norm": 0.7965008616447449,
"learning_rate": 3.806787034071244e-05,
"loss": 1.3065,
"step": 383
},
{
"epoch": 0.68,
"grad_norm": 0.17025770246982574,
"learning_rate": 3.805007084235009e-05,
"loss": 1.1674,
"step": 384
},
{
"epoch": 0.68,
"grad_norm": 0.1730756014585495,
"learning_rate": 3.803219393215683e-05,
"loss": 1.1614,
"step": 385
},
{
"epoch": 0.69,
"grad_norm": 0.16721907258033752,
"learning_rate": 3.801423968680185e-05,
"loss": 1.2812,
"step": 386
},
{
"epoch": 0.69,
"grad_norm": 0.17217952013015747,
"learning_rate": 3.7996208183286e-05,
"loss": 1.229,
"step": 387
},
{
"epoch": 0.69,
"grad_norm": 0.1746724396944046,
"learning_rate": 3.79780994989415e-05,
"loss": 1.3108,
"step": 388
},
{
"epoch": 0.69,
"grad_norm": 0.1702830046415329,
"learning_rate": 3.795991371143153e-05,
"loss": 1.2668,
"step": 389
},
{
"epoch": 0.69,
"grad_norm": 0.1598566621541977,
"learning_rate": 3.794165089875e-05,
"loss": 1.1801,
"step": 390
},
{
"epoch": 0.7,
"grad_norm": 0.17259812355041504,
"learning_rate": 3.7923311139221114e-05,
"loss": 1.2354,
"step": 391
},
{
"epoch": 0.7,
"grad_norm": 0.2091628760099411,
"learning_rate": 3.7904894511499115e-05,
"loss": 1.1883,
"step": 392
},
{
"epoch": 0.7,
"grad_norm": 0.22369763255119324,
"learning_rate": 3.788640109456788e-05,
"loss": 1.2687,
"step": 393
},
{
"epoch": 0.7,
"grad_norm": 0.17732800543308258,
"learning_rate": 3.7867830967740643e-05,
"loss": 1.3269,
"step": 394
},
{
"epoch": 0.7,
"grad_norm": 0.28118595480918884,
"learning_rate": 3.7849184210659614e-05,
"loss": 1.2424,
"step": 395
},
{
"epoch": 0.7,
"grad_norm": 0.18187764286994934,
"learning_rate": 3.7830460903295634e-05,
"loss": 1.1875,
"step": 396
},
{
"epoch": 0.71,
"grad_norm": 0.16909223794937134,
"learning_rate": 3.781166112594788e-05,
"loss": 1.2701,
"step": 397
},
{
"epoch": 0.71,
"grad_norm": 0.17135021090507507,
"learning_rate": 3.779278495924345e-05,
"loss": 1.1831,
"step": 398
},
{
"epoch": 0.71,
"grad_norm": 0.17674005031585693,
"learning_rate": 3.777383248413709e-05,
"loss": 1.2732,
"step": 399
},
{
"epoch": 0.71,
"grad_norm": 0.198370561003685,
"learning_rate": 3.775480378191079e-05,
"loss": 1.1929,
"step": 400
},
{
"epoch": 0.71,
"grad_norm": 0.18088266253471375,
"learning_rate": 3.773569893417347e-05,
"loss": 1.2575,
"step": 401
},
{
"epoch": 0.72,
"grad_norm": 0.16227401793003082,
"learning_rate": 3.7716518022860606e-05,
"loss": 1.1559,
"step": 402
},
{
"epoch": 0.72,
"grad_norm": 0.1971830427646637,
"learning_rate": 3.769726113023389e-05,
"loss": 1.211,
"step": 403
},
{
"epoch": 0.72,
"grad_norm": 0.1707913875579834,
"learning_rate": 3.76779283388809e-05,
"loss": 1.1535,
"step": 404
},
{
"epoch": 0.72,
"grad_norm": 0.1668080985546112,
"learning_rate": 3.765851973171469e-05,
"loss": 1.1838,
"step": 405
},
{
"epoch": 0.72,
"grad_norm": 0.16925190389156342,
"learning_rate": 3.763903539197348e-05,
"loss": 1.2518,
"step": 406
},
{
"epoch": 0.72,
"grad_norm": 0.1722031980752945,
"learning_rate": 3.76194754032203e-05,
"loss": 1.2118,
"step": 407
},
{
"epoch": 0.73,
"grad_norm": 0.17410987615585327,
"learning_rate": 3.759983984934261e-05,
"loss": 1.232,
"step": 408
},
{
"epoch": 0.73,
"grad_norm": 0.1774168461561203,
"learning_rate": 3.758012881455192e-05,
"loss": 1.1537,
"step": 409
},
{
"epoch": 0.73,
"grad_norm": 0.16939586400985718,
"learning_rate": 3.756034238338352e-05,
"loss": 1.1585,
"step": 410
},
{
"epoch": 0.73,
"grad_norm": 0.17839783430099487,
"learning_rate": 3.754048064069599e-05,
"loss": 1.3063,
"step": 411
},
{
"epoch": 0.73,
"grad_norm": 0.16792502999305725,
"learning_rate": 3.7520543671670936e-05,
"loss": 1.2978,
"step": 412
},
{
"epoch": 0.73,
"grad_norm": 0.189891517162323,
"learning_rate": 3.7500531561812576e-05,
"loss": 1.235,
"step": 413
},
{
"epoch": 0.74,
"grad_norm": 0.18355625867843628,
"learning_rate": 3.7480444396947396e-05,
"loss": 1.284,
"step": 414
},
{
"epoch": 0.74,
"grad_norm": 0.1714622974395752,
"learning_rate": 3.7460282263223764e-05,
"loss": 1.1672,
"step": 415
},
{
"epoch": 0.74,
"grad_norm": 0.1876678168773651,
"learning_rate": 3.744004524711158e-05,
"loss": 1.2938,
"step": 416
},
{
"epoch": 0.74,
"grad_norm": 0.16813495755195618,
"learning_rate": 3.741973343540188e-05,
"loss": 1.1843,
"step": 417
},
{
"epoch": 0.74,
"grad_norm": 0.2258601039648056,
"learning_rate": 3.739934691520648e-05,
"loss": 1.2196,
"step": 418
},
{
"epoch": 0.75,
"grad_norm": 0.17664629220962524,
"learning_rate": 3.7378885773957614e-05,
"loss": 1.1806,
"step": 419
},
{
"epoch": 0.75,
"grad_norm": 0.1906002312898636,
"learning_rate": 3.735835009940754e-05,
"loss": 1.2252,
"step": 420
},
{
"epoch": 0.75,
"grad_norm": 0.1772574931383133,
"learning_rate": 3.733773997962815e-05,
"loss": 1.2304,
"step": 421
},
{
"epoch": 0.75,
"grad_norm": 0.17094944417476654,
"learning_rate": 3.731705550301064e-05,
"loss": 1.2695,
"step": 422
},
{
"epoch": 0.75,
"grad_norm": 0.19538728892803192,
"learning_rate": 3.729629675826507e-05,
"loss": 1.2349,
"step": 423
},
{
"epoch": 0.75,
"grad_norm": 0.18487848341464996,
"learning_rate": 3.727546383442007e-05,
"loss": 1.2724,
"step": 424
},
{
"epoch": 0.76,
"grad_norm": 0.1757872849702835,
"learning_rate": 3.725455682082233e-05,
"loss": 1.2322,
"step": 425
},
{
"epoch": 0.76,
"grad_norm": 0.161984384059906,
"learning_rate": 3.7233575807136354e-05,
"loss": 1.1426,
"step": 426
},
{
"epoch": 0.76,
"grad_norm": 0.1794055700302124,
"learning_rate": 3.7212520883343974e-05,
"loss": 1.3217,
"step": 427
},
{
"epoch": 0.76,
"grad_norm": 0.17491760849952698,
"learning_rate": 3.719139213974403e-05,
"loss": 1.2233,
"step": 428
},
{
"epoch": 0.76,
"grad_norm": 0.21414370834827423,
"learning_rate": 3.717018966695192e-05,
"loss": 1.2594,
"step": 429
},
{
"epoch": 0.76,
"grad_norm": 0.1733601987361908,
"learning_rate": 3.714891355589929e-05,
"loss": 1.2172,
"step": 430
},
{
"epoch": 0.77,
"grad_norm": 0.1574425846338272,
"learning_rate": 3.712756389783356e-05,
"loss": 1.2312,
"step": 431
},
{
"epoch": 0.77,
"grad_norm": 0.18264387547969818,
"learning_rate": 3.7106140784317594e-05,
"loss": 1.2142,
"step": 432
},
{
"epoch": 0.77,
"grad_norm": 0.17057283222675323,
"learning_rate": 3.708464430722929e-05,
"loss": 1.1942,
"step": 433
},
{
"epoch": 0.77,
"grad_norm": 0.17199979722499847,
"learning_rate": 3.706307455876118e-05,
"loss": 1.2263,
"step": 434
},
{
"epoch": 0.77,
"grad_norm": 0.1813754439353943,
"learning_rate": 3.704143163142001e-05,
"loss": 1.2384,
"step": 435
},
{
"epoch": 0.78,
"grad_norm": 0.16909797489643097,
"learning_rate": 3.701971561802642e-05,
"loss": 1.1905,
"step": 436
},
{
"epoch": 0.78,
"grad_norm": 0.16116483509540558,
"learning_rate": 3.699792661171444e-05,
"loss": 1.1849,
"step": 437
},
{
"epoch": 0.78,
"grad_norm": 0.17043234407901764,
"learning_rate": 3.69760647059312e-05,
"loss": 1.2199,
"step": 438
},
{
"epoch": 0.78,
"grad_norm": 0.17161297798156738,
"learning_rate": 3.695412999443643e-05,
"loss": 1.2092,
"step": 439
},
{
"epoch": 0.78,
"grad_norm": 0.1632567048072815,
"learning_rate": 3.693212257130215e-05,
"loss": 1.202,
"step": 440
},
{
"epoch": 0.78,
"grad_norm": 0.17327187955379486,
"learning_rate": 3.691004253091217e-05,
"loss": 1.2268,
"step": 441
},
{
"epoch": 0.79,
"grad_norm": 0.17322610318660736,
"learning_rate": 3.688788996796179e-05,
"loss": 1.2197,
"step": 442
},
{
"epoch": 0.79,
"grad_norm": 0.16746391355991364,
"learning_rate": 3.686566497745728e-05,
"loss": 1.2467,
"step": 443
},
{
"epoch": 0.79,
"grad_norm": 0.16351164877414703,
"learning_rate": 3.6843367654715584e-05,
"loss": 1.2082,
"step": 444
},
{
"epoch": 0.79,
"grad_norm": 0.17086975276470184,
"learning_rate": 3.6820998095363834e-05,
"loss": 1.2093,
"step": 445
},
{
"epoch": 0.79,
"grad_norm": 0.18365664780139923,
"learning_rate": 3.679855639533895e-05,
"loss": 1.2005,
"step": 446
},
{
"epoch": 0.8,
"grad_norm": 0.17057694494724274,
"learning_rate": 3.677604265088729e-05,
"loss": 1.1776,
"step": 447
},
{
"epoch": 0.8,
"grad_norm": 0.1794084757566452,
"learning_rate": 3.675345695856415e-05,
"loss": 1.208,
"step": 448
},
{
"epoch": 0.8,
"grad_norm": 0.1862630546092987,
"learning_rate": 3.6730799415233414e-05,
"loss": 1.1669,
"step": 449
},
{
"epoch": 0.8,
"grad_norm": 0.19876237213611603,
"learning_rate": 3.670807011806709e-05,
"loss": 1.2048,
"step": 450
},
{
"epoch": 0.8,
"grad_norm": 0.1671525239944458,
"learning_rate": 3.668526916454495e-05,
"loss": 1.2165,
"step": 451
},
{
"epoch": 0.8,
"grad_norm": 0.18071943521499634,
"learning_rate": 3.666239665245405e-05,
"loss": 1.2544,
"step": 452
},
{
"epoch": 0.81,
"grad_norm": 0.17689716815948486,
"learning_rate": 3.6639452679888365e-05,
"loss": 1.2845,
"step": 453
},
{
"epoch": 0.81,
"grad_norm": 0.16965340077877045,
"learning_rate": 3.661643734524834e-05,
"loss": 1.2231,
"step": 454
},
{
"epoch": 0.81,
"grad_norm": 0.18019068241119385,
"learning_rate": 3.6593350747240456e-05,
"loss": 1.2223,
"step": 455
},
{
"epoch": 0.81,
"grad_norm": 0.18523040413856506,
"learning_rate": 3.657019298487685e-05,
"loss": 1.2486,
"step": 456
},
{
"epoch": 0.81,
"grad_norm": 0.19133590161800385,
"learning_rate": 3.654696415747483e-05,
"loss": 1.1961,
"step": 457
},
{
"epoch": 0.81,
"grad_norm": 0.17477400600910187,
"learning_rate": 3.652366436465652e-05,
"loss": 1.2621,
"step": 458
},
{
"epoch": 0.82,
"grad_norm": 0.21932773292064667,
"learning_rate": 3.650029370634837e-05,
"loss": 1.2104,
"step": 459
},
{
"epoch": 0.82,
"grad_norm": 0.18244686722755432,
"learning_rate": 3.6476852282780755e-05,
"loss": 1.2468,
"step": 460
},
{
"epoch": 0.82,
"grad_norm": 0.17326635122299194,
"learning_rate": 3.645334019448755e-05,
"loss": 1.1609,
"step": 461
},
{
"epoch": 0.82,
"grad_norm": 0.17420323193073273,
"learning_rate": 3.6429757542305686e-05,
"loss": 1.2156,
"step": 462
},
{
"epoch": 0.82,
"grad_norm": 0.1676824539899826,
"learning_rate": 3.6406104427374744e-05,
"loss": 1.1739,
"step": 463
},
{
"epoch": 0.83,
"grad_norm": 0.1757155805826187,
"learning_rate": 3.638238095113646e-05,
"loss": 1.187,
"step": 464
},
{
"epoch": 0.83,
"grad_norm": 0.18094448745250702,
"learning_rate": 3.6358587215334355e-05,
"loss": 1.2271,
"step": 465
},
{
"epoch": 0.83,
"grad_norm": 0.1914701908826828,
"learning_rate": 3.633472332201329e-05,
"loss": 1.0756,
"step": 466
},
{
"epoch": 0.83,
"grad_norm": 0.17444278299808502,
"learning_rate": 3.631078937351898e-05,
"loss": 1.2323,
"step": 467
},
{
"epoch": 0.83,
"grad_norm": 0.17253823578357697,
"learning_rate": 3.628678547249761e-05,
"loss": 1.2408,
"step": 468
},
{
"epoch": 0.83,
"grad_norm": 0.1650070697069168,
"learning_rate": 3.626271172189536e-05,
"loss": 1.1771,
"step": 469
},
{
"epoch": 0.84,
"grad_norm": 0.16705216467380524,
"learning_rate": 3.623856822495798e-05,
"loss": 1.2229,
"step": 470
},
{
"epoch": 0.84,
"grad_norm": 0.1749449521303177,
"learning_rate": 3.6214355085230346e-05,
"loss": 1.3156,
"step": 471
},
{
"epoch": 0.84,
"grad_norm": 0.1721351593732834,
"learning_rate": 3.6190072406556016e-05,
"loss": 1.2198,
"step": 472
},
{
"epoch": 0.84,
"grad_norm": 0.17338605225086212,
"learning_rate": 3.616572029307676e-05,
"loss": 1.2696,
"step": 473
},
{
"epoch": 0.84,
"grad_norm": 0.17081210017204285,
"learning_rate": 3.614129884923217e-05,
"loss": 1.1272,
"step": 474
},
{
"epoch": 0.85,
"grad_norm": 0.17321552336215973,
"learning_rate": 3.611680817975915e-05,
"loss": 1.0944,
"step": 475
},
{
"epoch": 0.85,
"grad_norm": 0.1784401535987854,
"learning_rate": 3.609224838969149e-05,
"loss": 1.2999,
"step": 476
},
{
"epoch": 0.85,
"grad_norm": 0.17898234724998474,
"learning_rate": 3.606761958435945e-05,
"loss": 1.2288,
"step": 477
},
{
"epoch": 0.85,
"grad_norm": 0.1713172197341919,
"learning_rate": 3.6042921869389255e-05,
"loss": 1.2837,
"step": 478
},
{
"epoch": 0.85,
"grad_norm": 0.16900764405727386,
"learning_rate": 3.601815535070266e-05,
"loss": 1.1852,
"step": 479
},
{
"epoch": 0.85,
"grad_norm": 0.16487158834934235,
"learning_rate": 3.599332013451651e-05,
"loss": 1.2508,
"step": 480
},
{
"epoch": 0.86,
"grad_norm": 0.1718226671218872,
"learning_rate": 3.596841632734228e-05,
"loss": 1.2721,
"step": 481
},
{
"epoch": 0.86,
"grad_norm": 0.17556148767471313,
"learning_rate": 3.594344403598561e-05,
"loss": 1.1579,
"step": 482
},
{
"epoch": 0.86,
"grad_norm": 0.1776830554008484,
"learning_rate": 3.591840336754584e-05,
"loss": 1.3364,
"step": 483
},
{
"epoch": 0.86,
"grad_norm": 0.17868830263614655,
"learning_rate": 3.589329442941556e-05,
"loss": 1.2904,
"step": 484
},
{
"epoch": 0.86,
"grad_norm": 0.16877397894859314,
"learning_rate": 3.586811732928017e-05,
"loss": 1.1634,
"step": 485
},
{
"epoch": 0.86,
"grad_norm": 0.29319822788238525,
"learning_rate": 3.5842872175117386e-05,
"loss": 1.1825,
"step": 486
},
{
"epoch": 0.87,
"grad_norm": 0.17021752893924713,
"learning_rate": 3.5817559075196775e-05,
"loss": 1.2404,
"step": 487
},
{
"epoch": 0.87,
"grad_norm": 0.18304027616977692,
"learning_rate": 3.579217813807934e-05,
"loss": 1.208,
"step": 488
},
{
"epoch": 0.87,
"grad_norm": 0.18062491714954376,
"learning_rate": 3.576672947261698e-05,
"loss": 1.3094,
"step": 489
},
{
"epoch": 0.87,
"grad_norm": 0.18421950936317444,
"learning_rate": 3.574121318795208e-05,
"loss": 1.2645,
"step": 490
},
{
"epoch": 0.87,
"grad_norm": 0.17431406676769257,
"learning_rate": 3.571562939351705e-05,
"loss": 1.241,
"step": 491
},
{
"epoch": 0.88,
"grad_norm": 0.1877688467502594,
"learning_rate": 3.568997819903377e-05,
"loss": 1.279,
"step": 492
},
{
"epoch": 0.88,
"grad_norm": 0.17437636852264404,
"learning_rate": 3.566425971451324e-05,
"loss": 1.1178,
"step": 493
},
{
"epoch": 0.88,
"grad_norm": 0.16442453861236572,
"learning_rate": 3.5638474050255024e-05,
"loss": 1.0344,
"step": 494
},
{
"epoch": 0.88,
"grad_norm": 0.1917441338300705,
"learning_rate": 3.5612621316846805e-05,
"loss": 1.2959,
"step": 495
},
{
"epoch": 0.88,
"grad_norm": 0.1886010766029358,
"learning_rate": 3.55867016251639e-05,
"loss": 1.187,
"step": 496
},
{
"epoch": 0.88,
"grad_norm": 0.20641809701919556,
"learning_rate": 3.556071508636879e-05,
"loss": 1.1979,
"step": 497
},
{
"epoch": 0.89,
"grad_norm": 0.1747037172317505,
"learning_rate": 3.553466181191067e-05,
"loss": 1.18,
"step": 498
},
{
"epoch": 0.89,
"grad_norm": 0.1825367510318756,
"learning_rate": 3.550854191352492e-05,
"loss": 1.293,
"step": 499
},
{
"epoch": 0.89,
"grad_norm": 0.17783713340759277,
"learning_rate": 3.5482355503232656e-05,
"loss": 1.2322,
"step": 500
},
{
"epoch": 0.89,
"grad_norm": 0.17146770656108856,
"learning_rate": 3.5456102693340255e-05,
"loss": 1.2166,
"step": 501
},
{
"epoch": 0.89,
"grad_norm": 0.1839715540409088,
"learning_rate": 3.5429783596438864e-05,
"loss": 1.2572,
"step": 502
},
{
"epoch": 0.89,
"grad_norm": 0.17346954345703125,
"learning_rate": 3.54033983254039e-05,
"loss": 1.1569,
"step": 503
},
{
"epoch": 0.9,
"grad_norm": 0.19239090383052826,
"learning_rate": 3.53769469933946e-05,
"loss": 1.1428,
"step": 504
},
{
"epoch": 0.9,
"grad_norm": 0.21293193101882935,
"learning_rate": 3.53504297138535e-05,
"loss": 1.3067,
"step": 505
},
{
"epoch": 0.9,
"grad_norm": 0.18217827379703522,
"learning_rate": 3.532384660050601e-05,
"loss": 1.3452,
"step": 506
},
{
"epoch": 0.9,
"grad_norm": 0.18584825098514557,
"learning_rate": 3.529719776735982e-05,
"loss": 1.3022,
"step": 507
},
{
"epoch": 0.9,
"grad_norm": 0.17959220707416534,
"learning_rate": 3.527048332870453e-05,
"loss": 1.2488,
"step": 508
},
{
"epoch": 0.91,
"grad_norm": 0.1819523572921753,
"learning_rate": 3.524370339911107e-05,
"loss": 1.1128,
"step": 509
},
{
"epoch": 0.91,
"grad_norm": 0.20110684633255005,
"learning_rate": 3.521685809343126e-05,
"loss": 1.2031,
"step": 510
},
{
"epoch": 0.91,
"grad_norm": 0.17916655540466309,
"learning_rate": 3.518994752679728e-05,
"loss": 1.2172,
"step": 511
},
{
"epoch": 0.91,
"grad_norm": 0.17345504462718964,
"learning_rate": 3.5162971814621234e-05,
"loss": 1.2089,
"step": 512
},
{
"epoch": 0.91,
"grad_norm": 0.5167191624641418,
"learning_rate": 3.513593107259458e-05,
"loss": 1.2281,
"step": 513
},
{
"epoch": 0.91,
"grad_norm": 0.17433781921863556,
"learning_rate": 3.510882541668769e-05,
"loss": 1.2192,
"step": 514
},
{
"epoch": 0.92,
"grad_norm": 0.1887521892786026,
"learning_rate": 3.508165496314931e-05,
"loss": 1.2763,
"step": 515
},
{
"epoch": 0.92,
"grad_norm": 0.1756310611963272,
"learning_rate": 3.505441982850615e-05,
"loss": 1.2834,
"step": 516
},
{
"epoch": 0.92,
"grad_norm": 0.17292964458465576,
"learning_rate": 3.502712012956223e-05,
"loss": 1.2629,
"step": 517
},
{
"epoch": 0.92,
"grad_norm": 0.18053486943244934,
"learning_rate": 3.4999755983398537e-05,
"loss": 1.2334,
"step": 518
},
{
"epoch": 0.92,
"grad_norm": 0.16213248670101166,
"learning_rate": 3.4972327507372415e-05,
"loss": 1.1131,
"step": 519
},
{
"epoch": 0.93,
"grad_norm": 0.18039150536060333,
"learning_rate": 3.494483481911713e-05,
"loss": 1.2284,
"step": 520
},
{
"epoch": 0.93,
"grad_norm": 0.17420712113380432,
"learning_rate": 3.491727803654132e-05,
"loss": 1.2631,
"step": 521
},
{
"epoch": 0.93,
"grad_norm": 0.17673422396183014,
"learning_rate": 3.488965727782851e-05,
"loss": 1.2223,
"step": 522
},
{
"epoch": 0.93,
"grad_norm": 0.17651581764221191,
"learning_rate": 3.486197266143659e-05,
"loss": 1.2411,
"step": 523
},
{
"epoch": 0.93,
"grad_norm": 0.18939518928527832,
"learning_rate": 3.483422430609735e-05,
"loss": 1.2125,
"step": 524
},
{
"epoch": 0.93,
"grad_norm": 0.1721743494272232,
"learning_rate": 3.48064123308159e-05,
"loss": 1.2753,
"step": 525
},
{
"epoch": 0.94,
"grad_norm": 0.18775472044944763,
"learning_rate": 3.477853685487023e-05,
"loss": 1.2722,
"step": 526
},
{
"epoch": 0.94,
"grad_norm": 0.17603406310081482,
"learning_rate": 3.4750597997810644e-05,
"loss": 1.3061,
"step": 527
},
{
"epoch": 0.94,
"grad_norm": 0.22322580218315125,
"learning_rate": 3.472259587945928e-05,
"loss": 1.1812,
"step": 528
},
{
"epoch": 0.94,
"grad_norm": 0.16920214891433716,
"learning_rate": 3.469453061990959e-05,
"loss": 1.2284,
"step": 529
},
{
"epoch": 0.94,
"grad_norm": 0.1781124472618103,
"learning_rate": 3.466640233952582e-05,
"loss": 1.1115,
"step": 530
},
{
"epoch": 0.94,
"grad_norm": 0.17156866192817688,
"learning_rate": 3.4638211158942493e-05,
"loss": 1.1759,
"step": 531
},
{
"epoch": 0.95,
"grad_norm": 0.18725483119487762,
"learning_rate": 3.460995719906389e-05,
"loss": 1.3214,
"step": 532
},
{
"epoch": 0.95,
"grad_norm": 0.17117691040039062,
"learning_rate": 3.458164058106353e-05,
"loss": 1.1723,
"step": 533
},
{
"epoch": 0.95,
"grad_norm": 0.18169349431991577,
"learning_rate": 3.455326142638369e-05,
"loss": 1.1945,
"step": 534
},
{
"epoch": 0.95,
"grad_norm": 0.17365239560604095,
"learning_rate": 3.45248198567348e-05,
"loss": 1.2686,
"step": 535
},
{
"epoch": 0.95,
"grad_norm": 0.23987340927124023,
"learning_rate": 3.4496315994094995e-05,
"loss": 1.2492,
"step": 536
},
{
"epoch": 0.96,
"grad_norm": 0.18593370914459229,
"learning_rate": 3.446774996070959e-05,
"loss": 1.209,
"step": 537
},
{
"epoch": 0.96,
"grad_norm": 0.1767171174287796,
"learning_rate": 3.443912187909049e-05,
"loss": 1.2453,
"step": 538
},
{
"epoch": 0.96,
"grad_norm": 0.17480580508708954,
"learning_rate": 3.441043187201574e-05,
"loss": 1.236,
"step": 539
},
{
"epoch": 0.96,
"grad_norm": 0.22028052806854248,
"learning_rate": 3.4381680062528957e-05,
"loss": 1.2248,
"step": 540
},
{
"epoch": 0.96,
"grad_norm": 0.18207862973213196,
"learning_rate": 3.43528665739388e-05,
"loss": 1.2862,
"step": 541
},
{
"epoch": 0.96,
"grad_norm": 0.17260274291038513,
"learning_rate": 3.432399152981847e-05,
"loss": 1.1853,
"step": 542
},
{
"epoch": 0.97,
"grad_norm": 0.18698668479919434,
"learning_rate": 3.429505505400516e-05,
"loss": 1.3278,
"step": 543
},
{
"epoch": 0.97,
"grad_norm": 0.18749062716960907,
"learning_rate": 3.426605727059952e-05,
"loss": 1.283,
"step": 544
},
{
"epoch": 0.97,
"grad_norm": 0.17615492641925812,
"learning_rate": 3.423699830396512e-05,
"loss": 1.1874,
"step": 545
},
{
"epoch": 0.97,
"grad_norm": 0.21085886657238007,
"learning_rate": 3.4207878278727956e-05,
"loss": 1.1462,
"step": 546
},
{
"epoch": 0.97,
"grad_norm": 0.1712028980255127,
"learning_rate": 3.417869731977588e-05,
"loss": 1.1746,
"step": 547
},
{
"epoch": 0.97,
"grad_norm": 0.17687669396400452,
"learning_rate": 3.4149455552258054e-05,
"loss": 1.2707,
"step": 548
},
{
"epoch": 0.98,
"grad_norm": 0.20794951915740967,
"learning_rate": 3.412015310158444e-05,
"loss": 1.2805,
"step": 549
},
{
"epoch": 0.98,
"grad_norm": 0.18447402119636536,
"learning_rate": 3.4090790093425276e-05,
"loss": 1.2066,
"step": 550
}
],
"logging_steps": 1.0,
"max_steps": 1686,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 50,
"total_flos": 2.2559932560074342e+19,
"train_batch_size": 3,
"trial_name": null,
"trial_params": null
}