aleegis11's picture
Training in progress, step 200, checkpoint
634eb21 verified
{
"best_metric": 0.8844783902168274,
"best_model_checkpoint": "miner_id_24/checkpoint-200",
"epoch": 2.73972602739726,
"eval_steps": 50,
"global_step": 200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0136986301369863,
"grad_norm": 2.2717444896698,
"learning_rate": 1e-05,
"loss": 2.6772,
"step": 1
},
{
"epoch": 0.0136986301369863,
"eval_loss": 2.6535723209381104,
"eval_runtime": 17.3536,
"eval_samples_per_second": 7.088,
"eval_steps_per_second": 1.786,
"step": 1
},
{
"epoch": 0.0273972602739726,
"grad_norm": 2.250619411468506,
"learning_rate": 2e-05,
"loss": 2.5427,
"step": 2
},
{
"epoch": 0.0410958904109589,
"grad_norm": 2.453151226043701,
"learning_rate": 3e-05,
"loss": 2.6224,
"step": 3
},
{
"epoch": 0.0547945205479452,
"grad_norm": 2.7786638736724854,
"learning_rate": 4e-05,
"loss": 2.4309,
"step": 4
},
{
"epoch": 0.0684931506849315,
"grad_norm": 1.7362089157104492,
"learning_rate": 5e-05,
"loss": 2.3675,
"step": 5
},
{
"epoch": 0.0821917808219178,
"grad_norm": 1.2283235788345337,
"learning_rate": 6e-05,
"loss": 2.2369,
"step": 6
},
{
"epoch": 0.0958904109589041,
"grad_norm": 0.7412413954734802,
"learning_rate": 7e-05,
"loss": 2.0749,
"step": 7
},
{
"epoch": 0.1095890410958904,
"grad_norm": 0.505423367023468,
"learning_rate": 8e-05,
"loss": 2.2423,
"step": 8
},
{
"epoch": 0.1232876712328767,
"grad_norm": 0.6371145844459534,
"learning_rate": 9e-05,
"loss": 2.0761,
"step": 9
},
{
"epoch": 0.136986301369863,
"grad_norm": 0.6269663572311401,
"learning_rate": 0.0001,
"loss": 1.9824,
"step": 10
},
{
"epoch": 0.1506849315068493,
"grad_norm": 0.7009660005569458,
"learning_rate": 9.999316524962345e-05,
"loss": 1.9261,
"step": 11
},
{
"epoch": 0.1643835616438356,
"grad_norm": 0.6795275211334229,
"learning_rate": 9.997266286704631e-05,
"loss": 2.0029,
"step": 12
},
{
"epoch": 0.1780821917808219,
"grad_norm": 0.6740257740020752,
"learning_rate": 9.993849845741524e-05,
"loss": 1.982,
"step": 13
},
{
"epoch": 0.1917808219178082,
"grad_norm": 0.5217537879943848,
"learning_rate": 9.989068136093873e-05,
"loss": 1.689,
"step": 14
},
{
"epoch": 0.2054794520547945,
"grad_norm": 0.6331390738487244,
"learning_rate": 9.98292246503335e-05,
"loss": 1.8042,
"step": 15
},
{
"epoch": 0.2191780821917808,
"grad_norm": 0.6667072772979736,
"learning_rate": 9.975414512725057e-05,
"loss": 1.9436,
"step": 16
},
{
"epoch": 0.2328767123287671,
"grad_norm": 0.700835108757019,
"learning_rate": 9.966546331768191e-05,
"loss": 1.8068,
"step": 17
},
{
"epoch": 0.2465753424657534,
"grad_norm": 0.8332269787788391,
"learning_rate": 9.956320346634876e-05,
"loss": 1.7354,
"step": 18
},
{
"epoch": 0.2602739726027397,
"grad_norm": 0.5449076294898987,
"learning_rate": 9.944739353007344e-05,
"loss": 1.635,
"step": 19
},
{
"epoch": 0.273972602739726,
"grad_norm": 0.5995677709579468,
"learning_rate": 9.931806517013612e-05,
"loss": 1.5748,
"step": 20
},
{
"epoch": 0.2876712328767123,
"grad_norm": 0.5445329546928406,
"learning_rate": 9.917525374361912e-05,
"loss": 1.4626,
"step": 21
},
{
"epoch": 0.3013698630136986,
"grad_norm": 0.46622234582901,
"learning_rate": 9.901899829374047e-05,
"loss": 1.5722,
"step": 22
},
{
"epoch": 0.3150684931506849,
"grad_norm": 0.48886317014694214,
"learning_rate": 9.884934153917997e-05,
"loss": 1.4759,
"step": 23
},
{
"epoch": 0.3287671232876712,
"grad_norm": 0.46129897236824036,
"learning_rate": 9.86663298624003e-05,
"loss": 1.5249,
"step": 24
},
{
"epoch": 0.3424657534246575,
"grad_norm": 0.465733140707016,
"learning_rate": 9.847001329696653e-05,
"loss": 1.4628,
"step": 25
},
{
"epoch": 0.3561643835616438,
"grad_norm": 0.537723958492279,
"learning_rate": 9.826044551386744e-05,
"loss": 1.2661,
"step": 26
},
{
"epoch": 0.3698630136986301,
"grad_norm": 0.4723285734653473,
"learning_rate": 9.803768380684242e-05,
"loss": 1.4456,
"step": 27
},
{
"epoch": 0.3835616438356164,
"grad_norm": 0.46580037474632263,
"learning_rate": 9.780178907671789e-05,
"loss": 1.4272,
"step": 28
},
{
"epoch": 0.3972602739726027,
"grad_norm": 0.5159716606140137,
"learning_rate": 9.755282581475769e-05,
"loss": 1.3328,
"step": 29
},
{
"epoch": 0.410958904109589,
"grad_norm": 0.5439394116401672,
"learning_rate": 9.729086208503174e-05,
"loss": 1.2224,
"step": 30
},
{
"epoch": 0.4246575342465753,
"grad_norm": 0.5588265657424927,
"learning_rate": 9.701596950580806e-05,
"loss": 1.3708,
"step": 31
},
{
"epoch": 0.4383561643835616,
"grad_norm": 0.5192043781280518,
"learning_rate": 9.672822322997305e-05,
"loss": 1.2998,
"step": 32
},
{
"epoch": 0.4520547945205479,
"grad_norm": 0.5172075033187866,
"learning_rate": 9.642770192448536e-05,
"loss": 1.2921,
"step": 33
},
{
"epoch": 0.4657534246575342,
"grad_norm": 0.6348913311958313,
"learning_rate": 9.611448774886924e-05,
"loss": 1.286,
"step": 34
},
{
"epoch": 0.4794520547945205,
"grad_norm": 0.5998979210853577,
"learning_rate": 9.578866633275288e-05,
"loss": 1.3788,
"step": 35
},
{
"epoch": 0.4931506849315068,
"grad_norm": 0.7929552793502808,
"learning_rate": 9.545032675245813e-05,
"loss": 1.3353,
"step": 36
},
{
"epoch": 0.5068493150684932,
"grad_norm": 0.5097240209579468,
"learning_rate": 9.509956150664796e-05,
"loss": 1.3159,
"step": 37
},
{
"epoch": 0.5205479452054794,
"grad_norm": 0.46544161438941956,
"learning_rate": 9.473646649103818e-05,
"loss": 1.2599,
"step": 38
},
{
"epoch": 0.5342465753424658,
"grad_norm": 0.5282853841781616,
"learning_rate": 9.43611409721806e-05,
"loss": 1.208,
"step": 39
},
{
"epoch": 0.547945205479452,
"grad_norm": 0.45313742756843567,
"learning_rate": 9.397368756032445e-05,
"loss": 1.188,
"step": 40
},
{
"epoch": 0.5616438356164384,
"grad_norm": 0.5271946787834167,
"learning_rate": 9.357421218136386e-05,
"loss": 1.19,
"step": 41
},
{
"epoch": 0.5753424657534246,
"grad_norm": 0.4225820302963257,
"learning_rate": 9.316282404787871e-05,
"loss": 1.2526,
"step": 42
},
{
"epoch": 0.589041095890411,
"grad_norm": 0.45803770422935486,
"learning_rate": 9.273963562927695e-05,
"loss": 1.2882,
"step": 43
},
{
"epoch": 0.6027397260273972,
"grad_norm": 0.4383608400821686,
"learning_rate": 9.230476262104677e-05,
"loss": 1.1984,
"step": 44
},
{
"epoch": 0.6164383561643836,
"grad_norm": 0.37650492787361145,
"learning_rate": 9.185832391312644e-05,
"loss": 1.0522,
"step": 45
},
{
"epoch": 0.6301369863013698,
"grad_norm": 0.47872722148895264,
"learning_rate": 9.140044155740101e-05,
"loss": 1.0916,
"step": 46
},
{
"epoch": 0.6438356164383562,
"grad_norm": 0.6601381301879883,
"learning_rate": 9.093124073433463e-05,
"loss": 1.25,
"step": 47
},
{
"epoch": 0.6575342465753424,
"grad_norm": 0.4518599808216095,
"learning_rate": 9.045084971874738e-05,
"loss": 1.1809,
"step": 48
},
{
"epoch": 0.6712328767123288,
"grad_norm": 0.4847405254840851,
"learning_rate": 8.995939984474624e-05,
"loss": 1.1609,
"step": 49
},
{
"epoch": 0.684931506849315,
"grad_norm": 0.4608555734157562,
"learning_rate": 8.945702546981969e-05,
"loss": 1.0136,
"step": 50
},
{
"epoch": 0.684931506849315,
"eval_loss": 1.1626672744750977,
"eval_runtime": 17.6106,
"eval_samples_per_second": 6.984,
"eval_steps_per_second": 1.76,
"step": 50
},
{
"epoch": 0.6986301369863014,
"grad_norm": 0.5371279716491699,
"learning_rate": 8.894386393810563e-05,
"loss": 1.3069,
"step": 51
},
{
"epoch": 0.7123287671232876,
"grad_norm": 0.5914545655250549,
"learning_rate": 8.842005554284296e-05,
"loss": 1.4408,
"step": 52
},
{
"epoch": 0.726027397260274,
"grad_norm": 0.5545901656150818,
"learning_rate": 8.788574348801675e-05,
"loss": 1.1461,
"step": 53
},
{
"epoch": 0.7397260273972602,
"grad_norm": 0.7079329490661621,
"learning_rate": 8.73410738492077e-05,
"loss": 1.1839,
"step": 54
},
{
"epoch": 0.7534246575342466,
"grad_norm": 0.48585987091064453,
"learning_rate": 8.678619553365659e-05,
"loss": 1.1192,
"step": 55
},
{
"epoch": 0.7671232876712328,
"grad_norm": 0.47277650237083435,
"learning_rate": 8.622126023955446e-05,
"loss": 1.1432,
"step": 56
},
{
"epoch": 0.7808219178082192,
"grad_norm": 0.45277538895606995,
"learning_rate": 8.564642241456986e-05,
"loss": 1.0386,
"step": 57
},
{
"epoch": 0.7945205479452054,
"grad_norm": 0.4574933648109436,
"learning_rate": 8.506183921362443e-05,
"loss": 1.1263,
"step": 58
},
{
"epoch": 0.8082191780821918,
"grad_norm": 0.45750612020492554,
"learning_rate": 8.44676704559283e-05,
"loss": 1.1829,
"step": 59
},
{
"epoch": 0.821917808219178,
"grad_norm": 0.4634532928466797,
"learning_rate": 8.386407858128706e-05,
"loss": 1.1831,
"step": 60
},
{
"epoch": 0.8356164383561644,
"grad_norm": 0.4355754852294922,
"learning_rate": 8.32512286056924e-05,
"loss": 1.0351,
"step": 61
},
{
"epoch": 0.8493150684931506,
"grad_norm": 0.4045752286911011,
"learning_rate": 8.262928807620843e-05,
"loss": 1.064,
"step": 62
},
{
"epoch": 0.863013698630137,
"grad_norm": 0.4316473603248596,
"learning_rate": 8.199842702516583e-05,
"loss": 1.1395,
"step": 63
},
{
"epoch": 0.8767123287671232,
"grad_norm": 0.43736621737480164,
"learning_rate": 8.135881792367686e-05,
"loss": 1.1869,
"step": 64
},
{
"epoch": 0.8904109589041096,
"grad_norm": 0.40786314010620117,
"learning_rate": 8.07106356344834e-05,
"loss": 1.083,
"step": 65
},
{
"epoch": 0.9041095890410958,
"grad_norm": 0.45700421929359436,
"learning_rate": 8.005405736415126e-05,
"loss": 1.0477,
"step": 66
},
{
"epoch": 0.9178082191780822,
"grad_norm": 0.44517654180526733,
"learning_rate": 7.938926261462366e-05,
"loss": 1.0986,
"step": 67
},
{
"epoch": 0.9315068493150684,
"grad_norm": 0.41826581954956055,
"learning_rate": 7.871643313414718e-05,
"loss": 0.9843,
"step": 68
},
{
"epoch": 0.9452054794520548,
"grad_norm": 0.5140989422798157,
"learning_rate": 7.803575286758364e-05,
"loss": 1.0801,
"step": 69
},
{
"epoch": 0.958904109589041,
"grad_norm": 0.5366918444633484,
"learning_rate": 7.734740790612136e-05,
"loss": 1.1685,
"step": 70
},
{
"epoch": 0.9726027397260274,
"grad_norm": 0.6053393483161926,
"learning_rate": 7.66515864363997e-05,
"loss": 1.033,
"step": 71
},
{
"epoch": 0.9863013698630136,
"grad_norm": 0.721362292766571,
"learning_rate": 7.594847868906076e-05,
"loss": 1.0463,
"step": 72
},
{
"epoch": 1.0,
"grad_norm": 0.48309996724128723,
"learning_rate": 7.52382768867422e-05,
"loss": 0.9676,
"step": 73
},
{
"epoch": 1.0136986301369864,
"grad_norm": 0.44758421182632446,
"learning_rate": 7.452117519152542e-05,
"loss": 1.0249,
"step": 74
},
{
"epoch": 1.0273972602739727,
"grad_norm": 0.4886939227581024,
"learning_rate": 7.379736965185368e-05,
"loss": 1.0235,
"step": 75
},
{
"epoch": 1.0410958904109588,
"grad_norm": 0.4135434031486511,
"learning_rate": 7.30670581489344e-05,
"loss": 1.0724,
"step": 76
},
{
"epoch": 1.0547945205479452,
"grad_norm": 0.4937535524368286,
"learning_rate": 7.233044034264034e-05,
"loss": 1.0435,
"step": 77
},
{
"epoch": 1.0684931506849316,
"grad_norm": 0.47225421667099,
"learning_rate": 7.158771761692464e-05,
"loss": 1.0213,
"step": 78
},
{
"epoch": 1.0821917808219177,
"grad_norm": 0.4080056846141815,
"learning_rate": 7.083909302476453e-05,
"loss": 0.8673,
"step": 79
},
{
"epoch": 1.095890410958904,
"grad_norm": 0.45888447761535645,
"learning_rate": 7.008477123264848e-05,
"loss": 1.0331,
"step": 80
},
{
"epoch": 1.1095890410958904,
"grad_norm": 0.4572179615497589,
"learning_rate": 6.932495846462261e-05,
"loss": 0.9557,
"step": 81
},
{
"epoch": 1.1232876712328768,
"grad_norm": 0.4643055200576782,
"learning_rate": 6.855986244591104e-05,
"loss": 1.0891,
"step": 82
},
{
"epoch": 1.1369863013698631,
"grad_norm": 0.4472576975822449,
"learning_rate": 6.778969234612584e-05,
"loss": 0.8666,
"step": 83
},
{
"epoch": 1.1506849315068493,
"grad_norm": 0.4406382441520691,
"learning_rate": 6.701465872208216e-05,
"loss": 0.9358,
"step": 84
},
{
"epoch": 1.1643835616438356,
"grad_norm": 0.430465966463089,
"learning_rate": 6.623497346023418e-05,
"loss": 0.9957,
"step": 85
},
{
"epoch": 1.178082191780822,
"grad_norm": 0.4511708617210388,
"learning_rate": 6.545084971874738e-05,
"loss": 0.8696,
"step": 86
},
{
"epoch": 1.191780821917808,
"grad_norm": 0.47725430130958557,
"learning_rate": 6.466250186922325e-05,
"loss": 0.8679,
"step": 87
},
{
"epoch": 1.2054794520547945,
"grad_norm": 0.4339418411254883,
"learning_rate": 6.387014543809223e-05,
"loss": 0.8531,
"step": 88
},
{
"epoch": 1.2191780821917808,
"grad_norm": 0.45652997493743896,
"learning_rate": 6.307399704769099e-05,
"loss": 1.007,
"step": 89
},
{
"epoch": 1.2328767123287672,
"grad_norm": 0.5905811786651611,
"learning_rate": 6.227427435703997e-05,
"loss": 0.9002,
"step": 90
},
{
"epoch": 1.2465753424657535,
"grad_norm": 0.6807141304016113,
"learning_rate": 6.147119600233758e-05,
"loss": 0.8187,
"step": 91
},
{
"epoch": 1.2602739726027397,
"grad_norm": 0.5293530821800232,
"learning_rate": 6.066498153718735e-05,
"loss": 0.9079,
"step": 92
},
{
"epoch": 1.273972602739726,
"grad_norm": 0.5398336052894592,
"learning_rate": 5.985585137257401e-05,
"loss": 0.99,
"step": 93
},
{
"epoch": 1.2876712328767124,
"grad_norm": 0.7187291979789734,
"learning_rate": 5.90440267166055e-05,
"loss": 0.8965,
"step": 94
},
{
"epoch": 1.3013698630136985,
"grad_norm": 0.4270886778831482,
"learning_rate": 5.8229729514036705e-05,
"loss": 0.8975,
"step": 95
},
{
"epoch": 1.3150684931506849,
"grad_norm": 0.49572721123695374,
"learning_rate": 5.74131823855921e-05,
"loss": 0.9729,
"step": 96
},
{
"epoch": 1.3287671232876712,
"grad_norm": 0.49190303683280945,
"learning_rate": 5.6594608567103456e-05,
"loss": 0.8512,
"step": 97
},
{
"epoch": 1.3424657534246576,
"grad_norm": 0.4469060003757477,
"learning_rate": 5.577423184847932e-05,
"loss": 0.8587,
"step": 98
},
{
"epoch": 1.356164383561644,
"grad_norm": 0.4466760456562042,
"learning_rate": 5.495227651252315e-05,
"loss": 0.9028,
"step": 99
},
{
"epoch": 1.36986301369863,
"grad_norm": 0.42854857444763184,
"learning_rate": 5.4128967273616625e-05,
"loss": 0.9019,
"step": 100
},
{
"epoch": 1.36986301369863,
"eval_loss": 0.9667966365814209,
"eval_runtime": 17.6076,
"eval_samples_per_second": 6.986,
"eval_steps_per_second": 1.761,
"step": 100
},
{
"epoch": 1.3835616438356164,
"grad_norm": 0.4722140431404114,
"learning_rate": 5.330452921628497e-05,
"loss": 0.9215,
"step": 101
},
{
"epoch": 1.3972602739726028,
"grad_norm": 0.4554084241390228,
"learning_rate": 5.247918773366112e-05,
"loss": 0.8165,
"step": 102
},
{
"epoch": 1.410958904109589,
"grad_norm": 0.507756233215332,
"learning_rate": 5.165316846586541e-05,
"loss": 0.949,
"step": 103
},
{
"epoch": 1.4246575342465753,
"grad_norm": 0.47338125109672546,
"learning_rate": 5.0826697238317935e-05,
"loss": 0.789,
"step": 104
},
{
"epoch": 1.4383561643835616,
"grad_norm": 0.5026863217353821,
"learning_rate": 5e-05,
"loss": 0.7763,
"step": 105
},
{
"epoch": 1.452054794520548,
"grad_norm": 0.7019026875495911,
"learning_rate": 4.917330276168208e-05,
"loss": 1.0031,
"step": 106
},
{
"epoch": 1.4657534246575343,
"grad_norm": 0.6011003851890564,
"learning_rate": 4.834683153413459e-05,
"loss": 0.9117,
"step": 107
},
{
"epoch": 1.4794520547945205,
"grad_norm": 0.6120484471321106,
"learning_rate": 4.7520812266338885e-05,
"loss": 0.9094,
"step": 108
},
{
"epoch": 1.4931506849315068,
"grad_norm": 0.8280837535858154,
"learning_rate": 4.669547078371504e-05,
"loss": 0.8034,
"step": 109
},
{
"epoch": 1.5068493150684932,
"grad_norm": 0.4636995792388916,
"learning_rate": 4.5871032726383386e-05,
"loss": 1.0061,
"step": 110
},
{
"epoch": 1.5205479452054793,
"grad_norm": 0.45758214592933655,
"learning_rate": 4.504772348747687e-05,
"loss": 0.9412,
"step": 111
},
{
"epoch": 1.5342465753424657,
"grad_norm": 0.6021467447280884,
"learning_rate": 4.4225768151520694e-05,
"loss": 0.8694,
"step": 112
},
{
"epoch": 1.547945205479452,
"grad_norm": 0.501178503036499,
"learning_rate": 4.3405391432896555e-05,
"loss": 1.0016,
"step": 113
},
{
"epoch": 1.5616438356164384,
"grad_norm": 0.4760044813156128,
"learning_rate": 4.2586817614407895e-05,
"loss": 0.9584,
"step": 114
},
{
"epoch": 1.5753424657534247,
"grad_norm": 0.48190802335739136,
"learning_rate": 4.17702704859633e-05,
"loss": 1.0039,
"step": 115
},
{
"epoch": 1.589041095890411,
"grad_norm": 0.43973857164382935,
"learning_rate": 4.095597328339452e-05,
"loss": 0.8378,
"step": 116
},
{
"epoch": 1.6027397260273972,
"grad_norm": 0.4319341778755188,
"learning_rate": 4.0144148627425993e-05,
"loss": 0.9102,
"step": 117
},
{
"epoch": 1.6164383561643836,
"grad_norm": 0.4170323610305786,
"learning_rate": 3.933501846281267e-05,
"loss": 0.9285,
"step": 118
},
{
"epoch": 1.6301369863013697,
"grad_norm": 0.4655342400074005,
"learning_rate": 3.852880399766243e-05,
"loss": 0.9126,
"step": 119
},
{
"epoch": 1.643835616438356,
"grad_norm": 0.41839924454689026,
"learning_rate": 3.772572564296005e-05,
"loss": 0.8802,
"step": 120
},
{
"epoch": 1.6575342465753424,
"grad_norm": 0.43748000264167786,
"learning_rate": 3.6926002952309016e-05,
"loss": 0.8768,
"step": 121
},
{
"epoch": 1.6712328767123288,
"grad_norm": 0.49058687686920166,
"learning_rate": 3.612985456190778e-05,
"loss": 0.9443,
"step": 122
},
{
"epoch": 1.6849315068493151,
"grad_norm": 0.4752422571182251,
"learning_rate": 3.533749813077677e-05,
"loss": 0.7484,
"step": 123
},
{
"epoch": 1.6986301369863015,
"grad_norm": 0.5436539649963379,
"learning_rate": 3.4549150281252636e-05,
"loss": 0.9132,
"step": 124
},
{
"epoch": 1.7123287671232876,
"grad_norm": 0.6123542189598083,
"learning_rate": 3.3765026539765834e-05,
"loss": 0.9182,
"step": 125
},
{
"epoch": 1.726027397260274,
"grad_norm": 0.5577338337898254,
"learning_rate": 3.298534127791785e-05,
"loss": 0.7582,
"step": 126
},
{
"epoch": 1.7397260273972601,
"grad_norm": 0.7534928321838379,
"learning_rate": 3.221030765387417e-05,
"loss": 0.7775,
"step": 127
},
{
"epoch": 1.7534246575342465,
"grad_norm": 0.5091196298599243,
"learning_rate": 3.144013755408895e-05,
"loss": 0.9271,
"step": 128
},
{
"epoch": 1.7671232876712328,
"grad_norm": 0.5113611221313477,
"learning_rate": 3.0675041535377405e-05,
"loss": 0.8719,
"step": 129
},
{
"epoch": 1.7808219178082192,
"grad_norm": 0.49497002363204956,
"learning_rate": 2.991522876735154e-05,
"loss": 0.9052,
"step": 130
},
{
"epoch": 1.7945205479452055,
"grad_norm": 0.4653341472148895,
"learning_rate": 2.916090697523549e-05,
"loss": 0.8384,
"step": 131
},
{
"epoch": 1.808219178082192,
"grad_norm": 0.48844584822654724,
"learning_rate": 2.8412282383075363e-05,
"loss": 0.9888,
"step": 132
},
{
"epoch": 1.821917808219178,
"grad_norm": 0.4494996964931488,
"learning_rate": 2.766955965735968e-05,
"loss": 0.8235,
"step": 133
},
{
"epoch": 1.8356164383561644,
"grad_norm": 0.47813329100608826,
"learning_rate": 2.693294185106562e-05,
"loss": 0.8007,
"step": 134
},
{
"epoch": 1.8493150684931505,
"grad_norm": 0.4347015619277954,
"learning_rate": 2.6202630348146324e-05,
"loss": 0.8159,
"step": 135
},
{
"epoch": 1.8630136986301369,
"grad_norm": 0.4807911217212677,
"learning_rate": 2.547882480847461e-05,
"loss": 0.8737,
"step": 136
},
{
"epoch": 1.8767123287671232,
"grad_norm": 0.42724063992500305,
"learning_rate": 2.476172311325783e-05,
"loss": 0.8337,
"step": 137
},
{
"epoch": 1.8904109589041096,
"grad_norm": 0.4619234502315521,
"learning_rate": 2.405152131093926e-05,
"loss": 0.8607,
"step": 138
},
{
"epoch": 1.904109589041096,
"grad_norm": 0.4360385835170746,
"learning_rate": 2.3348413563600325e-05,
"loss": 0.8472,
"step": 139
},
{
"epoch": 1.9178082191780823,
"grad_norm": 0.4591448903083801,
"learning_rate": 2.2652592093878666e-05,
"loss": 0.8806,
"step": 140
},
{
"epoch": 1.9315068493150684,
"grad_norm": 0.4580991864204407,
"learning_rate": 2.196424713241637e-05,
"loss": 0.845,
"step": 141
},
{
"epoch": 1.9452054794520548,
"grad_norm": 0.47901368141174316,
"learning_rate": 2.128356686585282e-05,
"loss": 0.8868,
"step": 142
},
{
"epoch": 1.958904109589041,
"grad_norm": 0.6799347400665283,
"learning_rate": 2.061073738537635e-05,
"loss": 0.9488,
"step": 143
},
{
"epoch": 1.9726027397260273,
"grad_norm": 0.5909904837608337,
"learning_rate": 1.9945942635848748e-05,
"loss": 0.8113,
"step": 144
},
{
"epoch": 1.9863013698630136,
"grad_norm": 0.7365491390228271,
"learning_rate": 1.928936436551661e-05,
"loss": 0.7967,
"step": 145
},
{
"epoch": 2.0,
"grad_norm": 0.5132492184638977,
"learning_rate": 1.8641182076323148e-05,
"loss": 0.8151,
"step": 146
},
{
"epoch": 2.0136986301369864,
"grad_norm": 0.4226134419441223,
"learning_rate": 1.800157297483417e-05,
"loss": 0.8009,
"step": 147
},
{
"epoch": 2.0273972602739727,
"grad_norm": 0.49170130491256714,
"learning_rate": 1.7370711923791567e-05,
"loss": 0.8525,
"step": 148
},
{
"epoch": 2.041095890410959,
"grad_norm": 0.4582540690898895,
"learning_rate": 1.6748771394307585e-05,
"loss": 0.815,
"step": 149
},
{
"epoch": 2.0547945205479454,
"grad_norm": 0.45990821719169617,
"learning_rate": 1.6135921418712956e-05,
"loss": 0.7943,
"step": 150
},
{
"epoch": 2.0547945205479454,
"eval_loss": 0.8967317938804626,
"eval_runtime": 17.6064,
"eval_samples_per_second": 6.986,
"eval_steps_per_second": 1.761,
"step": 150
},
{
"epoch": 2.0684931506849313,
"grad_norm": 0.4779188930988312,
"learning_rate": 1.553232954407171e-05,
"loss": 0.9413,
"step": 151
},
{
"epoch": 2.0821917808219177,
"grad_norm": 0.41810569167137146,
"learning_rate": 1.4938160786375572e-05,
"loss": 0.8122,
"step": 152
},
{
"epoch": 2.095890410958904,
"grad_norm": 0.47373005747795105,
"learning_rate": 1.435357758543015e-05,
"loss": 0.8918,
"step": 153
},
{
"epoch": 2.1095890410958904,
"grad_norm": 0.4416920244693756,
"learning_rate": 1.3778739760445552e-05,
"loss": 0.8963,
"step": 154
},
{
"epoch": 2.1232876712328768,
"grad_norm": 0.4114491641521454,
"learning_rate": 1.3213804466343421e-05,
"loss": 0.8023,
"step": 155
},
{
"epoch": 2.136986301369863,
"grad_norm": 0.39008828997612,
"learning_rate": 1.2658926150792322e-05,
"loss": 0.6837,
"step": 156
},
{
"epoch": 2.1506849315068495,
"grad_norm": 0.3919396996498108,
"learning_rate": 1.2114256511983274e-05,
"loss": 0.7901,
"step": 157
},
{
"epoch": 2.1643835616438354,
"grad_norm": 0.3843747079372406,
"learning_rate": 1.157994445715706e-05,
"loss": 0.7824,
"step": 158
},
{
"epoch": 2.1780821917808217,
"grad_norm": 0.45568573474884033,
"learning_rate": 1.1056136061894384e-05,
"loss": 0.8835,
"step": 159
},
{
"epoch": 2.191780821917808,
"grad_norm": 0.39322221279144287,
"learning_rate": 1.0542974530180327e-05,
"loss": 0.7361,
"step": 160
},
{
"epoch": 2.2054794520547945,
"grad_norm": 0.4604373276233673,
"learning_rate": 1.0040600155253765e-05,
"loss": 0.7979,
"step": 161
},
{
"epoch": 2.219178082191781,
"grad_norm": 0.5597333312034607,
"learning_rate": 9.549150281252633e-06,
"loss": 0.7723,
"step": 162
},
{
"epoch": 2.232876712328767,
"grad_norm": 0.575202226638794,
"learning_rate": 9.068759265665384e-06,
"loss": 0.741,
"step": 163
},
{
"epoch": 2.2465753424657535,
"grad_norm": 0.7536724209785461,
"learning_rate": 8.599558442598998e-06,
"loss": 0.6639,
"step": 164
},
{
"epoch": 2.26027397260274,
"grad_norm": 0.42641764879226685,
"learning_rate": 8.141676086873572e-06,
"loss": 0.7761,
"step": 165
},
{
"epoch": 2.2739726027397262,
"grad_norm": 0.4226329028606415,
"learning_rate": 7.695237378953223e-06,
"loss": 0.7867,
"step": 166
},
{
"epoch": 2.287671232876712,
"grad_norm": 0.45755329728126526,
"learning_rate": 7.260364370723044e-06,
"loss": 0.8356,
"step": 167
},
{
"epoch": 2.3013698630136985,
"grad_norm": 0.45723769068717957,
"learning_rate": 6.837175952121306e-06,
"loss": 0.8119,
"step": 168
},
{
"epoch": 2.315068493150685,
"grad_norm": 0.4459364712238312,
"learning_rate": 6.425787818636131e-06,
"loss": 0.7028,
"step": 169
},
{
"epoch": 2.328767123287671,
"grad_norm": 0.4375406801700592,
"learning_rate": 6.026312439675552e-06,
"loss": 0.822,
"step": 170
},
{
"epoch": 2.3424657534246576,
"grad_norm": 0.45448777079582214,
"learning_rate": 5.6388590278194096e-06,
"loss": 0.7764,
"step": 171
},
{
"epoch": 2.356164383561644,
"grad_norm": 0.41775596141815186,
"learning_rate": 5.263533508961827e-06,
"loss": 0.7729,
"step": 172
},
{
"epoch": 2.3698630136986303,
"grad_norm": 0.4652521014213562,
"learning_rate": 4.900438493352055e-06,
"loss": 0.8879,
"step": 173
},
{
"epoch": 2.383561643835616,
"grad_norm": 0.3823181092739105,
"learning_rate": 4.549673247541875e-06,
"loss": 0.76,
"step": 174
},
{
"epoch": 2.3972602739726026,
"grad_norm": 0.4191032350063324,
"learning_rate": 4.2113336672471245e-06,
"loss": 0.8116,
"step": 175
},
{
"epoch": 2.410958904109589,
"grad_norm": 0.43679967522621155,
"learning_rate": 3.885512251130763e-06,
"loss": 0.8764,
"step": 176
},
{
"epoch": 2.4246575342465753,
"grad_norm": 0.4129420518875122,
"learning_rate": 3.5722980755146517e-06,
"loss": 0.6745,
"step": 177
},
{
"epoch": 2.4383561643835616,
"grad_norm": 0.43422091007232666,
"learning_rate": 3.271776770026963e-06,
"loss": 0.7225,
"step": 178
},
{
"epoch": 2.452054794520548,
"grad_norm": 0.42894184589385986,
"learning_rate": 2.9840304941919415e-06,
"loss": 0.7447,
"step": 179
},
{
"epoch": 2.4657534246575343,
"grad_norm": 0.561370849609375,
"learning_rate": 2.7091379149682685e-06,
"loss": 0.9706,
"step": 180
},
{
"epoch": 2.4794520547945207,
"grad_norm": 0.5812061429023743,
"learning_rate": 2.4471741852423237e-06,
"loss": 0.6661,
"step": 181
},
{
"epoch": 2.493150684931507,
"grad_norm": 0.7121996879577637,
"learning_rate": 2.1982109232821178e-06,
"loss": 0.6989,
"step": 182
},
{
"epoch": 2.506849315068493,
"grad_norm": 0.42828068137168884,
"learning_rate": 1.962316193157593e-06,
"loss": 0.8475,
"step": 183
},
{
"epoch": 2.5205479452054793,
"grad_norm": 0.3967253863811493,
"learning_rate": 1.7395544861325718e-06,
"loss": 0.77,
"step": 184
},
{
"epoch": 2.5342465753424657,
"grad_norm": 0.3968483805656433,
"learning_rate": 1.5299867030334814e-06,
"loss": 0.835,
"step": 185
},
{
"epoch": 2.547945205479452,
"grad_norm": 0.42159703373908997,
"learning_rate": 1.333670137599713e-06,
"loss": 0.9025,
"step": 186
},
{
"epoch": 2.5616438356164384,
"grad_norm": 0.41942930221557617,
"learning_rate": 1.1506584608200367e-06,
"loss": 0.8929,
"step": 187
},
{
"epoch": 2.5753424657534247,
"grad_norm": 0.42676061391830444,
"learning_rate": 9.810017062595322e-07,
"loss": 0.8576,
"step": 188
},
{
"epoch": 2.589041095890411,
"grad_norm": 0.3957562744617462,
"learning_rate": 8.247462563808817e-07,
"loss": 0.7847,
"step": 189
},
{
"epoch": 2.602739726027397,
"grad_norm": 0.3963407576084137,
"learning_rate": 6.819348298638839e-07,
"loss": 0.832,
"step": 190
},
{
"epoch": 2.616438356164384,
"grad_norm": 0.42751544713974,
"learning_rate": 5.526064699265753e-07,
"loss": 0.7682,
"step": 191
},
{
"epoch": 2.6301369863013697,
"grad_norm": 0.42197951674461365,
"learning_rate": 4.367965336512403e-07,
"loss": 0.7825,
"step": 192
},
{
"epoch": 2.643835616438356,
"grad_norm": 0.4065631031990051,
"learning_rate": 3.3453668231809286e-07,
"loss": 0.7721,
"step": 193
},
{
"epoch": 2.6575342465753424,
"grad_norm": 0.43822962045669556,
"learning_rate": 2.458548727494292e-07,
"loss": 0.8622,
"step": 194
},
{
"epoch": 2.671232876712329,
"grad_norm": 0.4441068768501282,
"learning_rate": 1.7077534966650766e-07,
"loss": 0.783,
"step": 195
},
{
"epoch": 2.684931506849315,
"grad_norm": 0.3991951048374176,
"learning_rate": 1.0931863906127327e-07,
"loss": 0.643,
"step": 196
},
{
"epoch": 2.6986301369863015,
"grad_norm": 0.5015789866447449,
"learning_rate": 6.150154258476315e-08,
"loss": 0.7262,
"step": 197
},
{
"epoch": 2.712328767123288,
"grad_norm": 0.4599153995513916,
"learning_rate": 2.7337132953697554e-08,
"loss": 0.6851,
"step": 198
},
{
"epoch": 2.7260273972602738,
"grad_norm": 0.5867598056793213,
"learning_rate": 6.834750376549792e-09,
"loss": 0.7681,
"step": 199
},
{
"epoch": 2.73972602739726,
"grad_norm": 0.6048241257667542,
"learning_rate": 0.0,
"loss": 0.636,
"step": 200
},
{
"epoch": 2.73972602739726,
"eval_loss": 0.8844783902168274,
"eval_runtime": 17.6108,
"eval_samples_per_second": 6.984,
"eval_steps_per_second": 1.76,
"step": 200
}
],
"logging_steps": 1,
"max_steps": 200,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 50,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 5,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 5.495599768849613e+17,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}