Text Generation
Safetensors
Chinese
English
Aurora-Plus / checkpoint-18000 /trainer_state.json
wangrongsheng's picture
Upload 12 files
ee893bf
raw
history blame contribute delete
No virus
22.4 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9271779022599962,
"eval_steps": 500,
"global_step": 18000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 4.9996726480206315e-05,
"loss": 0.7422,
"step": 100
},
{
"epoch": 0.01,
"learning_rate": 4.9986906778099784e-05,
"loss": 0.6673,
"step": 200
},
{
"epoch": 0.02,
"learning_rate": 4.9970543465279565e-05,
"loss": 0.6749,
"step": 300
},
{
"epoch": 0.02,
"learning_rate": 4.994764082699591e-05,
"loss": 0.6481,
"step": 400
},
{
"epoch": 0.03,
"learning_rate": 4.991820486102801e-05,
"loss": 0.6505,
"step": 500
},
{
"epoch": 0.03,
"learning_rate": 4.9882243276113245e-05,
"loss": 0.6708,
"step": 600
},
{
"epoch": 0.04,
"learning_rate": 4.983976548992841e-05,
"loss": 0.6596,
"step": 700
},
{
"epoch": 0.04,
"learning_rate": 4.9790782626623436e-05,
"loss": 0.6657,
"step": 800
},
{
"epoch": 0.05,
"learning_rate": 4.97353075139081e-05,
"loss": 0.659,
"step": 900
},
{
"epoch": 0.05,
"learning_rate": 4.9673354679692785e-05,
"loss": 0.6519,
"step": 1000
},
{
"epoch": 0.06,
"learning_rate": 4.960494034828381e-05,
"loss": 0.638,
"step": 1100
},
{
"epoch": 0.06,
"learning_rate": 4.9530082436134614e-05,
"loss": 0.629,
"step": 1200
},
{
"epoch": 0.07,
"learning_rate": 4.944880054715378e-05,
"loss": 0.6464,
"step": 1300
},
{
"epoch": 0.07,
"learning_rate": 4.9361115967571094e-05,
"loss": 0.642,
"step": 1400
},
{
"epoch": 0.08,
"learning_rate": 4.926705166036311e-05,
"loss": 0.6431,
"step": 1500
},
{
"epoch": 0.08,
"learning_rate": 4.916663225923953e-05,
"loss": 0.6465,
"step": 1600
},
{
"epoch": 0.09,
"learning_rate": 4.905988406219217e-05,
"loss": 0.6439,
"step": 1700
},
{
"epoch": 0.09,
"learning_rate": 4.8946835024607885e-05,
"loss": 0.652,
"step": 1800
},
{
"epoch": 0.1,
"learning_rate": 4.8827514751947656e-05,
"loss": 0.6376,
"step": 1900
},
{
"epoch": 0.1,
"learning_rate": 4.8701954491993426e-05,
"loss": 0.6357,
"step": 2000
},
{
"epoch": 0.11,
"learning_rate": 4.85701871266649e-05,
"loss": 0.6338,
"step": 2100
},
{
"epoch": 0.11,
"learning_rate": 4.8432247163408365e-05,
"loss": 0.6591,
"step": 2200
},
{
"epoch": 0.12,
"learning_rate": 4.8288170726159815e-05,
"loss": 0.621,
"step": 2300
},
{
"epoch": 0.12,
"learning_rate": 4.8137995545884794e-05,
"loss": 0.6337,
"step": 2400
},
{
"epoch": 0.13,
"learning_rate": 4.798176095069731e-05,
"loss": 0.637,
"step": 2500
},
{
"epoch": 0.13,
"learning_rate": 4.781950785556054e-05,
"loss": 0.6464,
"step": 2600
},
{
"epoch": 0.14,
"learning_rate": 4.7651278751571984e-05,
"loss": 0.6539,
"step": 2700
},
{
"epoch": 0.14,
"learning_rate": 4.747711769483576e-05,
"loss": 0.6233,
"step": 2800
},
{
"epoch": 0.15,
"learning_rate": 4.729707029492521e-05,
"loss": 0.6476,
"step": 2900
},
{
"epoch": 0.15,
"learning_rate": 4.711118370293852e-05,
"loss": 0.6302,
"step": 3000
},
{
"epoch": 0.16,
"learning_rate": 4.691950659915074e-05,
"loss": 0.632,
"step": 3100
},
{
"epoch": 0.16,
"learning_rate": 4.672208918026535e-05,
"loss": 0.6281,
"step": 3200
},
{
"epoch": 0.17,
"learning_rate": 4.6518983146268604e-05,
"loss": 0.6514,
"step": 3300
},
{
"epoch": 0.18,
"learning_rate": 4.63102416868903e-05,
"loss": 0.6254,
"step": 3400
},
{
"epoch": 0.18,
"learning_rate": 4.609591946767437e-05,
"loss": 0.6412,
"step": 3500
},
{
"epoch": 0.19,
"learning_rate": 4.587607261566294e-05,
"loss": 0.6647,
"step": 3600
},
{
"epoch": 0.19,
"learning_rate": 4.565075870469777e-05,
"loss": 0.644,
"step": 3700
},
{
"epoch": 0.2,
"learning_rate": 4.542003674034263e-05,
"loss": 0.6328,
"step": 3800
},
{
"epoch": 0.2,
"learning_rate": 4.5183967144430904e-05,
"loss": 0.6454,
"step": 3900
},
{
"epoch": 0.21,
"learning_rate": 4.4942611739242166e-05,
"loss": 0.6619,
"step": 4000
},
{
"epoch": 0.21,
"learning_rate": 4.469603373131214e-05,
"loss": 0.6326,
"step": 4100
},
{
"epoch": 0.22,
"learning_rate": 4.444429769487997e-05,
"loss": 0.6373,
"step": 4200
},
{
"epoch": 0.22,
"learning_rate": 4.4187469554977503e-05,
"loss": 0.6375,
"step": 4300
},
{
"epoch": 0.23,
"learning_rate": 4.392561657016472e-05,
"loss": 0.6181,
"step": 4400
},
{
"epoch": 0.23,
"learning_rate": 4.3658807314915915e-05,
"loss": 0.6415,
"step": 4500
},
{
"epoch": 0.24,
"learning_rate": 4.338711166166135e-05,
"loss": 0.6235,
"step": 4600
},
{
"epoch": 0.24,
"learning_rate": 4.3110600762488915e-05,
"loss": 0.643,
"step": 4700
},
{
"epoch": 0.25,
"learning_rate": 4.282934703051076e-05,
"loss": 0.6488,
"step": 4800
},
{
"epoch": 0.25,
"learning_rate": 4.2543424120899556e-05,
"loss": 0.6536,
"step": 4900
},
{
"epoch": 0.26,
"learning_rate": 4.2252906911599646e-05,
"loss": 0.6396,
"step": 5000
},
{
"epoch": 0.26,
"learning_rate": 4.195787148371782e-05,
"loss": 0.6456,
"step": 5100
},
{
"epoch": 0.27,
"learning_rate": 4.165839510159914e-05,
"loss": 0.6213,
"step": 5200
},
{
"epoch": 0.27,
"learning_rate": 4.1354556192592766e-05,
"loss": 0.6408,
"step": 5300
},
{
"epoch": 0.28,
"learning_rate": 4.1046434326513305e-05,
"loss": 0.6394,
"step": 5400
},
{
"epoch": 0.28,
"learning_rate": 4.073411019480297e-05,
"loss": 0.6338,
"step": 5500
},
{
"epoch": 0.29,
"learning_rate": 4.041766558939991e-05,
"loss": 0.6271,
"step": 5600
},
{
"epoch": 0.29,
"learning_rate": 4.009718338131851e-05,
"loss": 0.6269,
"step": 5700
},
{
"epoch": 0.3,
"learning_rate": 3.97727474989469e-05,
"loss": 0.6465,
"step": 5800
},
{
"epoch": 0.3,
"learning_rate": 3.944444290606768e-05,
"loss": 0.6372,
"step": 5900
},
{
"epoch": 0.31,
"learning_rate": 3.911235557960752e-05,
"loss": 0.6399,
"step": 6000
},
{
"epoch": 0.31,
"learning_rate": 3.877657248712131e-05,
"loss": 0.62,
"step": 6100
},
{
"epoch": 0.32,
"learning_rate": 3.844059304094324e-05,
"loss": 0.6468,
"step": 6200
},
{
"epoch": 0.32,
"learning_rate": 3.8097717913954655e-05,
"loss": 0.6362,
"step": 6300
},
{
"epoch": 0.33,
"learning_rate": 3.775141273585859e-05,
"loss": 0.6302,
"step": 6400
},
{
"epoch": 0.33,
"learning_rate": 3.740176819760346e-05,
"loss": 0.6334,
"step": 6500
},
{
"epoch": 0.34,
"learning_rate": 3.704887586465459e-05,
"loss": 0.6507,
"step": 6600
},
{
"epoch": 0.35,
"learning_rate": 3.669282815301495e-05,
"loss": 0.6403,
"step": 6700
},
{
"epoch": 0.35,
"learning_rate": 3.6333718305023066e-05,
"loss": 0.6407,
"step": 6800
},
{
"epoch": 0.36,
"learning_rate": 3.597164036493457e-05,
"loss": 0.6477,
"step": 6900
},
{
"epoch": 0.36,
"learning_rate": 3.560668915429376e-05,
"loss": 0.656,
"step": 7000
},
{
"epoch": 0.37,
"learning_rate": 3.5238960247101584e-05,
"loss": 0.6252,
"step": 7100
},
{
"epoch": 0.37,
"learning_rate": 3.486854994478655e-05,
"loss": 0.6345,
"step": 7200
},
{
"epoch": 0.38,
"learning_rate": 3.4499297670475796e-05,
"loss": 0.6355,
"step": 7300
},
{
"epoch": 0.38,
"learning_rate": 3.412384064706181e-05,
"loss": 0.6468,
"step": 7400
},
{
"epoch": 0.39,
"learning_rate": 3.374599425781161e-05,
"loss": 0.6356,
"step": 7500
},
{
"epoch": 0.39,
"learning_rate": 3.336585745373593e-05,
"loss": 0.6335,
"step": 7600
},
{
"epoch": 0.4,
"learning_rate": 3.2983529785662964e-05,
"loss": 0.6092,
"step": 7700
},
{
"epoch": 0.4,
"learning_rate": 3.2599111378167855e-05,
"loss": 0.6337,
"step": 7800
},
{
"epoch": 0.41,
"learning_rate": 3.221657650708416e-05,
"loss": 0.6455,
"step": 7900
},
{
"epoch": 0.41,
"learning_rate": 3.182829754439824e-05,
"loss": 0.627,
"step": 8000
},
{
"epoch": 0.42,
"learning_rate": 3.143823037633881e-05,
"loss": 0.6272,
"step": 8100
},
{
"epoch": 0.42,
"learning_rate": 3.104647715431351e-05,
"loss": 0.6337,
"step": 8200
},
{
"epoch": 0.43,
"learning_rate": 3.0653140471276476e-05,
"loss": 0.6562,
"step": 8300
},
{
"epoch": 0.43,
"learning_rate": 3.0258323334861104e-05,
"loss": 0.6184,
"step": 8400
},
{
"epoch": 0.44,
"learning_rate": 2.9862129140404272e-05,
"loss": 0.6175,
"step": 8500
},
{
"epoch": 0.44,
"learning_rate": 2.9464661643868984e-05,
"loss": 0.6489,
"step": 8600
},
{
"epoch": 0.45,
"learning_rate": 2.9066024934672632e-05,
"loss": 0.6423,
"step": 8700
},
{
"epoch": 0.45,
"learning_rate": 2.866632340842786e-05,
"loss": 0.6127,
"step": 8800
},
{
"epoch": 0.46,
"learning_rate": 2.8265661739603277e-05,
"loss": 0.6247,
"step": 8900
},
{
"epoch": 0.46,
"learning_rate": 2.7864144854111168e-05,
"loss": 0.6307,
"step": 9000
},
{
"epoch": 0.47,
"learning_rate": 2.7461877901829303e-05,
"loss": 0.6231,
"step": 9100
},
{
"epoch": 0.47,
"learning_rate": 2.7058966229064143e-05,
"loss": 0.6304,
"step": 9200
},
{
"epoch": 0.48,
"learning_rate": 2.6655515350962545e-05,
"loss": 0.6408,
"step": 9300
},
{
"epoch": 0.48,
"learning_rate": 2.625163092387934e-05,
"loss": 0.6198,
"step": 9400
},
{
"epoch": 0.49,
"learning_rate": 2.584741871770784e-05,
"loss": 0.6378,
"step": 9500
},
{
"epoch": 0.49,
"learning_rate": 2.5442984588180657e-05,
"loss": 0.6303,
"step": 9600
},
{
"epoch": 0.5,
"learning_rate": 2.5038434449148057e-05,
"loss": 0.6297,
"step": 9700
},
{
"epoch": 0.5,
"learning_rate": 2.463387424484106e-05,
"loss": 0.6258,
"step": 9800
},
{
"epoch": 0.51,
"learning_rate": 2.4229409922126572e-05,
"loss": 0.6349,
"step": 9900
},
{
"epoch": 0.52,
"learning_rate": 2.382514740276191e-05,
"loss": 0.6259,
"step": 10000
},
{
"epoch": 0.52,
"learning_rate": 2.3421192555655785e-05,
"loss": 0.6067,
"step": 10100
},
{
"epoch": 0.53,
"learning_rate": 2.3017651169143217e-05,
"loss": 0.6316,
"step": 10200
},
{
"epoch": 0.53,
"learning_rate": 2.2614628923281524e-05,
"loss": 0.6402,
"step": 10300
},
{
"epoch": 0.54,
"learning_rate": 2.2212231362174614e-05,
"loss": 0.6211,
"step": 10400
},
{
"epoch": 0.54,
"learning_rate": 2.1810563866332996e-05,
"loss": 0.6315,
"step": 10500
},
{
"epoch": 0.55,
"learning_rate": 2.1409731625076533e-05,
"loss": 0.6206,
"step": 10600
},
{
"epoch": 0.55,
"learning_rate": 2.1009839608987253e-05,
"loss": 0.6201,
"step": 10700
},
{
"epoch": 0.56,
"learning_rate": 2.0610992542419582e-05,
"loss": 0.6489,
"step": 10800
},
{
"epoch": 0.56,
"learning_rate": 2.0213294876074866e-05,
"loss": 0.6381,
"step": 10900
},
{
"epoch": 0.57,
"learning_rate": 1.9816850759647733e-05,
"loss": 0.6321,
"step": 11000
},
{
"epoch": 0.57,
"learning_rate": 1.9421764014551165e-05,
"loss": 0.6222,
"step": 11100
},
{
"epoch": 0.58,
"learning_rate": 1.902813810672756e-05,
"loss": 0.6275,
"step": 11200
},
{
"epoch": 0.58,
"learning_rate": 1.8636076119553e-05,
"loss": 0.6281,
"step": 11300
},
{
"epoch": 0.59,
"learning_rate": 1.824568072684148e-05,
"loss": 0.6345,
"step": 11400
},
{
"epoch": 0.59,
"learning_rate": 1.7857054165956648e-05,
"loss": 0.621,
"step": 11500
},
{
"epoch": 0.6,
"learning_rate": 1.7470298211037665e-05,
"loss": 0.5951,
"step": 11600
},
{
"epoch": 0.6,
"learning_rate": 1.7085514146346415e-05,
"loss": 0.6293,
"step": 11700
},
{
"epoch": 0.61,
"learning_rate": 1.6702802739743083e-05,
"loss": 0.626,
"step": 11800
},
{
"epoch": 0.61,
"learning_rate": 1.6322264216296822e-05,
"loss": 0.6376,
"step": 11900
},
{
"epoch": 0.62,
"learning_rate": 1.594399823203876e-05,
"loss": 0.643,
"step": 12000
},
{
"epoch": 0.62,
"learning_rate": 1.5568103847863835e-05,
"loss": 0.6274,
"step": 12100
},
{
"epoch": 0.63,
"learning_rate": 1.5194679503588585e-05,
"loss": 0.6421,
"step": 12200
},
{
"epoch": 0.63,
"learning_rate": 1.4823822992171621e-05,
"loss": 0.6202,
"step": 12300
},
{
"epoch": 0.64,
"learning_rate": 1.445563143410339e-05,
"loss": 0.6156,
"step": 12400
},
{
"epoch": 0.64,
"learning_rate": 1.4090201251972163e-05,
"loss": 0.6159,
"step": 12500
},
{
"epoch": 0.65,
"learning_rate": 1.3727628145212673e-05,
"loss": 0.6285,
"step": 12600
},
{
"epoch": 0.65,
"learning_rate": 1.3368007065044269e-05,
"loss": 0.6356,
"step": 12700
},
{
"epoch": 0.66,
"learning_rate": 1.3011432189604872e-05,
"loss": 0.6285,
"step": 12800
},
{
"epoch": 0.66,
"learning_rate": 1.2657996899287505e-05,
"loss": 0.6319,
"step": 12900
},
{
"epoch": 0.67,
"learning_rate": 1.2307793752285665e-05,
"loss": 0.6166,
"step": 13000
},
{
"epoch": 0.67,
"learning_rate": 1.1960914460354017e-05,
"loss": 0.6316,
"step": 13100
},
{
"epoch": 0.68,
"learning_rate": 1.1617449864790823e-05,
"loss": 0.6124,
"step": 13200
},
{
"epoch": 0.69,
"learning_rate": 1.1277489912648251e-05,
"loss": 0.6318,
"step": 13300
},
{
"epoch": 0.69,
"learning_rate": 1.0944469217262731e-05,
"loss": 0.6409,
"step": 13400
},
{
"epoch": 0.7,
"learning_rate": 1.0615056158497555e-05,
"loss": 0.6244,
"step": 13500
},
{
"epoch": 0.7,
"learning_rate": 1.0286064299421735e-05,
"loss": 0.6529,
"step": 13600
},
{
"epoch": 0.71,
"learning_rate": 9.964157780320574e-06,
"loss": 0.6174,
"step": 13700
},
{
"epoch": 0.71,
"learning_rate": 9.642917883925478e-06,
"loss": 0.6359,
"step": 13800
},
{
"epoch": 0.72,
"learning_rate": 9.325699724512796e-06,
"loss": 0.6289,
"step": 13900
},
{
"epoch": 0.72,
"learning_rate": 9.012586375676443e-06,
"loss": 0.6221,
"step": 14000
},
{
"epoch": 0.73,
"learning_rate": 8.70365983603603e-06,
"loss": 0.6368,
"step": 14100
},
{
"epoch": 0.73,
"learning_rate": 8.399001007762921e-06,
"loss": 0.6225,
"step": 14200
},
{
"epoch": 0.74,
"learning_rate": 8.098689675393509e-06,
"loss": 0.6258,
"step": 14300
},
{
"epoch": 0.74,
"learning_rate": 7.802804484935048e-06,
"loss": 0.6212,
"step": 14400
},
{
"epoch": 0.75,
"learning_rate": 7.511422923269759e-06,
"loss": 0.6354,
"step": 14500
},
{
"epoch": 0.75,
"learning_rate": 7.224621297862396e-06,
"loss": 0.6396,
"step": 14600
},
{
"epoch": 0.76,
"learning_rate": 6.9424747167767785e-06,
"loss": 0.6066,
"step": 14700
},
{
"epoch": 0.76,
"learning_rate": 6.665057069006344e-06,
"loss": 0.6273,
"step": 14800
},
{
"epoch": 0.77,
"learning_rate": 6.39244100512397e-06,
"loss": 0.6264,
"step": 14900
},
{
"epoch": 0.77,
"learning_rate": 6.124697918256153e-06,
"loss": 0.6335,
"step": 15000
},
{
"epoch": 0.78,
"learning_rate": 5.8618979253864585e-06,
"loss": 0.6205,
"step": 15100
},
{
"epoch": 0.78,
"learning_rate": 5.604109848993158e-06,
"loss": 0.6349,
"step": 15200
},
{
"epoch": 0.79,
"learning_rate": 5.35140119902591e-06,
"loss": 0.6134,
"step": 15300
},
{
"epoch": 0.79,
"learning_rate": 5.103838155226118e-06,
"loss": 0.6275,
"step": 15400
},
{
"epoch": 0.8,
"learning_rate": 4.861485549795722e-06,
"loss": 0.6228,
"step": 15500
},
{
"epoch": 0.8,
"learning_rate": 4.6244068504187835e-06,
"loss": 0.6288,
"step": 15600
},
{
"epoch": 0.81,
"learning_rate": 4.392664143640512e-06,
"loss": 0.625,
"step": 15700
},
{
"epoch": 0.81,
"learning_rate": 4.166318118607923e-06,
"loss": 0.6322,
"step": 15800
},
{
"epoch": 0.82,
"learning_rate": 3.945428051176472e-06,
"loss": 0.6477,
"step": 15900
},
{
"epoch": 0.82,
"learning_rate": 3.7300517883868015e-06,
"loss": 0.6406,
"step": 16000
},
{
"epoch": 0.83,
"learning_rate": 3.5202457333156443e-06,
"loss": 0.6277,
"step": 16100
},
{
"epoch": 0.83,
"learning_rate": 3.3160648303049353e-06,
"loss": 0.6412,
"step": 16200
},
{
"epoch": 0.84,
"learning_rate": 3.1175625505728834e-06,
"loss": 0.6361,
"step": 16300
},
{
"epoch": 0.84,
"learning_rate": 2.9247908782108202e-06,
"loss": 0.6044,
"step": 16400
},
{
"epoch": 0.85,
"learning_rate": 2.7378002965695594e-06,
"loss": 0.6183,
"step": 16500
},
{
"epoch": 0.86,
"learning_rate": 2.5566397750387215e-06,
"loss": 0.6328,
"step": 16600
},
{
"epoch": 0.86,
"learning_rate": 2.3813567562225524e-06,
"loss": 0.6175,
"step": 16700
},
{
"epoch": 0.87,
"learning_rate": 2.2119971435155873e-06,
"loss": 0.6272,
"step": 16800
},
{
"epoch": 0.87,
"learning_rate": 2.048605289081365e-06,
"loss": 0.6404,
"step": 16900
},
{
"epoch": 0.88,
"learning_rate": 1.8912239822374695e-06,
"loss": 0.6259,
"step": 17000
},
{
"epoch": 0.88,
"learning_rate": 1.7398944382497424e-06,
"loss": 0.6254,
"step": 17100
},
{
"epoch": 0.89,
"learning_rate": 1.5946562875387927e-06,
"loss": 0.6249,
"step": 17200
},
{
"epoch": 0.89,
"learning_rate": 1.4555475653015127e-06,
"loss": 0.6199,
"step": 17300
},
{
"epoch": 0.9,
"learning_rate": 1.3226047015503646e-06,
"loss": 0.6249,
"step": 17400
},
{
"epoch": 0.9,
"learning_rate": 1.1958625115730232e-06,
"loss": 0.6212,
"step": 17500
},
{
"epoch": 0.91,
"learning_rate": 1.0753541868148835e-06,
"loss": 0.6162,
"step": 17600
},
{
"epoch": 0.91,
"learning_rate": 9.611112861868693e-07,
"loss": 0.6213,
"step": 17700
},
{
"epoch": 0.92,
"learning_rate": 8.53163727800696e-07,
"loss": 0.6089,
"step": 17800
},
{
"epoch": 0.92,
"learning_rate": 7.515397811338892e-07,
"loss": 0.6347,
"step": 17900
},
{
"epoch": 0.93,
"learning_rate": 6.562660596265202e-07,
"loss": 0.6209,
"step": 18000
}
],
"logging_steps": 100,
"max_steps": 19413,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 2000,
"total_flos": 4.082470834290347e+19,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}