deepseek-coder-1.3b-haskell-v0.1 / trainer_state.json
Bry14's picture
upload model
3438d95 verified
Raw
History Blame Contribute Delete
12.8 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 9.97191011235955,
"eval_steps": 25,
"global_step": 1775,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.1404494382022472,
"grad_norm": 0.5412795543670654,
"learning_rate": 0.0001973018549747049,
"loss": 1.3134,
"step": 25
},
{
"epoch": 0.2808988764044944,
"grad_norm": 0.4412384033203125,
"learning_rate": 0.0001944912872400225,
"loss": 0.6041,
"step": 50
},
{
"epoch": 0.42134831460674155,
"grad_norm": 0.45605987310409546,
"learning_rate": 0.00019168071950534008,
"loss": 0.6272,
"step": 75
},
{
"epoch": 0.5617977528089888,
"grad_norm": 0.3537271320819855,
"learning_rate": 0.00018887015177065767,
"loss": 0.5295,
"step": 100
},
{
"epoch": 0.702247191011236,
"grad_norm": 0.46697843074798584,
"learning_rate": 0.00018605958403597526,
"loss": 0.537,
"step": 125
},
{
"epoch": 0.8426966292134831,
"grad_norm": 0.4086565375328064,
"learning_rate": 0.00018324901630129288,
"loss": 0.5809,
"step": 150
},
{
"epoch": 0.9831460674157303,
"grad_norm": 0.5682910084724426,
"learning_rate": 0.00018043844856661047,
"loss": 0.4466,
"step": 175
},
{
"epoch": 1.1235955056179776,
"grad_norm": 0.5230486392974854,
"learning_rate": 0.00017762788083192804,
"loss": 0.5645,
"step": 200
},
{
"epoch": 1.2640449438202248,
"grad_norm": 0.49830254912376404,
"learning_rate": 0.00017481731309724566,
"loss": 0.3961,
"step": 225
},
{
"epoch": 1.404494382022472,
"grad_norm": 0.48381373286247253,
"learning_rate": 0.00017200674536256325,
"loss": 0.497,
"step": 250
},
{
"epoch": 1.5449438202247192,
"grad_norm": 0.4403741657733917,
"learning_rate": 0.00016919617762788084,
"loss": 0.4314,
"step": 275
},
{
"epoch": 1.6853932584269664,
"grad_norm": 0.4472004175186157,
"learning_rate": 0.00016638560989319843,
"loss": 0.406,
"step": 300
},
{
"epoch": 1.8258426966292136,
"grad_norm": 0.5165215134620667,
"learning_rate": 0.00016357504215851602,
"loss": 0.4481,
"step": 325
},
{
"epoch": 1.9662921348314608,
"grad_norm": 0.4695923626422882,
"learning_rate": 0.00016076447442383361,
"loss": 0.3498,
"step": 350
},
{
"epoch": 2.106741573033708,
"grad_norm": 0.4390884339809418,
"learning_rate": 0.00015795390668915123,
"loss": 0.3793,
"step": 375
},
{
"epoch": 2.247191011235955,
"grad_norm": 0.5412095785140991,
"learning_rate": 0.00015514333895446882,
"loss": 0.2648,
"step": 400
},
{
"epoch": 2.3876404494382024,
"grad_norm": 0.6369752287864685,
"learning_rate": 0.0001523327712197864,
"loss": 0.3644,
"step": 425
},
{
"epoch": 2.5280898876404496,
"grad_norm": 0.6540620923042297,
"learning_rate": 0.000149522203485104,
"loss": 0.3211,
"step": 450
},
{
"epoch": 2.668539325842697,
"grad_norm": 0.5721971988677979,
"learning_rate": 0.0001467116357504216,
"loss": 0.3184,
"step": 475
},
{
"epoch": 2.808988764044944,
"grad_norm": 0.7850697040557861,
"learning_rate": 0.0001439010680157392,
"loss": 0.3142,
"step": 500
},
{
"epoch": 2.949438202247191,
"grad_norm": 0.6294387578964233,
"learning_rate": 0.00014109050028105678,
"loss": 0.2964,
"step": 525
},
{
"epoch": 3.0898876404494384,
"grad_norm": 0.6372372508049011,
"learning_rate": 0.00013827993254637437,
"loss": 0.2902,
"step": 550
},
{
"epoch": 3.2303370786516856,
"grad_norm": 0.5713627934455872,
"learning_rate": 0.00013546936481169196,
"loss": 0.2066,
"step": 575
},
{
"epoch": 3.370786516853933,
"grad_norm": 0.5869475603103638,
"learning_rate": 0.00013265879707700956,
"loss": 0.2699,
"step": 600
},
{
"epoch": 3.51123595505618,
"grad_norm": 0.7703843116760254,
"learning_rate": 0.00012984822934232717,
"loss": 0.2038,
"step": 625
},
{
"epoch": 3.6516853932584272,
"grad_norm": 0.5455925464630127,
"learning_rate": 0.00012703766160764474,
"loss": 0.2509,
"step": 650
},
{
"epoch": 3.7921348314606744,
"grad_norm": 0.6485171318054199,
"learning_rate": 0.00012422709387296233,
"loss": 0.232,
"step": 675
},
{
"epoch": 3.932584269662921,
"grad_norm": 0.5719711780548096,
"learning_rate": 0.00012141652613827993,
"loss": 0.2115,
"step": 700
},
{
"epoch": 4.073033707865169,
"grad_norm": 0.5950255393981934,
"learning_rate": 0.00011860595840359754,
"loss": 0.2093,
"step": 725
},
{
"epoch": 4.213483146067416,
"grad_norm": 0.6047451496124268,
"learning_rate": 0.00011579539066891512,
"loss": 0.1529,
"step": 750
},
{
"epoch": 4.353932584269663,
"grad_norm": 0.4110608696937561,
"learning_rate": 0.00011298482293423271,
"loss": 0.1893,
"step": 775
},
{
"epoch": 4.49438202247191,
"grad_norm": 0.28061643242836,
"learning_rate": 0.00011017425519955031,
"loss": 0.1469,
"step": 800
},
{
"epoch": 4.634831460674158,
"grad_norm": 0.5715160369873047,
"learning_rate": 0.00010736368746486792,
"loss": 0.2024,
"step": 825
},
{
"epoch": 4.775280898876405,
"grad_norm": 0.8154908418655396,
"learning_rate": 0.00010455311973018551,
"loss": 0.1652,
"step": 850
},
{
"epoch": 4.915730337078652,
"grad_norm": 0.7108107209205627,
"learning_rate": 0.00010174255199550309,
"loss": 0.1824,
"step": 875
},
{
"epoch": 5.056179775280899,
"grad_norm": 0.4340110421180725,
"learning_rate": 0.00009893198426082069,
"loss": 0.1595,
"step": 900
},
{
"epoch": 5.196629213483146,
"grad_norm": 0.5752900838851929,
"learning_rate": 0.00009612141652613828,
"loss": 0.1282,
"step": 925
},
{
"epoch": 5.337078651685394,
"grad_norm": 0.7457758188247681,
"learning_rate": 0.00009331084879145588,
"loss": 0.1407,
"step": 950
},
{
"epoch": 5.477528089887641,
"grad_norm": 0.5357733368873596,
"learning_rate": 0.00009050028105677347,
"loss": 0.1233,
"step": 975
},
{
"epoch": 5.617977528089888,
"grad_norm": 0.5387812852859497,
"learning_rate": 0.00008768971332209107,
"loss": 0.1437,
"step": 1000
},
{
"epoch": 5.758426966292134,
"grad_norm": 0.8078483939170837,
"learning_rate": 0.00008487914558740866,
"loss": 0.1341,
"step": 1025
},
{
"epoch": 5.898876404494382,
"grad_norm": 0.841056227684021,
"learning_rate": 0.00008206857785272625,
"loss": 0.1443,
"step": 1050
},
{
"epoch": 6.03932584269663,
"grad_norm": 0.6065801382064819,
"learning_rate": 0.00007925801011804385,
"loss": 0.1285,
"step": 1075
},
{
"epoch": 6.179775280898877,
"grad_norm": 0.5575238466262817,
"learning_rate": 0.00007644744238336145,
"loss": 0.1088,
"step": 1100
},
{
"epoch": 6.320224719101123,
"grad_norm": 0.6412163376808167,
"learning_rate": 0.00007363687464867903,
"loss": 0.1079,
"step": 1125
},
{
"epoch": 6.460674157303371,
"grad_norm": 0.3780171573162079,
"learning_rate": 0.00007082630691399663,
"loss": 0.1087,
"step": 1150
},
{
"epoch": 6.601123595505618,
"grad_norm": 0.5227295160293579,
"learning_rate": 0.00006801573917931423,
"loss": 0.1204,
"step": 1175
},
{
"epoch": 6.741573033707866,
"grad_norm": 0.28560328483581543,
"learning_rate": 0.00006520517144463182,
"loss": 0.1119,
"step": 1200
},
{
"epoch": 6.882022471910112,
"grad_norm": 0.5268654227256775,
"learning_rate": 0.00006239460370994942,
"loss": 0.1124,
"step": 1225
},
{
"epoch": 7.022471910112359,
"grad_norm": 0.4442940354347229,
"learning_rate": 0.000059584035975267006,
"loss": 0.1138,
"step": 1250
},
{
"epoch": 7.162921348314606,
"grad_norm": 0.3350606858730316,
"learning_rate": 0.000056773468240584605,
"loss": 0.0937,
"step": 1275
},
{
"epoch": 7.303370786516854,
"grad_norm": 0.3864946961402893,
"learning_rate": 0.00005396290050590219,
"loss": 0.0968,
"step": 1300
},
{
"epoch": 7.443820224719101,
"grad_norm": 0.5451478958129883,
"learning_rate": 0.00005115233277121979,
"loss": 0.096,
"step": 1325
},
{
"epoch": 7.584269662921348,
"grad_norm": 0.463236927986145,
"learning_rate": 0.000048341765036537386,
"loss": 0.0957,
"step": 1350
},
{
"epoch": 7.724719101123595,
"grad_norm": 0.3199273347854614,
"learning_rate": 0.00004553119730185498,
"loss": 0.1027,
"step": 1375
},
{
"epoch": 7.865168539325842,
"grad_norm": 0.5982705950737,
"learning_rate": 0.00004272062956717257,
"loss": 0.1013,
"step": 1400
},
{
"epoch": 8.00561797752809,
"grad_norm": 0.4638069272041321,
"learning_rate": 0.00003991006183249017,
"loss": 0.1003,
"step": 1425
},
{
"epoch": 8.146067415730338,
"grad_norm": 0.40993738174438477,
"learning_rate": 0.00003709949409780776,
"loss": 0.084,
"step": 1450
},
{
"epoch": 8.286516853932584,
"grad_norm": 0.45901650190353394,
"learning_rate": 0.00003428892636312535,
"loss": 0.0874,
"step": 1475
},
{
"epoch": 8.426966292134832,
"grad_norm": 0.3773433566093445,
"learning_rate": 0.00003147835862844295,
"loss": 0.0836,
"step": 1500
},
{
"epoch": 8.567415730337078,
"grad_norm": 0.4382336437702179,
"learning_rate": 0.000028667790893760543,
"loss": 0.089,
"step": 1525
},
{
"epoch": 8.707865168539326,
"grad_norm": 0.4534280300140381,
"learning_rate": 0.000025857223159078137,
"loss": 0.0897,
"step": 1550
},
{
"epoch": 8.848314606741573,
"grad_norm": 0.37525683641433716,
"learning_rate": 0.00002304665542439573,
"loss": 0.0888,
"step": 1575
},
{
"epoch": 8.98876404494382,
"grad_norm": 0.3811222314834595,
"learning_rate": 0.000020236087689713324,
"loss": 0.0942,
"step": 1600
},
{
"epoch": 9.129213483146067,
"grad_norm": 0.4298257529735565,
"learning_rate": 0.00001742551995503092,
"loss": 0.0792,
"step": 1625
},
{
"epoch": 9.269662921348315,
"grad_norm": 0.3410011827945709,
"learning_rate": 0.00001461495222034851,
"loss": 0.0811,
"step": 1650
},
{
"epoch": 9.410112359550562,
"grad_norm": 0.4006299376487732,
"learning_rate": 0.000011804384485666105,
"loss": 0.0785,
"step": 1675
},
{
"epoch": 9.55056179775281,
"grad_norm": 0.35740622878074646,
"learning_rate": 0.0000089938167509837,
"loss": 0.0816,
"step": 1700
},
{
"epoch": 9.691011235955056,
"grad_norm": 0.4826361835002899,
"learning_rate": 0.000006183249016301293,
"loss": 0.0839,
"step": 1725
},
{
"epoch": 9.831460674157304,
"grad_norm": 0.46845364570617676,
"learning_rate": 0.000003372681281618887,
"loss": 0.0808,
"step": 1750
},
{
"epoch": 9.97191011235955,
"grad_norm": 0.3881346583366394,
"learning_rate": 5.621135469364812e-7,
"loss": 0.0845,
"step": 1775
}
],
"logging_steps": 25,
"max_steps": 1780,
"num_input_tokens_seen": 0,
"num_train_epochs": 10,
"save_steps": 25,
"total_flos": 5731260450938880,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}