{
"best_metric": 6.8334808349609375,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.17738359201773837,
"eval_steps": 50,
"global_step": 75,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0023651145602365115,
"grad_norm": 0.3946707546710968,
"learning_rate": 5e-06,
"loss": 6.9349,
"step": 1
},
{
"epoch": 0.0023651145602365115,
"eval_loss": 6.934997081756592,
"eval_runtime": 6.1429,
"eval_samples_per_second": 231.976,
"eval_steps_per_second": 58.116,
"step": 1
},
{
"epoch": 0.004730229120473023,
"grad_norm": 0.4014280140399933,
"learning_rate": 1e-05,
"loss": 6.9338,
"step": 2
},
{
"epoch": 0.007095343680709534,
"grad_norm": 0.39586779475212097,
"learning_rate": 1.5e-05,
"loss": 6.935,
"step": 3
},
{
"epoch": 0.009460458240946046,
"grad_norm": 0.38926222920417786,
"learning_rate": 2e-05,
"loss": 6.9362,
"step": 4
},
{
"epoch": 0.011825572801182557,
"grad_norm": 0.39917948842048645,
"learning_rate": 2.5e-05,
"loss": 6.9337,
"step": 5
},
{
"epoch": 0.014190687361419069,
"grad_norm": 0.39744725823402405,
"learning_rate": 3e-05,
"loss": 6.9328,
"step": 6
},
{
"epoch": 0.01655580192165558,
"grad_norm": 0.3910214900970459,
"learning_rate": 3.5e-05,
"loss": 6.9331,
"step": 7
},
{
"epoch": 0.01892091648189209,
"grad_norm": 0.3774503767490387,
"learning_rate": 4e-05,
"loss": 6.9325,
"step": 8
},
{
"epoch": 0.021286031042128603,
"grad_norm": 0.39553385972976685,
"learning_rate": 4.5e-05,
"loss": 6.9293,
"step": 9
},
{
"epoch": 0.023651145602365115,
"grad_norm": 0.3832446336746216,
"learning_rate": 5e-05,
"loss": 6.9301,
"step": 10
},
{
"epoch": 0.026016260162601626,
"grad_norm": 0.40504515171051025,
"learning_rate": 5.500000000000001e-05,
"loss": 6.9258,
"step": 11
},
{
"epoch": 0.028381374722838137,
"grad_norm": 0.3918725848197937,
"learning_rate": 6e-05,
"loss": 6.9249,
"step": 12
},
{
"epoch": 0.03074648928307465,
"grad_norm": 0.39670994877815247,
"learning_rate": 6.500000000000001e-05,
"loss": 6.9232,
"step": 13
},
{
"epoch": 0.03311160384331116,
"grad_norm": 0.378149151802063,
"learning_rate": 7e-05,
"loss": 6.9213,
"step": 14
},
{
"epoch": 0.03547671840354767,
"grad_norm": 0.3893481194972992,
"learning_rate": 7.500000000000001e-05,
"loss": 6.9208,
"step": 15
},
{
"epoch": 0.03784183296378418,
"grad_norm": 0.3807522654533386,
"learning_rate": 8e-05,
"loss": 6.9177,
"step": 16
},
{
"epoch": 0.040206947524020695,
"grad_norm": 0.4065469205379486,
"learning_rate": 8.5e-05,
"loss": 6.9143,
"step": 17
},
{
"epoch": 0.042572062084257206,
"grad_norm": 0.3988112807273865,
"learning_rate": 9e-05,
"loss": 6.9123,
"step": 18
},
{
"epoch": 0.04493717664449372,
"grad_norm": 0.4048674702644348,
"learning_rate": 9.5e-05,
"loss": 6.907,
"step": 19
},
{
"epoch": 0.04730229120473023,
"grad_norm": 0.40050169825553894,
"learning_rate": 0.0001,
"loss": 6.9051,
"step": 20
},
{
"epoch": 0.04966740576496674,
"grad_norm": 0.3904324173927307,
"learning_rate": 9.991845519630678e-05,
"loss": 6.9038,
"step": 21
},
{
"epoch": 0.05203252032520325,
"grad_norm": 0.39560967683792114,
"learning_rate": 9.967408676742751e-05,
"loss": 6.8988,
"step": 22
},
{
"epoch": 0.05439763488543976,
"grad_norm": 0.4060423672199249,
"learning_rate": 9.926769179238466e-05,
"loss": 6.8934,
"step": 23
},
{
"epoch": 0.056762749445676275,
"grad_norm": 0.39542973041534424,
"learning_rate": 9.870059584711668e-05,
"loss": 6.8914,
"step": 24
},
{
"epoch": 0.059127864005912786,
"grad_norm": 0.39145323634147644,
"learning_rate": 9.797464868072488e-05,
"loss": 6.8891,
"step": 25
},
{
"epoch": 0.0614929785661493,
"grad_norm": 0.39028435945510864,
"learning_rate": 9.709221818197624e-05,
"loss": 6.8854,
"step": 26
},
{
"epoch": 0.06385809312638581,
"grad_norm": 0.39404362440109253,
"learning_rate": 9.60561826557425e-05,
"loss": 6.8796,
"step": 27
},
{
"epoch": 0.06622320768662232,
"grad_norm": 0.3834414780139923,
"learning_rate": 9.486992143456792e-05,
"loss": 6.8775,
"step": 28
},
{
"epoch": 0.06858832224685883,
"grad_norm": 0.3780187666416168,
"learning_rate": 9.353730385598887e-05,
"loss": 6.8723,
"step": 29
},
{
"epoch": 0.07095343680709534,
"grad_norm": 0.3655235171318054,
"learning_rate": 9.206267664155907e-05,
"loss": 6.8706,
"step": 30
},
{
"epoch": 0.07331855136733186,
"grad_norm": 0.3587733209133148,
"learning_rate": 9.045084971874738e-05,
"loss": 6.8692,
"step": 31
},
{
"epoch": 0.07568366592756837,
"grad_norm": 0.3456673324108124,
"learning_rate": 8.870708053195413e-05,
"loss": 6.8652,
"step": 32
},
{
"epoch": 0.07804878048780488,
"grad_norm": 0.3350028395652771,
"learning_rate": 8.683705689382024e-05,
"loss": 6.86,
"step": 33
},
{
"epoch": 0.08041389504804139,
"grad_norm": 0.32171154022216797,
"learning_rate": 8.484687843276469e-05,
"loss": 6.8584,
"step": 34
},
{
"epoch": 0.0827790096082779,
"grad_norm": 0.3136931359767914,
"learning_rate": 8.274303669726426e-05,
"loss": 6.8545,
"step": 35
},
{
"epoch": 0.08514412416851441,
"grad_norm": 0.3053753077983856,
"learning_rate": 8.053239398177191e-05,
"loss": 6.8529,
"step": 36
},
{
"epoch": 0.08750923872875092,
"grad_norm": 0.2941104769706726,
"learning_rate": 7.822216094333847e-05,
"loss": 6.8514,
"step": 37
},
{
"epoch": 0.08987435328898744,
"grad_norm": 0.29255473613739014,
"learning_rate": 7.58198730819481e-05,
"loss": 6.8473,
"step": 38
},
{
"epoch": 0.09223946784922395,
"grad_norm": 0.28042399883270264,
"learning_rate": 7.333336616128369e-05,
"loss": 6.8455,
"step": 39
},
{
"epoch": 0.09460458240946046,
"grad_norm": 0.2808942198753357,
"learning_rate": 7.077075065009433e-05,
"loss": 6.841,
"step": 40
},
{
"epoch": 0.09696969696969697,
"grad_norm": 0.2601359188556671,
"learning_rate": 6.814038526753205e-05,
"loss": 6.8473,
"step": 41
},
{
"epoch": 0.09933481152993348,
"grad_norm": 0.25740042328834534,
"learning_rate": 6.545084971874738e-05,
"loss": 6.8442,
"step": 42
},
{
"epoch": 0.10169992609016999,
"grad_norm": 0.2538498342037201,
"learning_rate": 6.271091670967436e-05,
"loss": 6.845,
"step": 43
},
{
"epoch": 0.1040650406504065,
"grad_norm": 0.24804328382015228,
"learning_rate": 5.992952333228728e-05,
"loss": 6.8417,
"step": 44
},
{
"epoch": 0.10643015521064302,
"grad_norm": 0.2596859633922577,
"learning_rate": 5.7115741913664264e-05,
"loss": 6.8358,
"step": 45
},
{
"epoch": 0.10879526977087953,
"grad_norm": 0.245009183883667,
"learning_rate": 5.427875042394199e-05,
"loss": 6.8416,
"step": 46
},
{
"epoch": 0.11116038433111604,
"grad_norm": 0.24145188927650452,
"learning_rate": 5.142780253968481e-05,
"loss": 6.8381,
"step": 47
},
{
"epoch": 0.11352549889135255,
"grad_norm": 0.2484976202249527,
"learning_rate": 4.85721974603152e-05,
"loss": 6.8329,
"step": 48
},
{
"epoch": 0.11589061345158906,
"grad_norm": 0.24022603034973145,
"learning_rate": 4.5721249576058027e-05,
"loss": 6.8354,
"step": 49
},
{
"epoch": 0.11825572801182557,
"grad_norm": 0.23194454610347748,
"learning_rate": 4.288425808633575e-05,
"loss": 6.8367,
"step": 50
},
{
"epoch": 0.11825572801182557,
"eval_loss": 6.8334808349609375,
"eval_runtime": 5.8184,
"eval_samples_per_second": 244.912,
"eval_steps_per_second": 61.357,
"step": 50
},
{
"epoch": 0.12062084257206208,
"grad_norm": 0.2359568029642105,
"learning_rate": 4.007047666771274e-05,
"loss": 6.8327,
"step": 51
},
{
"epoch": 0.1229859571322986,
"grad_norm": 0.23612986505031586,
"learning_rate": 3.728908329032567e-05,
"loss": 6.832,
"step": 52
},
{
"epoch": 0.12535107169253512,
"grad_norm": 0.2312479317188263,
"learning_rate": 3.4549150281252636e-05,
"loss": 6.8325,
"step": 53
},
{
"epoch": 0.12771618625277162,
"grad_norm": 0.22688338160514832,
"learning_rate": 3.1859614732467954e-05,
"loss": 6.8332,
"step": 54
},
{
"epoch": 0.13008130081300814,
"grad_norm": 0.2325437366962433,
"learning_rate": 2.9229249349905684e-05,
"loss": 6.8307,
"step": 55
},
{
"epoch": 0.13244641537324464,
"grad_norm": 0.22511352598667145,
"learning_rate": 2.6666633838716314e-05,
"loss": 6.8324,
"step": 56
},
{
"epoch": 0.13481152993348117,
"grad_norm": 0.23657694458961487,
"learning_rate": 2.418012691805191e-05,
"loss": 6.8284,
"step": 57
},
{
"epoch": 0.13717664449371766,
"grad_norm": 0.23125885426998138,
"learning_rate": 2.1777839056661554e-05,
"loss": 6.8301,
"step": 58
},
{
"epoch": 0.1395417590539542,
"grad_norm": 0.223617821931839,
"learning_rate": 1.946760601822809e-05,
"loss": 6.8289,
"step": 59
},
{
"epoch": 0.1419068736141907,
"grad_norm": 0.2352152019739151,
"learning_rate": 1.725696330273575e-05,
"loss": 6.8294,
"step": 60
},
{
"epoch": 0.1442719881744272,
"grad_norm": 0.2208397537469864,
"learning_rate": 1.5153121567235335e-05,
"loss": 6.8318,
"step": 61
},
{
"epoch": 0.1466371027346637,
"grad_norm": 0.2222435176372528,
"learning_rate": 1.3162943106179749e-05,
"loss": 6.8241,
"step": 62
},
{
"epoch": 0.14900221729490024,
"grad_norm": 0.21461376547813416,
"learning_rate": 1.1292919468045877e-05,
"loss": 6.8299,
"step": 63
},
{
"epoch": 0.15136733185513673,
"grad_norm": 0.21560494601726532,
"learning_rate": 9.549150281252633e-06,
"loss": 6.833,
"step": 64
},
{
"epoch": 0.15373244641537326,
"grad_norm": 0.2203921377658844,
"learning_rate": 7.937323358440935e-06,
"loss": 6.828,
"step": 65
},
{
"epoch": 0.15609756097560976,
"grad_norm": 0.219926655292511,
"learning_rate": 6.462696144011149e-06,
"loss": 6.8277,
"step": 66
},
{
"epoch": 0.15846267553584628,
"grad_norm": 0.22064423561096191,
"learning_rate": 5.13007856543209e-06,
"loss": 6.8305,
"step": 67
},
{
"epoch": 0.16082779009608278,
"grad_norm": 0.21617873013019562,
"learning_rate": 3.9438173442575e-06,
"loss": 6.8269,
"step": 68
},
{
"epoch": 0.1631929046563193,
"grad_norm": 0.22675487399101257,
"learning_rate": 2.9077818180237693e-06,
"loss": 6.8228,
"step": 69
},
{
"epoch": 0.1655580192165558,
"grad_norm": 0.22574570775032043,
"learning_rate": 2.0253513192751373e-06,
"loss": 6.8249,
"step": 70
},
{
"epoch": 0.16792313377679233,
"grad_norm": 0.22798891365528107,
"learning_rate": 1.2994041528833266e-06,
"loss": 6.8268,
"step": 71
},
{
"epoch": 0.17028824833702882,
"grad_norm": 0.21950149536132812,
"learning_rate": 7.323082076153509e-07,
"loss": 6.824,
"step": 72
},
{
"epoch": 0.17265336289726535,
"grad_norm": 0.22483089566230774,
"learning_rate": 3.2591323257248893e-07,
"loss": 6.8232,
"step": 73
},
{
"epoch": 0.17501847745750185,
"grad_norm": 0.2169935554265976,
"learning_rate": 8.15448036932176e-08,
"loss": 6.8269,
"step": 74
},
{
"epoch": 0.17738359201773837,
"grad_norm": 0.21611732244491577,
"learning_rate": 0.0,
"loss": 6.8257,
"step": 75
}
],
"logging_steps": 1,
"max_steps": 75,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"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": 11533536460800.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}