{
"best_metric": 6.900269031524658,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.023767788704358417,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00047535577408716834,
"grad_norm": 0.2816944420337677,
"learning_rate": 5e-05,
"loss": 6.9372,
"step": 1
},
{
"epoch": 0.00047535577408716834,
"eval_loss": 6.9411163330078125,
"eval_runtime": 2.2114,
"eval_samples_per_second": 22.611,
"eval_steps_per_second": 5.879,
"step": 1
},
{
"epoch": 0.0009507115481743367,
"grad_norm": 0.25802749395370483,
"learning_rate": 0.0001,
"loss": 6.9376,
"step": 2
},
{
"epoch": 0.001426067322261505,
"grad_norm": 0.244500532746315,
"learning_rate": 9.990365154573717e-05,
"loss": 6.9349,
"step": 3
},
{
"epoch": 0.0019014230963486734,
"grad_norm": 0.24236252903938293,
"learning_rate": 9.961501876182148e-05,
"loss": 6.9347,
"step": 4
},
{
"epoch": 0.002376778870435842,
"grad_norm": 0.2415142059326172,
"learning_rate": 9.913533761814537e-05,
"loss": 6.933,
"step": 5
},
{
"epoch": 0.00285213464452301,
"grad_norm": 0.2429618239402771,
"learning_rate": 9.846666218300807e-05,
"loss": 6.9313,
"step": 6
},
{
"epoch": 0.0033274904186101784,
"grad_norm": 0.2322567105293274,
"learning_rate": 9.761185582727977e-05,
"loss": 6.9315,
"step": 7
},
{
"epoch": 0.0038028461926973467,
"grad_norm": 0.21697010099887848,
"learning_rate": 9.657457896300791e-05,
"loss": 6.9299,
"step": 8
},
{
"epoch": 0.004278201966784515,
"grad_norm": 0.20793764293193817,
"learning_rate": 9.535927336897098e-05,
"loss": 6.9323,
"step": 9
},
{
"epoch": 0.004753557740871684,
"grad_norm": 0.20627593994140625,
"learning_rate": 9.397114317029975e-05,
"loss": 6.9293,
"step": 10
},
{
"epoch": 0.005228913514958852,
"grad_norm": 0.17280302941799164,
"learning_rate": 9.241613255361455e-05,
"loss": 6.9335,
"step": 11
},
{
"epoch": 0.00570426928904602,
"grad_norm": 0.1537674367427826,
"learning_rate": 9.070090031310558e-05,
"loss": 6.9351,
"step": 12
},
{
"epoch": 0.006179625063133189,
"grad_norm": 0.33964458107948303,
"learning_rate": 8.883279133655399e-05,
"loss": 6.9212,
"step": 13
},
{
"epoch": 0.006654980837220357,
"grad_norm": 0.3010113835334778,
"learning_rate": 8.681980515339464e-05,
"loss": 6.9189,
"step": 14
},
{
"epoch": 0.007130336611307526,
"grad_norm": 0.27440688014030457,
"learning_rate": 8.467056167950311e-05,
"loss": 6.9158,
"step": 15
},
{
"epoch": 0.007605692385394693,
"grad_norm": 0.27747219800949097,
"learning_rate": 8.239426430539243e-05,
"loss": 6.9154,
"step": 16
},
{
"epoch": 0.008081048159481862,
"grad_norm": 0.27966931462287903,
"learning_rate": 8.000066048588211e-05,
"loss": 6.9156,
"step": 17
},
{
"epoch": 0.00855640393356903,
"grad_norm": 0.27389419078826904,
"learning_rate": 7.75e-05,
"loss": 6.9134,
"step": 18
},
{
"epoch": 0.0090317597076562,
"grad_norm": 0.27709779143333435,
"learning_rate": 7.490299105985507e-05,
"loss": 6.9137,
"step": 19
},
{
"epoch": 0.009507115481743367,
"grad_norm": 0.2647261321544647,
"learning_rate": 7.222075445642904e-05,
"loss": 6.9127,
"step": 20
},
{
"epoch": 0.009982471255830535,
"grad_norm": 0.2580931782722473,
"learning_rate": 6.946477593864228e-05,
"loss": 6.9136,
"step": 21
},
{
"epoch": 0.010457827029917705,
"grad_norm": 0.2511126399040222,
"learning_rate": 6.664685702961344e-05,
"loss": 6.9131,
"step": 22
},
{
"epoch": 0.010933182804004873,
"grad_norm": 0.19859854876995087,
"learning_rate": 6.377906449072578e-05,
"loss": 6.9198,
"step": 23
},
{
"epoch": 0.01140853857809204,
"grad_norm": 0.16508285701274872,
"learning_rate": 6.087367864990233e-05,
"loss": 6.9241,
"step": 24
},
{
"epoch": 0.011883894352179208,
"grad_norm": 0.2387620210647583,
"learning_rate": 5.794314081535644e-05,
"loss": 6.9247,
"step": 25
},
{
"epoch": 0.011883894352179208,
"eval_loss": 6.913173675537109,
"eval_runtime": 0.0886,
"eval_samples_per_second": 564.04,
"eval_steps_per_second": 146.65,
"step": 25
},
{
"epoch": 0.012359250126266378,
"grad_norm": 0.3777521550655365,
"learning_rate": 5.500000000000001e-05,
"loss": 6.8997,
"step": 26
},
{
"epoch": 0.012834605900353546,
"grad_norm": 0.31511756777763367,
"learning_rate": 5.205685918464356e-05,
"loss": 6.9013,
"step": 27
},
{
"epoch": 0.013309961674440714,
"grad_norm": 0.3206568956375122,
"learning_rate": 4.912632135009769e-05,
"loss": 6.8988,
"step": 28
},
{
"epoch": 0.013785317448527883,
"grad_norm": 0.3120715618133545,
"learning_rate": 4.6220935509274235e-05,
"loss": 6.8991,
"step": 29
},
{
"epoch": 0.014260673222615051,
"grad_norm": 0.30434051156044006,
"learning_rate": 4.3353142970386564e-05,
"loss": 6.8997,
"step": 30
},
{
"epoch": 0.014736028996702219,
"grad_norm": 0.32293179631233215,
"learning_rate": 4.053522406135775e-05,
"loss": 6.8968,
"step": 31
},
{
"epoch": 0.015211384770789387,
"grad_norm": 0.3022577166557312,
"learning_rate": 3.777924554357096e-05,
"loss": 6.9002,
"step": 32
},
{
"epoch": 0.015686740544876555,
"grad_norm": 0.276790052652359,
"learning_rate": 3.509700894014496e-05,
"loss": 6.9018,
"step": 33
},
{
"epoch": 0.016162096318963724,
"grad_norm": 0.27103278040885925,
"learning_rate": 3.250000000000001e-05,
"loss": 6.9013,
"step": 34
},
{
"epoch": 0.016637452093050894,
"grad_norm": 0.24876445531845093,
"learning_rate": 2.9999339514117912e-05,
"loss": 6.9043,
"step": 35
},
{
"epoch": 0.01711280786713806,
"grad_norm": 0.19545753300189972,
"learning_rate": 2.760573569460757e-05,
"loss": 6.9152,
"step": 36
},
{
"epoch": 0.01758816364122523,
"grad_norm": 0.1613902449607849,
"learning_rate": 2.53294383204969e-05,
"loss": 6.9259,
"step": 37
},
{
"epoch": 0.0180635194153124,
"grad_norm": 0.4136228561401367,
"learning_rate": 2.3180194846605367e-05,
"loss": 6.8879,
"step": 38
},
{
"epoch": 0.018538875189399565,
"grad_norm": 0.34804272651672363,
"learning_rate": 2.1167208663446025e-05,
"loss": 6.8892,
"step": 39
},
{
"epoch": 0.019014230963486735,
"grad_norm": 0.3347592353820801,
"learning_rate": 1.9299099686894423e-05,
"loss": 6.8905,
"step": 40
},
{
"epoch": 0.019489586737573904,
"grad_norm": 0.3388766944408417,
"learning_rate": 1.758386744638546e-05,
"loss": 6.8902,
"step": 41
},
{
"epoch": 0.01996494251166107,
"grad_norm": 0.314827024936676,
"learning_rate": 1.602885682970026e-05,
"loss": 6.8922,
"step": 42
},
{
"epoch": 0.02044029828574824,
"grad_norm": 0.3265056610107422,
"learning_rate": 1.464072663102903e-05,
"loss": 6.8902,
"step": 43
},
{
"epoch": 0.02091565405983541,
"grad_norm": 0.310298353433609,
"learning_rate": 1.3425421036992098e-05,
"loss": 6.8928,
"step": 44
},
{
"epoch": 0.021391009833922576,
"grad_norm": 0.3022330701351166,
"learning_rate": 1.2388144172720251e-05,
"loss": 6.8925,
"step": 45
},
{
"epoch": 0.021866365608009745,
"grad_norm": 0.2826597988605499,
"learning_rate": 1.1533337816991932e-05,
"loss": 6.8954,
"step": 46
},
{
"epoch": 0.02234172138209691,
"grad_norm": 0.26531800627708435,
"learning_rate": 1.0864662381854632e-05,
"loss": 6.8986,
"step": 47
},
{
"epoch": 0.02281707715618408,
"grad_norm": 0.22228993475437164,
"learning_rate": 1.0384981238178534e-05,
"loss": 6.9088,
"step": 48
},
{
"epoch": 0.02329243293027125,
"grad_norm": 0.17581987380981445,
"learning_rate": 1.0096348454262845e-05,
"loss": 6.9162,
"step": 49
},
{
"epoch": 0.023767788704358417,
"grad_norm": 0.2906361222267151,
"learning_rate": 1e-05,
"loss": 6.9222,
"step": 50
},
{
"epoch": 0.023767788704358417,
"eval_loss": 6.900269031524658,
"eval_runtime": 0.0883,
"eval_samples_per_second": 566.131,
"eval_steps_per_second": 147.194,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 50,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 25,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 1,
"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": 6231975329792.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}