{
"best_metric": 2.793875217437744,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.45172219085262566,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.009034443817052512,
"grad_norm": 2.003566265106201,
"learning_rate": 5e-05,
"loss": 4.0946,
"step": 1
},
{
"epoch": 0.009034443817052512,
"eval_loss": 4.7396464347839355,
"eval_runtime": 1.439,
"eval_samples_per_second": 34.746,
"eval_steps_per_second": 9.034,
"step": 1
},
{
"epoch": 0.018068887634105024,
"grad_norm": 2.189868688583374,
"learning_rate": 0.0001,
"loss": 4.3342,
"step": 2
},
{
"epoch": 0.02710333145115754,
"grad_norm": 2.21208119392395,
"learning_rate": 9.990365154573717e-05,
"loss": 4.4961,
"step": 3
},
{
"epoch": 0.03613777526821005,
"grad_norm": 2.0794777870178223,
"learning_rate": 9.961501876182148e-05,
"loss": 4.3343,
"step": 4
},
{
"epoch": 0.04517221908526256,
"grad_norm": 1.9956696033477783,
"learning_rate": 9.913533761814537e-05,
"loss": 4.3286,
"step": 5
},
{
"epoch": 0.05420666290231508,
"grad_norm": 1.8608264923095703,
"learning_rate": 9.846666218300807e-05,
"loss": 4.27,
"step": 6
},
{
"epoch": 0.06324110671936758,
"grad_norm": 1.900020956993103,
"learning_rate": 9.761185582727977e-05,
"loss": 4.1662,
"step": 7
},
{
"epoch": 0.0722755505364201,
"grad_norm": 1.935903549194336,
"learning_rate": 9.657457896300791e-05,
"loss": 4.2807,
"step": 8
},
{
"epoch": 0.08130999435347261,
"grad_norm": 2.3480167388916016,
"learning_rate": 9.535927336897098e-05,
"loss": 4.1362,
"step": 9
},
{
"epoch": 0.09034443817052512,
"grad_norm": 2.073352098464966,
"learning_rate": 9.397114317029975e-05,
"loss": 4.1167,
"step": 10
},
{
"epoch": 0.09937888198757763,
"grad_norm": 2.1261823177337646,
"learning_rate": 9.241613255361455e-05,
"loss": 4.1793,
"step": 11
},
{
"epoch": 0.10841332580463016,
"grad_norm": 2.4966211318969727,
"learning_rate": 9.070090031310558e-05,
"loss": 4.2189,
"step": 12
},
{
"epoch": 0.11744776962168267,
"grad_norm": 2.2679433822631836,
"learning_rate": 8.883279133655399e-05,
"loss": 3.3898,
"step": 13
},
{
"epoch": 0.12648221343873517,
"grad_norm": 2.481332540512085,
"learning_rate": 8.681980515339464e-05,
"loss": 3.2862,
"step": 14
},
{
"epoch": 0.13551665725578768,
"grad_norm": 2.439176559448242,
"learning_rate": 8.467056167950311e-05,
"loss": 3.3162,
"step": 15
},
{
"epoch": 0.1445511010728402,
"grad_norm": 2.2607650756835938,
"learning_rate": 8.239426430539243e-05,
"loss": 3.2706,
"step": 16
},
{
"epoch": 0.1535855448898927,
"grad_norm": 2.212808847427368,
"learning_rate": 8.000066048588211e-05,
"loss": 3.3389,
"step": 17
},
{
"epoch": 0.16261998870694522,
"grad_norm": 1.979434847831726,
"learning_rate": 7.75e-05,
"loss": 3.3197,
"step": 18
},
{
"epoch": 0.17165443252399773,
"grad_norm": 2.090688467025757,
"learning_rate": 7.490299105985507e-05,
"loss": 3.323,
"step": 19
},
{
"epoch": 0.18068887634105024,
"grad_norm": 2.0628461837768555,
"learning_rate": 7.222075445642904e-05,
"loss": 3.2508,
"step": 20
},
{
"epoch": 0.18972332015810275,
"grad_norm": 1.9474982023239136,
"learning_rate": 6.946477593864228e-05,
"loss": 3.2158,
"step": 21
},
{
"epoch": 0.19875776397515527,
"grad_norm": 1.8773258924484253,
"learning_rate": 6.664685702961344e-05,
"loss": 3.1406,
"step": 22
},
{
"epoch": 0.2077922077922078,
"grad_norm": 1.9906569719314575,
"learning_rate": 6.377906449072578e-05,
"loss": 3.0506,
"step": 23
},
{
"epoch": 0.21682665160926032,
"grad_norm": 1.8546196222305298,
"learning_rate": 6.087367864990233e-05,
"loss": 3.3689,
"step": 24
},
{
"epoch": 0.22586109542631283,
"grad_norm": 2.4350030422210693,
"learning_rate": 5.794314081535644e-05,
"loss": 3.1943,
"step": 25
},
{
"epoch": 0.22586109542631283,
"eval_loss": 2.9668586254119873,
"eval_runtime": 0.7671,
"eval_samples_per_second": 65.182,
"eval_steps_per_second": 16.947,
"step": 25
},
{
"epoch": 0.23489553924336534,
"grad_norm": 3.4056997299194336,
"learning_rate": 5.500000000000001e-05,
"loss": 2.833,
"step": 26
},
{
"epoch": 0.24392998306041785,
"grad_norm": 2.812286376953125,
"learning_rate": 5.205685918464356e-05,
"loss": 2.8717,
"step": 27
},
{
"epoch": 0.25296442687747034,
"grad_norm": 2.095891237258911,
"learning_rate": 4.912632135009769e-05,
"loss": 2.8854,
"step": 28
},
{
"epoch": 0.2619988706945229,
"grad_norm": 1.4537508487701416,
"learning_rate": 4.6220935509274235e-05,
"loss": 2.9089,
"step": 29
},
{
"epoch": 0.27103331451157536,
"grad_norm": 1.6657167673110962,
"learning_rate": 4.3353142970386564e-05,
"loss": 2.9235,
"step": 30
},
{
"epoch": 0.2800677583286279,
"grad_norm": 2.1017632484436035,
"learning_rate": 4.053522406135775e-05,
"loss": 2.9568,
"step": 31
},
{
"epoch": 0.2891022021456804,
"grad_norm": 2.183953285217285,
"learning_rate": 3.777924554357096e-05,
"loss": 3.0283,
"step": 32
},
{
"epoch": 0.2981366459627329,
"grad_norm": 2.4140827655792236,
"learning_rate": 3.509700894014496e-05,
"loss": 3.0614,
"step": 33
},
{
"epoch": 0.3071710897797854,
"grad_norm": 2.358403205871582,
"learning_rate": 3.250000000000001e-05,
"loss": 3.0056,
"step": 34
},
{
"epoch": 0.31620553359683795,
"grad_norm": 2.1688156127929688,
"learning_rate": 2.9999339514117912e-05,
"loss": 2.9959,
"step": 35
},
{
"epoch": 0.32523997741389044,
"grad_norm": 2.245919942855835,
"learning_rate": 2.760573569460757e-05,
"loss": 3.1243,
"step": 36
},
{
"epoch": 0.334274421230943,
"grad_norm": 2.8014612197875977,
"learning_rate": 2.53294383204969e-05,
"loss": 2.9782,
"step": 37
},
{
"epoch": 0.34330886504799546,
"grad_norm": 1.5078074932098389,
"learning_rate": 2.3180194846605367e-05,
"loss": 2.7734,
"step": 38
},
{
"epoch": 0.352343308865048,
"grad_norm": 2.7210867404937744,
"learning_rate": 2.1167208663446025e-05,
"loss": 2.7651,
"step": 39
},
{
"epoch": 0.3613777526821005,
"grad_norm": 2.568594217300415,
"learning_rate": 1.9299099686894423e-05,
"loss": 2.7891,
"step": 40
},
{
"epoch": 0.370412196499153,
"grad_norm": 2.5484235286712646,
"learning_rate": 1.758386744638546e-05,
"loss": 2.8569,
"step": 41
},
{
"epoch": 0.3794466403162055,
"grad_norm": 2.261082649230957,
"learning_rate": 1.602885682970026e-05,
"loss": 2.8647,
"step": 42
},
{
"epoch": 0.38848108413325805,
"grad_norm": 1.782665729522705,
"learning_rate": 1.464072663102903e-05,
"loss": 2.8813,
"step": 43
},
{
"epoch": 0.39751552795031053,
"grad_norm": 1.6664153337478638,
"learning_rate": 1.3425421036992098e-05,
"loss": 2.8563,
"step": 44
},
{
"epoch": 0.40654997176736307,
"grad_norm": 1.345274806022644,
"learning_rate": 1.2388144172720251e-05,
"loss": 2.7682,
"step": 45
},
{
"epoch": 0.4155844155844156,
"grad_norm": 1.3299596309661865,
"learning_rate": 1.1533337816991932e-05,
"loss": 2.9492,
"step": 46
},
{
"epoch": 0.4246188594014681,
"grad_norm": 1.2749146223068237,
"learning_rate": 1.0864662381854632e-05,
"loss": 2.8559,
"step": 47
},
{
"epoch": 0.43365330321852064,
"grad_norm": 1.496679425239563,
"learning_rate": 1.0384981238178534e-05,
"loss": 2.9331,
"step": 48
},
{
"epoch": 0.4426877470355731,
"grad_norm": 1.9860912561416626,
"learning_rate": 1.0096348454262845e-05,
"loss": 3.0028,
"step": 49
},
{
"epoch": 0.45172219085262566,
"grad_norm": 2.868028163909912,
"learning_rate": 1e-05,
"loss": 3.1519,
"step": 50
},
{
"epoch": 0.45172219085262566,
"eval_loss": 2.793875217437744,
"eval_runtime": 0.7447,
"eval_samples_per_second": 67.145,
"eval_steps_per_second": 17.458,
"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": 1.059536353886208e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}