{
"best_metric": 2.112521171569824,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.04958472790380563,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0009916945580761127,
"grad_norm": 1.8448106050491333,
"learning_rate": 5e-05,
"loss": 2.9265,
"step": 1
},
{
"epoch": 0.0009916945580761127,
"eval_loss": 2.9538509845733643,
"eval_runtime": 1.4353,
"eval_samples_per_second": 34.836,
"eval_steps_per_second": 9.057,
"step": 1
},
{
"epoch": 0.0019833891161522253,
"grad_norm": 1.9753819704055786,
"learning_rate": 0.0001,
"loss": 2.842,
"step": 2
},
{
"epoch": 0.0029750836742283376,
"grad_norm": 1.7899694442749023,
"learning_rate": 9.990365154573717e-05,
"loss": 2.776,
"step": 3
},
{
"epoch": 0.003966778232304451,
"grad_norm": 1.7245805263519287,
"learning_rate": 9.961501876182148e-05,
"loss": 2.5315,
"step": 4
},
{
"epoch": 0.0049584727903805624,
"grad_norm": 1.708620309829712,
"learning_rate": 9.913533761814537e-05,
"loss": 2.4045,
"step": 5
},
{
"epoch": 0.005950167348456675,
"grad_norm": 1.0672885179519653,
"learning_rate": 9.846666218300807e-05,
"loss": 2.3025,
"step": 6
},
{
"epoch": 0.006941861906532788,
"grad_norm": 0.992870032787323,
"learning_rate": 9.761185582727977e-05,
"loss": 2.2333,
"step": 7
},
{
"epoch": 0.007933556464608901,
"grad_norm": 0.9287258386611938,
"learning_rate": 9.657457896300791e-05,
"loss": 2.1955,
"step": 8
},
{
"epoch": 0.008925251022685012,
"grad_norm": 0.9728707075119019,
"learning_rate": 9.535927336897098e-05,
"loss": 2.1102,
"step": 9
},
{
"epoch": 0.009916945580761125,
"grad_norm": 1.126459002494812,
"learning_rate": 9.397114317029975e-05,
"loss": 2.3005,
"step": 10
},
{
"epoch": 0.010908640138837238,
"grad_norm": 0.9696996808052063,
"learning_rate": 9.241613255361455e-05,
"loss": 2.185,
"step": 11
},
{
"epoch": 0.01190033469691335,
"grad_norm": 1.0382564067840576,
"learning_rate": 9.070090031310558e-05,
"loss": 2.1723,
"step": 12
},
{
"epoch": 0.012892029254989463,
"grad_norm": 0.8205527663230896,
"learning_rate": 8.883279133655399e-05,
"loss": 2.2143,
"step": 13
},
{
"epoch": 0.013883723813065576,
"grad_norm": 0.7997962236404419,
"learning_rate": 8.681980515339464e-05,
"loss": 2.1577,
"step": 14
},
{
"epoch": 0.014875418371141688,
"grad_norm": 0.7631952166557312,
"learning_rate": 8.467056167950311e-05,
"loss": 2.1757,
"step": 15
},
{
"epoch": 0.015867112929217803,
"grad_norm": 0.7147464752197266,
"learning_rate": 8.239426430539243e-05,
"loss": 2.2479,
"step": 16
},
{
"epoch": 0.016858807487293914,
"grad_norm": 0.6940491795539856,
"learning_rate": 8.000066048588211e-05,
"loss": 2.0892,
"step": 17
},
{
"epoch": 0.017850502045370024,
"grad_norm": 0.6920349597930908,
"learning_rate": 7.75e-05,
"loss": 2.1457,
"step": 18
},
{
"epoch": 0.01884219660344614,
"grad_norm": 0.6729762554168701,
"learning_rate": 7.490299105985507e-05,
"loss": 2.0448,
"step": 19
},
{
"epoch": 0.01983389116152225,
"grad_norm": 0.673019289970398,
"learning_rate": 7.222075445642904e-05,
"loss": 2.1296,
"step": 20
},
{
"epoch": 0.020825585719598364,
"grad_norm": 0.6313472986221313,
"learning_rate": 6.946477593864228e-05,
"loss": 2.1292,
"step": 21
},
{
"epoch": 0.021817280277674475,
"grad_norm": 0.6517207622528076,
"learning_rate": 6.664685702961344e-05,
"loss": 2.111,
"step": 22
},
{
"epoch": 0.02280897483575059,
"grad_norm": 0.6630841493606567,
"learning_rate": 6.377906449072578e-05,
"loss": 2.1643,
"step": 23
},
{
"epoch": 0.0238006693938267,
"grad_norm": 0.6734326481819153,
"learning_rate": 6.087367864990233e-05,
"loss": 2.1137,
"step": 24
},
{
"epoch": 0.024792363951902815,
"grad_norm": 0.6314123272895813,
"learning_rate": 5.794314081535644e-05,
"loss": 2.0499,
"step": 25
},
{
"epoch": 0.024792363951902815,
"eval_loss": 2.1400809288024902,
"eval_runtime": 1.4334,
"eval_samples_per_second": 34.882,
"eval_steps_per_second": 9.069,
"step": 25
},
{
"epoch": 0.025784058509978926,
"grad_norm": 0.6622329950332642,
"learning_rate": 5.500000000000001e-05,
"loss": 2.1491,
"step": 26
},
{
"epoch": 0.02677575306805504,
"grad_norm": 0.6250461339950562,
"learning_rate": 5.205685918464356e-05,
"loss": 2.1379,
"step": 27
},
{
"epoch": 0.02776744762613115,
"grad_norm": 0.5818557143211365,
"learning_rate": 4.912632135009769e-05,
"loss": 2.0769,
"step": 28
},
{
"epoch": 0.028759142184207265,
"grad_norm": 0.6050412058830261,
"learning_rate": 4.6220935509274235e-05,
"loss": 2.135,
"step": 29
},
{
"epoch": 0.029750836742283376,
"grad_norm": 0.634053111076355,
"learning_rate": 4.3353142970386564e-05,
"loss": 2.0189,
"step": 30
},
{
"epoch": 0.03074253130035949,
"grad_norm": 0.6110137701034546,
"learning_rate": 4.053522406135775e-05,
"loss": 2.0755,
"step": 31
},
{
"epoch": 0.031734225858435605,
"grad_norm": 0.5948219299316406,
"learning_rate": 3.777924554357096e-05,
"loss": 2.0746,
"step": 32
},
{
"epoch": 0.03272592041651171,
"grad_norm": 0.5863483548164368,
"learning_rate": 3.509700894014496e-05,
"loss": 2.1102,
"step": 33
},
{
"epoch": 0.03371761497458783,
"grad_norm": 0.5736821293830872,
"learning_rate": 3.250000000000001e-05,
"loss": 1.9682,
"step": 34
},
{
"epoch": 0.03470930953266394,
"grad_norm": 0.5776990652084351,
"learning_rate": 2.9999339514117912e-05,
"loss": 2.0821,
"step": 35
},
{
"epoch": 0.03570100409074005,
"grad_norm": 0.6396189332008362,
"learning_rate": 2.760573569460757e-05,
"loss": 2.1349,
"step": 36
},
{
"epoch": 0.03669269864881616,
"grad_norm": 0.606553852558136,
"learning_rate": 2.53294383204969e-05,
"loss": 2.0829,
"step": 37
},
{
"epoch": 0.03768439320689228,
"grad_norm": 0.6115500330924988,
"learning_rate": 2.3180194846605367e-05,
"loss": 2.2099,
"step": 38
},
{
"epoch": 0.03867608776496839,
"grad_norm": 0.606846272945404,
"learning_rate": 2.1167208663446025e-05,
"loss": 2.1354,
"step": 39
},
{
"epoch": 0.0396677823230445,
"grad_norm": 0.5994709134101868,
"learning_rate": 1.9299099686894423e-05,
"loss": 2.1579,
"step": 40
},
{
"epoch": 0.040659476881120614,
"grad_norm": 0.5895546674728394,
"learning_rate": 1.758386744638546e-05,
"loss": 2.0635,
"step": 41
},
{
"epoch": 0.04165117143919673,
"grad_norm": 0.5925672650337219,
"learning_rate": 1.602885682970026e-05,
"loss": 2.0997,
"step": 42
},
{
"epoch": 0.04264286599727284,
"grad_norm": 0.6125743985176086,
"learning_rate": 1.464072663102903e-05,
"loss": 2.0312,
"step": 43
},
{
"epoch": 0.04363456055534895,
"grad_norm": 0.593887448310852,
"learning_rate": 1.3425421036992098e-05,
"loss": 2.0319,
"step": 44
},
{
"epoch": 0.044626255113425065,
"grad_norm": 0.5913119316101074,
"learning_rate": 1.2388144172720251e-05,
"loss": 2.0568,
"step": 45
},
{
"epoch": 0.04561794967150118,
"grad_norm": 0.6023686528205872,
"learning_rate": 1.1533337816991932e-05,
"loss": 2.1055,
"step": 46
},
{
"epoch": 0.04660964422957729,
"grad_norm": 0.5734410881996155,
"learning_rate": 1.0864662381854632e-05,
"loss": 2.0804,
"step": 47
},
{
"epoch": 0.0476013387876534,
"grad_norm": 0.601888120174408,
"learning_rate": 1.0384981238178534e-05,
"loss": 2.1679,
"step": 48
},
{
"epoch": 0.048593033345729515,
"grad_norm": 0.6172356605529785,
"learning_rate": 1.0096348454262845e-05,
"loss": 2.2193,
"step": 49
},
{
"epoch": 0.04958472790380563,
"grad_norm": 0.6247469782829285,
"learning_rate": 1e-05,
"loss": 2.0932,
"step": 50
},
{
"epoch": 0.04958472790380563,
"eval_loss": 2.112521171569824,
"eval_runtime": 1.4403,
"eval_samples_per_second": 34.715,
"eval_steps_per_second": 9.026,
"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": 7.83042868150272e+16,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}