{
"best_metric": 11.929398536682129,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.12569722680493361,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.002513944536098672,
"grad_norm": 0.012646043673157692,
"learning_rate": 5e-05,
"loss": 11.9327,
"step": 1
},
{
"epoch": 0.002513944536098672,
"eval_loss": 11.931513786315918,
"eval_runtime": 0.2515,
"eval_samples_per_second": 198.82,
"eval_steps_per_second": 51.693,
"step": 1
},
{
"epoch": 0.005027889072197344,
"grad_norm": 0.012877545319497585,
"learning_rate": 0.0001,
"loss": 11.9322,
"step": 2
},
{
"epoch": 0.007541833608296017,
"grad_norm": 0.013343454338610172,
"learning_rate": 9.990365154573717e-05,
"loss": 11.932,
"step": 3
},
{
"epoch": 0.010055778144394689,
"grad_norm": 0.012295612134039402,
"learning_rate": 9.961501876182148e-05,
"loss": 11.9316,
"step": 4
},
{
"epoch": 0.012569722680493361,
"grad_norm": 0.013433913700282574,
"learning_rate": 9.913533761814537e-05,
"loss": 11.9319,
"step": 5
},
{
"epoch": 0.015083667216592034,
"grad_norm": 0.017989417538046837,
"learning_rate": 9.846666218300807e-05,
"loss": 11.9317,
"step": 6
},
{
"epoch": 0.017597611752690707,
"grad_norm": 0.019290514290332794,
"learning_rate": 9.761185582727977e-05,
"loss": 11.931,
"step": 7
},
{
"epoch": 0.020111556288789377,
"grad_norm": 0.018904713913798332,
"learning_rate": 9.657457896300791e-05,
"loss": 11.9307,
"step": 8
},
{
"epoch": 0.02262550082488805,
"grad_norm": 0.02798588201403618,
"learning_rate": 9.535927336897098e-05,
"loss": 11.9314,
"step": 9
},
{
"epoch": 0.025139445360986723,
"grad_norm": 0.030021728947758675,
"learning_rate": 9.397114317029975e-05,
"loss": 11.9326,
"step": 10
},
{
"epoch": 0.027653389897085396,
"grad_norm": 0.03367425501346588,
"learning_rate": 9.241613255361455e-05,
"loss": 11.9304,
"step": 11
},
{
"epoch": 0.03016733443318407,
"grad_norm": 0.03730316087603569,
"learning_rate": 9.070090031310558e-05,
"loss": 11.928,
"step": 12
},
{
"epoch": 0.03268127896928274,
"grad_norm": 0.017860587686300278,
"learning_rate": 8.883279133655399e-05,
"loss": 11.9323,
"step": 13
},
{
"epoch": 0.035195223505381415,
"grad_norm": 0.01678677462041378,
"learning_rate": 8.681980515339464e-05,
"loss": 11.9322,
"step": 14
},
{
"epoch": 0.037709168041480084,
"grad_norm": 0.017414981499314308,
"learning_rate": 8.467056167950311e-05,
"loss": 11.9321,
"step": 15
},
{
"epoch": 0.040223112577578754,
"grad_norm": 0.018565161153674126,
"learning_rate": 8.239426430539243e-05,
"loss": 11.9315,
"step": 16
},
{
"epoch": 0.04273705711367743,
"grad_norm": 0.023156052455306053,
"learning_rate": 8.000066048588211e-05,
"loss": 11.9313,
"step": 17
},
{
"epoch": 0.0452510016497761,
"grad_norm": 0.024580350145697594,
"learning_rate": 7.75e-05,
"loss": 11.9309,
"step": 18
},
{
"epoch": 0.047764946185874776,
"grad_norm": 0.025019587948918343,
"learning_rate": 7.490299105985507e-05,
"loss": 11.9314,
"step": 19
},
{
"epoch": 0.050278890721973446,
"grad_norm": 0.03346352279186249,
"learning_rate": 7.222075445642904e-05,
"loss": 11.9309,
"step": 20
},
{
"epoch": 0.052792835258072116,
"grad_norm": 0.030500687658786774,
"learning_rate": 6.946477593864228e-05,
"loss": 11.9301,
"step": 21
},
{
"epoch": 0.05530677979417079,
"grad_norm": 0.04018493369221687,
"learning_rate": 6.664685702961344e-05,
"loss": 11.9317,
"step": 22
},
{
"epoch": 0.05782072433026946,
"grad_norm": 0.03532632812857628,
"learning_rate": 6.377906449072578e-05,
"loss": 11.9303,
"step": 23
},
{
"epoch": 0.06033466886636814,
"grad_norm": 0.0557476244866848,
"learning_rate": 6.087367864990233e-05,
"loss": 11.9325,
"step": 24
},
{
"epoch": 0.06284861340246681,
"grad_norm": 0.0716874822974205,
"learning_rate": 5.794314081535644e-05,
"loss": 11.9321,
"step": 25
},
{
"epoch": 0.06284861340246681,
"eval_loss": 11.930267333984375,
"eval_runtime": 0.2538,
"eval_samples_per_second": 197.011,
"eval_steps_per_second": 51.223,
"step": 25
},
{
"epoch": 0.06536255793856548,
"grad_norm": 0.025449182838201523,
"learning_rate": 5.500000000000001e-05,
"loss": 11.931,
"step": 26
},
{
"epoch": 0.06787650247466415,
"grad_norm": 0.03068012185394764,
"learning_rate": 5.205685918464356e-05,
"loss": 11.9312,
"step": 27
},
{
"epoch": 0.07039044701076283,
"grad_norm": 0.026767347007989883,
"learning_rate": 4.912632135009769e-05,
"loss": 11.9317,
"step": 28
},
{
"epoch": 0.0729043915468615,
"grad_norm": 0.025178169831633568,
"learning_rate": 4.6220935509274235e-05,
"loss": 11.9317,
"step": 29
},
{
"epoch": 0.07541833608296017,
"grad_norm": 0.03514225035905838,
"learning_rate": 4.3353142970386564e-05,
"loss": 11.9309,
"step": 30
},
{
"epoch": 0.07793228061905884,
"grad_norm": 0.03260508179664612,
"learning_rate": 4.053522406135775e-05,
"loss": 11.9319,
"step": 31
},
{
"epoch": 0.08044622515515751,
"grad_norm": 0.040161751210689545,
"learning_rate": 3.777924554357096e-05,
"loss": 11.9295,
"step": 32
},
{
"epoch": 0.08296016969125619,
"grad_norm": 0.04335453361272812,
"learning_rate": 3.509700894014496e-05,
"loss": 11.9302,
"step": 33
},
{
"epoch": 0.08547411422735486,
"grad_norm": 0.04472953453660011,
"learning_rate": 3.250000000000001e-05,
"loss": 11.9298,
"step": 34
},
{
"epoch": 0.08798805876345353,
"grad_norm": 0.047546010464429855,
"learning_rate": 2.9999339514117912e-05,
"loss": 11.9285,
"step": 35
},
{
"epoch": 0.0905020032995522,
"grad_norm": 0.07338829338550568,
"learning_rate": 2.760573569460757e-05,
"loss": 11.9262,
"step": 36
},
{
"epoch": 0.09301594783565087,
"grad_norm": 0.08542904257774353,
"learning_rate": 2.53294383204969e-05,
"loss": 11.9253,
"step": 37
},
{
"epoch": 0.09552989237174955,
"grad_norm": 0.04177666828036308,
"learning_rate": 2.3180194846605367e-05,
"loss": 11.9309,
"step": 38
},
{
"epoch": 0.09804383690784822,
"grad_norm": 0.03181887045502663,
"learning_rate": 2.1167208663446025e-05,
"loss": 11.9304,
"step": 39
},
{
"epoch": 0.10055778144394689,
"grad_norm": 0.03152301162481308,
"learning_rate": 1.9299099686894423e-05,
"loss": 11.9316,
"step": 40
},
{
"epoch": 0.10307172598004556,
"grad_norm": 0.03929756209254265,
"learning_rate": 1.758386744638546e-05,
"loss": 11.9312,
"step": 41
},
{
"epoch": 0.10558567051614423,
"grad_norm": 0.042001765221357346,
"learning_rate": 1.602885682970026e-05,
"loss": 11.9309,
"step": 42
},
{
"epoch": 0.10809961505224291,
"grad_norm": 0.040411677211523056,
"learning_rate": 1.464072663102903e-05,
"loss": 11.9297,
"step": 43
},
{
"epoch": 0.11061355958834158,
"grad_norm": 0.039004117250442505,
"learning_rate": 1.3425421036992098e-05,
"loss": 11.9291,
"step": 44
},
{
"epoch": 0.11312750412444025,
"grad_norm": 0.04640093818306923,
"learning_rate": 1.2388144172720251e-05,
"loss": 11.9294,
"step": 45
},
{
"epoch": 0.11564144866053892,
"grad_norm": 0.05690125748515129,
"learning_rate": 1.1533337816991932e-05,
"loss": 11.9288,
"step": 46
},
{
"epoch": 0.11815539319663759,
"grad_norm": 0.05605897307395935,
"learning_rate": 1.0864662381854632e-05,
"loss": 11.9292,
"step": 47
},
{
"epoch": 0.12066933773273628,
"grad_norm": 0.08062251657247543,
"learning_rate": 1.0384981238178534e-05,
"loss": 11.9273,
"step": 48
},
{
"epoch": 0.12318328226883495,
"grad_norm": 0.07040993124246597,
"learning_rate": 1.0096348454262845e-05,
"loss": 11.9273,
"step": 49
},
{
"epoch": 0.12569722680493361,
"grad_norm": 0.08358202874660492,
"learning_rate": 1e-05,
"loss": 11.9257,
"step": 50
},
{
"epoch": 0.12569722680493361,
"eval_loss": 11.929398536682129,
"eval_runtime": 0.2521,
"eval_samples_per_second": 198.37,
"eval_steps_per_second": 51.576,
"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": 1042494259200.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}