dsakerkwq's picture
Training in progress, step 50, checkpoint
02dc4a8 verified
raw
history blame
10.1 kB
{
"best_metric": NaN,
"best_model_checkpoint": "miner_id_24/checkpoint-25",
"epoch": 0.5751258087706685,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.011502516175413372,
"grad_norm": 9.297219276428223,
"learning_rate": 5e-05,
"loss": 3.1748,
"step": 1
},
{
"epoch": 0.011502516175413372,
"eval_loss": NaN,
"eval_runtime": 5.2573,
"eval_samples_per_second": 9.511,
"eval_steps_per_second": 2.473,
"step": 1
},
{
"epoch": 0.023005032350826744,
"grad_norm": 10.791241645812988,
"learning_rate": 0.0001,
"loss": 3.8789,
"step": 2
},
{
"epoch": 0.03450754852624011,
"grad_norm": 7.613100528717041,
"learning_rate": 9.990365154573717e-05,
"loss": 2.732,
"step": 3
},
{
"epoch": 0.04601006470165349,
"grad_norm": 5.033226013183594,
"learning_rate": 9.961501876182148e-05,
"loss": 1.8498,
"step": 4
},
{
"epoch": 0.05751258087706686,
"grad_norm": 3.803105115890503,
"learning_rate": 9.913533761814537e-05,
"loss": 1.5294,
"step": 5
},
{
"epoch": 0.06901509705248023,
"grad_norm": 3.32814884185791,
"learning_rate": 9.846666218300807e-05,
"loss": 1.1577,
"step": 6
},
{
"epoch": 0.08051761322789361,
"grad_norm": 3.300325393676758,
"learning_rate": 9.761185582727977e-05,
"loss": 0.906,
"step": 7
},
{
"epoch": 0.09202012940330698,
"grad_norm": 2.58109450340271,
"learning_rate": 9.657457896300791e-05,
"loss": 0.7892,
"step": 8
},
{
"epoch": 0.10352264557872035,
"grad_norm": 1.908664345741272,
"learning_rate": 9.535927336897098e-05,
"loss": 0.7642,
"step": 9
},
{
"epoch": 0.11502516175413371,
"grad_norm": 2.238858699798584,
"learning_rate": 9.397114317029975e-05,
"loss": 0.7971,
"step": 10
},
{
"epoch": 0.12652767792954708,
"grad_norm": 9.872129440307617,
"learning_rate": 9.241613255361455e-05,
"loss": 1.2803,
"step": 11
},
{
"epoch": 0.13803019410496045,
"grad_norm": 7.013273239135742,
"learning_rate": 9.070090031310558e-05,
"loss": 0.774,
"step": 12
},
{
"epoch": 0.14953271028037382,
"grad_norm": 18.253293991088867,
"learning_rate": 8.883279133655399e-05,
"loss": 1.6844,
"step": 13
},
{
"epoch": 0.16103522645578722,
"grad_norm": 11.80898380279541,
"learning_rate": 8.681980515339464e-05,
"loss": 1.4835,
"step": 14
},
{
"epoch": 0.17253774263120059,
"grad_norm": 8.237065315246582,
"learning_rate": 8.467056167950311e-05,
"loss": 1.2241,
"step": 15
},
{
"epoch": 0.18404025880661395,
"grad_norm": 5.11019229888916,
"learning_rate": 8.239426430539243e-05,
"loss": 0.966,
"step": 16
},
{
"epoch": 0.19554277498202732,
"grad_norm": 2.444025993347168,
"learning_rate": 8.000066048588211e-05,
"loss": 0.8415,
"step": 17
},
{
"epoch": 0.2070452911574407,
"grad_norm": 1.611665964126587,
"learning_rate": 7.75e-05,
"loss": 0.7324,
"step": 18
},
{
"epoch": 0.21854780733285406,
"grad_norm": 1.7055110931396484,
"learning_rate": 7.490299105985507e-05,
"loss": 0.7249,
"step": 19
},
{
"epoch": 0.23005032350826743,
"grad_norm": 1.4277286529541016,
"learning_rate": 7.222075445642904e-05,
"loss": 0.6496,
"step": 20
},
{
"epoch": 0.2415528396836808,
"grad_norm": 1.4963089227676392,
"learning_rate": 6.946477593864228e-05,
"loss": 0.6319,
"step": 21
},
{
"epoch": 0.25305535585909417,
"grad_norm": 1.690994143486023,
"learning_rate": 6.664685702961344e-05,
"loss": 0.5724,
"step": 22
},
{
"epoch": 0.26455787203450754,
"grad_norm": 2.5603814125061035,
"learning_rate": 6.377906449072578e-05,
"loss": 0.8262,
"step": 23
},
{
"epoch": 0.2760603882099209,
"grad_norm": 7.202908039093018,
"learning_rate": 6.087367864990233e-05,
"loss": 1.0099,
"step": 24
},
{
"epoch": 0.2875629043853343,
"grad_norm": 6.888559341430664,
"learning_rate": 5.794314081535644e-05,
"loss": 0.8738,
"step": 25
},
{
"epoch": 0.2875629043853343,
"eval_loss": NaN,
"eval_runtime": 5.2585,
"eval_samples_per_second": 9.508,
"eval_steps_per_second": 2.472,
"step": 25
},
{
"epoch": 0.29906542056074764,
"grad_norm": 3.764979124069214,
"learning_rate": 5.500000000000001e-05,
"loss": 0.8616,
"step": 26
},
{
"epoch": 0.310567936736161,
"grad_norm": 3.678941249847412,
"learning_rate": 5.205685918464356e-05,
"loss": 0.8434,
"step": 27
},
{
"epoch": 0.32207045291157443,
"grad_norm": 3.1119205951690674,
"learning_rate": 4.912632135009769e-05,
"loss": 0.7273,
"step": 28
},
{
"epoch": 0.3335729690869878,
"grad_norm": 2.377394199371338,
"learning_rate": 4.6220935509274235e-05,
"loss": 0.6829,
"step": 29
},
{
"epoch": 0.34507548526240117,
"grad_norm": 1.8314098119735718,
"learning_rate": 4.3353142970386564e-05,
"loss": 0.5708,
"step": 30
},
{
"epoch": 0.35657800143781454,
"grad_norm": 1.2278950214385986,
"learning_rate": 4.053522406135775e-05,
"loss": 0.5391,
"step": 31
},
{
"epoch": 0.3680805176132279,
"grad_norm": 1.1506680250167847,
"learning_rate": 3.777924554357096e-05,
"loss": 0.5648,
"step": 32
},
{
"epoch": 0.3795830337886413,
"grad_norm": 0.9588247537612915,
"learning_rate": 3.509700894014496e-05,
"loss": 0.489,
"step": 33
},
{
"epoch": 0.39108554996405465,
"grad_norm": 1.5099307298660278,
"learning_rate": 3.250000000000001e-05,
"loss": 0.4334,
"step": 34
},
{
"epoch": 0.402588066139468,
"grad_norm": 2.1597650051116943,
"learning_rate": 2.9999339514117912e-05,
"loss": 0.5894,
"step": 35
},
{
"epoch": 0.4140905823148814,
"grad_norm": 5.968879699707031,
"learning_rate": 2.760573569460757e-05,
"loss": 0.9712,
"step": 36
},
{
"epoch": 0.42559309849029475,
"grad_norm": 8.183683395385742,
"learning_rate": 2.53294383204969e-05,
"loss": 0.8839,
"step": 37
},
{
"epoch": 0.4370956146657081,
"grad_norm": 1.7860997915267944,
"learning_rate": 2.3180194846605367e-05,
"loss": 0.6139,
"step": 38
},
{
"epoch": 0.4485981308411215,
"grad_norm": 1.6000277996063232,
"learning_rate": 2.1167208663446025e-05,
"loss": 0.616,
"step": 39
},
{
"epoch": 0.46010064701653486,
"grad_norm": 1.1554548740386963,
"learning_rate": 1.9299099686894423e-05,
"loss": 0.5576,
"step": 40
},
{
"epoch": 0.4716031631919482,
"grad_norm": 0.9421719312667847,
"learning_rate": 1.758386744638546e-05,
"loss": 0.4917,
"step": 41
},
{
"epoch": 0.4831056793673616,
"grad_norm": 0.9385743141174316,
"learning_rate": 1.602885682970026e-05,
"loss": 0.4912,
"step": 42
},
{
"epoch": 0.49460819554277496,
"grad_norm": 0.9931282997131348,
"learning_rate": 1.464072663102903e-05,
"loss": 0.4781,
"step": 43
},
{
"epoch": 0.5061107117181883,
"grad_norm": 1.0186808109283447,
"learning_rate": 1.3425421036992098e-05,
"loss": 0.5008,
"step": 44
},
{
"epoch": 0.5176132278936018,
"grad_norm": 0.9983035326004028,
"learning_rate": 1.2388144172720251e-05,
"loss": 0.4088,
"step": 45
},
{
"epoch": 0.5291157440690151,
"grad_norm": 1.0832576751708984,
"learning_rate": 1.1533337816991932e-05,
"loss": 0.4366,
"step": 46
},
{
"epoch": 0.5406182602444285,
"grad_norm": 1.115883231163025,
"learning_rate": 1.0864662381854632e-05,
"loss": 0.4505,
"step": 47
},
{
"epoch": 0.5521207764198418,
"grad_norm": 2.39801287651062,
"learning_rate": 1.0384981238178534e-05,
"loss": 0.6856,
"step": 48
},
{
"epoch": 0.5636232925952552,
"grad_norm": 4.311333656311035,
"learning_rate": 1.0096348454262845e-05,
"loss": 0.7679,
"step": 49
},
{
"epoch": 0.5751258087706685,
"grad_norm": 7.141336917877197,
"learning_rate": 1e-05,
"loss": 0.8328,
"step": 50
},
{
"epoch": 0.5751258087706685,
"eval_loss": NaN,
"eval_runtime": 5.284,
"eval_samples_per_second": 9.462,
"eval_steps_per_second": 2.46,
"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": 1
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 6.631381723512832e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}