dada22231's picture
Training in progress, step 50, checkpoint
3b2e2b8 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.09471378677558752,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0018942757355117504,
"grad_norm": 17.73568344116211,
"learning_rate": 5e-05,
"loss": 17.9654,
"step": 1
},
{
"epoch": 0.0018942757355117504,
"eval_loss": 18.271326065063477,
"eval_runtime": 0.276,
"eval_samples_per_second": 181.183,
"eval_steps_per_second": 47.108,
"step": 1
},
{
"epoch": 0.003788551471023501,
"grad_norm": 18.474077224731445,
"learning_rate": 0.0001,
"loss": 18.0377,
"step": 2
},
{
"epoch": 0.005682827206535251,
"grad_norm": 17.73746109008789,
"learning_rate": 9.990365154573717e-05,
"loss": 17.9062,
"step": 3
},
{
"epoch": 0.007577102942047002,
"grad_norm": 16.060392379760742,
"learning_rate": 9.961501876182148e-05,
"loss": 16.6973,
"step": 4
},
{
"epoch": 0.009471378677558753,
"grad_norm": 15.940348625183105,
"learning_rate": 9.913533761814537e-05,
"loss": 15.5204,
"step": 5
},
{
"epoch": 0.011365654413070502,
"grad_norm": 17.00814437866211,
"learning_rate": 9.846666218300807e-05,
"loss": 14.2094,
"step": 6
},
{
"epoch": 0.013259930148582254,
"grad_norm": 16.360950469970703,
"learning_rate": 9.761185582727977e-05,
"loss": 12.9718,
"step": 7
},
{
"epoch": 0.015154205884094003,
"grad_norm": 16.17061996459961,
"learning_rate": 9.657457896300791e-05,
"loss": 11.8125,
"step": 8
},
{
"epoch": 0.017048481619605753,
"grad_norm": 17.933435440063477,
"learning_rate": 9.535927336897098e-05,
"loss": 10.5544,
"step": 9
},
{
"epoch": 0.018942757355117506,
"grad_norm": 20.367813110351562,
"learning_rate": 9.397114317029975e-05,
"loss": 9.5232,
"step": 10
},
{
"epoch": 0.020837033090629255,
"grad_norm": 18.844270706176758,
"learning_rate": 9.241613255361455e-05,
"loss": 8.4227,
"step": 11
},
{
"epoch": 0.022731308826141005,
"grad_norm": 22.40756607055664,
"learning_rate": 9.070090031310558e-05,
"loss": 7.2888,
"step": 12
},
{
"epoch": 0.024625584561652755,
"grad_norm": 21.323381423950195,
"learning_rate": 8.883279133655399e-05,
"loss": 6.4086,
"step": 13
},
{
"epoch": 0.026519860297164508,
"grad_norm": 21.993743896484375,
"learning_rate": 8.681980515339464e-05,
"loss": 5.7215,
"step": 14
},
{
"epoch": 0.028414136032676257,
"grad_norm": 21.057640075683594,
"learning_rate": 8.467056167950311e-05,
"loss": 4.8282,
"step": 15
},
{
"epoch": 0.030308411768188007,
"grad_norm": 15.885592460632324,
"learning_rate": 8.239426430539243e-05,
"loss": 4.0022,
"step": 16
},
{
"epoch": 0.032202687503699756,
"grad_norm": 15.36170482635498,
"learning_rate": 8.000066048588211e-05,
"loss": 3.6137,
"step": 17
},
{
"epoch": 0.034096963239211506,
"grad_norm": 11.217368125915527,
"learning_rate": 7.75e-05,
"loss": 3.3815,
"step": 18
},
{
"epoch": 0.035991238974723255,
"grad_norm": 8.858229637145996,
"learning_rate": 7.490299105985507e-05,
"loss": 3.1201,
"step": 19
},
{
"epoch": 0.03788551471023501,
"grad_norm": 12.784908294677734,
"learning_rate": 7.222075445642904e-05,
"loss": 3.0107,
"step": 20
},
{
"epoch": 0.03977979044574676,
"grad_norm": 13.20235824584961,
"learning_rate": 6.946477593864228e-05,
"loss": 2.7859,
"step": 21
},
{
"epoch": 0.04167406618125851,
"grad_norm": 7.274486064910889,
"learning_rate": 6.664685702961344e-05,
"loss": 2.504,
"step": 22
},
{
"epoch": 0.04356834191677026,
"grad_norm": 14.551770210266113,
"learning_rate": 6.377906449072578e-05,
"loss": 2.3864,
"step": 23
},
{
"epoch": 0.04546261765228201,
"grad_norm": 9.747319221496582,
"learning_rate": 6.087367864990233e-05,
"loss": 2.1798,
"step": 24
},
{
"epoch": 0.04735689338779376,
"grad_norm": 9.093273162841797,
"learning_rate": 5.794314081535644e-05,
"loss": 2.0124,
"step": 25
},
{
"epoch": 0.04735689338779376,
"eval_loss": 1.9233975410461426,
"eval_runtime": 0.2717,
"eval_samples_per_second": 184.013,
"eval_steps_per_second": 47.843,
"step": 25
},
{
"epoch": 0.04925116912330551,
"grad_norm": 7.154636859893799,
"learning_rate": 5.500000000000001e-05,
"loss": 2.0059,
"step": 26
},
{
"epoch": 0.05114544485881726,
"grad_norm": 6.04072904586792,
"learning_rate": 5.205685918464356e-05,
"loss": 1.8339,
"step": 27
},
{
"epoch": 0.053039720594329015,
"grad_norm": 6.786121845245361,
"learning_rate": 4.912632135009769e-05,
"loss": 1.6648,
"step": 28
},
{
"epoch": 0.054933996329840765,
"grad_norm": 8.46012020111084,
"learning_rate": 4.6220935509274235e-05,
"loss": 1.5453,
"step": 29
},
{
"epoch": 0.056828272065352514,
"grad_norm": 4.880290985107422,
"learning_rate": 4.3353142970386564e-05,
"loss": 1.3827,
"step": 30
},
{
"epoch": 0.058722547800864264,
"grad_norm": 10.083189964294434,
"learning_rate": 4.053522406135775e-05,
"loss": 1.2982,
"step": 31
},
{
"epoch": 0.06061682353637601,
"grad_norm": 9.618666648864746,
"learning_rate": 3.777924554357096e-05,
"loss": 1.2296,
"step": 32
},
{
"epoch": 0.06251109927188776,
"grad_norm": 4.841005325317383,
"learning_rate": 3.509700894014496e-05,
"loss": 1.1246,
"step": 33
},
{
"epoch": 0.06440537500739951,
"grad_norm": 6.0139689445495605,
"learning_rate": 3.250000000000001e-05,
"loss": 1.07,
"step": 34
},
{
"epoch": 0.06629965074291126,
"grad_norm": 9.682035446166992,
"learning_rate": 2.9999339514117912e-05,
"loss": 1.0266,
"step": 35
},
{
"epoch": 0.06819392647842301,
"grad_norm": 6.757871150970459,
"learning_rate": 2.760573569460757e-05,
"loss": 0.9599,
"step": 36
},
{
"epoch": 0.07008820221393476,
"grad_norm": 8.511247634887695,
"learning_rate": 2.53294383204969e-05,
"loss": 0.9227,
"step": 37
},
{
"epoch": 0.07198247794944651,
"grad_norm": 5.393513202667236,
"learning_rate": 2.3180194846605367e-05,
"loss": 0.9367,
"step": 38
},
{
"epoch": 0.07387675368495826,
"grad_norm": 4.358278274536133,
"learning_rate": 2.1167208663446025e-05,
"loss": 0.8792,
"step": 39
},
{
"epoch": 0.07577102942047002,
"grad_norm": 6.174125671386719,
"learning_rate": 1.9299099686894423e-05,
"loss": 0.8522,
"step": 40
},
{
"epoch": 0.07766530515598177,
"grad_norm": 2.78643536567688,
"learning_rate": 1.758386744638546e-05,
"loss": 0.7627,
"step": 41
},
{
"epoch": 0.07955958089149352,
"grad_norm": 4.229548454284668,
"learning_rate": 1.602885682970026e-05,
"loss": 0.7697,
"step": 42
},
{
"epoch": 0.08145385662700527,
"grad_norm": 8.319055557250977,
"learning_rate": 1.464072663102903e-05,
"loss": 0.7423,
"step": 43
},
{
"epoch": 0.08334813236251702,
"grad_norm": 5.810864448547363,
"learning_rate": 1.3425421036992098e-05,
"loss": 0.7089,
"step": 44
},
{
"epoch": 0.08524240809802877,
"grad_norm": 3.4576828479766846,
"learning_rate": 1.2388144172720251e-05,
"loss": 0.7014,
"step": 45
},
{
"epoch": 0.08713668383354052,
"grad_norm": 6.672909736633301,
"learning_rate": 1.1533337816991932e-05,
"loss": 0.6643,
"step": 46
},
{
"epoch": 0.08903095956905227,
"grad_norm": 7.78269624710083,
"learning_rate": 1.0864662381854632e-05,
"loss": 0.6579,
"step": 47
},
{
"epoch": 0.09092523530456402,
"grad_norm": 8.599817276000977,
"learning_rate": 1.0384981238178534e-05,
"loss": 0.618,
"step": 48
},
{
"epoch": 0.09281951104007577,
"grad_norm": 3.791947841644287,
"learning_rate": 1.0096348454262845e-05,
"loss": 0.6064,
"step": 49
},
{
"epoch": 0.09471378677558752,
"grad_norm": 3.6942226886749268,
"learning_rate": 1e-05,
"loss": 0.5882,
"step": 50
},
{
"epoch": 0.09471378677558752,
"eval_loss": 0.6685722470283508,
"eval_runtime": 0.2827,
"eval_samples_per_second": 176.857,
"eval_steps_per_second": 45.983,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 50,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 25,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1.13737243557888e+16,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}