autoprogrammer's picture
upload checkpoint-246
50a5377 verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"eval_steps": 500,
"global_step": 246,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0408997955010225,
"grad_norm": 7.998523235321045,
"learning_rate": 3.3333333333333333e-06,
"loss": 0.5733,
"step": 5
},
{
"epoch": 0.081799591002045,
"grad_norm": 9.153129577636719,
"learning_rate": 7.500000000000001e-06,
"loss": 0.5196,
"step": 10
},
{
"epoch": 0.12269938650306748,
"grad_norm": 8.34139347076416,
"learning_rate": 9.999225623611208e-06,
"loss": 0.5806,
"step": 15
},
{
"epoch": 0.16359918200409,
"grad_norm": 7.1141204833984375,
"learning_rate": 9.990516643685222e-06,
"loss": 0.4941,
"step": 20
},
{
"epoch": 0.20449897750511248,
"grad_norm": 8.44301700592041,
"learning_rate": 9.972147627352593e-06,
"loss": 0.6074,
"step": 25
},
{
"epoch": 0.24539877300613497,
"grad_norm": 6.837522029876709,
"learning_rate": 9.944154131125643e-06,
"loss": 0.6176,
"step": 30
},
{
"epoch": 0.28629856850715746,
"grad_norm": 6.722048282623291,
"learning_rate": 9.906590341416725e-06,
"loss": 0.6011,
"step": 35
},
{
"epoch": 0.32719836400818,
"grad_norm": 6.896355152130127,
"learning_rate": 9.859528969650739e-06,
"loss": 0.5717,
"step": 40
},
{
"epoch": 0.36809815950920244,
"grad_norm": 7.0612945556640625,
"learning_rate": 9.803061111519188e-06,
"loss": 0.5783,
"step": 45
},
{
"epoch": 0.40899795501022496,
"grad_norm": 6.113592147827148,
"learning_rate": 9.737296070648187e-06,
"loss": 0.6013,
"step": 50
},
{
"epoch": 0.4498977505112474,
"grad_norm": 6.054924488067627,
"learning_rate": 9.66236114702178e-06,
"loss": 0.612,
"step": 55
},
{
"epoch": 0.49079754601226994,
"grad_norm": 5.854165554046631,
"learning_rate": 9.57840139057007e-06,
"loss": 0.5835,
"step": 60
},
{
"epoch": 0.5316973415132924,
"grad_norm": 6.945219993591309,
"learning_rate": 9.485579320399184e-06,
"loss": 0.5709,
"step": 65
},
{
"epoch": 0.5725971370143149,
"grad_norm": 6.699445724487305,
"learning_rate": 9.384074610206495e-06,
"loss": 0.6038,
"step": 70
},
{
"epoch": 0.6134969325153374,
"grad_norm": 6.41201114654541,
"learning_rate": 9.274083740490097e-06,
"loss": 0.6221,
"step": 75
},
{
"epoch": 0.65439672801636,
"grad_norm": 5.748655796051025,
"learning_rate": 9.155819618225707e-06,
"loss": 0.6027,
"step": 80
},
{
"epoch": 0.6952965235173824,
"grad_norm": 6.205794334411621,
"learning_rate": 9.029511164747175e-06,
"loss": 0.5737,
"step": 85
},
{
"epoch": 0.7361963190184049,
"grad_norm": 6.745859622955322,
"learning_rate": 8.895402872628352e-06,
"loss": 0.6281,
"step": 90
},
{
"epoch": 0.7770961145194274,
"grad_norm": 5.8365302085876465,
"learning_rate": 8.753754332424047e-06,
"loss": 0.5721,
"step": 95
},
{
"epoch": 0.8179959100204499,
"grad_norm": 6.5638532638549805,
"learning_rate": 8.604839730186125e-06,
"loss": 0.6225,
"step": 100
},
{
"epoch": 0.8588957055214724,
"grad_norm": 9.908438682556152,
"learning_rate": 8.448947316727444e-06,
"loss": 0.6062,
"step": 105
},
{
"epoch": 0.8997955010224948,
"grad_norm": 7.083659648895264,
"learning_rate": 8.286378849660895e-06,
"loss": 0.5851,
"step": 110
},
{
"epoch": 0.9406952965235174,
"grad_norm": 5.502669811248779,
"learning_rate": 8.117449009293668e-06,
"loss": 0.5388,
"step": 115
},
{
"epoch": 0.9815950920245399,
"grad_norm": 5.813559055328369,
"learning_rate": 7.942484789507282e-06,
"loss": 0.6135,
"step": 120
},
{
"epoch": 1.016359918200409,
"grad_norm": 4.387826442718506,
"learning_rate": 7.76182486480253e-06,
"loss": 0.3565,
"step": 125
},
{
"epoch": 1.0572597137014315,
"grad_norm": 3.389594793319702,
"learning_rate": 7.57581893473448e-06,
"loss": 0.185,
"step": 130
},
{
"epoch": 1.098159509202454,
"grad_norm": 3.6928842067718506,
"learning_rate": 7.38482704700653e-06,
"loss": 0.1724,
"step": 135
},
{
"epoch": 1.1390593047034765,
"grad_norm": 4.740786552429199,
"learning_rate": 7.1892189005337494e-06,
"loss": 0.1397,
"step": 140
},
{
"epoch": 1.179959100204499,
"grad_norm": 6.11871862411499,
"learning_rate": 6.989373129824605e-06,
"loss": 0.1564,
"step": 145
},
{
"epoch": 1.2208588957055215,
"grad_norm": 4.457100868225098,
"learning_rate": 6.785676572066225e-06,
"loss": 0.1557,
"step": 150
},
{
"epoch": 1.261758691206544,
"grad_norm": 4.849860191345215,
"learning_rate": 6.5785235183319266e-06,
"loss": 0.142,
"step": 155
},
{
"epoch": 1.3026584867075663,
"grad_norm": 4.870535373687744,
"learning_rate": 6.368314950360416e-06,
"loss": 0.1623,
"step": 160
},
{
"epoch": 1.343558282208589,
"grad_norm": 4.23346471786499,
"learning_rate": 6.155457764384001e-06,
"loss": 0.1615,
"step": 165
},
{
"epoch": 1.3844580777096114,
"grad_norm": 4.38654088973999,
"learning_rate": 5.940363983508257e-06,
"loss": 0.1759,
"step": 170
},
{
"epoch": 1.425357873210634,
"grad_norm": 4.874055862426758,
"learning_rate": 5.723449960167703e-06,
"loss": 0.1886,
"step": 175
},
{
"epoch": 1.4662576687116564,
"grad_norm": 4.817355155944824,
"learning_rate": 5.50513557020129e-06,
"loss": 0.165,
"step": 180
},
{
"epoch": 1.5071574642126788,
"grad_norm": 4.6559953689575195,
"learning_rate": 5.285843400107722e-06,
"loss": 0.1718,
"step": 185
},
{
"epoch": 1.5480572597137015,
"grad_norm": 4.32926082611084,
"learning_rate": 5.065997929053795e-06,
"loss": 0.1644,
"step": 190
},
{
"epoch": 1.588957055214724,
"grad_norm": 4.097021102905273,
"learning_rate": 4.846024707219149e-06,
"loss": 0.1648,
"step": 195
},
{
"epoch": 1.6298568507157465,
"grad_norm": 5.297605037689209,
"learning_rate": 4.626349532067879e-06,
"loss": 0.1847,
"step": 200
},
{
"epoch": 1.670756646216769,
"grad_norm": 3.8317348957061768,
"learning_rate": 4.407397624141487e-06,
"loss": 0.1595,
"step": 205
},
{
"epoch": 1.7116564417177913,
"grad_norm": 5.160454750061035,
"learning_rate": 4.1895928039685635e-06,
"loss": 0.1692,
"step": 210
},
{
"epoch": 1.752556237218814,
"grad_norm": 3.6158623695373535,
"learning_rate": 3.973356671684455e-06,
"loss": 0.1531,
"step": 215
},
{
"epoch": 1.7934560327198366,
"grad_norm": 4.5961503982543945,
"learning_rate": 3.7591077909488817e-06,
"loss": 0.1621,
"step": 220
},
{
"epoch": 1.834355828220859,
"grad_norm": 4.000308036804199,
"learning_rate": 3.54726087874122e-06,
"loss": 0.1456,
"step": 225
},
{
"epoch": 1.8752556237218814,
"grad_norm": 4.329658031463623,
"learning_rate": 3.3382260026017027e-06,
"loss": 0.1514,
"step": 230
},
{
"epoch": 1.9161554192229038,
"grad_norm": 4.9972028732299805,
"learning_rate": 3.132407786872442e-06,
"loss": 0.1659,
"step": 235
},
{
"epoch": 1.9570552147239264,
"grad_norm": 4.748896598815918,
"learning_rate": 2.9302046294747498e-06,
"loss": 0.148,
"step": 240
},
{
"epoch": 1.997955010224949,
"grad_norm": 5.426475524902344,
"learning_rate": 2.7320079307387788e-06,
"loss": 0.1588,
"step": 245
}
],
"logging_steps": 5,
"max_steps": 369,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 7.766141115752776e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}