ryusangwon's picture
End of training
2ba3ffe verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.37341299477221807,
"eval_steps": 500,
"global_step": 500,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 4.98755290017426e-05,
"loss": 1.7892,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 4.975105800348519e-05,
"loss": 1.7869,
"step": 20
},
{
"epoch": 0.02,
"learning_rate": 4.962658700522779e-05,
"loss": 1.7872,
"step": 30
},
{
"epoch": 0.03,
"learning_rate": 4.9502116006970375e-05,
"loss": 1.7552,
"step": 40
},
{
"epoch": 0.04,
"learning_rate": 4.937764500871298e-05,
"loss": 1.6772,
"step": 50
},
{
"epoch": 0.04,
"learning_rate": 4.9253174010455565e-05,
"loss": 1.7078,
"step": 60
},
{
"epoch": 0.05,
"learning_rate": 4.912870301219816e-05,
"loss": 1.6951,
"step": 70
},
{
"epoch": 0.06,
"learning_rate": 4.9004232013940755e-05,
"loss": 1.7137,
"step": 80
},
{
"epoch": 0.07,
"learning_rate": 4.887976101568335e-05,
"loss": 1.7008,
"step": 90
},
{
"epoch": 0.07,
"learning_rate": 4.8755290017425944e-05,
"loss": 1.725,
"step": 100
},
{
"epoch": 0.08,
"learning_rate": 4.863081901916854e-05,
"loss": 1.7187,
"step": 110
},
{
"epoch": 0.09,
"learning_rate": 4.850634802091113e-05,
"loss": 1.7209,
"step": 120
},
{
"epoch": 0.1,
"learning_rate": 4.838187702265373e-05,
"loss": 1.7354,
"step": 130
},
{
"epoch": 0.1,
"learning_rate": 4.825740602439632e-05,
"loss": 1.7021,
"step": 140
},
{
"epoch": 0.11,
"learning_rate": 4.813293502613891e-05,
"loss": 1.6657,
"step": 150
},
{
"epoch": 0.12,
"learning_rate": 4.800846402788151e-05,
"loss": 1.6852,
"step": 160
},
{
"epoch": 0.13,
"learning_rate": 4.78839930296241e-05,
"loss": 1.6746,
"step": 170
},
{
"epoch": 0.13,
"learning_rate": 4.7759522031366697e-05,
"loss": 1.6886,
"step": 180
},
{
"epoch": 0.14,
"learning_rate": 4.763505103310929e-05,
"loss": 1.6571,
"step": 190
},
{
"epoch": 0.15,
"learning_rate": 4.751058003485188e-05,
"loss": 1.7131,
"step": 200
},
{
"epoch": 0.16,
"learning_rate": 4.738610903659448e-05,
"loss": 1.7099,
"step": 210
},
{
"epoch": 0.16,
"learning_rate": 4.726163803833707e-05,
"loss": 1.7284,
"step": 220
},
{
"epoch": 0.17,
"learning_rate": 4.7137167040079664e-05,
"loss": 1.704,
"step": 230
},
{
"epoch": 0.18,
"learning_rate": 4.701269604182226e-05,
"loss": 1.6921,
"step": 240
},
{
"epoch": 0.19,
"learning_rate": 4.6888225043564854e-05,
"loss": 1.6828,
"step": 250
},
{
"epoch": 0.19,
"learning_rate": 4.676375404530744e-05,
"loss": 1.7255,
"step": 260
},
{
"epoch": 0.2,
"learning_rate": 4.6639283047050044e-05,
"loss": 1.6767,
"step": 270
},
{
"epoch": 0.21,
"learning_rate": 4.651481204879263e-05,
"loss": 1.6796,
"step": 280
},
{
"epoch": 0.22,
"learning_rate": 4.6390341050535227e-05,
"loss": 1.7305,
"step": 290
},
{
"epoch": 0.22,
"learning_rate": 4.626587005227782e-05,
"loss": 1.7471,
"step": 300
},
{
"epoch": 0.23,
"learning_rate": 4.6141399054020416e-05,
"loss": 1.6348,
"step": 310
},
{
"epoch": 0.24,
"learning_rate": 4.601692805576301e-05,
"loss": 1.676,
"step": 320
},
{
"epoch": 0.25,
"learning_rate": 4.5892457057505606e-05,
"loss": 1.6602,
"step": 330
},
{
"epoch": 0.25,
"learning_rate": 4.5767986059248194e-05,
"loss": 1.6634,
"step": 340
},
{
"epoch": 0.26,
"learning_rate": 4.5643515060990796e-05,
"loss": 1.6952,
"step": 350
},
{
"epoch": 0.27,
"learning_rate": 4.5519044062733384e-05,
"loss": 1.683,
"step": 360
},
{
"epoch": 0.28,
"learning_rate": 4.539457306447598e-05,
"loss": 1.6572,
"step": 370
},
{
"epoch": 0.28,
"learning_rate": 4.5270102066218574e-05,
"loss": 1.6472,
"step": 380
},
{
"epoch": 0.29,
"learning_rate": 4.514563106796117e-05,
"loss": 1.6852,
"step": 390
},
{
"epoch": 0.3,
"learning_rate": 4.502116006970376e-05,
"loss": 1.6737,
"step": 400
},
{
"epoch": 0.31,
"learning_rate": 4.489668907144636e-05,
"loss": 1.6936,
"step": 410
},
{
"epoch": 0.31,
"learning_rate": 4.4772218073188946e-05,
"loss": 1.6713,
"step": 420
},
{
"epoch": 0.32,
"learning_rate": 4.464774707493155e-05,
"loss": 1.6681,
"step": 430
},
{
"epoch": 0.33,
"learning_rate": 4.4523276076674136e-05,
"loss": 1.6231,
"step": 440
},
{
"epoch": 0.34,
"learning_rate": 4.439880507841673e-05,
"loss": 1.6593,
"step": 450
},
{
"epoch": 0.34,
"learning_rate": 4.4274334080159326e-05,
"loss": 1.6844,
"step": 460
},
{
"epoch": 0.35,
"learning_rate": 4.414986308190192e-05,
"loss": 1.6751,
"step": 470
},
{
"epoch": 0.36,
"learning_rate": 4.4025392083644516e-05,
"loss": 1.6748,
"step": 480
},
{
"epoch": 0.37,
"learning_rate": 4.390092108538711e-05,
"loss": 1.6793,
"step": 490
},
{
"epoch": 0.37,
"learning_rate": 4.37764500871297e-05,
"loss": 1.6959,
"step": 500
}
],
"logging_steps": 10,
"max_steps": 4017,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"total_flos": 3.1601241096192e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}