aixk's picture
Auto-upload checkpoint step 200
0a17bf8 verified
Raw History Blame Contribute Delete
4.47 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.001168613381791835,
"eval_steps": 500,
"global_step": 200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 5.8430669089591743e-05,
"grad_norm": 9.783331871032715,
"learning_rate": 6e-06,
"loss": 36.68600158691406,
"step": 10
},
{
"epoch": 0.00011686133817918349,
"grad_norm": 11.469252586364746,
"learning_rate": 1.2666666666666668e-05,
"loss": 36.55324096679688,
"step": 20
},
{
"epoch": 0.00017529200726877522,
"grad_norm": 12.40107250213623,
"learning_rate": 1.9333333333333333e-05,
"loss": 36.35345458984375,
"step": 30
},
{
"epoch": 0.00023372267635836697,
"grad_norm": 11.716872215270996,
"learning_rate": 2.6000000000000002e-05,
"loss": 36.08180236816406,
"step": 40
},
{
"epoch": 0.0002921533454479587,
"grad_norm": 14.445358276367188,
"learning_rate": 3.266666666666667e-05,
"loss": 35.567361450195314,
"step": 50
},
{
"epoch": 0.00035058401453755045,
"grad_norm": 12.091419219970703,
"learning_rate": 3.933333333333333e-05,
"loss": 35.10403137207031,
"step": 60
},
{
"epoch": 0.0004090146836271422,
"grad_norm": 13.730995178222656,
"learning_rate": 4.600000000000001e-05,
"loss": 33.99032287597656,
"step": 70
},
{
"epoch": 0.00046744535271673395,
"grad_norm": 14.165889739990234,
"learning_rate": 5.266666666666666e-05,
"loss": 33.32759094238281,
"step": 80
},
{
"epoch": 0.0005258760218063257,
"grad_norm": 17.01044273376465,
"learning_rate": 5.9333333333333343e-05,
"loss": 31.982687377929686,
"step": 90
},
{
"epoch": 0.0005843066908959174,
"grad_norm": 20.539939880371094,
"learning_rate": 6.6e-05,
"loss": 30.40308532714844,
"step": 100
},
{
"epoch": 0.0006427373599855092,
"grad_norm": 20.50539207458496,
"learning_rate": 7.266666666666667e-05,
"loss": 28.605145263671876,
"step": 110
},
{
"epoch": 0.0007011680290751009,
"grad_norm": 35.68551254272461,
"learning_rate": 7.933333333333334e-05,
"loss": 26.790576171875,
"step": 120
},
{
"epoch": 0.0007595986981646927,
"grad_norm": 22.74065589904785,
"learning_rate": 8.6e-05,
"loss": 24.934747314453126,
"step": 130
},
{
"epoch": 0.0008180293672542844,
"grad_norm": 59.207008361816406,
"learning_rate": 9.266666666666666e-05,
"loss": 23.048512268066407,
"step": 140
},
{
"epoch": 0.0008764600363438762,
"grad_norm": 46.39744186401367,
"learning_rate": 9.933333333333334e-05,
"loss": 21.81122589111328,
"step": 150
},
{
"epoch": 0.0009348907054334679,
"grad_norm": 46.57512283325195,
"learning_rate": 0.00010600000000000002,
"loss": 21.49383087158203,
"step": 160
},
{
"epoch": 0.0009933213745230596,
"grad_norm": 20.875106811523438,
"learning_rate": 0.00011266666666666668,
"loss": 20.477175903320312,
"step": 170
},
{
"epoch": 0.0010517520436126514,
"grad_norm": 31.581335067749023,
"learning_rate": 0.00011933333333333334,
"loss": 19.832745361328126,
"step": 180
},
{
"epoch": 0.001110182712702243,
"grad_norm": 56.4605712890625,
"learning_rate": 0.000126,
"loss": 19.4491943359375,
"step": 190
},
{
"epoch": 0.001168613381791835,
"grad_norm": 162.9219512939453,
"learning_rate": 0.00013266666666666667,
"loss": 19.48320617675781,
"step": 200
}
],
"logging_steps": 10,
"max_steps": 1000000,
"num_input_tokens_seen": 0,
"num_train_epochs": 6,
"save_steps": 200,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1598220482291712.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}