MsIssuesBERT / run-1 /checkpoint-250 /trainer_state.json
YagiASAFAS's picture
Training in progress, epoch 2
cc3c1cf verified
Invalid JSON: Unexpected token 'N', ..."al_loss": NaN, "... is not valid JSON
{
"best_global_step": 125,
"best_metric": 0.7222001215424422,
"best_model_checkpoint": "./results/run-1/checkpoint-125",
"epoch": 2.0,
"eval_steps": 500,
"global_step": 250,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.8,
"grad_norm": 12.130753517150879,
"learning_rate": 1.6523003188214528e-05,
"loss": 1623.5764,
"step": 100
},
{
"epoch": 1.0,
"eval_economic_inequality_accuracy": 0.7770780856423174,
"eval_economic_inequality_f1": 0.6795991195482776,
"eval_economic_policy_benefits_accuracy": 0.8215488215488216,
"eval_economic_policy_benefits_f1": 0.7410643713786043,
"eval_ethnic_boundaries_accuracy": 0.946078431372549,
"eval_ethnic_boundaries_f1": 0.9198646713093299,
"eval_language_policy_accuracy": 0.6764705882352942,
"eval_language_policy_f1": 0.545923632610939,
"eval_loss": NaN,
"eval_mother_tongue_education_accuracy": 0.7777777777777778,
"eval_mother_tongue_education_f1": 0.6805555555555556,
"eval_overall_accuracy": 0.8064020197505432,
"eval_overall_f1": 0.7222001215424422,
"eval_religion_ethnic_identity_accuracy": 0.839458413926499,
"eval_religion_ethnic_identity_f1": 0.7661933788519465,
"eval_runtime": 4.4741,
"eval_samples_per_second": 894.041,
"eval_steps_per_second": 55.878,
"step": 125
},
{
"epoch": 1.6,
"grad_norm": 7.246724605560303,
"learning_rate": 3.3212905398532236e-05,
"loss": 4406.7347,
"step": 200
},
{
"epoch": 2.0,
"eval_economic_inequality_accuracy": 0.7770780856423174,
"eval_economic_inequality_f1": 0.6795991195482776,
"eval_economic_policy_benefits_accuracy": 0.8215488215488216,
"eval_economic_policy_benefits_f1": 0.7410643713786043,
"eval_ethnic_boundaries_accuracy": 0.946078431372549,
"eval_ethnic_boundaries_f1": 0.9198646713093299,
"eval_language_policy_accuracy": 0.6764705882352942,
"eval_language_policy_f1": 0.545923632610939,
"eval_loss": NaN,
"eval_mother_tongue_education_accuracy": 0.7777777777777778,
"eval_mother_tongue_education_f1": 0.6805555555555556,
"eval_overall_accuracy": 0.8064020197505432,
"eval_overall_f1": 0.7222001215424422,
"eval_religion_ethnic_identity_accuracy": 0.839458413926499,
"eval_religion_ethnic_identity_f1": 0.7661933788519465,
"eval_runtime": 4.4873,
"eval_samples_per_second": 891.403,
"eval_steps_per_second": 55.713,
"step": 250
}
],
"logging_steps": 100,
"max_steps": 2000,
"num_input_tokens_seen": 0,
"num_train_epochs": 16,
"save_steps": 500,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 2,
"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": false
},
"attributes": {}
}
},
"total_flos": 6736610643148800.0,
"train_batch_size": 32,
"trial_name": null,
"trial_params": {
"gradient_accumulation_steps": 4,
"learning_rate": 4.305994770261968e-05,
"num_train_epochs": 16,
"per_device_train_batch_size": 32,
"warmup_steps": 258,
"weight_decay": 0.09399341365652919
}
}