jpherrerap's picture
End of training
116a310 verified
Raw
History Blame Contribute Delete
1.87 kB
{
"best_global_step": 140,
"best_metric": 0.8378378378378378,
"best_model_checkpoint": "models/fake-news-bert-base-spanish-wwm-cased/checkpoint-140",
"epoch": 2.0,
"eval_steps": 500,
"global_step": 140,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 6.333802223205566,
"learning_rate": 1.0142857142857143e-05,
"loss": 0.5238,
"step": 70
},
{
"epoch": 1.0,
"eval_f1": 0.7599999999999999,
"eval_loss": 0.42333319783210754,
"eval_runtime": 4.1419,
"eval_samples_per_second": 57.944,
"eval_steps_per_second": 3.621,
"step": 70
},
{
"epoch": 2.0,
"grad_norm": 15.530929565429688,
"learning_rate": 1.4285714285714287e-07,
"loss": 0.2693,
"step": 140
},
{
"epoch": 2.0,
"eval_f1": 0.8378378378378378,
"eval_loss": 0.3234243392944336,
"eval_runtime": 4.0599,
"eval_samples_per_second": 59.114,
"eval_steps_per_second": 3.695,
"step": 140
},
{
"epoch": 2.0,
"step": 140,
"total_flos": 589368764006400.0,
"train_loss": 0.39655887058803013,
"train_runtime": 130.5105,
"train_samples_per_second": 17.163,
"train_steps_per_second": 1.073
}
],
"logging_steps": 500,
"max_steps": 140,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 589368764006400.0,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}