hatespeech-xlmr-v4 / trainer_state.json
nahiar's picture
Initial upload (auto-create if missing)
aed3fae verified
{
"best_global_step": 1839,
"best_metric": 0.9135068219633944,
"best_model_checkpoint": "./xlmr-hatespeech/checkpoint-1839",
"epoch": 3.0,
"eval_steps": 500,
"global_step": 1839,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 19.032840728759766,
"learning_rate": 1.3344208809135401e-05,
"loss": 0.4131,
"step": 613
},
{
"epoch": 1.0,
"eval_accuracy": 0.8915171288743883,
"eval_f1_macro": 0.8914910678338873,
"eval_loss": 0.2685175836086273,
"eval_runtime": 6.1365,
"eval_samples_per_second": 399.578,
"eval_steps_per_second": 12.548,
"step": 613
},
{
"epoch": 2.0,
"grad_norm": 62.996768951416016,
"learning_rate": 6.677542142468733e-06,
"loss": 0.2397,
"step": 1226
},
{
"epoch": 2.0,
"eval_accuracy": 0.9131321370309952,
"eval_f1_macro": 0.9131002088985283,
"eval_loss": 0.2940494120121002,
"eval_runtime": 6.1267,
"eval_samples_per_second": 400.215,
"eval_steps_per_second": 12.568,
"step": 1226
},
{
"epoch": 3.0,
"grad_norm": 22.773950576782227,
"learning_rate": 1.0875475802066341e-08,
"loss": 0.1769,
"step": 1839
},
{
"epoch": 3.0,
"eval_accuracy": 0.9135399673735726,
"eval_f1_macro": 0.9135068219633944,
"eval_loss": 0.32052531838417053,
"eval_runtime": 6.1929,
"eval_samples_per_second": 395.935,
"eval_steps_per_second": 12.434,
"step": 1839
}
],
"logging_steps": 500,
"max_steps": 1839,
"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": true
},
"attributes": {}
}
},
"total_flos": 2158763514797640.0,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}