checkpoint-4452/trainer_state.json

{
 "best_metric": 0.6224449276924133,
 "best_model_checkpoint": "/content/drive/MyDrive/XLM-RoBERTa/checkpoint-4452",
 "epoch": 4.0,
 "eval_steps": 100,
 "global_step": 4452,
 "is_hyper_param_search": false,
 "is_local_process_zero": true,
 "is_world_process_zero": true,
 "log_history": [
 {
 "epoch": 1.0,
 "grad_norm": 8.267438888549805,
 "learning_rate": 4.5e-06,
 "loss": 0.6879,
 "step": 1113
 },
 {
 "epoch": 1.0,
 "eval_accuracy": 0.6130337078651685,
 "eval_f1": 0.674233825198638,
 "eval_loss": 0.6553897857666016,
 "eval_precision": 0.5920265780730897,
 "eval_recall": 0.7829525483304042,
 "eval_runtime": 16.6298,
 "eval_samples_per_second": 133.796,
 "eval_steps_per_second": 8.419,
 "step": 1113
 },
 {
 "epoch": 2.0,
 "grad_norm": 11.426044464111328,
 "learning_rate": 4.000000000000001e-06,
 "loss": 0.6446,
 "step": 2226
 },
 {
 "epoch": 2.0,
 "eval_accuracy": 0.6449438202247191,
 "eval_f1": 0.6786004882017901,
 "eval_loss": 0.6413919925689697,
 "eval_precision": 0.6318181818181818,
 "eval_recall": 0.7328646748681898,
 "eval_runtime": 16.2984,
 "eval_samples_per_second": 136.517,
 "eval_steps_per_second": 8.59,
 "step": 2226
 },
 {
 "epoch": 3.0,
 "grad_norm": 34.342185974121094,
 "learning_rate": 3.5e-06,
 "loss": 0.62,
 "step": 3339
 },
 {
 "epoch": 3.0,
 "eval_accuracy": 0.6494382022471911,
 "eval_f1": 0.6758104738154613,
 "eval_loss": 0.6359991431236267,
 "eval_precision": 0.6411671924290221,
 "eval_recall": 0.7144112478031635,
 "eval_runtime": 16.3309,
 "eval_samples_per_second": 136.245,
 "eval_steps_per_second": 8.573,
 "step": 3339
 },
 {
 "epoch": 4.0,
 "grad_norm": 15.571684837341309,
 "learning_rate": 3e-06,
 "loss": 0.5939,
 "step": 4452
 },
 {
 "epoch": 4.0,
 "eval_accuracy": 0.6548314606741573,
 "eval_f1": 0.7009345794392523,
 "eval_loss": 0.6224449276924133,
 "eval_precision": 0.6293706293706294,
 "eval_recall": 0.7908611599297012,
 "eval_runtime": 16.3616,
 "eval_samples_per_second": 135.99,
 "eval_steps_per_second": 8.557,
 "step": 4452
 }
 ],
 "logging_steps": 100,
 "max_steps": 11130,
 "num_input_tokens_seen": 0,
 "num_train_epochs": 10,
 "save_steps": 100,
 "stateful_callbacks": {
 "EarlyStoppingCallback": {
 "args": {
 "early_stopping_patience": 2,
 "early_stopping_threshold": 0.0
 },
 "attributes": {
 "early_stopping_patience_counter": 0
 }
 },
 "TrainerControl": {
 "args": {
 "should_epoch_stop": false,
 "should_evaluate": false,
 "should_log": false,
 "should_save": true,
 "should_training_stop": false
 },
 "attributes": {}
 }
 },
 "total_flos": 1.872929736474624e+16,
 "train_batch_size": 16,
 "trial_name": null,
 "trial_params": null
}