| { | |
| "best_metric": 0.8851654529571533, | |
| "best_model_checkpoint": "finetune-tiktok-brat4\\checkpoint-20", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 54.496673583984375, | |
| "learning_rate": 1.6666666666666667e-06, | |
| "loss": 0.7894, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 11.606372833251953, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 0.7589, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 38.31898498535156, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2543, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 47.521976470947266, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.8361, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 23.255413055419922, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.2909, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 36.35523986816406, | |
| "learning_rate": 1e-05, | |
| "loss": 0.7906, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 35.16067886352539, | |
| "learning_rate": 9.814814814814815e-06, | |
| "loss": 0.96, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 36.35455322265625, | |
| "learning_rate": 9.62962962962963e-06, | |
| "loss": 0.3895, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 119.45866394042969, | |
| "learning_rate": 9.444444444444445e-06, | |
| "loss": 0.5939, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 32.66160202026367, | |
| "learning_rate": 9.25925925925926e-06, | |
| "loss": 0.9343, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 16.789913177490234, | |
| "learning_rate": 9.074074074074075e-06, | |
| "loss": 0.6067, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 13.208721160888672, | |
| "learning_rate": 8.888888888888888e-06, | |
| "loss": 0.3274, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 21.66659927368164, | |
| "learning_rate": 8.703703703703705e-06, | |
| "loss": 1.8018, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 14.522764205932617, | |
| "learning_rate": 8.518518518518519e-06, | |
| "loss": 0.9705, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 33.81802749633789, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 1.3949, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 46.284576416015625, | |
| "learning_rate": 8.148148148148148e-06, | |
| "loss": 1.7191, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 18.38251304626465, | |
| "learning_rate": 7.962962962962963e-06, | |
| "loss": 0.4667, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 18.9488582611084, | |
| "learning_rate": 7.77777777777778e-06, | |
| "loss": 1.1351, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 9.29172420501709, | |
| "learning_rate": 7.592592592592594e-06, | |
| "loss": 0.1151, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 39.511680603027344, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 1.3048, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6805555555555556, | |
| "eval_f1_macro": 0.6377799415774099, | |
| "eval_f1_micro": 0.6805555555555556, | |
| "eval_f1_weighted": 0.6723466407010711, | |
| "eval_loss": 0.8851654529571533, | |
| "eval_precision_macro": 0.6714285714285714, | |
| "eval_precision_micro": 0.6805555555555556, | |
| "eval_precision_weighted": 0.680952380952381, | |
| "eval_recall_macro": 0.6266299193930772, | |
| "eval_recall_micro": 0.6805555555555556, | |
| "eval_recall_weighted": 0.6805555555555556, | |
| "eval_runtime": 85.5963, | |
| "eval_samples_per_second": 0.841, | |
| "eval_steps_per_second": 0.058, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 60, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "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": 42098146836480.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |