| { |
| "best_metric": 0.827, |
| "best_model_checkpoint": "models/adu_parser/checkpoint-1815", |
| "epoch": 5.0, |
| "eval_steps": 500, |
| "global_step": 3025, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.1652892561983471, |
| "grad_norm": 360209.0, |
| "learning_rate": 6.600660066006602e-05, |
| "loss": 1.5772, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.3305785123966942, |
| "grad_norm": 195230.484375, |
| "learning_rate": 0.00013201320132013203, |
| "loss": 0.6384, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.49586776859504134, |
| "grad_norm": 143748.359375, |
| "learning_rate": 0.00019801980198019803, |
| "loss": 0.4274, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.6611570247933884, |
| "grad_norm": 187710.203125, |
| "learning_rate": 0.00019287288758265981, |
| "loss": 0.3765, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.8264462809917356, |
| "grad_norm": 123676.3125, |
| "learning_rate": 0.0001855253490080823, |
| "loss": 0.3827, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.9917355371900827, |
| "grad_norm": 179717.921875, |
| "learning_rate": 0.0001781778104335048, |
| "loss": 0.3307, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.888, |
| "eval_f1": 0.7892, |
| "eval_loss": 0.3547873795032501, |
| "eval_precision": 0.7275, |
| "eval_recall": 0.8624, |
| "eval_runtime": 19.2905, |
| "eval_samples_per_second": 125.346, |
| "eval_steps_per_second": 3.94, |
| "step": 605 |
| }, |
| { |
| "epoch": 1.1570247933884297, |
| "grad_norm": 148071.671875, |
| "learning_rate": 0.00017083027185892726, |
| "loss": 0.3299, |
| "step": 700 |
| }, |
| { |
| "epoch": 1.322314049586777, |
| "grad_norm": 96186.578125, |
| "learning_rate": 0.00016348273328434975, |
| "loss": 0.3216, |
| "step": 800 |
| }, |
| { |
| "epoch": 1.487603305785124, |
| "grad_norm": 76934.8203125, |
| "learning_rate": 0.0001561351947097722, |
| "loss": 0.3119, |
| "step": 900 |
| }, |
| { |
| "epoch": 1.6528925619834711, |
| "grad_norm": 109702.9453125, |
| "learning_rate": 0.00014878765613519473, |
| "loss": 0.3181, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.8181818181818183, |
| "grad_norm": 298751.0, |
| "learning_rate": 0.0001414401175606172, |
| "loss": 0.2937, |
| "step": 1100 |
| }, |
| { |
| "epoch": 1.9834710743801653, |
| "grad_norm": 159368.796875, |
| "learning_rate": 0.00013409257898603968, |
| "loss": 0.2963, |
| "step": 1200 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9042, |
| "eval_f1": 0.8267, |
| "eval_loss": 0.27530255913734436, |
| "eval_precision": 0.7794, |
| "eval_recall": 0.8801, |
| "eval_runtime": 19.2072, |
| "eval_samples_per_second": 125.89, |
| "eval_steps_per_second": 3.957, |
| "step": 1210 |
| }, |
| { |
| "epoch": 2.1487603305785123, |
| "grad_norm": 206873.609375, |
| "learning_rate": 0.00012674504041146215, |
| "loss": 0.2772, |
| "step": 1300 |
| }, |
| { |
| "epoch": 2.3140495867768593, |
| "grad_norm": 80094.4609375, |
| "learning_rate": 0.00011939750183688465, |
| "loss": 0.2771, |
| "step": 1400 |
| }, |
| { |
| "epoch": 2.479338842975207, |
| "grad_norm": 191308.390625, |
| "learning_rate": 0.00011204996326230713, |
| "loss": 0.2749, |
| "step": 1500 |
| }, |
| { |
| "epoch": 2.644628099173554, |
| "grad_norm": 134234.203125, |
| "learning_rate": 0.00010470242468772962, |
| "loss": 0.2746, |
| "step": 1600 |
| }, |
| { |
| "epoch": 2.809917355371901, |
| "grad_norm": 96117.125, |
| "learning_rate": 9.73548861131521e-05, |
| "loss": 0.2684, |
| "step": 1700 |
| }, |
| { |
| "epoch": 2.975206611570248, |
| "grad_norm": 109045.7421875, |
| "learning_rate": 9.000734753857459e-05, |
| "loss": 0.2481, |
| "step": 1800 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9036, |
| "eval_f1": 0.827, |
| "eval_loss": 0.26943454146385193, |
| "eval_precision": 0.7786, |
| "eval_recall": 0.8818, |
| "eval_runtime": 19.2976, |
| "eval_samples_per_second": 125.301, |
| "eval_steps_per_second": 3.938, |
| "step": 1815 |
| }, |
| { |
| "epoch": 3.1404958677685952, |
| "grad_norm": 133268.59375, |
| "learning_rate": 8.265980896399706e-05, |
| "loss": 0.2384, |
| "step": 1900 |
| }, |
| { |
| "epoch": 3.3057851239669422, |
| "grad_norm": 341372.5, |
| "learning_rate": 7.531227038941955e-05, |
| "loss": 0.2463, |
| "step": 2000 |
| }, |
| { |
| "epoch": 3.4710743801652892, |
| "grad_norm": 110221.5625, |
| "learning_rate": 6.796473181484203e-05, |
| "loss": 0.2512, |
| "step": 2100 |
| }, |
| { |
| "epoch": 3.6363636363636362, |
| "grad_norm": 173338.03125, |
| "learning_rate": 6.0617193240264514e-05, |
| "loss": 0.2586, |
| "step": 2200 |
| }, |
| { |
| "epoch": 3.8016528925619832, |
| "grad_norm": 180035.3125, |
| "learning_rate": 5.3269654665687e-05, |
| "loss": 0.2639, |
| "step": 2300 |
| }, |
| { |
| "epoch": 3.9669421487603307, |
| "grad_norm": 44317.7578125, |
| "learning_rate": 4.592211609110948e-05, |
| "loss": 0.2377, |
| "step": 2400 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.903, |
| "eval_f1": 0.8197, |
| "eval_loss": 0.2731046676635742, |
| "eval_precision": 0.7671, |
| "eval_recall": 0.8801, |
| "eval_runtime": 19.2631, |
| "eval_samples_per_second": 125.525, |
| "eval_steps_per_second": 3.945, |
| "step": 2420 |
| }, |
| { |
| "epoch": 4.132231404958677, |
| "grad_norm": 141946.765625, |
| "learning_rate": 3.8574577516531966e-05, |
| "loss": 0.2376, |
| "step": 2500 |
| }, |
| { |
| "epoch": 4.297520661157025, |
| "grad_norm": 81543.375, |
| "learning_rate": 3.122703894195444e-05, |
| "loss": 0.2373, |
| "step": 2600 |
| }, |
| { |
| "epoch": 4.462809917355372, |
| "grad_norm": 92284.8359375, |
| "learning_rate": 2.387950036737693e-05, |
| "loss": 0.2424, |
| "step": 2700 |
| }, |
| { |
| "epoch": 4.628099173553719, |
| "grad_norm": 51905.05078125, |
| "learning_rate": 1.6531961792799413e-05, |
| "loss": 0.2246, |
| "step": 2800 |
| }, |
| { |
| "epoch": 4.793388429752066, |
| "grad_norm": 157494.578125, |
| "learning_rate": 9.184423218221897e-06, |
| "loss": 0.2408, |
| "step": 2900 |
| }, |
| { |
| "epoch": 4.958677685950414, |
| "grad_norm": 134388.328125, |
| "learning_rate": 1.8368846436443793e-06, |
| "loss": 0.2266, |
| "step": 3000 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9042, |
| "eval_f1": 0.8228, |
| "eval_loss": 0.2719922959804535, |
| "eval_precision": 0.7732, |
| "eval_recall": 0.8793, |
| "eval_runtime": 19.2747, |
| "eval_samples_per_second": 125.449, |
| "eval_steps_per_second": 3.943, |
| "step": 3025 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 3025, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "save_steps": 500, |
| "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": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 6383455545761280.0, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
