| { | |
| "best_metric": 1.6190818548202515, | |
| "best_model_checkpoint": "bert_base_lda_5_v1_stsb/checkpoint-138", | |
| "epoch": 11.0, | |
| "eval_steps": 500, | |
| "global_step": 253, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 3.5698792934417725, | |
| "learning_rate": 4.9e-05, | |
| "loss": 2.6199, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_combined_score": 0.0762828613089408, | |
| "eval_loss": 2.5334348678588867, | |
| "eval_pearson": 0.08810304441387712, | |
| "eval_runtime": 0.9594, | |
| "eval_samples_per_second": 1563.484, | |
| "eval_spearmanr": 0.06446267820400446, | |
| "eval_steps_per_second": 6.254, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 14.151108741760254, | |
| "learning_rate": 4.8e-05, | |
| "loss": 1.9109, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_combined_score": 0.36476464733810526, | |
| "eval_loss": 2.047811985015869, | |
| "eval_pearson": 0.36724434323508826, | |
| "eval_runtime": 0.9781, | |
| "eval_samples_per_second": 1533.516, | |
| "eval_spearmanr": 0.36228495144112227, | |
| "eval_steps_per_second": 6.134, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 22.73438835144043, | |
| "learning_rate": 4.7e-05, | |
| "loss": 1.4094, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_combined_score": 0.5038154114449356, | |
| "eval_loss": 1.7320016622543335, | |
| "eval_pearson": 0.5080314849305678, | |
| "eval_runtime": 0.9668, | |
| "eval_samples_per_second": 1551.517, | |
| "eval_spearmanr": 0.4995993379593033, | |
| "eval_steps_per_second": 6.206, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 10.041772842407227, | |
| "learning_rate": 4.600000000000001e-05, | |
| "loss": 0.9385, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_combined_score": 0.5257169620696511, | |
| "eval_loss": 1.9693756103515625, | |
| "eval_pearson": 0.5238214152085215, | |
| "eval_runtime": 0.9678, | |
| "eval_samples_per_second": 1549.828, | |
| "eval_spearmanr": 0.5276125089307807, | |
| "eval_steps_per_second": 6.199, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 17.2652645111084, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.6759, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_combined_score": 0.5430029550606046, | |
| "eval_loss": 1.6463857889175415, | |
| "eval_pearson": 0.5449225085129881, | |
| "eval_runtime": 0.9788, | |
| "eval_samples_per_second": 1532.5, | |
| "eval_spearmanr": 0.5410834016082212, | |
| "eval_steps_per_second": 6.13, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 11.10145092010498, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 0.5133, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_combined_score": 0.562871620868381, | |
| "eval_loss": 1.6190818548202515, | |
| "eval_pearson": 0.5646223727019971, | |
| "eval_runtime": 0.9701, | |
| "eval_samples_per_second": 1546.162, | |
| "eval_spearmanr": 0.5611208690347649, | |
| "eval_steps_per_second": 6.185, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "grad_norm": 7.592547416687012, | |
| "learning_rate": 4.3e-05, | |
| "loss": 0.377, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_combined_score": 0.5338739723007462, | |
| "eval_loss": 1.7542551755905151, | |
| "eval_pearson": 0.5361279903927652, | |
| "eval_runtime": 0.9773, | |
| "eval_samples_per_second": 1534.871, | |
| "eval_spearmanr": 0.5316199542087273, | |
| "eval_steps_per_second": 6.139, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 7.5484232902526855, | |
| "learning_rate": 4.2e-05, | |
| "loss": 0.3223, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_combined_score": 0.5719622639217419, | |
| "eval_loss": 1.6248753070831299, | |
| "eval_pearson": 0.5752071229769086, | |
| "eval_runtime": 0.9811, | |
| "eval_samples_per_second": 1528.848, | |
| "eval_spearmanr": 0.5687174048665751, | |
| "eval_steps_per_second": 6.115, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "grad_norm": 11.02824592590332, | |
| "learning_rate": 4.1e-05, | |
| "loss": 0.2679, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_combined_score": 0.5653106471913698, | |
| "eval_loss": 1.679746150970459, | |
| "eval_pearson": 0.5684789908543003, | |
| "eval_runtime": 0.9683, | |
| "eval_samples_per_second": 1549.087, | |
| "eval_spearmanr": 0.5621423035284394, | |
| "eval_steps_per_second": 6.196, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 5.702976703643799, | |
| "learning_rate": 4e-05, | |
| "loss": 0.2156, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_combined_score": 0.5539869393273291, | |
| "eval_loss": 1.6664037704467773, | |
| "eval_pearson": 0.559161559056532, | |
| "eval_runtime": 0.9742, | |
| "eval_samples_per_second": 1539.752, | |
| "eval_spearmanr": 0.5488123195981262, | |
| "eval_steps_per_second": 6.159, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "grad_norm": 4.3981852531433105, | |
| "learning_rate": 3.9000000000000006e-05, | |
| "loss": 0.1962, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_combined_score": 0.5756187387849405, | |
| "eval_loss": 1.6273460388183594, | |
| "eval_pearson": 0.5784070931166707, | |
| "eval_runtime": 0.9851, | |
| "eval_samples_per_second": 1522.642, | |
| "eval_spearmanr": 0.5728303844532103, | |
| "eval_steps_per_second": 6.091, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "step": 253, | |
| "total_flos": 8319365318060544.0, | |
| "train_loss": 0.8587995838270828, | |
| "train_runtime": 139.3814, | |
| "train_samples_per_second": 2062.327, | |
| "train_steps_per_second": 8.251 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 1150, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 50, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 5 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8319365318060544.0, | |
| "train_batch_size": 256, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |