| { | |
| "best_metric": 1.6844276189804077, | |
| "best_model_checkpoint": "bert_base_lda_100_v1_stsb/checkpoint-184", | |
| "epoch": 13.0, | |
| "eval_steps": 500, | |
| "global_step": 299, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 9.02434253692627, | |
| "learning_rate": 4.9e-05, | |
| "loss": 2.7331, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_combined_score": 0.07012747710946046, | |
| "eval_loss": 2.6188812255859375, | |
| "eval_pearson": 0.0642887160182263, | |
| "eval_runtime": 0.9624, | |
| "eval_samples_per_second": 1558.649, | |
| "eval_spearmanr": 0.0759662382006946, | |
| "eval_steps_per_second": 6.235, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 23.63865852355957, | |
| "learning_rate": 4.8e-05, | |
| "loss": 1.9804, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_combined_score": 0.27527671204636106, | |
| "eval_loss": 2.0897152423858643, | |
| "eval_pearson": 0.28175468669023457, | |
| "eval_runtime": 0.9642, | |
| "eval_samples_per_second": 1555.678, | |
| "eval_spearmanr": 0.2687987374024875, | |
| "eval_steps_per_second": 6.223, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 10.638742446899414, | |
| "learning_rate": 4.7e-05, | |
| "loss": 1.7486, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_combined_score": 0.41554924979667834, | |
| "eval_loss": 1.9471008777618408, | |
| "eval_pearson": 0.41582453640686257, | |
| "eval_runtime": 0.9708, | |
| "eval_samples_per_second": 1545.093, | |
| "eval_spearmanr": 0.4152739631864941, | |
| "eval_steps_per_second": 6.18, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 16.40125846862793, | |
| "learning_rate": 4.600000000000001e-05, | |
| "loss": 1.2963, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_combined_score": 0.4597302763812634, | |
| "eval_loss": 2.3058416843414307, | |
| "eval_pearson": 0.4520132571391213, | |
| "eval_runtime": 0.993, | |
| "eval_samples_per_second": 1510.585, | |
| "eval_spearmanr": 0.4674472956234055, | |
| "eval_steps_per_second": 6.042, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 42.770668029785156, | |
| "learning_rate": 4.5e-05, | |
| "loss": 1.0162, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_combined_score": 0.48877111938435025, | |
| "eval_loss": 1.8441771268844604, | |
| "eval_pearson": 0.4886953649858171, | |
| "eval_runtime": 0.974, | |
| "eval_samples_per_second": 1540.11, | |
| "eval_spearmanr": 0.48884687378288344, | |
| "eval_steps_per_second": 6.16, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 22.240951538085938, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 0.8446, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_combined_score": 0.5259105826273307, | |
| "eval_loss": 1.7663521766662598, | |
| "eval_pearson": 0.5228342603176177, | |
| "eval_runtime": 0.9691, | |
| "eval_samples_per_second": 1547.89, | |
| "eval_spearmanr": 0.5289869049370436, | |
| "eval_steps_per_second": 6.192, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "grad_norm": 9.541956901550293, | |
| "learning_rate": 4.3e-05, | |
| "loss": 0.6767, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_combined_score": 0.5168115431891785, | |
| "eval_loss": 1.7573641538619995, | |
| "eval_pearson": 0.5151591812766733, | |
| "eval_runtime": 0.9781, | |
| "eval_samples_per_second": 1533.662, | |
| "eval_spearmanr": 0.5184639051016838, | |
| "eval_steps_per_second": 6.135, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 18.553218841552734, | |
| "learning_rate": 4.2e-05, | |
| "loss": 0.5349, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_combined_score": 0.5327909501566208, | |
| "eval_loss": 1.6844276189804077, | |
| "eval_pearson": 0.5330379395182387, | |
| "eval_runtime": 0.967, | |
| "eval_samples_per_second": 1551.234, | |
| "eval_spearmanr": 0.5325439607950028, | |
| "eval_steps_per_second": 6.205, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "grad_norm": 8.788359642028809, | |
| "learning_rate": 4.1e-05, | |
| "loss": 0.4606, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_combined_score": 0.5061528931646921, | |
| "eval_loss": 1.9861546754837036, | |
| "eval_pearson": 0.503941115665909, | |
| "eval_runtime": 0.9662, | |
| "eval_samples_per_second": 1552.405, | |
| "eval_spearmanr": 0.5083646706634753, | |
| "eval_steps_per_second": 6.21, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 9.931353569030762, | |
| "learning_rate": 4e-05, | |
| "loss": 0.3951, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_combined_score": 0.5270205929961109, | |
| "eval_loss": 1.8024095296859741, | |
| "eval_pearson": 0.5265505998740807, | |
| "eval_runtime": 0.9616, | |
| "eval_samples_per_second": 1559.852, | |
| "eval_spearmanr": 0.527490586118141, | |
| "eval_steps_per_second": 6.239, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "grad_norm": 21.041873931884766, | |
| "learning_rate": 3.9000000000000006e-05, | |
| "loss": 0.3624, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_combined_score": 0.5382256315731109, | |
| "eval_loss": 2.015653371810913, | |
| "eval_pearson": 0.5341689579826407, | |
| "eval_runtime": 0.9659, | |
| "eval_samples_per_second": 1552.881, | |
| "eval_spearmanr": 0.5422823051635811, | |
| "eval_steps_per_second": 6.212, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "grad_norm": 19.475910186767578, | |
| "learning_rate": 3.8e-05, | |
| "loss": 0.3087, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_combined_score": 0.5305901722528907, | |
| "eval_loss": 2.409419059753418, | |
| "eval_pearson": 0.5226677549863216, | |
| "eval_runtime": 0.9641, | |
| "eval_samples_per_second": 1555.776, | |
| "eval_spearmanr": 0.5385125895194598, | |
| "eval_steps_per_second": 6.223, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "grad_norm": 15.23548412322998, | |
| "learning_rate": 3.7e-05, | |
| "loss": 0.2879, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_combined_score": 0.5327170657272342, | |
| "eval_loss": 2.0560126304626465, | |
| "eval_pearson": 0.5303940978069547, | |
| "eval_runtime": 0.966, | |
| "eval_samples_per_second": 1552.868, | |
| "eval_spearmanr": 0.5350400336475136, | |
| "eval_steps_per_second": 6.211, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "step": 299, | |
| "total_flos": 9831977194071552.0, | |
| "train_loss": 0.9727236291636592, | |
| "train_runtime": 168.3036, | |
| "train_samples_per_second": 1707.925, | |
| "train_steps_per_second": 6.833 | |
| } | |
| ], | |
| "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": 9831977194071552.0, | |
| "train_batch_size": 256, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |