| { | |
| "best_metric": 1.6650625467300415, | |
| "best_model_checkpoint": "bert_base_lda_20_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": 9.738332748413086, | |
| "learning_rate": 4.9e-05, | |
| "loss": 2.9133, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_combined_score": 0.0876826822817508, | |
| "eval_loss": 2.431685209274292, | |
| "eval_pearson": 0.07911668732334376, | |
| "eval_runtime": 0.9718, | |
| "eval_samples_per_second": 1543.503, | |
| "eval_spearmanr": 0.09624867724015784, | |
| "eval_steps_per_second": 6.174, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 7.058999061584473, | |
| "learning_rate": 4.8e-05, | |
| "loss": 1.7921, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_combined_score": 0.4556578456594328, | |
| "eval_loss": 2.1686253547668457, | |
| "eval_pearson": 0.4521331798111072, | |
| "eval_runtime": 0.9704, | |
| "eval_samples_per_second": 1545.826, | |
| "eval_spearmanr": 0.45918251150775835, | |
| "eval_steps_per_second": 6.183, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 10.802772521972656, | |
| "learning_rate": 4.7e-05, | |
| "loss": 1.4021, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_combined_score": 0.4786612048961132, | |
| "eval_loss": 1.9878859519958496, | |
| "eval_pearson": 0.47632579208141346, | |
| "eval_runtime": 0.9615, | |
| "eval_samples_per_second": 1560.037, | |
| "eval_spearmanr": 0.4809966177108129, | |
| "eval_steps_per_second": 6.24, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 12.505186080932617, | |
| "learning_rate": 4.600000000000001e-05, | |
| "loss": 1.0503, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_combined_score": 0.49639717241844983, | |
| "eval_loss": 1.933651328086853, | |
| "eval_pearson": 0.49418117132384864, | |
| "eval_runtime": 0.9692, | |
| "eval_samples_per_second": 1547.742, | |
| "eval_spearmanr": 0.49861317351305107, | |
| "eval_steps_per_second": 6.191, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 22.745203018188477, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.8246, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_combined_score": 0.5342338035217759, | |
| "eval_loss": 1.713676929473877, | |
| "eval_pearson": 0.5359622180256605, | |
| "eval_runtime": 0.957, | |
| "eval_samples_per_second": 1567.479, | |
| "eval_spearmanr": 0.5325053890178912, | |
| "eval_steps_per_second": 6.27, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 8.874309539794922, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 0.6757, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_combined_score": 0.5438926115492484, | |
| "eval_loss": 1.6650625467300415, | |
| "eval_pearson": 0.5450617299778879, | |
| "eval_runtime": 0.9929, | |
| "eval_samples_per_second": 1510.787, | |
| "eval_spearmanr": 0.542723493120609, | |
| "eval_steps_per_second": 6.043, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "grad_norm": 7.297491550445557, | |
| "learning_rate": 4.3e-05, | |
| "loss": 0.5303, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_combined_score": 0.5421078551362122, | |
| "eval_loss": 1.7656605243682861, | |
| "eval_pearson": 0.5455585471094383, | |
| "eval_runtime": 0.9748, | |
| "eval_samples_per_second": 1538.833, | |
| "eval_spearmanr": 0.5386571631629862, | |
| "eval_steps_per_second": 6.155, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 10.889992713928223, | |
| "learning_rate": 4.2e-05, | |
| "loss": 0.4539, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_combined_score": 0.5493515644466885, | |
| "eval_loss": 1.9937711954116821, | |
| "eval_pearson": 0.548189645149559, | |
| "eval_runtime": 1.0094, | |
| "eval_samples_per_second": 1486.068, | |
| "eval_spearmanr": 0.550513483743818, | |
| "eval_steps_per_second": 5.944, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "grad_norm": 5.418324947357178, | |
| "learning_rate": 4.1e-05, | |
| "loss": 0.399, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_combined_score": 0.5356497995592364, | |
| "eval_loss": 1.7298147678375244, | |
| "eval_pearson": 0.5401914274028985, | |
| "eval_runtime": 0.9724, | |
| "eval_samples_per_second": 1542.516, | |
| "eval_spearmanr": 0.5311081717155742, | |
| "eval_steps_per_second": 6.17, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 12.156574249267578, | |
| "learning_rate": 4e-05, | |
| "loss": 0.3663, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_combined_score": 0.5606574879091346, | |
| "eval_loss": 1.8046331405639648, | |
| "eval_pearson": 0.5614070412566732, | |
| "eval_runtime": 0.9685, | |
| "eval_samples_per_second": 1548.827, | |
| "eval_spearmanr": 0.5599079345615962, | |
| "eval_steps_per_second": 6.195, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "grad_norm": 5.27700662612915, | |
| "learning_rate": 3.9000000000000006e-05, | |
| "loss": 0.2964, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_combined_score": 0.5435187902847016, | |
| "eval_loss": 1.7390520572662354, | |
| "eval_pearson": 0.5469683812366085, | |
| "eval_runtime": 0.968, | |
| "eval_samples_per_second": 1549.517, | |
| "eval_spearmanr": 0.5400691993327947, | |
| "eval_steps_per_second": 6.198, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "step": 253, | |
| "total_flos": 8319365318060544.0, | |
| "train_loss": 0.973101574441661, | |
| "train_runtime": 142.7213, | |
| "train_samples_per_second": 2014.066, | |
| "train_steps_per_second": 8.058 | |
| } | |
| ], | |
| "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 | |
| } | |