| { |
| "best_global_step": 92, |
| "best_metric": 2.300028085708618, |
| "best_model_checkpoint": "bert_base_rand_10_v2_stsb/checkpoint-92", |
| "epoch": 9.0, |
| "eval_steps": 500, |
| "global_step": 207, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 3.1556599140167236, |
| "learning_rate": 4.9e-05, |
| "loss": 2.6698, |
| "step": 23 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_combined_score": 0.10479443210144217, |
| "eval_loss": 2.3702478408813477, |
| "eval_pearson": 0.11544894026626165, |
| "eval_runtime": 0.9905, |
| "eval_samples_per_second": 1514.445, |
| "eval_spearmanr": 0.09413992393662268, |
| "eval_steps_per_second": 6.058, |
| "step": 23 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 5.611752033233643, |
| "learning_rate": 4.8e-05, |
| "loss": 1.9073, |
| "step": 46 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_combined_score": 0.16761938741730856, |
| "eval_loss": 2.555327892303467, |
| "eval_pearson": 0.17617707166607635, |
| "eval_runtime": 1.0346, |
| "eval_samples_per_second": 1449.779, |
| "eval_spearmanr": 0.15906170316854076, |
| "eval_steps_per_second": 5.799, |
| "step": 46 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 5.752660274505615, |
| "learning_rate": 4.7e-05, |
| "loss": 1.7118, |
| "step": 69 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_combined_score": 0.18800992971158775, |
| "eval_loss": 2.5235419273376465, |
| "eval_pearson": 0.18295548381708027, |
| "eval_runtime": 0.9548, |
| "eval_samples_per_second": 1571.04, |
| "eval_spearmanr": 0.19306437560609527, |
| "eval_steps_per_second": 6.284, |
| "step": 69 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 7.791083812713623, |
| "learning_rate": 4.600000000000001e-05, |
| "loss": 1.3839, |
| "step": 92 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_combined_score": 0.2714432152820957, |
| "eval_loss": 2.300028085708618, |
| "eval_pearson": 0.27167266143211555, |
| "eval_runtime": 0.9961, |
| "eval_samples_per_second": 1505.928, |
| "eval_spearmanr": 0.27121376913207584, |
| "eval_steps_per_second": 6.024, |
| "step": 92 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 9.9015531539917, |
| "learning_rate": 4.5e-05, |
| "loss": 1.0676, |
| "step": 115 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_combined_score": 0.2322167397561643, |
| "eval_loss": 2.644531488418579, |
| "eval_pearson": 0.23226744942699318, |
| "eval_runtime": 0.9721, |
| "eval_samples_per_second": 1543.007, |
| "eval_spearmanr": 0.23216603008533546, |
| "eval_steps_per_second": 6.172, |
| "step": 115 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 11.220279693603516, |
| "learning_rate": 4.4000000000000006e-05, |
| "loss": 0.8664, |
| "step": 138 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_combined_score": 0.25523625065074984, |
| "eval_loss": 2.731415033340454, |
| "eval_pearson": 0.25216377143919866, |
| "eval_runtime": 0.9824, |
| "eval_samples_per_second": 1526.86, |
| "eval_spearmanr": 0.25830872986230097, |
| "eval_steps_per_second": 6.107, |
| "step": 138 |
| }, |
| { |
| "epoch": 7.0, |
| "grad_norm": 11.725672721862793, |
| "learning_rate": 4.3e-05, |
| "loss": 0.6989, |
| "step": 161 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_combined_score": 0.2738422432920177, |
| "eval_loss": 2.669050693511963, |
| "eval_pearson": 0.2727143819462094, |
| "eval_runtime": 0.9597, |
| "eval_samples_per_second": 1562.996, |
| "eval_spearmanr": 0.27497010463782595, |
| "eval_steps_per_second": 6.252, |
| "step": 161 |
| }, |
| { |
| "epoch": 8.0, |
| "grad_norm": 6.371002674102783, |
| "learning_rate": 4.2e-05, |
| "loss": 0.568, |
| "step": 184 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_combined_score": 0.26579102150617695, |
| "eval_loss": 2.861511707305908, |
| "eval_pearson": 0.2634561345521147, |
| "eval_runtime": 1.005, |
| "eval_samples_per_second": 1492.599, |
| "eval_spearmanr": 0.26812590846023926, |
| "eval_steps_per_second": 5.97, |
| "step": 184 |
| }, |
| { |
| "epoch": 9.0, |
| "grad_norm": 14.52209186553955, |
| "learning_rate": 4.1e-05, |
| "loss": 0.4705, |
| "step": 207 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_combined_score": 0.24701988988733217, |
| "eval_loss": 2.7113146781921387, |
| "eval_pearson": 0.25543142600651153, |
| "eval_runtime": 0.959, |
| "eval_samples_per_second": 1564.172, |
| "eval_spearmanr": 0.23860835376815281, |
| "eval_steps_per_second": 6.257, |
| "step": 207 |
| }, |
| { |
| "epoch": 9.0, |
| "step": 207, |
| "total_flos": 6806753442049536.0, |
| "train_loss": 1.2604616275732068, |
| "train_runtime": 113.3035, |
| "train_samples_per_second": 2536.99, |
| "train_steps_per_second": 10.15 |
| } |
| ], |
| "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": 6806753442049536.0, |
| "train_batch_size": 256, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
