| { | |
| "best_metric": 0.5588609576225281, | |
| "best_model_checkpoint": "/content/drive/MyDrive/Colab Notebooks/models/t5-small-codesearchnet-multilang-python-java-javascript-go/checkpoint-3750", | |
| "epoch": 14.0, | |
| "global_step": 5250, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_avg_length": 16.436, | |
| "eval_bleu": 0.0028, | |
| "eval_loss": 0.7349299192428589, | |
| "eval_rouge1": 0.1562, | |
| "eval_rouge2": 0.0364, | |
| "eval_runtime": 171.828, | |
| "eval_samples_per_second": 29.099, | |
| "eval_steps_per_second": 3.637, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.011613096110522747, | |
| "loss": 2.3117, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_avg_length": 16.824, | |
| "eval_bleu": 0.0066, | |
| "eval_loss": 0.6613165736198425, | |
| "eval_rouge1": 0.1818, | |
| "eval_rouge2": 0.0531, | |
| "eval_runtime": 169.3563, | |
| "eval_samples_per_second": 29.524, | |
| "eval_steps_per_second": 3.69, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 0.023271184414625168, | |
| "loss": 0.6755, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_avg_length": 16.931, | |
| "eval_bleu": 0.007, | |
| "eval_loss": 0.6232756972312927, | |
| "eval_rouge1": 0.1957, | |
| "eval_rouge2": 0.0594, | |
| "eval_runtime": 169.3476, | |
| "eval_samples_per_second": 29.525, | |
| "eval_steps_per_second": 3.691, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 0.03499825298786163, | |
| "loss": 0.5998, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_avg_length": 16.7154, | |
| "eval_bleu": 0.0082, | |
| "eval_loss": 0.6022565364837646, | |
| "eval_rouge1": 0.202, | |
| "eval_rouge2": 0.063, | |
| "eval_runtime": 165.1906, | |
| "eval_samples_per_second": 30.268, | |
| "eval_steps_per_second": 3.784, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_avg_length": 16.5468, | |
| "eval_bleu": 0.0096, | |
| "eval_loss": 0.5925326943397522, | |
| "eval_rouge1": 0.2154, | |
| "eval_rouge2": 0.0703, | |
| "eval_runtime": 162.8367, | |
| "eval_samples_per_second": 30.706, | |
| "eval_steps_per_second": 3.838, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 5.33, | |
| "learning_rate": 0.04682626947760582, | |
| "loss": 0.5511, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_avg_length": 15.7216, | |
| "eval_bleu": 0.0091, | |
| "eval_loss": 0.5728126168251038, | |
| "eval_rouge1": 0.2213, | |
| "eval_rouge2": 0.0774, | |
| "eval_runtime": 160.1137, | |
| "eval_samples_per_second": 31.228, | |
| "eval_steps_per_second": 3.903, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 0.05879075452685356, | |
| "loss": 0.5147, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_avg_length": 16.6658, | |
| "eval_bleu": 0.0111, | |
| "eval_loss": 0.5669918060302734, | |
| "eval_rouge1": 0.2311, | |
| "eval_rouge2": 0.0815, | |
| "eval_runtime": 160.5038, | |
| "eval_samples_per_second": 31.152, | |
| "eval_steps_per_second": 3.894, | |
| "step": 2625 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 0.07094069570302963, | |
| "loss": 0.4861, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_avg_length": 17.038, | |
| "eval_bleu": 0.0089, | |
| "eval_loss": 0.5627844929695129, | |
| "eval_rouge1": 0.2217, | |
| "eval_rouge2": 0.077, | |
| "eval_runtime": 160.3931, | |
| "eval_samples_per_second": 31.173, | |
| "eval_steps_per_second": 3.897, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_avg_length": 16.362, | |
| "eval_bleu": 0.0103, | |
| "eval_loss": 0.5597769618034363, | |
| "eval_rouge1": 0.2311, | |
| "eval_rouge2": 0.0825, | |
| "eval_runtime": 159.243, | |
| "eval_samples_per_second": 31.399, | |
| "eval_steps_per_second": 3.925, | |
| "step": 3375 | |
| }, | |
| { | |
| "epoch": 9.33, | |
| "learning_rate": 0.08328617364168167, | |
| "loss": 0.4526, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_avg_length": 15.4298, | |
| "eval_bleu": 0.0083, | |
| "eval_loss": 0.5588609576225281, | |
| "eval_rouge1": 0.232, | |
| "eval_rouge2": 0.086, | |
| "eval_runtime": 160.7722, | |
| "eval_samples_per_second": 31.1, | |
| "eval_steps_per_second": 3.887, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 10.67, | |
| "learning_rate": 0.09589392691850662, | |
| "loss": 0.4329, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_avg_length": 16.5468, | |
| "eval_bleu": 0.0098, | |
| "eval_loss": 0.5649139285087585, | |
| "eval_rouge1": 0.2349, | |
| "eval_rouge2": 0.0839, | |
| "eval_runtime": 168.9129, | |
| "eval_samples_per_second": 29.601, | |
| "eval_steps_per_second": 3.7, | |
| "step": 4125 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 0.10882016271352768, | |
| "loss": 0.4102, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_avg_length": 16.4136, | |
| "eval_bleu": 0.0098, | |
| "eval_loss": 0.5633437633514404, | |
| "eval_rouge1": 0.2366, | |
| "eval_rouge2": 0.0867, | |
| "eval_runtime": 166.1994, | |
| "eval_samples_per_second": 30.084, | |
| "eval_steps_per_second": 3.761, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_avg_length": 15.9864, | |
| "eval_bleu": 0.01, | |
| "eval_loss": 0.5841416120529175, | |
| "eval_rouge1": 0.2385, | |
| "eval_rouge2": 0.0869, | |
| "eval_runtime": 162.6882, | |
| "eval_samples_per_second": 30.734, | |
| "eval_steps_per_second": 3.842, | |
| "step": 4875 | |
| }, | |
| { | |
| "epoch": 13.33, | |
| "learning_rate": 0.12202449887990952, | |
| "loss": 0.3841, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_avg_length": 16.842, | |
| "eval_bleu": 0.0128, | |
| "eval_loss": 0.5776922106742859, | |
| "eval_rouge1": 0.2437, | |
| "eval_rouge2": 0.0894, | |
| "eval_runtime": 165.8581, | |
| "eval_samples_per_second": 30.146, | |
| "eval_steps_per_second": 3.768, | |
| "step": 5250 | |
| } | |
| ], | |
| "max_steps": 5625, | |
| "num_train_epochs": 15, | |
| "total_flos": 2.842177830912e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |