| { | |
| "best_metric": 0.05236489325761795, | |
| "best_model_checkpoint": "/content/drive/MyDrive/Colab Notebooks/models/google/flan-t5-small-codesearchnet-python/checkpoint-1500", | |
| "epoch": 13.0, | |
| "global_step": 4875, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_avg_length": 17.029, | |
| "eval_bleu": 0.0364, | |
| "eval_loss": 0.06356053799390793, | |
| "eval_rouge1": 0.6253, | |
| "eval_rouge2": 0.6076, | |
| "eval_runtime": 194.621, | |
| "eval_samples_per_second": 25.691, | |
| "eval_steps_per_second": 3.211, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.006761715281754732, | |
| "loss": 5.5166, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_avg_length": 16.9996, | |
| "eval_bleu": 0.0351, | |
| "eval_loss": 0.05532339960336685, | |
| "eval_rouge1": 0.6259, | |
| "eval_rouge2": 0.6081, | |
| "eval_runtime": 191.1842, | |
| "eval_samples_per_second": 26.153, | |
| "eval_steps_per_second": 3.269, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 0.013524587266147137, | |
| "loss": 0.0485, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_avg_length": 16.99, | |
| "eval_bleu": 0.0351, | |
| "eval_loss": 0.05369499325752258, | |
| "eval_rouge1": 0.6258, | |
| "eval_rouge2": 0.6083, | |
| "eval_runtime": 189.3124, | |
| "eval_samples_per_second": 26.411, | |
| "eval_steps_per_second": 3.301, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 0.02029060572385788, | |
| "loss": 0.0409, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_avg_length": 16.9942, | |
| "eval_bleu": 0.0351, | |
| "eval_loss": 0.05236489325761795, | |
| "eval_rouge1": 0.6258, | |
| "eval_rouge2": 0.6082, | |
| "eval_runtime": 189.5235, | |
| "eval_samples_per_second": 26.382, | |
| "eval_steps_per_second": 3.298, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_avg_length": 16.997, | |
| "eval_bleu": 0.0351, | |
| "eval_loss": 0.052440039813518524, | |
| "eval_rouge1": 0.6261, | |
| "eval_rouge2": 0.6086, | |
| "eval_runtime": 188.8356, | |
| "eval_samples_per_second": 26.478, | |
| "eval_steps_per_second": 3.31, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 5.33, | |
| "learning_rate": 0.027062522247433662, | |
| "loss": 0.0345, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_avg_length": 16.9936, | |
| "eval_bleu": 0.0351, | |
| "eval_loss": 0.052636753767728806, | |
| "eval_rouge1": 0.6258, | |
| "eval_rouge2": 0.6081, | |
| "eval_runtime": 188.807, | |
| "eval_samples_per_second": 26.482, | |
| "eval_steps_per_second": 3.31, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 0.03384636715054512, | |
| "loss": 0.0303, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_avg_length": 16.991, | |
| "eval_bleu": 0.035, | |
| "eval_loss": 0.0532960519194603, | |
| "eval_rouge1": 0.6254, | |
| "eval_rouge2": 0.6076, | |
| "eval_runtime": 195.9042, | |
| "eval_samples_per_second": 25.523, | |
| "eval_steps_per_second": 3.19, | |
| "step": 2625 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 0.04064999520778656, | |
| "loss": 0.0256, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_avg_length": 16.9964, | |
| "eval_bleu": 0.035, | |
| "eval_loss": 0.05655151233077049, | |
| "eval_rouge1": 0.6257, | |
| "eval_rouge2": 0.6074, | |
| "eval_runtime": 193.7837, | |
| "eval_samples_per_second": 25.802, | |
| "eval_steps_per_second": 3.225, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_avg_length": 16.998, | |
| "eval_bleu": 0.0349, | |
| "eval_loss": 0.05918492376804352, | |
| "eval_rouge1": 0.6253, | |
| "eval_rouge2": 0.6074, | |
| "eval_runtime": 190.3532, | |
| "eval_samples_per_second": 26.267, | |
| "eval_steps_per_second": 3.283, | |
| "step": 3375 | |
| }, | |
| { | |
| "epoch": 9.33, | |
| "learning_rate": 0.047494322061538696, | |
| "loss": 0.0205, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_avg_length": 16.9932, | |
| "eval_bleu": 0.0351, | |
| "eval_loss": 0.06117509678006172, | |
| "eval_rouge1": 0.6255, | |
| "eval_rouge2": 0.6073, | |
| "eval_runtime": 197.2772, | |
| "eval_samples_per_second": 25.345, | |
| "eval_steps_per_second": 3.168, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 10.67, | |
| "learning_rate": 0.054379865527153015, | |
| "loss": 0.0185, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_avg_length": 16.996, | |
| "eval_bleu": 0.035, | |
| "eval_loss": 0.06389027088880539, | |
| "eval_rouge1": 0.6257, | |
| "eval_rouge2": 0.6079, | |
| "eval_runtime": 194.6757, | |
| "eval_samples_per_second": 25.684, | |
| "eval_steps_per_second": 3.21, | |
| "step": 4125 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 0.0613127239048481, | |
| "loss": 0.0157, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_avg_length": 16.9944, | |
| "eval_bleu": 0.035, | |
| "eval_loss": 0.06984004378318787, | |
| "eval_rouge1": 0.625, | |
| "eval_rouge2": 0.6064, | |
| "eval_runtime": 196.3811, | |
| "eval_samples_per_second": 25.461, | |
| "eval_steps_per_second": 3.183, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_avg_length": 16.991, | |
| "eval_bleu": 0.035, | |
| "eval_loss": 0.07201451808214188, | |
| "eval_rouge1": 0.6246, | |
| "eval_rouge2": 0.6062, | |
| "eval_runtime": 192.0847, | |
| "eval_samples_per_second": 26.03, | |
| "eval_steps_per_second": 3.254, | |
| "step": 4875 | |
| } | |
| ], | |
| "max_steps": 5625, | |
| "num_train_epochs": 15, | |
| "total_flos": 3.624864841728e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |