| { |
| "best_metric": 0.05212199687957764, |
| "best_model_checkpoint": "/content/drive/MyDrive/Colab Notebooks/models/t5-small-codesearchnet-multilang-python/checkpoint-2625", |
| "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": 17.046, |
| "eval_bleu": 0.0407, |
| "eval_loss": 0.07167458534240723, |
| "eval_rouge1": 0.6244, |
| "eval_rouge2": 0.6063, |
| "eval_runtime": 146.8983, |
| "eval_samples_per_second": 34.037, |
| "eval_steps_per_second": 4.255, |
| "step": 375 |
| }, |
| { |
| "epoch": 1.33, |
| "learning_rate": 0.011602410115301609, |
| "loss": 1.6287, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_avg_length": 16.9924, |
| "eval_bleu": 0.041, |
| "eval_loss": 0.05889422446489334, |
| "eval_rouge1": 0.6321, |
| "eval_rouge2": 0.6136, |
| "eval_runtime": 145.8711, |
| "eval_samples_per_second": 34.277, |
| "eval_steps_per_second": 4.285, |
| "step": 750 |
| }, |
| { |
| "epoch": 2.67, |
| "learning_rate": 0.023224830627441406, |
| "loss": 0.0592, |
| "step": 1000 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_avg_length": 16.971, |
| "eval_bleu": 0.0402, |
| "eval_loss": 0.0550708994269371, |
| "eval_rouge1": 0.6334, |
| "eval_rouge2": 0.6152, |
| "eval_runtime": 143.6698, |
| "eval_samples_per_second": 34.802, |
| "eval_steps_per_second": 4.35, |
| "step": 1125 |
| }, |
| { |
| "epoch": 4.0, |
| "learning_rate": 0.03487464413046837, |
| "loss": 0.0511, |
| "step": 1500 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_avg_length": 16.9718, |
| "eval_bleu": 0.0402, |
| "eval_loss": 0.054238129407167435, |
| "eval_rouge1": 0.6336, |
| "eval_rouge2": 0.6155, |
| "eval_runtime": 144.3554, |
| "eval_samples_per_second": 34.637, |
| "eval_steps_per_second": 4.33, |
| "step": 1500 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_avg_length": 16.961, |
| "eval_bleu": 0.0401, |
| "eval_loss": 0.05285137891769409, |
| "eval_rouge1": 0.6343, |
| "eval_rouge2": 0.6161, |
| "eval_runtime": 144.2239, |
| "eval_samples_per_second": 34.668, |
| "eval_steps_per_second": 4.334, |
| "step": 1875 |
| }, |
| { |
| "epoch": 5.33, |
| "learning_rate": 0.046562861651182175, |
| "loss": 0.0441, |
| "step": 2000 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_avg_length": 16.9626, |
| "eval_bleu": 0.0402, |
| "eval_loss": 0.05305228382349014, |
| "eval_rouge1": 0.6341, |
| "eval_rouge2": 0.6158, |
| "eval_runtime": 144.1713, |
| "eval_samples_per_second": 34.681, |
| "eval_steps_per_second": 4.335, |
| "step": 2250 |
| }, |
| { |
| "epoch": 6.67, |
| "learning_rate": 0.058299630880355835, |
| "loss": 0.0399, |
| "step": 2500 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_avg_length": 16.97, |
| "eval_bleu": 0.0402, |
| "eval_loss": 0.05212199687957764, |
| "eval_rouge1": 0.6337, |
| "eval_rouge2": 0.6154, |
| "eval_runtime": 143.8202, |
| "eval_samples_per_second": 34.766, |
| "eval_steps_per_second": 4.346, |
| "step": 2625 |
| }, |
| { |
| "epoch": 8.0, |
| "learning_rate": 0.07010027766227722, |
| "loss": 0.0351, |
| "step": 3000 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_avg_length": 16.964, |
| "eval_bleu": 0.0401, |
| "eval_loss": 0.05471711605787277, |
| "eval_rouge1": 0.6341, |
| "eval_rouge2": 0.6159, |
| "eval_runtime": 144.436, |
| "eval_samples_per_second": 34.617, |
| "eval_steps_per_second": 4.327, |
| "step": 3000 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_avg_length": 16.962, |
| "eval_bleu": 0.0402, |
| "eval_loss": 0.054534584283828735, |
| "eval_rouge1": 0.635, |
| "eval_rouge2": 0.6167, |
| "eval_runtime": 143.3352, |
| "eval_samples_per_second": 34.883, |
| "eval_steps_per_second": 4.36, |
| "step": 3375 |
| }, |
| { |
| "epoch": 9.33, |
| "learning_rate": 0.08195903152227402, |
| "loss": 0.0301, |
| "step": 3500 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_avg_length": 16.9646, |
| "eval_bleu": 0.0402, |
| "eval_loss": 0.05570118501782417, |
| "eval_rouge1": 0.6342, |
| "eval_rouge2": 0.6159, |
| "eval_runtime": 143.514, |
| "eval_samples_per_second": 34.84, |
| "eval_steps_per_second": 4.355, |
| "step": 3750 |
| }, |
| { |
| "epoch": 10.67, |
| "learning_rate": 0.09392501413822174, |
| "loss": 0.027, |
| "step": 4000 |
| }, |
| { |
| "epoch": 11.0, |
| "eval_avg_length": 16.9622, |
| "eval_bleu": 0.0402, |
| "eval_loss": 0.05687524378299713, |
| "eval_rouge1": 0.6342, |
| "eval_rouge2": 0.6157, |
| "eval_runtime": 144.0849, |
| "eval_samples_per_second": 34.702, |
| "eval_steps_per_second": 4.338, |
| "step": 4125 |
| }, |
| { |
| "epoch": 12.0, |
| "learning_rate": 0.10599534213542938, |
| "loss": 0.0239, |
| "step": 4500 |
| }, |
| { |
| "epoch": 12.0, |
| "eval_avg_length": 16.9564, |
| "eval_bleu": 0.0401, |
| "eval_loss": 0.060644153505563736, |
| "eval_rouge1": 0.6342, |
| "eval_rouge2": 0.6158, |
| "eval_runtime": 143.5445, |
| "eval_samples_per_second": 34.832, |
| "eval_steps_per_second": 4.354, |
| "step": 4500 |
| }, |
| { |
| "epoch": 13.0, |
| "eval_avg_length": 16.963, |
| "eval_bleu": 0.0401, |
| "eval_loss": 0.06158696860074997, |
| "eval_rouge1": 0.6343, |
| "eval_rouge2": 0.6163, |
| "eval_runtime": 144.0161, |
| "eval_samples_per_second": 34.718, |
| "eval_steps_per_second": 4.34, |
| "step": 4875 |
| } |
| ], |
| "max_steps": 5625, |
| "num_train_epochs": 15, |
| "total_flos": 2.639165128704e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
