| { | |
| "best_metric": 0.7449400424957275, | |
| "best_model_checkpoint": "/content/drive/MyDrive/Colab Notebooks/models/t5-small-codesearchnet-python/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": 14.1472, | |
| "eval_bleu": 0.0004, | |
| "eval_loss": 0.966545581817627, | |
| "eval_rouge1": 0.1696, | |
| "eval_rouge2": 0.0384, | |
| "eval_runtime": 148.9068, | |
| "eval_samples_per_second": 33.578, | |
| "eval_steps_per_second": 4.197, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.011612925678491592, | |
| "loss": 2.0677, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_avg_length": 13.38, | |
| "eval_bleu": 0.0004, | |
| "eval_loss": 0.8739555478096008, | |
| "eval_rouge1": 0.1758, | |
| "eval_rouge2": 0.0428, | |
| "eval_runtime": 148.3073, | |
| "eval_samples_per_second": 33.714, | |
| "eval_steps_per_second": 4.214, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 0.02327043004333973, | |
| "loss": 0.8314, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_avg_length": 14.8026, | |
| "eval_bleu": 0.001, | |
| "eval_loss": 0.8281144499778748, | |
| "eval_rouge1": 0.1925, | |
| "eval_rouge2": 0.0505, | |
| "eval_runtime": 149.134, | |
| "eval_samples_per_second": 33.527, | |
| "eval_steps_per_second": 4.191, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 0.03499961644411087, | |
| "loss": 0.7563, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_avg_length": 14.9606, | |
| "eval_bleu": 0.0017, | |
| "eval_loss": 0.7996220588684082, | |
| "eval_rouge1": 0.2033, | |
| "eval_rouge2": 0.0582, | |
| "eval_runtime": 150.6141, | |
| "eval_samples_per_second": 33.197, | |
| "eval_steps_per_second": 4.15, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_avg_length": 14.9434, | |
| "eval_bleu": 0.0022, | |
| "eval_loss": 0.7780128121376038, | |
| "eval_rouge1": 0.2117, | |
| "eval_rouge2": 0.0607, | |
| "eval_runtime": 150.0628, | |
| "eval_samples_per_second": 33.319, | |
| "eval_steps_per_second": 4.165, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 5.33, | |
| "learning_rate": 0.04683296009898186, | |
| "loss": 0.6959, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_avg_length": 14.6926, | |
| "eval_bleu": 0.002, | |
| "eval_loss": 0.7587344646453857, | |
| "eval_rouge1": 0.2135, | |
| "eval_rouge2": 0.0621, | |
| "eval_runtime": 149.6348, | |
| "eval_samples_per_second": 33.415, | |
| "eval_steps_per_second": 4.177, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 0.058812398463487625, | |
| "loss": 0.6591, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_avg_length": 15.2818, | |
| "eval_bleu": 0.002, | |
| "eval_loss": 0.7544705271720886, | |
| "eval_rouge1": 0.2073, | |
| "eval_rouge2": 0.0605, | |
| "eval_runtime": 150.3492, | |
| "eval_samples_per_second": 33.256, | |
| "eval_steps_per_second": 4.157, | |
| "step": 2625 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 0.07098705321550369, | |
| "loss": 0.6205, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_avg_length": 15.051, | |
| "eval_bleu": 0.0024, | |
| "eval_loss": 0.7471866011619568, | |
| "eval_rouge1": 0.2187, | |
| "eval_rouge2": 0.0674, | |
| "eval_runtime": 150.0125, | |
| "eval_samples_per_second": 33.331, | |
| "eval_steps_per_second": 4.166, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_avg_length": 15.6286, | |
| "eval_bleu": 0.0031, | |
| "eval_loss": 0.7505583763122559, | |
| "eval_rouge1": 0.2266, | |
| "eval_rouge2": 0.0696, | |
| "eval_runtime": 151.1802, | |
| "eval_samples_per_second": 33.073, | |
| "eval_steps_per_second": 4.134, | |
| "step": 3375 | |
| }, | |
| { | |
| "epoch": 9.33, | |
| "learning_rate": 0.08336292207241058, | |
| "loss": 0.5822, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_avg_length": 13.1462, | |
| "eval_bleu": 0.001, | |
| "eval_loss": 0.7449400424957275, | |
| "eval_rouge1": 0.206, | |
| "eval_rouge2": 0.063, | |
| "eval_runtime": 149.4965, | |
| "eval_samples_per_second": 33.446, | |
| "eval_steps_per_second": 4.181, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 10.67, | |
| "learning_rate": 0.09602057933807373, | |
| "loss": 0.5553, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_avg_length": 16.4076, | |
| "eval_bleu": 0.0027, | |
| "eval_loss": 0.7572856545448303, | |
| "eval_rouge1": 0.2148, | |
| "eval_rouge2": 0.0647, | |
| "eval_runtime": 151.0658, | |
| "eval_samples_per_second": 33.098, | |
| "eval_steps_per_second": 4.137, | |
| "step": 4125 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 0.10902385413646698, | |
| "loss": 0.5295, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_avg_length": 15.8986, | |
| "eval_bleu": 0.0026, | |
| "eval_loss": 0.7677233219146729, | |
| "eval_rouge1": 0.2185, | |
| "eval_rouge2": 0.0658, | |
| "eval_runtime": 150.5334, | |
| "eval_samples_per_second": 33.215, | |
| "eval_steps_per_second": 4.152, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_avg_length": 12.3528, | |
| "eval_bleu": 0.0009, | |
| "eval_loss": 0.759487509727478, | |
| "eval_rouge1": 0.2052, | |
| "eval_rouge2": 0.0618, | |
| "eval_runtime": 147.275, | |
| "eval_samples_per_second": 33.95, | |
| "eval_steps_per_second": 4.244, | |
| "step": 4875 | |
| }, | |
| { | |
| "epoch": 13.33, | |
| "learning_rate": 0.12233853340148926, | |
| "loss": 0.4977, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_avg_length": 16.6706, | |
| "eval_bleu": 0.0035, | |
| "eval_loss": 0.7765543460845947, | |
| "eval_rouge1": 0.2177, | |
| "eval_rouge2": 0.0636, | |
| "eval_runtime": 151.0761, | |
| "eval_samples_per_second": 33.096, | |
| "eval_steps_per_second": 4.137, | |
| "step": 5250 | |
| } | |
| ], | |
| "max_steps": 5625, | |
| "num_train_epochs": 15, | |
| "total_flos": 2.842177830912e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |