| { | |
| "best_metric": 1.4045040607452393, | |
| "best_model_checkpoint": "/content/drive/MyDrive/Graduation_Models/Summary_Model/peftmodel/output/checkpoint-9210", | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 9210, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.728555917480999e-05, | |
| "loss": 1.5128, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.457111834961998e-05, | |
| "loss": 1.4734, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 4.185667752442997e-05, | |
| "loss": 1.4822, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_gen_len": 17.18192918192918, | |
| "eval_loss": 1.412906527519226, | |
| "eval_rouge1": 46.4948, | |
| "eval_rouge2": 22.3122, | |
| "eval_rougeL": 38.6849, | |
| "eval_rougeLsum": 42.8536, | |
| "eval_runtime": 136.9551, | |
| "eval_samples_per_second": 5.98, | |
| "eval_steps_per_second": 0.752, | |
| "step": 1842 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 3.914223669923996e-05, | |
| "loss": 1.4543, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 3.642779587404995e-05, | |
| "loss": 1.4473, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 3.3713355048859935e-05, | |
| "loss": 1.4735, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 3.099891422366993e-05, | |
| "loss": 1.4562, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_gen_len": 17.29059829059829, | |
| "eval_loss": 1.4075654745101929, | |
| "eval_rouge1": 46.4026, | |
| "eval_rouge2": 22.2865, | |
| "eval_rougeL": 38.4756, | |
| "eval_rougeLsum": 42.5601, | |
| "eval_runtime": 130.4435, | |
| "eval_samples_per_second": 6.279, | |
| "eval_steps_per_second": 0.79, | |
| "step": 3684 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 2.8284473398479917e-05, | |
| "loss": 1.4496, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 2.5570032573289905e-05, | |
| "loss": 1.4404, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 2.2855591748099893e-05, | |
| "loss": 1.4567, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 2.0141150922909884e-05, | |
| "loss": 1.4513, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_gen_len": 17.056166056166056, | |
| "eval_loss": 1.4049729108810425, | |
| "eval_rouge1": 46.7241, | |
| "eval_rouge2": 22.6258, | |
| "eval_rougeL": 38.9944, | |
| "eval_rougeLsum": 42.8509, | |
| "eval_runtime": 127.7298, | |
| "eval_samples_per_second": 6.412, | |
| "eval_steps_per_second": 0.806, | |
| "step": 5526 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 1.742671009771987e-05, | |
| "loss": 1.4434, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 1.471226927252986e-05, | |
| "loss": 1.4436, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 1.1997828447339848e-05, | |
| "loss": 1.4416, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_gen_len": 17.194139194139193, | |
| "eval_loss": 1.4050428867340088, | |
| "eval_rouge1": 46.5545, | |
| "eval_rouge2": 22.5187, | |
| "eval_rougeL": 38.8127, | |
| "eval_rougeLsum": 42.7317, | |
| "eval_runtime": 127.6425, | |
| "eval_samples_per_second": 6.416, | |
| "eval_steps_per_second": 0.807, | |
| "step": 7368 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 9.283387622149838e-06, | |
| "loss": 1.4425, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 4.34, | |
| "learning_rate": 6.568946796959827e-06, | |
| "loss": 1.44, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 4.61, | |
| "learning_rate": 3.854505971769816e-06, | |
| "loss": 1.4523, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 1.1400651465798045e-06, | |
| "loss": 1.4356, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_gen_len": 17.158730158730158, | |
| "eval_loss": 1.4045040607452393, | |
| "eval_rouge1": 46.5502, | |
| "eval_rouge2": 22.5448, | |
| "eval_rougeL": 38.7975, | |
| "eval_rougeLsum": 42.6867, | |
| "eval_runtime": 128.8557, | |
| "eval_samples_per_second": 6.356, | |
| "eval_steps_per_second": 0.799, | |
| "step": 9210 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 9210, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "total_flos": 5.124003128672256e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |