| { | |
| "best_metric": 1.3700677156448364, | |
| "best_model_checkpoint": "/content/drive/MyDrive/Graduation_Models/Summary_Model/output/checkpoint-7368", | |
| "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": 1.4736, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.457111834961998e-05, | |
| "loss": 1.44, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 4.185667752442997e-05, | |
| "loss": 1.4497, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_gen_len": 17.29181929181929, | |
| "eval_loss": 1.3855763673782349, | |
| "eval_rouge1": 46.4182, | |
| "eval_rouge2": 22.6793, | |
| "eval_rougeL": 38.696, | |
| "eval_rougeLsum": 42.6475, | |
| "eval_runtime": 121.3592, | |
| "eval_samples_per_second": 6.749, | |
| "eval_steps_per_second": 0.849, | |
| "step": 1842 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 3.914223669923996e-05, | |
| "loss": 1.4192, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 3.642779587404995e-05, | |
| "loss": 1.3345, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 3.3713355048859935e-05, | |
| "loss": 1.3562, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 3.099891422366993e-05, | |
| "loss": 1.3474, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_gen_len": 17.273504273504273, | |
| "eval_loss": 1.3723567724227905, | |
| "eval_rouge1": 47.1674, | |
| "eval_rouge2": 23.3092, | |
| "eval_rougeL": 39.4164, | |
| "eval_rougeLsum": 43.3552, | |
| "eval_runtime": 119.0693, | |
| "eval_samples_per_second": 6.878, | |
| "eval_steps_per_second": 0.865, | |
| "step": 3684 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 2.8284473398479917e-05, | |
| "loss": 1.2971, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 2.5570032573289905e-05, | |
| "loss": 1.2711, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 2.2855591748099893e-05, | |
| "loss": 1.2859, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 2.0141150922909884e-05, | |
| "loss": 1.2818, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_gen_len": 17.247863247863247, | |
| "eval_loss": 1.3706920146942139, | |
| "eval_rouge1": 47.4185, | |
| "eval_rouge2": 23.5442, | |
| "eval_rougeL": 39.7883, | |
| "eval_rougeLsum": 43.4867, | |
| "eval_runtime": 118.5587, | |
| "eval_samples_per_second": 6.908, | |
| "eval_steps_per_second": 0.869, | |
| "step": 5526 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 1.742671009771987e-05, | |
| "loss": 1.2272, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 1.471226927252986e-05, | |
| "loss": 1.2389, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 1.1997828447339848e-05, | |
| "loss": 1.2285, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_gen_len": 17.35286935286935, | |
| "eval_loss": 1.3700677156448364, | |
| "eval_rouge1": 47.4833, | |
| "eval_rouge2": 23.614, | |
| "eval_rougeL": 39.8945, | |
| "eval_rougeLsum": 43.6297, | |
| "eval_runtime": 118.838, | |
| "eval_samples_per_second": 6.892, | |
| "eval_steps_per_second": 0.867, | |
| "step": 7368 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 9.283387622149838e-06, | |
| "loss": 1.1985, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 4.34, | |
| "learning_rate": 6.568946796959827e-06, | |
| "loss": 1.1972, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 4.61, | |
| "learning_rate": 3.854505971769816e-06, | |
| "loss": 1.2093, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 1.1400651465798045e-06, | |
| "loss": 1.196, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_gen_len": 17.313797313797313, | |
| "eval_loss": 1.3741676807403564, | |
| "eval_rouge1": 47.4109, | |
| "eval_rouge2": 23.6186, | |
| "eval_rougeL": 39.6383, | |
| "eval_rougeLsum": 43.5567, | |
| "eval_runtime": 122.3234, | |
| "eval_samples_per_second": 6.695, | |
| "eval_steps_per_second": 0.842, | |
| "step": 9210 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 9210, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "total_flos": 5.048305105187635e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |