| { | |
| "best_metric": 85.1786, | |
| "best_model_checkpoint": "./output/checkpoint-800", | |
| "epoch": 0.7317073170731707, | |
| "global_step": 800, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.798350137488543e-05, | |
| "loss": 0.0831, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.569202566452796e-05, | |
| "loss": 0.1124, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.34005499541705e-05, | |
| "loss": 0.1095, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.110907424381301e-05, | |
| "loss": 0.1127, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 8.881759853345555e-05, | |
| "loss": 0.1108, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 8.652612282309808e-05, | |
| "loss": 0.1037, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 8.423464711274061e-05, | |
| "loss": 0.1124, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 8.194317140238313e-05, | |
| "loss": 0.1183, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_Bleu_1": 0.8403, | |
| "eval_Bleu_2": 0.0008, | |
| "eval_Bleu_3": 0.0001, | |
| "eval_Bleu_4": 0.0, | |
| "eval_ROUGE_L": 0.8403, | |
| "eval_accuracy": 84.0339, | |
| "eval_f1": 84.0339, | |
| "eval_gen_len": 2.2024, | |
| "eval_loss": 0.22444528341293335, | |
| "eval_precision": 84.0339, | |
| "eval_recall": 84.0339, | |
| "eval_rouge1": 84.249, | |
| "eval_rouge2": 3.2506, | |
| "eval_rougeL": 84.247, | |
| "eval_rougeLsum": 84.2327, | |
| "eval_runtime": 932.0787, | |
| "eval_samples_per_second": 37.395, | |
| "eval_steps_per_second": 4.674, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 7.965169569202566e-05, | |
| "loss": 0.1154, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 7.736021998166821e-05, | |
| "loss": 0.1101, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 7.506874427131073e-05, | |
| "loss": 0.1164, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 7.277726856095326e-05, | |
| "loss": 0.1188, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 7.048579285059579e-05, | |
| "loss": 0.109, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 6.819431714023832e-05, | |
| "loss": 0.1196, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 6.590284142988084e-05, | |
| "loss": 0.1144, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 6.361136571952338e-05, | |
| "loss": 0.1237, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_Bleu_1": 0.8409, | |
| "eval_Bleu_2": 0.0008, | |
| "eval_Bleu_3": 0.0001, | |
| "eval_Bleu_4": 0.0, | |
| "eval_ROUGE_L": 0.8409, | |
| "eval_accuracy": 84.0941, | |
| "eval_f1": 84.0941, | |
| "eval_gen_len": 2.2108, | |
| "eval_loss": 0.20932114124298096, | |
| "eval_precision": 84.0941, | |
| "eval_recall": 84.0941, | |
| "eval_rouge1": 84.2638, | |
| "eval_rouge2": 3.351, | |
| "eval_rougeL": 84.2454, | |
| "eval_rougeLsum": 84.2519, | |
| "eval_runtime": 942.3935, | |
| "eval_samples_per_second": 36.986, | |
| "eval_steps_per_second": 4.623, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 6.131989000916591e-05, | |
| "loss": 0.1228, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 5.902841429880843e-05, | |
| "loss": 0.1247, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 5.673693858845096e-05, | |
| "loss": 0.1175, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 5.444546287809349e-05, | |
| "loss": 0.1202, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 5.215398716773603e-05, | |
| "loss": 0.1173, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.986251145737855e-05, | |
| "loss": 0.1216, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.757103574702109e-05, | |
| "loss": 0.1187, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.5279560036663614e-05, | |
| "loss": 0.1216, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_Bleu_1": 0.8479, | |
| "eval_Bleu_2": 0.0008, | |
| "eval_Bleu_3": 0.0001, | |
| "eval_Bleu_4": 0.0, | |
| "eval_ROUGE_L": 0.8479, | |
| "eval_accuracy": 84.7884, | |
| "eval_f1": 84.7884, | |
| "eval_gen_len": 2.2086, | |
| "eval_loss": 0.20068727433681488, | |
| "eval_precision": 84.7884, | |
| "eval_recall": 84.7884, | |
| "eval_rouge1": 84.9111, | |
| "eval_rouge2": 3.5605, | |
| "eval_rougeL": 84.92, | |
| "eval_rougeLsum": 84.9162, | |
| "eval_runtime": 939.736, | |
| "eval_samples_per_second": 37.09, | |
| "eval_steps_per_second": 4.636, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.298808432630615e-05, | |
| "loss": 0.1192, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.069660861594867e-05, | |
| "loss": 0.1163, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.84051329055912e-05, | |
| "loss": 0.1207, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.611365719523373e-05, | |
| "loss": 0.1329, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.382218148487626e-05, | |
| "loss": 0.1239, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 3.1530705774518795e-05, | |
| "loss": 0.129, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 2.923923006416132e-05, | |
| "loss": 0.1346, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 2.694775435380385e-05, | |
| "loss": 0.131, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_Bleu_1": 0.8518, | |
| "eval_Bleu_2": 0.0009, | |
| "eval_Bleu_3": 0.0001, | |
| "eval_Bleu_4": 0.0, | |
| "eval_ROUGE_L": 0.8518, | |
| "eval_accuracy": 85.1786, | |
| "eval_f1": 85.1786, | |
| "eval_gen_len": 2.223, | |
| "eval_loss": 0.19242975115776062, | |
| "eval_precision": 85.1786, | |
| "eval_recall": 85.1786, | |
| "eval_rouge1": 85.3238, | |
| "eval_rouge2": 3.8158, | |
| "eval_rougeL": 85.3232, | |
| "eval_rougeLsum": 85.3196, | |
| "eval_runtime": 941.7662, | |
| "eval_samples_per_second": 37.01, | |
| "eval_steps_per_second": 4.626, | |
| "step": 800 | |
| } | |
| ], | |
| "max_steps": 1093, | |
| "num_train_epochs": 1, | |
| "total_flos": 1.3891177077224243e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |