| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 6.527415143603133, | |
| "global_step": 2500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_gen_len": 81.7789, | |
| "eval_loss": 0.7409296035766602, | |
| "eval_rouge-1": 52.5771, | |
| "eval_rouge-2": 35.6684, | |
| "eval_rouge-l": 49.1637, | |
| "eval_runtime": 402.5304, | |
| "eval_samples_per_second": 0.236, | |
| "eval_steps_per_second": 0.119, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 1.6307348004475943e-05, | |
| "loss": 0.9884, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_gen_len": 82.1263, | |
| "eval_loss": 0.7081394195556641, | |
| "eval_rouge-1": 53.3979, | |
| "eval_rouge-2": 36.4405, | |
| "eval_rouge-l": 49.9086, | |
| "eval_runtime": 389.2507, | |
| "eval_samples_per_second": 0.244, | |
| "eval_steps_per_second": 0.123, | |
| "step": 766 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 1.2584856396866842e-05, | |
| "loss": 0.7265, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_gen_len": 83.6211, | |
| "eval_loss": 0.6961584091186523, | |
| "eval_rouge-1": 53.1336, | |
| "eval_rouge-2": 36.0563, | |
| "eval_rouge-l": 49.7218, | |
| "eval_runtime": 395.7734, | |
| "eval_samples_per_second": 0.24, | |
| "eval_steps_per_second": 0.121, | |
| "step": 1149 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 8.86236478925774e-06, | |
| "loss": 0.6564, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_gen_len": 83.7895, | |
| "eval_loss": 0.693389892578125, | |
| "eval_rouge-1": 53.6419, | |
| "eval_rouge-2": 36.5755, | |
| "eval_rouge-l": 50.0063, | |
| "eval_runtime": 394.1844, | |
| "eval_samples_per_second": 0.241, | |
| "eval_steps_per_second": 0.122, | |
| "step": 1532 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_gen_len": 82.1474, | |
| "eval_loss": 0.6953384280204773, | |
| "eval_rouge-1": 54.1103, | |
| "eval_rouge-2": 37.0725, | |
| "eval_rouge-l": 50.7383, | |
| "eval_runtime": 388.3706, | |
| "eval_samples_per_second": 0.245, | |
| "eval_steps_per_second": 0.124, | |
| "step": 1915 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "learning_rate": 5.132413278627378e-06, | |
| "loss": 0.6026, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_gen_len": 82.1053, | |
| "eval_loss": 0.6941447257995605, | |
| "eval_rouge-1": 53.5465, | |
| "eval_rouge-2": 36.571, | |
| "eval_rouge-l": 50.1244, | |
| "eval_runtime": 382.416, | |
| "eval_samples_per_second": 0.248, | |
| "eval_steps_per_second": 0.126, | |
| "step": 2298 | |
| }, | |
| { | |
| "epoch": 6.53, | |
| "learning_rate": 1.4024617679970163e-06, | |
| "loss": 0.5873, | |
| "step": 2500 | |
| } | |
| ], | |
| "max_steps": 2681, | |
| "num_train_epochs": 7, | |
| "total_flos": 6497005883228160.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |