| { | |
| "best_metric": 0.3732990631191409, | |
| "best_model_checkpoint": "./flan-t5-dialogsum/checkpoint-1560", | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 1950, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.31267526745796204, | |
| "eval_rouge1": 0.44388160380951946, | |
| "eval_rouge2": 0.17811053634418733, | |
| "eval_rougeL": 0.35470174491389483, | |
| "eval_rougeLsum": 0.35400351619004, | |
| "eval_runtime": 73.2026, | |
| "eval_samples_per_second": 6.83, | |
| "eval_steps_per_second": 0.219, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.282051282051282, | |
| "grad_norm": 0.25125354528427124, | |
| "learning_rate": 0.00022307692307692306, | |
| "loss": 0.3886, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.3003218472003937, | |
| "eval_rouge1": 0.4481724027358116, | |
| "eval_rouge2": 0.18706683962522586, | |
| "eval_rougeL": 0.36502676602307105, | |
| "eval_rougeLsum": 0.3646421437489298, | |
| "eval_runtime": 65.5308, | |
| "eval_samples_per_second": 7.63, | |
| "eval_steps_per_second": 0.244, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 2.564102564102564, | |
| "grad_norm": 0.29500189423561096, | |
| "learning_rate": 0.00014615384615384615, | |
| "loss": 0.3356, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.2967517375946045, | |
| "eval_rouge1": 0.45487076866137466, | |
| "eval_rouge2": 0.19364689560301196, | |
| "eval_rougeL": 0.37278811615341145, | |
| "eval_rougeLsum": 0.3724689402967539, | |
| "eval_runtime": 67.4046, | |
| "eval_samples_per_second": 7.418, | |
| "eval_steps_per_second": 0.237, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 3.8461538461538463, | |
| "grad_norm": 0.2650415599346161, | |
| "learning_rate": 6.923076923076922e-05, | |
| "loss": 0.3152, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.29470932483673096, | |
| "eval_rouge1": 0.45634329846140587, | |
| "eval_rouge2": 0.1935668856761302, | |
| "eval_rougeL": 0.3732990631191409, | |
| "eval_rougeLsum": 0.3728926972461234, | |
| "eval_runtime": 64.629, | |
| "eval_samples_per_second": 7.736, | |
| "eval_steps_per_second": 0.248, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.29482799768447876, | |
| "eval_rouge1": 0.4547042383346209, | |
| "eval_rouge2": 0.18917345073480046, | |
| "eval_rougeL": 0.3670910829591487, | |
| "eval_rougeLsum": 0.3666732624155983, | |
| "eval_runtime": 65.3537, | |
| "eval_samples_per_second": 7.651, | |
| "eval_steps_per_second": 0.245, | |
| "step": 1950 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1950, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.15809784430592e+16, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |