| { |
| "best_global_step": 800, |
| "best_metric": 2.764420747756958, |
| "best_model_checkpoint": "/users/sf4003/sharedscratch/lectures/athnlp/t5-model-arg-eng_parallel-translation/checkpoint-800", |
| "epoch": 16.0, |
| "eval_steps": 500, |
| "global_step": 800, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_loss": 3.0652856826782227, |
| "eval_model_preparation_time": 0.0017, |
| "eval_runtime": 1.2, |
| "eval_samples_per_second": 166.673, |
| "eval_steps_per_second": 83.337, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 2.9778356552124023, |
| "eval_model_preparation_time": 0.0017, |
| "eval_runtime": 1.194, |
| "eval_samples_per_second": 167.503, |
| "eval_steps_per_second": 83.752, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 2.9258811473846436, |
| "eval_model_preparation_time": 0.0017, |
| "eval_runtime": 1.195, |
| "eval_samples_per_second": 167.366, |
| "eval_steps_per_second": 83.683, |
| "step": 150 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 2.8856306076049805, |
| "eval_model_preparation_time": 0.0017, |
| "eval_runtime": 1.1953, |
| "eval_samples_per_second": 167.324, |
| "eval_steps_per_second": 83.662, |
| "step": 200 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 2.8581366539001465, |
| "eval_model_preparation_time": 0.0017, |
| "eval_runtime": 1.1942, |
| "eval_samples_per_second": 167.472, |
| "eval_steps_per_second": 83.736, |
| "step": 250 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_loss": 2.8342669010162354, |
| "eval_model_preparation_time": 0.0017, |
| "eval_runtime": 1.1953, |
| "eval_samples_per_second": 167.317, |
| "eval_steps_per_second": 83.658, |
| "step": 300 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_loss": 2.8252429962158203, |
| "eval_model_preparation_time": 0.0017, |
| "eval_runtime": 1.1919, |
| "eval_samples_per_second": 167.799, |
| "eval_steps_per_second": 83.899, |
| "step": 350 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_loss": 2.8020739555358887, |
| "eval_model_preparation_time": 0.0017, |
| "eval_runtime": 1.1968, |
| "eval_samples_per_second": 167.118, |
| "eval_steps_per_second": 83.559, |
| "step": 400 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_loss": 2.7865664958953857, |
| "eval_model_preparation_time": 0.0017, |
| "eval_runtime": 1.194, |
| "eval_samples_per_second": 167.507, |
| "eval_steps_per_second": 83.754, |
| "step": 450 |
| }, |
| { |
| "epoch": 10.0, |
| "grad_norm": 15.644015312194824, |
| "learning_rate": 8.004e-05, |
| "loss": 23.546189453125, |
| "step": 500 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_loss": 2.7913711071014404, |
| "eval_model_preparation_time": 0.0017, |
| "eval_runtime": 1.1961, |
| "eval_samples_per_second": 167.211, |
| "eval_steps_per_second": 83.606, |
| "step": 500 |
| }, |
| { |
| "epoch": 11.0, |
| "eval_loss": 2.779904842376709, |
| "eval_model_preparation_time": 0.0017, |
| "eval_runtime": 1.1964, |
| "eval_samples_per_second": 167.166, |
| "eval_steps_per_second": 83.583, |
| "step": 550 |
| }, |
| { |
| "epoch": 12.0, |
| "eval_loss": 2.7796366214752197, |
| "eval_model_preparation_time": 0.0017, |
| "eval_runtime": 1.1948, |
| "eval_samples_per_second": 167.399, |
| "eval_steps_per_second": 83.699, |
| "step": 600 |
| }, |
| { |
| "epoch": 13.0, |
| "eval_loss": 2.7685296535491943, |
| "eval_model_preparation_time": 0.0017, |
| "eval_runtime": 1.1937, |
| "eval_samples_per_second": 167.546, |
| "eval_steps_per_second": 83.773, |
| "step": 650 |
| }, |
| { |
| "epoch": 14.0, |
| "eval_loss": 2.7661306858062744, |
| "eval_model_preparation_time": 0.0017, |
| "eval_runtime": 1.1923, |
| "eval_samples_per_second": 167.74, |
| "eval_steps_per_second": 83.87, |
| "step": 700 |
| }, |
| { |
| "epoch": 15.0, |
| "eval_loss": 2.7681777477264404, |
| "eval_model_preparation_time": 0.0017, |
| "eval_runtime": 1.1942, |
| "eval_samples_per_second": 167.47, |
| "eval_steps_per_second": 83.735, |
| "step": 750 |
| }, |
| { |
| "epoch": 16.0, |
| "eval_loss": 2.764420747756958, |
| "eval_model_preparation_time": 0.0017, |
| "eval_runtime": 1.1959, |
| "eval_samples_per_second": 167.236, |
| "eval_steps_per_second": 83.618, |
| "step": 800 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 2500, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 50, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 5, |
| "early_stopping_threshold": 0.0 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 0 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 286069745319936.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
