| { |
| "best_global_step": 2750, |
| "best_metric": 3.8375539779663086, |
| "best_model_checkpoint": "/work/10368/siyuansong/vista/models/opt-clean_plus_random_error_5pct_42_1e-3/checkpoint-2750", |
| "epoch": 10.0, |
| "eval_steps": 500, |
| "global_step": 2750, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_loss": 7.028458118438721, |
| "eval_runtime": 34.4024, |
| "eval_samples_per_second": 1507.541, |
| "eval_steps_per_second": 5.901, |
| "step": 275 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 5.513585090637207, |
| "eval_runtime": 34.6442, |
| "eval_samples_per_second": 1497.019, |
| "eval_steps_per_second": 5.86, |
| "step": 550 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 4.975468158721924, |
| "eval_runtime": 34.637, |
| "eval_samples_per_second": 1497.331, |
| "eval_steps_per_second": 5.861, |
| "step": 825 |
| }, |
| { |
| "epoch": 3.6363636363636362, |
| "grad_norm": 0.36213040351867676, |
| "learning_rate": 3.121875e-05, |
| "loss": 6.3614, |
| "step": 1000 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 4.67366361618042, |
| "eval_runtime": 34.8284, |
| "eval_samples_per_second": 1489.101, |
| "eval_steps_per_second": 5.829, |
| "step": 1100 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 4.447249412536621, |
| "eval_runtime": 35.1314, |
| "eval_samples_per_second": 1476.256, |
| "eval_steps_per_second": 5.778, |
| "step": 1375 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_loss": 4.273419380187988, |
| "eval_runtime": 34.6465, |
| "eval_samples_per_second": 1496.92, |
| "eval_steps_per_second": 5.859, |
| "step": 1650 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_loss": 4.134232044219971, |
| "eval_runtime": 34.948, |
| "eval_samples_per_second": 1484.003, |
| "eval_steps_per_second": 5.809, |
| "step": 1925 |
| }, |
| { |
| "epoch": 7.2727272727272725, |
| "grad_norm": 0.47896745800971985, |
| "learning_rate": 6.246875000000001e-05, |
| "loss": 4.4187, |
| "step": 2000 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_loss": 4.015931606292725, |
| "eval_runtime": 34.6793, |
| "eval_samples_per_second": 1495.504, |
| "eval_steps_per_second": 5.854, |
| "step": 2200 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_loss": 3.9174964427948, |
| "eval_runtime": 34.7464, |
| "eval_samples_per_second": 1492.614, |
| "eval_steps_per_second": 5.842, |
| "step": 2475 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_loss": 3.8375539779663086, |
| "eval_runtime": 34.869, |
| "eval_samples_per_second": 1487.366, |
| "eval_steps_per_second": 5.822, |
| "step": 2750 |
| }, |
| { |
| "epoch": 10.0, |
| "step": 2750, |
| "total_flos": 7.35798362112e+17, |
| "train_loss": 5.007823774857955, |
| "train_runtime": 7268.5565, |
| "train_samples_per_second": 775.124, |
| "train_steps_per_second": 0.378 |
| } |
| ], |
| "logging_steps": 1000, |
| "max_steps": 2750, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 3, |
| "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": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 7.35798362112e+17, |
| "train_batch_size": 256, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
