| { |
| "best_global_step": 1250, |
| "best_metric": 2.6514861583709717, |
| "best_model_checkpoint": "/users/sf4003/sharedscratch/lectures/athnlp/mt5-model-arg-eng_parallel-translation/checkpoint-1250", |
| "epoch": 25.0, |
| "eval_steps": 500, |
| "global_step": 1250, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_loss": 5.835180759429932, |
| "eval_model_preparation_time": 0.0024, |
| "eval_runtime": 1.8793, |
| "eval_samples_per_second": 106.42, |
| "eval_steps_per_second": 53.21, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 4.068732738494873, |
| "eval_model_preparation_time": 0.0024, |
| "eval_runtime": 1.886, |
| "eval_samples_per_second": 106.046, |
| "eval_steps_per_second": 53.023, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 3.460021734237671, |
| "eval_model_preparation_time": 0.0024, |
| "eval_runtime": 1.8699, |
| "eval_samples_per_second": 106.96, |
| "eval_steps_per_second": 53.48, |
| "step": 150 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 3.172445297241211, |
| "eval_model_preparation_time": 0.0024, |
| "eval_runtime": 1.8859, |
| "eval_samples_per_second": 106.053, |
| "eval_steps_per_second": 53.026, |
| "step": 200 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 2.9968864917755127, |
| "eval_model_preparation_time": 0.0024, |
| "eval_runtime": 1.8727, |
| "eval_samples_per_second": 106.798, |
| "eval_steps_per_second": 53.399, |
| "step": 250 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_loss": 2.915433406829834, |
| "eval_model_preparation_time": 0.0024, |
| "eval_runtime": 1.8737, |
| "eval_samples_per_second": 106.742, |
| "eval_steps_per_second": 53.371, |
| "step": 300 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_loss": 2.8528802394866943, |
| "eval_model_preparation_time": 0.0024, |
| "eval_runtime": 1.8696, |
| "eval_samples_per_second": 106.973, |
| "eval_steps_per_second": 53.486, |
| "step": 350 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_loss": 2.8033382892608643, |
| "eval_model_preparation_time": 0.0024, |
| "eval_runtime": 1.8631, |
| "eval_samples_per_second": 107.347, |
| "eval_steps_per_second": 53.674, |
| "step": 400 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_loss": 2.7748770713806152, |
| "eval_model_preparation_time": 0.0024, |
| "eval_runtime": 1.8606, |
| "eval_samples_per_second": 107.494, |
| "eval_steps_per_second": 53.747, |
| "step": 450 |
| }, |
| { |
| "epoch": 10.0, |
| "grad_norm": 24.606786727905273, |
| "learning_rate": 8.004e-05, |
| "loss": 43.7401875, |
| "step": 500 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_loss": 2.753805637359619, |
| "eval_model_preparation_time": 0.0024, |
| "eval_runtime": 1.8401, |
| "eval_samples_per_second": 108.691, |
| "eval_steps_per_second": 54.345, |
| "step": 500 |
| }, |
| { |
| "epoch": 11.0, |
| "eval_loss": 2.736203670501709, |
| "eval_model_preparation_time": 0.0024, |
| "eval_runtime": 1.8629, |
| "eval_samples_per_second": 107.36, |
| "eval_steps_per_second": 53.68, |
| "step": 550 |
| }, |
| { |
| "epoch": 12.0, |
| "eval_loss": 2.7296948432922363, |
| "eval_model_preparation_time": 0.0024, |
| "eval_runtime": 1.8608, |
| "eval_samples_per_second": 107.482, |
| "eval_steps_per_second": 53.741, |
| "step": 600 |
| }, |
| { |
| "epoch": 13.0, |
| "eval_loss": 2.708575963973999, |
| "eval_model_preparation_time": 0.0024, |
| "eval_runtime": 1.8603, |
| "eval_samples_per_second": 107.509, |
| "eval_steps_per_second": 53.754, |
| "step": 650 |
| }, |
| { |
| "epoch": 14.0, |
| "eval_loss": 2.7046337127685547, |
| "eval_model_preparation_time": 0.0024, |
| "eval_runtime": 1.8571, |
| "eval_samples_per_second": 107.693, |
| "eval_steps_per_second": 53.847, |
| "step": 700 |
| }, |
| { |
| "epoch": 15.0, |
| "eval_loss": 2.696824312210083, |
| "eval_model_preparation_time": 0.0024, |
| "eval_runtime": 1.8638, |
| "eval_samples_per_second": 107.308, |
| "eval_steps_per_second": 53.654, |
| "step": 750 |
| }, |
| { |
| "epoch": 16.0, |
| "eval_loss": 2.685243844985962, |
| "eval_model_preparation_time": 0.0024, |
| "eval_runtime": 1.8603, |
| "eval_samples_per_second": 107.511, |
| "eval_steps_per_second": 53.756, |
| "step": 800 |
| }, |
| { |
| "epoch": 17.0, |
| "eval_loss": 2.6752429008483887, |
| "eval_model_preparation_time": 0.0024, |
| "eval_runtime": 1.8649, |
| "eval_samples_per_second": 107.246, |
| "eval_steps_per_second": 53.623, |
| "step": 850 |
| }, |
| { |
| "epoch": 18.0, |
| "eval_loss": 2.6729724407196045, |
| "eval_model_preparation_time": 0.0024, |
| "eval_runtime": 1.8652, |
| "eval_samples_per_second": 107.227, |
| "eval_steps_per_second": 53.613, |
| "step": 900 |
| }, |
| { |
| "epoch": 19.0, |
| "eval_loss": 2.6718413829803467, |
| "eval_model_preparation_time": 0.0024, |
| "eval_runtime": 1.8659, |
| "eval_samples_per_second": 107.189, |
| "eval_steps_per_second": 53.595, |
| "step": 950 |
| }, |
| { |
| "epoch": 20.0, |
| "grad_norm": 25.384899139404297, |
| "learning_rate": 6.004000000000001e-05, |
| "loss": 24.35806640625, |
| "step": 1000 |
| }, |
| { |
| "epoch": 20.0, |
| "eval_loss": 2.6660306453704834, |
| "eval_model_preparation_time": 0.0024, |
| "eval_runtime": 1.842, |
| "eval_samples_per_second": 108.579, |
| "eval_steps_per_second": 54.289, |
| "step": 1000 |
| }, |
| { |
| "epoch": 21.0, |
| "eval_loss": 2.6635730266571045, |
| "eval_model_preparation_time": 0.0024, |
| "eval_runtime": 1.8577, |
| "eval_samples_per_second": 107.66, |
| "eval_steps_per_second": 53.83, |
| "step": 1050 |
| }, |
| { |
| "epoch": 22.0, |
| "eval_loss": 2.655503273010254, |
| "eval_model_preparation_time": 0.0024, |
| "eval_runtime": 1.8572, |
| "eval_samples_per_second": 107.688, |
| "eval_steps_per_second": 53.844, |
| "step": 1100 |
| }, |
| { |
| "epoch": 23.0, |
| "eval_loss": 2.654468297958374, |
| "eval_model_preparation_time": 0.0024, |
| "eval_runtime": 1.8529, |
| "eval_samples_per_second": 107.94, |
| "eval_steps_per_second": 53.97, |
| "step": 1150 |
| }, |
| { |
| "epoch": 24.0, |
| "eval_loss": 2.654360294342041, |
| "eval_model_preparation_time": 0.0024, |
| "eval_runtime": 1.8554, |
| "eval_samples_per_second": 107.793, |
| "eval_steps_per_second": 53.896, |
| "step": 1200 |
| }, |
| { |
| "epoch": 25.0, |
| "eval_loss": 2.6514861583709717, |
| "eval_model_preparation_time": 0.0024, |
| "eval_runtime": 1.8573, |
| "eval_samples_per_second": 107.682, |
| "eval_steps_per_second": 53.841, |
| "step": 1250 |
| } |
| ], |
| "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": 1277763903866880.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
