| { |
| "best_global_step": 1564, |
| "best_metric": 24.946759180636583, |
| "best_model_checkpoint": "/content/morphbart_large_tr_en_100k_5ep/checkpoint-1564", |
| "epoch": 5.0, |
| "eval_steps": 500, |
| "global_step": 1955, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 4.3125, |
| "learning_rate": 1.8937463191111367e-05, |
| "loss": 3.1417, |
| "step": 391 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_bleu": 24.47811018150474, |
| "eval_chrf_pp": 44.210691638302166, |
| "eval_empty_rate": 0.0, |
| "eval_gen_len": 9.358, |
| "eval_loss": 3.2217891216278076, |
| "eval_runtime": 37.134, |
| "eval_samples_per_second": 53.859, |
| "eval_steps_per_second": 1.697, |
| "step": 391 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 3.75, |
| "learning_rate": 1.4231778836571683e-05, |
| "loss": 3.0882, |
| "step": 782 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_bleu": 24.490127610416852, |
| "eval_chrf_pp": 44.29566068475588, |
| "eval_empty_rate": 0.0, |
| "eval_gen_len": 9.3065, |
| "eval_loss": 3.2145493030548096, |
| "eval_runtime": 34.9594, |
| "eval_samples_per_second": 57.209, |
| "eval_steps_per_second": 1.802, |
| "step": 782 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 4.34375, |
| "learning_rate": 7.703395440736275e-06, |
| "loss": 3.0698, |
| "step": 1173 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_bleu": 24.61496648794109, |
| "eval_chrf_pp": 44.47233702829275, |
| "eval_empty_rate": 0.0, |
| "eval_gen_len": 9.3005, |
| "eval_loss": 3.204270362854004, |
| "eval_runtime": 35.7598, |
| "eval_samples_per_second": 55.929, |
| "eval_steps_per_second": 1.762, |
| "step": 1173 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 5.96875, |
| "learning_rate": 2.1641986470524667e-06, |
| "loss": 3.0598, |
| "step": 1564 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_bleu": 24.946759180636583, |
| "eval_chrf_pp": 44.74298861851367, |
| "eval_empty_rate": 0.0, |
| "eval_gen_len": 9.3375, |
| "eval_loss": 3.198596715927124, |
| "eval_runtime": 36.0307, |
| "eval_samples_per_second": 55.508, |
| "eval_steps_per_second": 1.749, |
| "step": 1564 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 4.4375, |
| "learning_rate": 1.4623500060872985e-11, |
| "loss": 3.0555, |
| "step": 1955 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_bleu": 24.849663294250245, |
| "eval_chrf_pp": 44.622513534306755, |
| "eval_empty_rate": 0.0, |
| "eval_gen_len": 9.3225, |
| "eval_loss": 3.2052407264709473, |
| "eval_runtime": 35.4494, |
| "eval_samples_per_second": 56.418, |
| "eval_steps_per_second": 1.777, |
| "step": 1955 |
| }, |
| { |
| "epoch": 5.0, |
| "step": 1955, |
| "total_flos": 1.8940131431940096e+16, |
| "train_loss": 3.0829814003556586, |
| "train_runtime": 2357.2745, |
| "train_samples_per_second": 212.109, |
| "train_steps_per_second": 0.829 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 1955, |
| "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": 1.8940131431940096e+16, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
