| { |
| "best_global_step": 696, |
| "best_metric": 37.6433, |
| "best_model_checkpoint": "./results_bart_large/checkpoint-696", |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 696, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.14398848092152627, |
| "grad_norm": 86.04337310791016, |
| "learning_rate": 2.859195402298851e-05, |
| "loss": 23.5227392578125, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.28797696184305255, |
| "grad_norm": 125.26842498779297, |
| "learning_rate": 2.7155172413793102e-05, |
| "loss": 20.470574951171876, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.4319654427645788, |
| "grad_norm": 165.9732208251953, |
| "learning_rate": 2.57183908045977e-05, |
| "loss": 20.68321044921875, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.5759539236861051, |
| "grad_norm": 102.4205551147461, |
| "learning_rate": 2.4281609195402298e-05, |
| "loss": 20.2867919921875, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.7199424046076314, |
| "grad_norm": 97.07613372802734, |
| "learning_rate": 2.2844827586206897e-05, |
| "loss": 19.927686767578123, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.8639308855291576, |
| "grad_norm": 213.36459350585938, |
| "learning_rate": 2.1408045977011497e-05, |
| "loss": 19.565047607421874, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 2.2826883792877197, |
| "eval_rouge1": 44.9926, |
| "eval_rouge2": 21.3081, |
| "eval_rougeL": 36.6377, |
| "eval_rougeLsum": 36.6539, |
| "eval_runtime": 171.3954, |
| "eval_samples_per_second": 2.025, |
| "eval_steps_per_second": 2.025, |
| "step": 348 |
| }, |
| { |
| "epoch": 1.005759539236861, |
| "grad_norm": 145.24673461914062, |
| "learning_rate": 1.997126436781609e-05, |
| "loss": 19.29373291015625, |
| "step": 350 |
| }, |
| { |
| "epoch": 1.1497480201583874, |
| "grad_norm": 270.0838623046875, |
| "learning_rate": 1.853448275862069e-05, |
| "loss": 16.37059326171875, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.2937365010799136, |
| "grad_norm": 87.3062973022461, |
| "learning_rate": 1.709770114942529e-05, |
| "loss": 15.338236083984375, |
| "step": 450 |
| }, |
| { |
| "epoch": 1.43772498200144, |
| "grad_norm": 138.10104370117188, |
| "learning_rate": 1.5660919540229885e-05, |
| "loss": 16.017222900390625, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.5817134629229663, |
| "grad_norm": 221.23165893554688, |
| "learning_rate": 1.4224137931034483e-05, |
| "loss": 15.628026123046874, |
| "step": 550 |
| }, |
| { |
| "epoch": 1.7257019438444925, |
| "grad_norm": 87.9384994506836, |
| "learning_rate": 1.2787356321839081e-05, |
| "loss": 15.281673583984375, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.8696904247660187, |
| "grad_norm": 80.72342681884766, |
| "learning_rate": 1.1350574712643677e-05, |
| "loss": 15.443740234375, |
| "step": 650 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 2.2174012660980225, |
| "eval_rouge1": 45.7446, |
| "eval_rouge2": 22.2135, |
| "eval_rougeL": 37.6433, |
| "eval_rougeLsum": 37.6641, |
| "eval_runtime": 160.8627, |
| "eval_samples_per_second": 2.157, |
| "eval_steps_per_second": 2.157, |
| "step": 696 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 1044, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2429561286033408.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
