| { |
| "best_metric": 0.00013167245197109878, |
| "best_model_checkpoint": "/content/donut_finetuned/checkpoint-40", |
| "epoch": 8.0, |
| "eval_steps": 500, |
| "global_step": 40, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_loss": 9.464871406555176, |
| "eval_runtime": 4.0077, |
| "eval_samples_per_second": 3.743, |
| "eval_steps_per_second": 1.996, |
| "step": 5 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 46.585044860839844, |
| "learning_rate": 2.4e-05, |
| "loss": 10.4972, |
| "step": 10 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 6.029897689819336, |
| "eval_runtime": 3.4276, |
| "eval_samples_per_second": 4.376, |
| "eval_steps_per_second": 2.334, |
| "step": 10 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 2.0910725593566895, |
| "eval_runtime": 3.4674, |
| "eval_samples_per_second": 4.326, |
| "eval_steps_per_second": 2.307, |
| "step": 15 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 11.026430130004883, |
| "learning_rate": 2.9418925439074784e-05, |
| "loss": 3.1451, |
| "step": 20 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 0.37007761001586914, |
| "eval_runtime": 4.5507, |
| "eval_samples_per_second": 3.296, |
| "eval_steps_per_second": 1.758, |
| "step": 20 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 0.020941253751516342, |
| "eval_runtime": 3.4626, |
| "eval_samples_per_second": 4.332, |
| "eval_steps_per_second": 2.31, |
| "step": 25 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 0.41835108399391174, |
| "learning_rate": 2.7135254915624213e-05, |
| "loss": 0.1413, |
| "step": 30 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_loss": 0.0015195924788713455, |
| "eval_runtime": 3.3155, |
| "eval_samples_per_second": 4.524, |
| "eval_steps_per_second": 2.413, |
| "step": 30 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_loss": 0.000456114619737491, |
| "eval_runtime": 3.3952, |
| "eval_samples_per_second": 4.418, |
| "eval_steps_per_second": 2.356, |
| "step": 35 |
| }, |
| { |
| "epoch": 8.0, |
| "grad_norm": 0.04658687859773636, |
| "learning_rate": 2.3387893552061202e-05, |
| "loss": 0.0024, |
| "step": 40 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_loss": 0.00013167245197109878, |
| "eval_runtime": 4.4677, |
| "eval_samples_per_second": 3.357, |
| "eval_steps_per_second": 1.791, |
| "step": 40 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 100, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 20, |
| "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": 2.001223456653312e+18, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
