| { |
| "best_metric": 3.0490849894704297e-05, |
| "best_model_checkpoint": "/content/donut_finetuned/checkpoint-95", |
| "epoch": 19.0, |
| "eval_steps": 500, |
| "global_step": 95, |
| "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 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_loss": 7.056079630274326e-05, |
| "eval_runtime": 3.3248, |
| "eval_samples_per_second": 4.512, |
| "eval_steps_per_second": 2.406, |
| "step": 45 |
| }, |
| { |
| "epoch": 10.0, |
| "grad_norm": 0.029017027467489243, |
| "learning_rate": 1.8628828433995013e-05, |
| "loss": 0.0009, |
| "step": 50 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_loss": 5.423852053354494e-05, |
| "eval_runtime": 3.3999, |
| "eval_samples_per_second": 4.412, |
| "eval_steps_per_second": 2.353, |
| "step": 50 |
| }, |
| { |
| "epoch": 11.0, |
| "eval_loss": 5.392546518123709e-05, |
| "eval_runtime": 3.3083, |
| "eval_samples_per_second": 4.534, |
| "eval_steps_per_second": 2.418, |
| "step": 55 |
| }, |
| { |
| "epoch": 12.0, |
| "grad_norm": 0.020294995978474617, |
| "learning_rate": 1.3432073050985201e-05, |
| "loss": 0.0013, |
| "step": 60 |
| }, |
| { |
| "epoch": 12.0, |
| "eval_loss": 6.161272176541388e-05, |
| "eval_runtime": 3.3432, |
| "eval_samples_per_second": 4.487, |
| "eval_steps_per_second": 2.393, |
| "step": 60 |
| }, |
| { |
| "epoch": 13.0, |
| "eval_loss": 5.105292802909389e-05, |
| "eval_runtime": 3.3625, |
| "eval_samples_per_second": 4.461, |
| "eval_steps_per_second": 2.379, |
| "step": 65 |
| }, |
| { |
| "epoch": 14.0, |
| "grad_norm": 0.01635734736919403, |
| "learning_rate": 8.424432798163838e-06, |
| "loss": 0.0005, |
| "step": 70 |
| }, |
| { |
| "epoch": 14.0, |
| "eval_loss": 4.1975537897087634e-05, |
| "eval_runtime": 3.3631, |
| "eval_samples_per_second": 4.46, |
| "eval_steps_per_second": 2.379, |
| "step": 70 |
| }, |
| { |
| "epoch": 15.0, |
| "eval_loss": 3.658093191916123e-05, |
| "eval_runtime": 4.1596, |
| "eval_samples_per_second": 3.606, |
| "eval_steps_per_second": 1.923, |
| "step": 75 |
| }, |
| { |
| "epoch": 16.0, |
| "grad_norm": 0.01364582497626543, |
| "learning_rate": 4.209902994920236e-06, |
| "loss": 0.0003, |
| "step": 80 |
| }, |
| { |
| "epoch": 16.0, |
| "eval_loss": 3.365544762345962e-05, |
| "eval_runtime": 3.9937, |
| "eval_samples_per_second": 3.756, |
| "eval_steps_per_second": 2.003, |
| "step": 80 |
| }, |
| { |
| "epoch": 17.0, |
| "eval_loss": 3.177617327310145e-05, |
| "eval_runtime": 4.0483, |
| "eval_samples_per_second": 3.705, |
| "eval_steps_per_second": 1.976, |
| "step": 85 |
| }, |
| { |
| "epoch": 18.0, |
| "grad_norm": 0.015181575901806355, |
| "learning_rate": 1.2968181353609854e-06, |
| "loss": 0.0003, |
| "step": 90 |
| }, |
| { |
| "epoch": 18.0, |
| "eval_loss": 3.098776505794376e-05, |
| "eval_runtime": 3.2974, |
| "eval_samples_per_second": 4.549, |
| "eval_steps_per_second": 2.426, |
| "step": 90 |
| }, |
| { |
| "epoch": 19.0, |
| "eval_loss": 3.0490849894704297e-05, |
| "eval_runtime": 3.3676, |
| "eval_samples_per_second": 4.454, |
| "eval_steps_per_second": 2.376, |
| "step": 95 |
| } |
| ], |
| "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": 4.752905709551616e+18, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
