| { |
| "best_metric": 0.0, |
| "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-2138", |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 6414, |
| "is_hyper_param_search": true, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.23, |
| "learning_rate": 6.673421496233018e-05, |
| "loss": 0.6049, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.47, |
| "learning_rate": 6.259026222000962e-05, |
| "loss": 0.6341, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.7, |
| "learning_rate": 5.844630947768907e-05, |
| "loss": 0.6276, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.94, |
| "learning_rate": 5.4302356735368516e-05, |
| "loss": 0.614, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.619145393371582, |
| "eval_matthews_correlation": 0.0, |
| "eval_runtime": 0.7293, |
| "eval_samples_per_second": 1430.082, |
| "eval_steps_per_second": 90.494, |
| "step": 2138 |
| }, |
| { |
| "epoch": 1.17, |
| "learning_rate": 5.015840399304796e-05, |
| "loss": 0.6223, |
| "step": 2500 |
| }, |
| { |
| "epoch": 1.4, |
| "learning_rate": 4.601445125072741e-05, |
| "loss": 0.6101, |
| "step": 3000 |
| }, |
| { |
| "epoch": 1.64, |
| "learning_rate": 4.187049850840686e-05, |
| "loss": 0.6246, |
| "step": 3500 |
| }, |
| { |
| "epoch": 1.87, |
| "learning_rate": 3.7726545766086306e-05, |
| "loss": 0.603, |
| "step": 4000 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.6236200332641602, |
| "eval_matthews_correlation": 0.0, |
| "eval_runtime": 0.7355, |
| "eval_samples_per_second": 1418.007, |
| "eval_steps_per_second": 89.73, |
| "step": 4276 |
| }, |
| { |
| "epoch": 2.1, |
| "learning_rate": 3.358259302376575e-05, |
| "loss": 0.6119, |
| "step": 4500 |
| }, |
| { |
| "epoch": 2.34, |
| "learning_rate": 2.9438640281445205e-05, |
| "loss": 0.6139, |
| "step": 5000 |
| }, |
| { |
| "epoch": 2.57, |
| "learning_rate": 2.529468753912465e-05, |
| "loss": 0.6024, |
| "step": 5500 |
| }, |
| { |
| "epoch": 2.81, |
| "learning_rate": 2.1150734796804097e-05, |
| "loss": 0.6212, |
| "step": 6000 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 0.6302978992462158, |
| "eval_matthews_correlation": 0.0, |
| "eval_runtime": 0.7272, |
| "eval_samples_per_second": 1434.322, |
| "eval_steps_per_second": 90.762, |
| "step": 6414 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 8552, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 4, |
| "save_steps": 500, |
| "total_flos": 97903756622304.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": { |
| "learning_rate": 7.087816770465073e-05, |
| "num_train_epochs": 4, |
| "per_device_train_batch_size": 4, |
| "seed": 26 |
| } |
| } |
|
|
