| { |
| "best_metric": 1.0597896575927734, |
| "best_model_checkpoint": "runs/codeparrot/codeparrot-small-multi-xtext_mar-line-dedup-512/checkpoint-640", |
| "epoch": 7.996108949416342, |
| "global_step": 640, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "learning_rate": 4.5e-05, |
| "loss": 1.3972, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 1.1680763959884644, |
| "eval_runtime": 9.276, |
| "eval_samples_per_second": 78.159, |
| "eval_steps_per_second": 19.621, |
| "step": 80 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 4e-05, |
| "loss": 1.1503, |
| "step": 160 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 1.1147633790969849, |
| "eval_runtime": 9.0648, |
| "eval_samples_per_second": 79.979, |
| "eval_steps_per_second": 20.078, |
| "step": 160 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 3.5e-05, |
| "loss": 1.0648, |
| "step": 240 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 1.0921669006347656, |
| "eval_runtime": 9.3128, |
| "eval_samples_per_second": 77.85, |
| "eval_steps_per_second": 19.543, |
| "step": 240 |
| }, |
| { |
| "epoch": 4.0, |
| "learning_rate": 3e-05, |
| "loss": 1.0046, |
| "step": 320 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 1.0750280618667603, |
| "eval_runtime": 9.2369, |
| "eval_samples_per_second": 78.49, |
| "eval_steps_per_second": 19.704, |
| "step": 320 |
| }, |
| { |
| "epoch": 5.0, |
| "learning_rate": 2.5e-05, |
| "loss": 0.9591, |
| "step": 400 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 1.07002854347229, |
| "eval_runtime": 9.2974, |
| "eval_samples_per_second": 77.979, |
| "eval_steps_per_second": 19.575, |
| "step": 400 |
| }, |
| { |
| "epoch": 6.0, |
| "learning_rate": 2e-05, |
| "loss": 0.9228, |
| "step": 480 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_loss": 1.0629867315292358, |
| "eval_runtime": 9.2375, |
| "eval_samples_per_second": 78.484, |
| "eval_steps_per_second": 19.702, |
| "step": 480 |
| }, |
| { |
| "epoch": 7.0, |
| "learning_rate": 1.5e-05, |
| "loss": 0.8922, |
| "step": 560 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_loss": 1.0609277486801147, |
| "eval_runtime": 9.2071, |
| "eval_samples_per_second": 78.744, |
| "eval_steps_per_second": 19.767, |
| "step": 560 |
| }, |
| { |
| "epoch": 8.0, |
| "learning_rate": 1e-05, |
| "loss": 0.8689, |
| "step": 640 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_loss": 1.0597896575927734, |
| "eval_runtime": 9.2819, |
| "eval_samples_per_second": 78.109, |
| "eval_steps_per_second": 19.608, |
| "step": 640 |
| } |
| ], |
| "max_steps": 800, |
| "num_train_epochs": 10, |
| "total_flos": 1.0740147683328e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
