| { |
| "best_metric": 1.964630365371704, |
| "best_model_checkpoint": "output/ariya/checkpoint-77", |
| "epoch": 7.0, |
| "global_step": 77, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.45, |
| "learning_rate": 7.836279790554737e-05, |
| "loss": 2.5022, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.91, |
| "learning_rate": 2.778782010045488e-06, |
| "loss": 2.2601, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 2.1270811557769775, |
| "eval_runtime": 0.2424, |
| "eval_samples_per_second": 74.243, |
| "eval_steps_per_second": 12.374, |
| "step": 11 |
| }, |
| { |
| "epoch": 1.36, |
| "learning_rate": 4.0102530108070535e-05, |
| "loss": 2.2382, |
| "step": 15 |
| }, |
| { |
| "epoch": 1.82, |
| "learning_rate": 0.000126309992352219, |
| "loss": 2.1551, |
| "step": 20 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 2.044888734817505, |
| "eval_runtime": 0.2452, |
| "eval_samples_per_second": 73.408, |
| "eval_steps_per_second": 12.235, |
| "step": 22 |
| }, |
| { |
| "epoch": 2.27, |
| "learning_rate": 0.00011352344634864655, |
| "loss": 2.1093, |
| "step": 25 |
| }, |
| { |
| "epoch": 2.73, |
| "learning_rate": 2.3676553651353525e-05, |
| "loss": 2.0408, |
| "step": 30 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 2.019381523132324, |
| "eval_runtime": 0.2439, |
| "eval_samples_per_second": 73.799, |
| "eval_steps_per_second": 12.3, |
| "step": 33 |
| }, |
| { |
| "epoch": 3.18, |
| "learning_rate": 1.0890007647780947e-05, |
| "loss": 1.9664, |
| "step": 35 |
| }, |
| { |
| "epoch": 3.64, |
| "learning_rate": 9.709746989192932e-05, |
| "loss": 1.9754, |
| "step": 40 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 1.988910436630249, |
| "eval_runtime": 0.2422, |
| "eval_samples_per_second": 74.31, |
| "eval_steps_per_second": 12.385, |
| "step": 44 |
| }, |
| { |
| "epoch": 4.09, |
| "learning_rate": 0.00013442121798995453, |
| "loss": 1.9406, |
| "step": 45 |
| }, |
| { |
| "epoch": 4.55, |
| "learning_rate": 5.883720209445262e-05, |
| "loss": 1.9442, |
| "step": 50 |
| }, |
| { |
| "epoch": 5.0, |
| "learning_rate": 0.0, |
| "loss": 1.8989, |
| "step": 55 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 1.9963830709457397, |
| "eval_runtime": 0.2445, |
| "eval_samples_per_second": 73.608, |
| "eval_steps_per_second": 12.268, |
| "step": 55 |
| }, |
| { |
| "epoch": 5.45, |
| "learning_rate": 5.883720209445242e-05, |
| "loss": 1.8248, |
| "step": 60 |
| }, |
| { |
| "epoch": 5.91, |
| "learning_rate": 0.00013442121798995453, |
| "loss": 1.8456, |
| "step": 65 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_loss": 1.9840502738952637, |
| "eval_runtime": 0.2442, |
| "eval_samples_per_second": 73.696, |
| "eval_steps_per_second": 12.283, |
| "step": 66 |
| }, |
| { |
| "epoch": 6.36, |
| "learning_rate": 9.70974698919295e-05, |
| "loss": 1.7729, |
| "step": 70 |
| }, |
| { |
| "epoch": 6.82, |
| "learning_rate": 1.0890007647780993e-05, |
| "loss": 1.7715, |
| "step": 75 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_loss": 1.964630365371704, |
| "eval_runtime": 0.2443, |
| "eval_samples_per_second": 73.674, |
| "eval_steps_per_second": 12.279, |
| "step": 77 |
| } |
| ], |
| "max_steps": 1100, |
| "num_train_epochs": 100, |
| "total_flos": 74990813184000.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
