| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 23.076923076923077, |
| "global_step": 1200, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.92, |
| "learning_rate": 3.7200000000000004e-06, |
| "loss": 3.4957, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.92, |
| "eval_loss": 3.337008237838745, |
| "eval_runtime": 4.5047, |
| "eval_samples_per_second": 4.662, |
| "eval_steps_per_second": 0.666, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.85, |
| "learning_rate": 7.72e-06, |
| "loss": 2.8817, |
| "step": 200 |
| }, |
| { |
| "epoch": 3.85, |
| "eval_loss": 2.994506597518921, |
| "eval_runtime": 4.0853, |
| "eval_samples_per_second": 5.14, |
| "eval_steps_per_second": 0.734, |
| "step": 200 |
| }, |
| { |
| "epoch": 5.77, |
| "learning_rate": 1.172e-05, |
| "loss": 2.5363, |
| "step": 300 |
| }, |
| { |
| "epoch": 5.77, |
| "eval_loss": 2.85880970954895, |
| "eval_runtime": 4.1442, |
| "eval_samples_per_second": 5.067, |
| "eval_steps_per_second": 0.724, |
| "step": 300 |
| }, |
| { |
| "epoch": 7.69, |
| "learning_rate": 1.5720000000000002e-05, |
| "loss": 2.3781, |
| "step": 400 |
| }, |
| { |
| "epoch": 7.69, |
| "eval_loss": 2.8444266319274902, |
| "eval_runtime": 4.0477, |
| "eval_samples_per_second": 5.188, |
| "eval_steps_per_second": 0.741, |
| "step": 400 |
| }, |
| { |
| "epoch": 9.62, |
| "learning_rate": 1.968e-05, |
| "loss": 2.2276, |
| "step": 500 |
| }, |
| { |
| "epoch": 9.62, |
| "eval_loss": 2.846156120300293, |
| "eval_runtime": 4.0932, |
| "eval_samples_per_second": 5.13, |
| "eval_steps_per_second": 0.733, |
| "step": 500 |
| }, |
| { |
| "epoch": 11.54, |
| "learning_rate": 1.8835443037974686e-05, |
| "loss": 2.249, |
| "step": 600 |
| }, |
| { |
| "epoch": 11.54, |
| "eval_loss": 2.6710026264190674, |
| "eval_runtime": 4.1454, |
| "eval_samples_per_second": 5.066, |
| "eval_steps_per_second": 0.724, |
| "step": 600 |
| }, |
| { |
| "epoch": 13.46, |
| "learning_rate": 1.7569620253164558e-05, |
| "loss": 2.0842, |
| "step": 700 |
| }, |
| { |
| "epoch": 13.46, |
| "eval_loss": 2.591163396835327, |
| "eval_runtime": 4.2833, |
| "eval_samples_per_second": 4.903, |
| "eval_steps_per_second": 0.7, |
| "step": 700 |
| }, |
| { |
| "epoch": 15.38, |
| "learning_rate": 1.6303797468354434e-05, |
| "loss": 1.9348, |
| "step": 800 |
| }, |
| { |
| "epoch": 15.38, |
| "eval_loss": 2.744408369064331, |
| "eval_runtime": 4.1103, |
| "eval_samples_per_second": 5.109, |
| "eval_steps_per_second": 0.73, |
| "step": 800 |
| }, |
| { |
| "epoch": 17.31, |
| "learning_rate": 1.5037974683544306e-05, |
| "loss": 1.9074, |
| "step": 900 |
| }, |
| { |
| "epoch": 17.31, |
| "eval_loss": 2.6080548763275146, |
| "eval_runtime": 4.1034, |
| "eval_samples_per_second": 5.118, |
| "eval_steps_per_second": 0.731, |
| "step": 900 |
| }, |
| { |
| "epoch": 19.23, |
| "learning_rate": 1.377215189873418e-05, |
| "loss": 1.8806, |
| "step": 1000 |
| }, |
| { |
| "epoch": 19.23, |
| "eval_loss": 2.558474540710449, |
| "eval_runtime": 4.3476, |
| "eval_samples_per_second": 4.83, |
| "eval_steps_per_second": 0.69, |
| "step": 1000 |
| }, |
| { |
| "epoch": 21.15, |
| "learning_rate": 1.2506329113924051e-05, |
| "loss": 1.8524, |
| "step": 1100 |
| }, |
| { |
| "epoch": 21.15, |
| "eval_loss": 2.5464015007019043, |
| "eval_runtime": 4.1253, |
| "eval_samples_per_second": 5.09, |
| "eval_steps_per_second": 0.727, |
| "step": 1100 |
| }, |
| { |
| "epoch": 23.08, |
| "learning_rate": 1.1240506329113925e-05, |
| "loss": 1.6774, |
| "step": 1200 |
| }, |
| { |
| "epoch": 23.08, |
| "eval_loss": 2.465409755706787, |
| "eval_runtime": 4.0985, |
| "eval_samples_per_second": 5.124, |
| "eval_steps_per_second": 0.732, |
| "step": 1200 |
| } |
| ], |
| "max_steps": 2080, |
| "num_train_epochs": 40, |
| "total_flos": 2.892968558906573e+18, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
