| { |
| "best_metric": 1.9167455434799194, |
| "best_model_checkpoint": "lora/checkpoint-50", |
| "epoch": 3.7209302325581395, |
| "eval_steps": 10, |
| "global_step": 50, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.07, |
| "learning_rate": 1.0000000000000002e-06, |
| "loss": 2.6945, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.15, |
| "learning_rate": 2.0000000000000003e-06, |
| "loss": 2.821, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.22, |
| "learning_rate": 3e-06, |
| "loss": 2.951, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.3, |
| "learning_rate": 4.000000000000001e-06, |
| "loss": 2.6822, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.37, |
| "learning_rate": 5e-06, |
| "loss": 2.7875, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.45, |
| "learning_rate": 6e-06, |
| "loss": 2.9668, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.52, |
| "learning_rate": 7.000000000000001e-06, |
| "loss": 2.6852, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.6, |
| "learning_rate": 8.000000000000001e-06, |
| "loss": 2.791, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.67, |
| "learning_rate": 9e-06, |
| "loss": 2.9174, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.74, |
| "learning_rate": 1e-05, |
| "loss": 2.6653, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.74, |
| "eval_loss": 2.7832038402557373, |
| "eval_runtime": 6.0415, |
| "eval_samples_per_second": 31.615, |
| "eval_steps_per_second": 3.973, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.82, |
| "learning_rate": 1.1000000000000001e-05, |
| "loss": 2.79, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.89, |
| "learning_rate": 1.2e-05, |
| "loss": 2.9187, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.97, |
| "learning_rate": 1.3000000000000001e-05, |
| "loss": 2.7263, |
| "step": 13 |
| }, |
| { |
| "epoch": 1.04, |
| "learning_rate": 1.4000000000000001e-05, |
| "loss": 2.7614, |
| "step": 14 |
| }, |
| { |
| "epoch": 1.12, |
| "learning_rate": 1.5e-05, |
| "loss": 2.7264, |
| "step": 15 |
| }, |
| { |
| "epoch": 1.19, |
| "learning_rate": 1.6000000000000003e-05, |
| "loss": 2.817, |
| "step": 16 |
| }, |
| { |
| "epoch": 1.27, |
| "learning_rate": 1.7000000000000003e-05, |
| "loss": 2.7676, |
| "step": 17 |
| }, |
| { |
| "epoch": 1.34, |
| "learning_rate": 1.8e-05, |
| "loss": 2.6791, |
| "step": 18 |
| }, |
| { |
| "epoch": 1.41, |
| "learning_rate": 1.9e-05, |
| "loss": 2.7726, |
| "step": 19 |
| }, |
| { |
| "epoch": 1.49, |
| "learning_rate": 2e-05, |
| "loss": 2.7456, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.49, |
| "eval_loss": 2.711270809173584, |
| "eval_runtime": 5.8906, |
| "eval_samples_per_second": 32.425, |
| "eval_steps_per_second": 4.074, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.56, |
| "learning_rate": 2.1e-05, |
| "loss": 2.6796, |
| "step": 21 |
| }, |
| { |
| "epoch": 1.64, |
| "learning_rate": 2.2000000000000003e-05, |
| "loss": 2.8011, |
| "step": 22 |
| }, |
| { |
| "epoch": 1.71, |
| "learning_rate": 2.3000000000000003e-05, |
| "loss": 2.723, |
| "step": 23 |
| }, |
| { |
| "epoch": 1.79, |
| "learning_rate": 2.4e-05, |
| "loss": 2.6006, |
| "step": 24 |
| }, |
| { |
| "epoch": 1.86, |
| "learning_rate": 2.5e-05, |
| "loss": 2.7069, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.93, |
| "learning_rate": 2.6000000000000002e-05, |
| "loss": 2.65, |
| "step": 26 |
| }, |
| { |
| "epoch": 2.01, |
| "learning_rate": 2.7000000000000002e-05, |
| "loss": 2.6998, |
| "step": 27 |
| }, |
| { |
| "epoch": 2.08, |
| "learning_rate": 2.8000000000000003e-05, |
| "loss": 2.4935, |
| "step": 28 |
| }, |
| { |
| "epoch": 2.16, |
| "learning_rate": 2.9e-05, |
| "loss": 2.6282, |
| "step": 29 |
| }, |
| { |
| "epoch": 2.23, |
| "learning_rate": 3e-05, |
| "loss": 2.6905, |
| "step": 30 |
| }, |
| { |
| "epoch": 2.23, |
| "eval_loss": 2.5354292392730713, |
| "eval_runtime": 5.7422, |
| "eval_samples_per_second": 33.262, |
| "eval_steps_per_second": 4.18, |
| "step": 30 |
| }, |
| { |
| "epoch": 2.31, |
| "learning_rate": 3.1e-05, |
| "loss": 2.4446, |
| "step": 31 |
| }, |
| { |
| "epoch": 2.38, |
| "learning_rate": 3.2000000000000005e-05, |
| "loss": 2.5132, |
| "step": 32 |
| }, |
| { |
| "epoch": 2.46, |
| "learning_rate": 3.3e-05, |
| "loss": 2.5779, |
| "step": 33 |
| }, |
| { |
| "epoch": 2.53, |
| "learning_rate": 3.4000000000000007e-05, |
| "loss": 2.3595, |
| "step": 34 |
| }, |
| { |
| "epoch": 2.6, |
| "learning_rate": 3.5e-05, |
| "loss": 2.4434, |
| "step": 35 |
| }, |
| { |
| "epoch": 2.68, |
| "learning_rate": 3.6e-05, |
| "loss": 2.4813, |
| "step": 36 |
| }, |
| { |
| "epoch": 2.75, |
| "learning_rate": 3.7e-05, |
| "loss": 2.2946, |
| "step": 37 |
| }, |
| { |
| "epoch": 2.83, |
| "learning_rate": 3.8e-05, |
| "loss": 2.3288, |
| "step": 38 |
| }, |
| { |
| "epoch": 2.9, |
| "learning_rate": 3.9000000000000006e-05, |
| "loss": 2.3864, |
| "step": 39 |
| }, |
| { |
| "epoch": 2.98, |
| "learning_rate": 4e-05, |
| "loss": 2.243, |
| "step": 40 |
| }, |
| { |
| "epoch": 2.98, |
| "eval_loss": 2.237229347229004, |
| "eval_runtime": 5.7266, |
| "eval_samples_per_second": 33.353, |
| "eval_steps_per_second": 4.191, |
| "step": 40 |
| }, |
| { |
| "epoch": 3.05, |
| "learning_rate": 4.1e-05, |
| "loss": 2.2389, |
| "step": 41 |
| }, |
| { |
| "epoch": 3.13, |
| "learning_rate": 4.2e-05, |
| "loss": 2.1705, |
| "step": 42 |
| }, |
| { |
| "epoch": 3.2, |
| "learning_rate": 4.3e-05, |
| "loss": 2.2266, |
| "step": 43 |
| }, |
| { |
| "epoch": 3.27, |
| "learning_rate": 4.4000000000000006e-05, |
| "loss": 2.1714, |
| "step": 44 |
| }, |
| { |
| "epoch": 3.35, |
| "learning_rate": 4.5e-05, |
| "loss": 2.0949, |
| "step": 45 |
| }, |
| { |
| "epoch": 3.42, |
| "learning_rate": 4.600000000000001e-05, |
| "loss": 2.1432, |
| "step": 46 |
| }, |
| { |
| "epoch": 3.5, |
| "learning_rate": 4.7e-05, |
| "loss": 2.0676, |
| "step": 47 |
| }, |
| { |
| "epoch": 3.57, |
| "learning_rate": 4.8e-05, |
| "loss": 2.0115, |
| "step": 48 |
| }, |
| { |
| "epoch": 3.65, |
| "learning_rate": 4.9e-05, |
| "loss": 2.0231, |
| "step": 49 |
| }, |
| { |
| "epoch": 3.72, |
| "learning_rate": 5e-05, |
| "loss": 1.9708, |
| "step": 50 |
| }, |
| { |
| "epoch": 3.72, |
| "eval_loss": 1.9167455434799194, |
| "eval_runtime": 5.7354, |
| "eval_samples_per_second": 33.302, |
| "eval_steps_per_second": 4.185, |
| "step": 50 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 52, |
| "num_train_epochs": 4, |
| "save_steps": 10, |
| "total_flos": 4.32902346080256e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
