| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 8, |
| "global_step": 32, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.03, |
| "learning_rate": 2.0000000000000003e-06, |
| "loss": 0.9016, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.03, |
| "eval_loss": 1.1080207824707031, |
| "eval_runtime": 11.5977, |
| "eval_samples_per_second": 8.622, |
| "eval_steps_per_second": 2.932, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.06, |
| "learning_rate": 4.000000000000001e-06, |
| "loss": 1.0535, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.09, |
| "learning_rate": 6e-06, |
| "loss": 0.9383, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.12, |
| "learning_rate": 8.000000000000001e-06, |
| "loss": 0.9804, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.16, |
| "learning_rate": 1e-05, |
| "loss": 0.933, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.19, |
| "learning_rate": 1.2e-05, |
| "loss": 0.8544, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.22, |
| "learning_rate": 1.4000000000000001e-05, |
| "loss": 0.8906, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.25, |
| "learning_rate": 1.6000000000000003e-05, |
| "loss": 0.8288, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.25, |
| "eval_loss": 0.8721821904182434, |
| "eval_runtime": 11.6468, |
| "eval_samples_per_second": 8.586, |
| "eval_steps_per_second": 2.919, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.28, |
| "learning_rate": 1.8e-05, |
| "loss": 0.9369, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.31, |
| "learning_rate": 2e-05, |
| "loss": 0.8713, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.34, |
| "learning_rate": 2.2000000000000003e-05, |
| "loss": 0.9194, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.38, |
| "learning_rate": 2.4e-05, |
| "loss": 0.9693, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.41, |
| "learning_rate": 2.6000000000000002e-05, |
| "loss": 0.9782, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.44, |
| "learning_rate": 2.8000000000000003e-05, |
| "loss": 1.108, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.47, |
| "learning_rate": 3e-05, |
| "loss": 1.0411, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.5, |
| "learning_rate": 3.2000000000000005e-05, |
| "loss": 1.0797, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.5, |
| "eval_loss": 0.9858229160308838, |
| "eval_runtime": 11.6476, |
| "eval_samples_per_second": 8.585, |
| "eval_steps_per_second": 2.919, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.53, |
| "learning_rate": 3.4000000000000007e-05, |
| "loss": 1.0883, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.56, |
| "learning_rate": 3.6e-05, |
| "loss": 1.1135, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.59, |
| "learning_rate": 3.8e-05, |
| "loss": 1.1446, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.62, |
| "learning_rate": 4e-05, |
| "loss": 1.1355, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.66, |
| "learning_rate": 4.2e-05, |
| "loss": 1.1383, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.69, |
| "learning_rate": 4.4000000000000006e-05, |
| "loss": 1.1454, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.72, |
| "learning_rate": 4.600000000000001e-05, |
| "loss": 1.1797, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.75, |
| "learning_rate": 4.8e-05, |
| "loss": 1.036, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.75, |
| "eval_loss": 1.128091812133789, |
| "eval_runtime": 11.6435, |
| "eval_samples_per_second": 8.588, |
| "eval_steps_per_second": 2.92, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.78, |
| "learning_rate": 5e-05, |
| "loss": 1.146, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.81, |
| "learning_rate": 5.2000000000000004e-05, |
| "loss": 1.2633, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.84, |
| "learning_rate": 5.4000000000000005e-05, |
| "loss": 1.1635, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.88, |
| "learning_rate": 5.6000000000000006e-05, |
| "loss": 1.1703, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.91, |
| "learning_rate": 5.8e-05, |
| "loss": 1.3711, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.94, |
| "learning_rate": 6e-05, |
| "loss": 1.2206, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.97, |
| "learning_rate": 6.2e-05, |
| "loss": 1.3504, |
| "step": 31 |
| }, |
| { |
| "epoch": 1.0, |
| "learning_rate": 6.400000000000001e-05, |
| "loss": 1.4318, |
| "step": 32 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 1.2369011640548706, |
| "eval_runtime": 11.6666, |
| "eval_samples_per_second": 8.571, |
| "eval_steps_per_second": 2.914, |
| "step": 32 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 32, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 500, |
| "total_flos": 1.6776151921852416e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
