| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.9257465698143665, |
| "global_step": 14500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.1, |
| "learning_rate": 1.9327414581651872e-05, |
| "loss": 1.564, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.2, |
| "learning_rate": 1.865482916330374e-05, |
| "loss": 1.2226, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.3, |
| "learning_rate": 1.798224374495561e-05, |
| "loss": 1.0935, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.4, |
| "learning_rate": 1.730965832660748e-05, |
| "loss": 1.0043, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.5, |
| "learning_rate": 1.6637072908259352e-05, |
| "loss": 0.9485, |
| "step": 2500 |
| }, |
| { |
| "epoch": 0.61, |
| "learning_rate": 1.596448748991122e-05, |
| "loss": 0.8943, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.71, |
| "learning_rate": 1.529190207156309e-05, |
| "loss": 0.8591, |
| "step": 3500 |
| }, |
| { |
| "epoch": 0.81, |
| "learning_rate": 1.461931665321496e-05, |
| "loss": 0.8368, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.91, |
| "learning_rate": 1.3946731234866828e-05, |
| "loss": 0.8083, |
| "step": 4500 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.8127919435501099, |
| "eval_runtime": 4016.0168, |
| "eval_samples_per_second": 13.347, |
| "eval_steps_per_second": 1.669, |
| "step": 4956 |
| }, |
| { |
| "epoch": 1.01, |
| "learning_rate": 1.3274145816518699e-05, |
| "loss": 0.7892, |
| "step": 5000 |
| }, |
| { |
| "epoch": 1.11, |
| "learning_rate": 1.260156039817057e-05, |
| "loss": 0.7637, |
| "step": 5500 |
| }, |
| { |
| "epoch": 1.21, |
| "learning_rate": 1.1928974979822439e-05, |
| "loss": 0.7426, |
| "step": 6000 |
| }, |
| { |
| "epoch": 1.31, |
| "learning_rate": 1.1256389561474308e-05, |
| "loss": 0.7256, |
| "step": 6500 |
| }, |
| { |
| "epoch": 1.41, |
| "learning_rate": 1.0583804143126177e-05, |
| "loss": 0.7224, |
| "step": 7000 |
| }, |
| { |
| "epoch": 1.51, |
| "learning_rate": 9.911218724778048e-06, |
| "loss": 0.7081, |
| "step": 7500 |
| }, |
| { |
| "epoch": 1.61, |
| "learning_rate": 9.238633306429917e-06, |
| "loss": 0.6939, |
| "step": 8000 |
| }, |
| { |
| "epoch": 1.72, |
| "learning_rate": 8.566047888081786e-06, |
| "loss": 0.6842, |
| "step": 8500 |
| }, |
| { |
| "epoch": 1.82, |
| "learning_rate": 7.893462469733657e-06, |
| "loss": 0.6675, |
| "step": 9000 |
| }, |
| { |
| "epoch": 1.92, |
| "learning_rate": 7.220877051385527e-06, |
| "loss": 0.6621, |
| "step": 9500 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.7235483527183533, |
| "eval_runtime": 3969.5306, |
| "eval_samples_per_second": 13.503, |
| "eval_steps_per_second": 1.688, |
| "step": 9912 |
| }, |
| { |
| "epoch": 2.02, |
| "learning_rate": 6.548291633037396e-06, |
| "loss": 0.6682, |
| "step": 10000 |
| }, |
| { |
| "epoch": 2.12, |
| "learning_rate": 5.8757062146892665e-06, |
| "loss": 0.6388, |
| "step": 10500 |
| }, |
| { |
| "epoch": 2.22, |
| "learning_rate": 5.203120796341136e-06, |
| "loss": 0.6469, |
| "step": 11000 |
| }, |
| { |
| "epoch": 2.32, |
| "learning_rate": 4.5305353779930055e-06, |
| "loss": 0.6288, |
| "step": 11500 |
| }, |
| { |
| "epoch": 2.42, |
| "learning_rate": 3.8579499596448746e-06, |
| "loss": 0.6279, |
| "step": 12000 |
| }, |
| { |
| "epoch": 2.52, |
| "learning_rate": 3.185364541296745e-06, |
| "loss": 0.6363, |
| "step": 12500 |
| }, |
| { |
| "epoch": 2.62, |
| "learning_rate": 2.512779122948615e-06, |
| "loss": 0.6203, |
| "step": 13000 |
| }, |
| { |
| "epoch": 2.72, |
| "learning_rate": 1.8401937046004845e-06, |
| "loss": 0.6193, |
| "step": 13500 |
| }, |
| { |
| "epoch": 2.82, |
| "learning_rate": 1.167608286252354e-06, |
| "loss": 0.62, |
| "step": 14000 |
| }, |
| { |
| "epoch": 2.93, |
| "learning_rate": 4.950228679042239e-07, |
| "loss": 0.6088, |
| "step": 14500 |
| } |
| ], |
| "max_steps": 14868, |
| "num_train_epochs": 3, |
| "total_flos": 3845568214844928.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
