| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0253164556962024, |
| "eval_steps": 20, |
| "global_step": 81, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.01, |
| "learning_rate": 0.0, |
| "loss": 0.6625, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.01, |
| "eval_loss": 0.9669284820556641, |
| "eval_runtime": 22.2599, |
| "eval_samples_per_second": 11.231, |
| "eval_steps_per_second": 2.83, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.03, |
| "learning_rate": 6.666666e-07, |
| "loss": 0.7012, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.04, |
| "learning_rate": 1.3333332e-06, |
| "loss": 0.6954, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.05, |
| "learning_rate": 1.9999997999999996e-06, |
| "loss": 0.6383, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.06, |
| "learning_rate": 2.6666664e-06, |
| "loss": 0.6993, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.08, |
| "learning_rate": 3.3333329999999998e-06, |
| "loss": 0.6388, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.09, |
| "learning_rate": 3.999999599999999e-06, |
| "loss": 0.6847, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.1, |
| "learning_rate": 4.6666662e-06, |
| "loss": 0.6973, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.11, |
| "learning_rate": 5.3333328e-06, |
| "loss": 0.703, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.13, |
| "learning_rate": 5.999999399999999e-06, |
| "loss": 0.6826, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.14, |
| "learning_rate": 6.6666659999999995e-06, |
| "loss": 0.6939, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.15, |
| "learning_rate": 7.333332599999999e-06, |
| "loss": 0.6879, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.16, |
| "learning_rate": 7.999999199999998e-06, |
| "loss": 0.687, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.18, |
| "learning_rate": 8.6666658e-06, |
| "loss": 0.6471, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.19, |
| "learning_rate": 9.3333324e-06, |
| "loss": 0.6658, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.2, |
| "learning_rate": 9.999998999999998e-06, |
| "loss": 0.6669, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.22, |
| "learning_rate": 1.06666656e-05, |
| "loss": 0.6451, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.23, |
| "learning_rate": 1.13333322e-05, |
| "loss": 0.6558, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.24, |
| "learning_rate": 1.1999998799999998e-05, |
| "loss": 0.6714, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.25, |
| "learning_rate": 1.26666654e-05, |
| "loss": 0.7123, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.25, |
| "eval_loss": 0.9579811096191406, |
| "eval_runtime": 22.7924, |
| "eval_samples_per_second": 10.969, |
| "eval_steps_per_second": 2.764, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.27, |
| "learning_rate": 1.3333331999999999e-05, |
| "loss": 0.6388, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.28, |
| "learning_rate": 1.3999998599999999e-05, |
| "loss": 0.6355, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.29, |
| "learning_rate": 1.4666665199999999e-05, |
| "loss": 0.6237, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.3, |
| "learning_rate": 1.53333318e-05, |
| "loss": 0.6214, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.32, |
| "learning_rate": 1.5999998399999997e-05, |
| "loss": 0.6045, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.33, |
| "learning_rate": 1.6666665e-05, |
| "loss": 0.671, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.34, |
| "learning_rate": 1.73333316e-05, |
| "loss": 0.6042, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.35, |
| "learning_rate": 1.7999998199999998e-05, |
| "loss": 0.6722, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.37, |
| "learning_rate": 1.86666648e-05, |
| "loss": 0.6132, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.38, |
| "learning_rate": 1.9333331399999998e-05, |
| "loss": 0.5651, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.39, |
| "learning_rate": 1.9999997999999996e-05, |
| "loss": 0.6525, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.41, |
| "learning_rate": 2.0666664599999998e-05, |
| "loss": 0.6532, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.42, |
| "learning_rate": 2.13333312e-05, |
| "loss": 0.6167, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.43, |
| "learning_rate": 2.1999997799999997e-05, |
| "loss": 0.607, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.44, |
| "learning_rate": 2.26666644e-05, |
| "loss": 0.5843, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.46, |
| "learning_rate": 2.3333330999999997e-05, |
| "loss": 0.6093, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.47, |
| "learning_rate": 2.3999997599999995e-05, |
| "loss": 0.5967, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.48, |
| "learning_rate": 2.4666664199999997e-05, |
| "loss": 0.6015, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.49, |
| "learning_rate": 2.53333308e-05, |
| "loss": 0.6263, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.51, |
| "learning_rate": 2.59999974e-05, |
| "loss": 0.5923, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.51, |
| "eval_loss": 0.9467829465866089, |
| "eval_runtime": 22.6276, |
| "eval_samples_per_second": 11.048, |
| "eval_steps_per_second": 2.784, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.52, |
| "learning_rate": 2.6666663999999998e-05, |
| "loss": 0.5801, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.53, |
| "learning_rate": 2.7333330599999996e-05, |
| "loss": 0.576, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.54, |
| "learning_rate": 2.7999997199999998e-05, |
| "loss": 0.6317, |
| "step": 43 |
| }, |
| { |
| "epoch": 0.56, |
| "learning_rate": 2.8666663799999996e-05, |
| "loss": 0.5874, |
| "step": 44 |
| }, |
| { |
| "epoch": 0.57, |
| "learning_rate": 2.9333330399999998e-05, |
| "loss": 0.6109, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.58, |
| "learning_rate": 2.9999997e-05, |
| "loss": 0.5274, |
| "step": 46 |
| }, |
| { |
| "epoch": 0.59, |
| "learning_rate": 3.06666636e-05, |
| "loss": 0.5698, |
| "step": 47 |
| }, |
| { |
| "epoch": 0.61, |
| "learning_rate": 3.133333019999999e-05, |
| "loss": 0.544, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.62, |
| "learning_rate": 3.1999996799999994e-05, |
| "loss": 0.5586, |
| "step": 49 |
| }, |
| { |
| "epoch": 0.63, |
| "learning_rate": 3.2666663399999995e-05, |
| "loss": 0.5666, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.65, |
| "learning_rate": 3.333333e-05, |
| "loss": 0.586, |
| "step": 51 |
| }, |
| { |
| "epoch": 0.66, |
| "learning_rate": 3.39999966e-05, |
| "loss": 0.6225, |
| "step": 52 |
| }, |
| { |
| "epoch": 0.67, |
| "learning_rate": 3.46666632e-05, |
| "loss": 0.5588, |
| "step": 53 |
| }, |
| { |
| "epoch": 0.68, |
| "learning_rate": 3.53333298e-05, |
| "loss": 0.5705, |
| "step": 54 |
| }, |
| { |
| "epoch": 0.7, |
| "learning_rate": 3.5999996399999996e-05, |
| "loss": 0.5628, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.71, |
| "learning_rate": 3.6666663e-05, |
| "loss": 0.5868, |
| "step": 56 |
| }, |
| { |
| "epoch": 0.72, |
| "learning_rate": 3.73333296e-05, |
| "loss": 0.5583, |
| "step": 57 |
| }, |
| { |
| "epoch": 0.73, |
| "learning_rate": 3.7999996199999994e-05, |
| "loss": 0.5858, |
| "step": 58 |
| }, |
| { |
| "epoch": 0.75, |
| "learning_rate": 3.8666662799999996e-05, |
| "loss": 0.5756, |
| "step": 59 |
| }, |
| { |
| "epoch": 0.76, |
| "learning_rate": 3.93333294e-05, |
| "loss": 0.5822, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.76, |
| "eval_loss": 0.9389348030090332, |
| "eval_runtime": 22.5892, |
| "eval_samples_per_second": 11.067, |
| "eval_steps_per_second": 2.789, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.77, |
| "learning_rate": 3.999999599999999e-05, |
| "loss": 0.5667, |
| "step": 61 |
| }, |
| { |
| "epoch": 0.78, |
| "learning_rate": 4.0666662599999994e-05, |
| "loss": 0.5616, |
| "step": 62 |
| }, |
| { |
| "epoch": 0.8, |
| "learning_rate": 4.1333329199999995e-05, |
| "loss": 0.5678, |
| "step": 63 |
| }, |
| { |
| "epoch": 0.81, |
| "learning_rate": 4.19999958e-05, |
| "loss": 0.5514, |
| "step": 64 |
| }, |
| { |
| "epoch": 0.82, |
| "learning_rate": 4.26666624e-05, |
| "loss": 0.5732, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.84, |
| "learning_rate": 4.3333329e-05, |
| "loss": 0.5794, |
| "step": 66 |
| }, |
| { |
| "epoch": 0.85, |
| "learning_rate": 4.3999995599999995e-05, |
| "loss": 0.5582, |
| "step": 67 |
| }, |
| { |
| "epoch": 0.86, |
| "learning_rate": 4.4666662199999996e-05, |
| "loss": 0.5575, |
| "step": 68 |
| }, |
| { |
| "epoch": 0.87, |
| "learning_rate": 4.53333288e-05, |
| "loss": 0.5558, |
| "step": 69 |
| }, |
| { |
| "epoch": 0.89, |
| "learning_rate": 4.599999539999999e-05, |
| "loss": 0.5707, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.9, |
| "learning_rate": 4.6666661999999994e-05, |
| "loss": 0.54, |
| "step": 71 |
| }, |
| { |
| "epoch": 0.91, |
| "learning_rate": 4.7333328599999996e-05, |
| "loss": 0.5435, |
| "step": 72 |
| }, |
| { |
| "epoch": 0.92, |
| "learning_rate": 4.799999519999999e-05, |
| "loss": 0.5649, |
| "step": 73 |
| }, |
| { |
| "epoch": 0.94, |
| "learning_rate": 4.866666179999999e-05, |
| "loss": 0.5617, |
| "step": 74 |
| }, |
| { |
| "epoch": 0.95, |
| "learning_rate": 4.9333328399999994e-05, |
| "loss": 0.5651, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.96, |
| "learning_rate": 4.9999994999999995e-05, |
| "loss": 0.5113, |
| "step": 76 |
| }, |
| { |
| "epoch": 0.97, |
| "learning_rate": 5.06666616e-05, |
| "loss": 0.5389, |
| "step": 77 |
| }, |
| { |
| "epoch": 0.99, |
| "learning_rate": 5.13333282e-05, |
| "loss": 0.5162, |
| "step": 78 |
| }, |
| { |
| "epoch": 1.0, |
| "learning_rate": 5.19999948e-05, |
| "loss": 0.5397, |
| "step": 79 |
| }, |
| { |
| "epoch": 1.01, |
| "learning_rate": 5.2666661399999995e-05, |
| "loss": 0.5794, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.01, |
| "eval_loss": 0.9314417839050293, |
| "eval_runtime": 22.7753, |
| "eval_samples_per_second": 10.977, |
| "eval_steps_per_second": 2.766, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.03, |
| "learning_rate": 5.3333327999999996e-05, |
| "loss": 0.5263, |
| "step": 81 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 395, |
| "num_train_epochs": 5, |
| "save_steps": 500, |
| "total_flos": 4.582997284010066e+17, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
