| { | |
| "best_metric": 0.7727344036102295, | |
| "best_model_checkpoint": "ckpt/origin/vehicle_environment/checkpoint-91", | |
| "epoch": 4.830917874396135, | |
| "eval_steps": 7, | |
| "global_step": 125, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0, | |
| "loss": 0.8677, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1e-05, | |
| "loss": 0.8182, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1e-05, | |
| "loss": 0.8928, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1e-05, | |
| "loss": 0.9758, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1e-05, | |
| "loss": 0.8773, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1e-05, | |
| "loss": 0.8984, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1e-05, | |
| "loss": 0.793, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 0.954296886920929, | |
| "eval_runtime": 44.1101, | |
| "eval_samples_per_second": 1.134, | |
| "eval_steps_per_second": 0.567, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1e-05, | |
| "loss": 0.8718, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1e-05, | |
| "loss": 0.8806, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1e-05, | |
| "loss": 0.7152, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1e-05, | |
| "loss": 0.7653, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1e-05, | |
| "loss": 0.7864, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1e-05, | |
| "loss": 0.7629, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 1e-05, | |
| "loss": 0.8066, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 0.8725000023841858, | |
| "eval_runtime": 43.3056, | |
| "eval_samples_per_second": 1.155, | |
| "eval_steps_per_second": 0.577, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 1e-05, | |
| "loss": 0.793, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1e-05, | |
| "loss": 0.7722, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1e-05, | |
| "loss": 0.8317, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1e-05, | |
| "loss": 0.7793, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6925, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1e-05, | |
| "loss": 0.7365, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1e-05, | |
| "loss": 0.7505, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": 0.8274219036102295, | |
| "eval_runtime": 43.2778, | |
| "eval_samples_per_second": 1.155, | |
| "eval_steps_per_second": 0.578, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1e-05, | |
| "loss": 0.7391, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 1e-05, | |
| "loss": 0.7058, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6859, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1e-05, | |
| "loss": 0.679, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6708, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6968, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6937, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "eval_loss": 0.802539050579071, | |
| "eval_runtime": 43.6, | |
| "eval_samples_per_second": 1.147, | |
| "eval_steps_per_second": 0.573, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 1e-05, | |
| "loss": 0.7578, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6307, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6949, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6743, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6814, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5865, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5945, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "eval_loss": 0.7889453172683716, | |
| "eval_runtime": 43.2969, | |
| "eval_samples_per_second": 1.155, | |
| "eval_steps_per_second": 0.577, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6505, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 1e-05, | |
| "loss": 0.7418, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6592, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6829, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 1e-05, | |
| "loss": 0.7168, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 1e-05, | |
| "loss": 0.7255, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 1e-05, | |
| "loss": 0.7029, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "eval_loss": 0.7841406464576721, | |
| "eval_runtime": 43.3346, | |
| "eval_samples_per_second": 1.154, | |
| "eval_steps_per_second": 0.577, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 1e-05, | |
| "loss": 0.589, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6757, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 1e-05, | |
| "loss": 0.7625, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6877, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6104, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6581, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6228, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "eval_loss": 0.7757421731948853, | |
| "eval_runtime": 43.3021, | |
| "eval_samples_per_second": 1.155, | |
| "eval_steps_per_second": 0.577, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 1e-05, | |
| "loss": 0.7766, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5925, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6484, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 1e-05, | |
| "loss": 0.7354, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6472, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 1e-05, | |
| "loss": 0.64, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6172, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "eval_loss": 0.7679296731948853, | |
| "eval_runtime": 43.362, | |
| "eval_samples_per_second": 1.153, | |
| "eval_steps_per_second": 0.577, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6298, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5544, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6791, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6732, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6169, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6215, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5446, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "eval_loss": 0.7676171660423279, | |
| "eval_runtime": 43.2939, | |
| "eval_samples_per_second": 1.155, | |
| "eval_steps_per_second": 0.577, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5829, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6256, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5826, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6113, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6292, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6434, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5857, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "eval_loss": 0.7694922089576721, | |
| "eval_runtime": 43.2962, | |
| "eval_samples_per_second": 1.155, | |
| "eval_steps_per_second": 0.577, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5844, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 1e-05, | |
| "loss": 0.63, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5413, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6852, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5592, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6597, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5186, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "eval_loss": 0.7741405963897705, | |
| "eval_runtime": 43.2995, | |
| "eval_samples_per_second": 1.155, | |
| "eval_steps_per_second": 0.577, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6163, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5931, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6509, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6136, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5426, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 1e-05, | |
| "loss": 0.575, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5386, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "eval_loss": 0.7715234160423279, | |
| "eval_runtime": 43.3518, | |
| "eval_samples_per_second": 1.153, | |
| "eval_steps_per_second": 0.577, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5588, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5428, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6062, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5421, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6211, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6537, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5364, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "eval_loss": 0.7727344036102295, | |
| "eval_runtime": 43.2938, | |
| "eval_samples_per_second": 1.155, | |
| "eval_steps_per_second": 0.577, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5734, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5648, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5326, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5787, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5831, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6093, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6548, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "eval_loss": 0.7698047161102295, | |
| "eval_runtime": 43.3828, | |
| "eval_samples_per_second": 1.153, | |
| "eval_steps_per_second": 0.576, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5649, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5951, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5956, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5413, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5199, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5608, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5592, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "eval_loss": 0.7690625190734863, | |
| "eval_runtime": 43.3059, | |
| "eval_samples_per_second": 1.155, | |
| "eval_steps_per_second": 0.577, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5203, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5927, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6014, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5519, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5568, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5682, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5782, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "eval_loss": 0.7662500143051147, | |
| "eval_runtime": 43.2755, | |
| "eval_samples_per_second": 1.155, | |
| "eval_steps_per_second": 0.578, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4916, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5217, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6367, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 1e-05, | |
| "loss": 0.562, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5706, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 4.56, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5658, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 1e-05, | |
| "loss": 0.549, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "eval_loss": 0.7637890577316284, | |
| "eval_runtime": 43.2782, | |
| "eval_samples_per_second": 1.155, | |
| "eval_steps_per_second": 0.578, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5286, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4961, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 4.71, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5203, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5485, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "learning_rate": 1e-05, | |
| "loss": 0.599, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4822, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "step": 125, | |
| "total_flos": 66871008165888.0, | |
| "train_loss": 0.6458125, | |
| "train_runtime": 5591.1555, | |
| "train_samples_per_second": 1.11, | |
| "train_steps_per_second": 0.022 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 125, | |
| "num_train_epochs": 5, | |
| "save_steps": 13, | |
| "total_flos": 66871008165888.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |