| { | |
| "best_metric": 3648.62841796875, | |
| "best_model_checkpoint": "./ckpts/tiny_llama_v1.1/int1-g128/checkpoint-400", | |
| "epoch": 4.0, | |
| "eval_steps": 4, | |
| "global_step": 400, | |
| "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": 11380.3086, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 2e-05, | |
| "loss": 12868.3359, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2e-05, | |
| "loss": 12883.2969, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 2e-05, | |
| "loss": 11909.3701, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 10881.7998046875, | |
| "eval_runtime": 94.8632, | |
| "eval_samples_per_second": 16.824, | |
| "eval_steps_per_second": 1.054, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 2e-05, | |
| "loss": 10834.709, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 2e-05, | |
| "loss": 11078.376, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 2e-05, | |
| "loss": 8636.8652, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 2e-05, | |
| "loss": 9161.7168, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 7404.39404296875, | |
| "eval_runtime": 95.0792, | |
| "eval_samples_per_second": 16.786, | |
| "eval_steps_per_second": 1.052, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 2e-05, | |
| "loss": 8061.96, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 2e-05, | |
| "loss": 7025.2109, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 2e-05, | |
| "loss": 10119.207, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 2e-05, | |
| "loss": 8901.1523, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 7435.04150390625, | |
| "eval_runtime": 95.107, | |
| "eval_samples_per_second": 16.781, | |
| "eval_steps_per_second": 1.051, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 2e-05, | |
| "loss": 6522.3311, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 2e-05, | |
| "loss": 7874.7578, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 2e-05, | |
| "loss": 7117.9897, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 2e-05, | |
| "loss": 7384.1929, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 7038.021484375, | |
| "eval_runtime": 95.1143, | |
| "eval_samples_per_second": 16.78, | |
| "eval_steps_per_second": 1.051, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 2e-05, | |
| "loss": 6837.7974, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 2e-05, | |
| "loss": 6401.292, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 2e-05, | |
| "loss": 7396.1997, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 2e-05, | |
| "loss": 5846.4893, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 6782.6787109375, | |
| "eval_runtime": 95.1226, | |
| "eval_samples_per_second": 16.778, | |
| "eval_steps_per_second": 1.051, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 2e-05, | |
| "loss": 7062.3677, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 2e-05, | |
| "loss": 6488.6855, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 2e-05, | |
| "loss": 7019.1787, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 2e-05, | |
| "loss": 6871.1865, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 6575.58154296875, | |
| "eval_runtime": 95.0095, | |
| "eval_samples_per_second": 16.798, | |
| "eval_steps_per_second": 1.053, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 2e-05, | |
| "loss": 6340.9995, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 2e-05, | |
| "loss": 6536.9585, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 2e-05, | |
| "loss": 6144.7646, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 2e-05, | |
| "loss": 6152.7886, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 6434.06640625, | |
| "eval_runtime": 95.1456, | |
| "eval_samples_per_second": 16.774, | |
| "eval_steps_per_second": 1.051, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 2e-05, | |
| "loss": 5927.832, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 2e-05, | |
| "loss": 6375.9375, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 2e-05, | |
| "loss": 6714.1953, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 2e-05, | |
| "loss": 5591.8081, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 6206.52197265625, | |
| "eval_runtime": 95.0989, | |
| "eval_samples_per_second": 16.783, | |
| "eval_steps_per_second": 1.052, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 2e-05, | |
| "loss": 6417.4902, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 2e-05, | |
| "loss": 5807.3662, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 2e-05, | |
| "loss": 6891.5049, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 2e-05, | |
| "loss": 6353.3838, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 6035.97705078125, | |
| "eval_runtime": 95.1008, | |
| "eval_samples_per_second": 16.782, | |
| "eval_steps_per_second": 1.052, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 2e-05, | |
| "loss": 5999.5938, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 2e-05, | |
| "loss": 5384.0732, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 2e-05, | |
| "loss": 6043.8564, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 2e-05, | |
| "loss": 5397.1992, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 5899.00927734375, | |
| "eval_runtime": 95.1465, | |
| "eval_samples_per_second": 16.774, | |
| "eval_steps_per_second": 1.051, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 2e-05, | |
| "loss": 5770.0815, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 2e-05, | |
| "loss": 5922.8789, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 2e-05, | |
| "loss": 5941.6562, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 2e-05, | |
| "loss": 6474.5508, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 5830.09716796875, | |
| "eval_runtime": 94.9508, | |
| "eval_samples_per_second": 16.809, | |
| "eval_steps_per_second": 1.053, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 2e-05, | |
| "loss": 6641.1704, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 2e-05, | |
| "loss": 5292.1631, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 2e-05, | |
| "loss": 5402.1309, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 2e-05, | |
| "loss": 5108.5684, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 5756.92724609375, | |
| "eval_runtime": 95.3749, | |
| "eval_samples_per_second": 16.734, | |
| "eval_steps_per_second": 1.048, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 2e-05, | |
| "loss": 5287.3154, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 2e-05, | |
| "loss": 5745.0361, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 2e-05, | |
| "loss": 5594.8262, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 2e-05, | |
| "loss": 6582.165, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": 5648.44091796875, | |
| "eval_runtime": 95.5253, | |
| "eval_samples_per_second": 16.708, | |
| "eval_steps_per_second": 1.047, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 2e-05, | |
| "loss": 6087.4844, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 2e-05, | |
| "loss": 6035.2637, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 2e-05, | |
| "loss": 6145.3789, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 2e-05, | |
| "loss": 5178.7305, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": 5449.46240234375, | |
| "eval_runtime": 95.1764, | |
| "eval_samples_per_second": 16.769, | |
| "eval_steps_per_second": 1.051, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 2e-05, | |
| "loss": 5329.77, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 2e-05, | |
| "loss": 6133.9678, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 2e-05, | |
| "loss": 5170.7642, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 2e-05, | |
| "loss": 4754.7891, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 5294.06494140625, | |
| "eval_runtime": 95.2108, | |
| "eval_samples_per_second": 16.763, | |
| "eval_steps_per_second": 1.05, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 2e-05, | |
| "loss": 5026.2295, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 2e-05, | |
| "loss": 5056.1416, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 2e-05, | |
| "loss": 4999.1313, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 2e-05, | |
| "loss": 5597.2129, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 5080.79638671875, | |
| "eval_runtime": 95.0431, | |
| "eval_samples_per_second": 16.792, | |
| "eval_steps_per_second": 1.052, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 2e-05, | |
| "loss": 5225.0186, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 2e-05, | |
| "loss": 4696.772, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 2e-05, | |
| "loss": 4756.3345, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 2e-05, | |
| "loss": 5449.8564, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 4948.94287109375, | |
| "eval_runtime": 95.1267, | |
| "eval_samples_per_second": 16.778, | |
| "eval_steps_per_second": 1.051, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2e-05, | |
| "loss": 5115.0347, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2e-05, | |
| "loss": 4621.6206, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 2e-05, | |
| "loss": 4672.1475, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 2e-05, | |
| "loss": 5242.2466, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 4875.96826171875, | |
| "eval_runtime": 95.1339, | |
| "eval_samples_per_second": 16.776, | |
| "eval_steps_per_second": 1.051, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 2e-05, | |
| "loss": 4792.4268, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 2e-05, | |
| "loss": 4925.5439, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 2e-05, | |
| "loss": 4519.2134, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 2e-05, | |
| "loss": 4790.4316, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 4870.0810546875, | |
| "eval_runtime": 95.1754, | |
| "eval_samples_per_second": 16.769, | |
| "eval_steps_per_second": 1.051, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 2e-05, | |
| "loss": 5035.2295, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 2e-05, | |
| "loss": 4832.3154, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 2e-05, | |
| "loss": 5150.7158, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 2e-05, | |
| "loss": 4470.4863, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 4762.04150390625, | |
| "eval_runtime": 95.1952, | |
| "eval_samples_per_second": 16.766, | |
| "eval_steps_per_second": 1.05, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 2e-05, | |
| "loss": 4649.1685, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 2e-05, | |
| "loss": 4672.1406, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 2e-05, | |
| "loss": 5002.249, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 2e-05, | |
| "loss": 4852.25, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_loss": 4709.67431640625, | |
| "eval_runtime": 95.0691, | |
| "eval_samples_per_second": 16.788, | |
| "eval_steps_per_second": 1.052, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 2e-05, | |
| "loss": 4892.4893, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 2e-05, | |
| "loss": 4282.9248, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 2e-05, | |
| "loss": 4886.5312, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 2e-05, | |
| "loss": 4792.9912, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_loss": 4597.8984375, | |
| "eval_runtime": 95.2285, | |
| "eval_samples_per_second": 16.76, | |
| "eval_steps_per_second": 1.05, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 2e-05, | |
| "loss": 3879.5151, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 2e-05, | |
| "loss": 4130.7891, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 2e-05, | |
| "loss": 4897.5684, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 2e-05, | |
| "loss": 5063.8096, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_loss": 4595.23046875, | |
| "eval_runtime": 95.2271, | |
| "eval_samples_per_second": 16.76, | |
| "eval_steps_per_second": 1.05, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 2e-05, | |
| "loss": 4932.4224, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 2e-05, | |
| "loss": 4803.2412, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 2e-05, | |
| "loss": 4688.5557, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 2e-05, | |
| "loss": 4638.0762, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 4560.80810546875, | |
| "eval_runtime": 95.1641, | |
| "eval_samples_per_second": 16.771, | |
| "eval_steps_per_second": 1.051, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 2e-05, | |
| "loss": 4238.0225, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 2e-05, | |
| "loss": 4853.1382, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 2e-05, | |
| "loss": 5206.4658, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 2e-05, | |
| "loss": 3976.3425, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 4543.9541015625, | |
| "eval_runtime": 95.1889, | |
| "eval_samples_per_second": 16.767, | |
| "eval_steps_per_second": 1.051, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 2e-05, | |
| "loss": 4047.6965, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 2e-05, | |
| "loss": 4423.4912, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 2e-05, | |
| "loss": 4422.5103, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 2e-05, | |
| "loss": 4676.5659, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "eval_loss": 4510.7314453125, | |
| "eval_runtime": 95.0706, | |
| "eval_samples_per_second": 16.788, | |
| "eval_steps_per_second": 1.052, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 2e-05, | |
| "loss": 4369.8477, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 2e-05, | |
| "loss": 4672.6108, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 2e-05, | |
| "loss": 4738.3755, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 2e-05, | |
| "loss": 4361.5522, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "eval_loss": 4447.572265625, | |
| "eval_runtime": 95.1237, | |
| "eval_samples_per_second": 16.778, | |
| "eval_steps_per_second": 1.051, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 2e-05, | |
| "loss": 4602.5703, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 2e-05, | |
| "loss": 4380.708, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 2e-05, | |
| "loss": 4037.3726, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 2e-05, | |
| "loss": 4673.7178, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "eval_loss": 4398.06640625, | |
| "eval_runtime": 95.1992, | |
| "eval_samples_per_second": 16.765, | |
| "eval_steps_per_second": 1.05, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 2e-05, | |
| "loss": 4349.0542, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 2e-05, | |
| "loss": 4754.3525, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 2e-05, | |
| "loss": 3983.9561, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 2e-05, | |
| "loss": 3387.5273, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "eval_loss": 4363.39501953125, | |
| "eval_runtime": 95.226, | |
| "eval_samples_per_second": 16.76, | |
| "eval_steps_per_second": 1.05, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 2e-05, | |
| "loss": 4539.5605, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 2e-05, | |
| "loss": 4573.0249, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 2e-05, | |
| "loss": 4173.1982, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 2e-05, | |
| "loss": 4301.8296, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_loss": 4314.70166015625, | |
| "eval_runtime": 95.1567, | |
| "eval_samples_per_second": 16.772, | |
| "eval_steps_per_second": 1.051, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 2e-05, | |
| "loss": 4462.0898, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 2e-05, | |
| "loss": 4151.0615, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 2e-05, | |
| "loss": 4575.5889, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 2e-05, | |
| "loss": 4630.2876, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "eval_loss": 4325.21875, | |
| "eval_runtime": 95.0575, | |
| "eval_samples_per_second": 16.79, | |
| "eval_steps_per_second": 1.052, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 2e-05, | |
| "loss": 4619.9248, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 2e-05, | |
| "loss": 3764.6904, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 2e-05, | |
| "loss": 4107.4839, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 2e-05, | |
| "loss": 4439.1548, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "eval_loss": 4270.97998046875, | |
| "eval_runtime": 95.2025, | |
| "eval_samples_per_second": 16.764, | |
| "eval_steps_per_second": 1.05, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 2e-05, | |
| "loss": 4332.3652, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 2e-05, | |
| "loss": 4009.8579, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 2e-05, | |
| "loss": 4263.3091, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 2e-05, | |
| "loss": 4529.6118, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "eval_loss": 4247.3193359375, | |
| "eval_runtime": 95.1903, | |
| "eval_samples_per_second": 16.766, | |
| "eval_steps_per_second": 1.051, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 2e-05, | |
| "loss": 4782.1045, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 2e-05, | |
| "loss": 4572.3145, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 2e-05, | |
| "loss": 3709.7561, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 2e-05, | |
| "loss": 5060.5757, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "eval_loss": 4267.9052734375, | |
| "eval_runtime": 95.2344, | |
| "eval_samples_per_second": 16.759, | |
| "eval_steps_per_second": 1.05, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 2e-05, | |
| "loss": 4048.5073, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 2e-05, | |
| "loss": 4337.002, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2e-05, | |
| "loss": 4471.6353, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 2e-05, | |
| "loss": 4257.4619, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "eval_loss": 4241.09912109375, | |
| "eval_runtime": 95.1639, | |
| "eval_samples_per_second": 16.771, | |
| "eval_steps_per_second": 1.051, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 2e-05, | |
| "loss": 4113.8926, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 2e-05, | |
| "loss": 4255.1045, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 2e-05, | |
| "loss": 4150.0469, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 2e-05, | |
| "loss": 4069.4043, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "eval_loss": 4201.818359375, | |
| "eval_runtime": 95.2146, | |
| "eval_samples_per_second": 16.762, | |
| "eval_steps_per_second": 1.05, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 2e-05, | |
| "loss": 4251.7646, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 2e-05, | |
| "loss": 4371.7056, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 2e-05, | |
| "loss": 4043.783, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 2e-05, | |
| "loss": 3856.8018, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "eval_loss": 4195.00439453125, | |
| "eval_runtime": 95.3553, | |
| "eval_samples_per_second": 16.737, | |
| "eval_steps_per_second": 1.049, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 2e-05, | |
| "loss": 4359.2188, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 2e-05, | |
| "loss": 4015.7729, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 2e-05, | |
| "loss": 4574.147, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 2e-05, | |
| "loss": 4308.5566, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "eval_loss": 4192.68798828125, | |
| "eval_runtime": 95.3592, | |
| "eval_samples_per_second": 16.737, | |
| "eval_steps_per_second": 1.049, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 2e-05, | |
| "loss": 3850.4014, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 2e-05, | |
| "loss": 4326.3857, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 2e-05, | |
| "loss": 4223.0674, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 2e-05, | |
| "loss": 4567.7056, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "eval_loss": 4181.10009765625, | |
| "eval_runtime": 95.2118, | |
| "eval_samples_per_second": 16.763, | |
| "eval_steps_per_second": 1.05, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 2e-05, | |
| "loss": 4342.7461, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 2e-05, | |
| "loss": 3950.2617, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 2e-05, | |
| "loss": 3843.9983, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 2e-05, | |
| "loss": 4143.4326, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_loss": 4187.84912109375, | |
| "eval_runtime": 95.4267, | |
| "eval_samples_per_second": 16.725, | |
| "eval_steps_per_second": 1.048, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 2e-05, | |
| "loss": 5007.4238, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 2e-05, | |
| "loss": 4008.7954, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 2e-05, | |
| "loss": 3739.9316, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 2e-05, | |
| "loss": 3865.8225, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "eval_loss": 4126.61669921875, | |
| "eval_runtime": 95.1828, | |
| "eval_samples_per_second": 16.768, | |
| "eval_steps_per_second": 1.051, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 2e-05, | |
| "loss": 4461.7637, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 2e-05, | |
| "loss": 3879.4729, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 2e-05, | |
| "loss": 3731.812, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 2e-05, | |
| "loss": 4175.4346, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "eval_loss": 4113.404296875, | |
| "eval_runtime": 95.5754, | |
| "eval_samples_per_second": 16.699, | |
| "eval_steps_per_second": 1.046, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 2e-05, | |
| "loss": 3942.5459, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 2e-05, | |
| "loss": 4637.8037, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 2e-05, | |
| "loss": 4628.354, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 2e-05, | |
| "loss": 4403.8843, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "eval_loss": 4094.84375, | |
| "eval_runtime": 95.3998, | |
| "eval_samples_per_second": 16.73, | |
| "eval_steps_per_second": 1.048, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 2e-05, | |
| "loss": 3811.9785, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 2e-05, | |
| "loss": 4257.5371, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 2e-05, | |
| "loss": 3668.6951, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 2e-05, | |
| "loss": 3921.7227, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "eval_loss": 4081.22021484375, | |
| "eval_runtime": 95.4773, | |
| "eval_samples_per_second": 16.716, | |
| "eval_steps_per_second": 1.047, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 2e-05, | |
| "loss": 3529.4546, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 2e-05, | |
| "loss": 4019.564, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 2e-05, | |
| "loss": 4207.9526, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 2e-05, | |
| "loss": 4506.7544, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "eval_loss": 4089.59033203125, | |
| "eval_runtime": 95.5353, | |
| "eval_samples_per_second": 16.706, | |
| "eval_steps_per_second": 1.047, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 2e-05, | |
| "loss": 3739.2524, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 2e-05, | |
| "loss": 4080.3894, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 2e-05, | |
| "loss": 3937.1353, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 2e-05, | |
| "loss": 4788.46, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "eval_loss": 4071.869140625, | |
| "eval_runtime": 95.2152, | |
| "eval_samples_per_second": 16.762, | |
| "eval_steps_per_second": 1.05, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 2e-05, | |
| "loss": 3903.95, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 2e-05, | |
| "loss": 4017.4819, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 2e-05, | |
| "loss": 3605.0239, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 2e-05, | |
| "loss": 4021.0627, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "eval_loss": 4055.228271484375, | |
| "eval_runtime": 95.2891, | |
| "eval_samples_per_second": 16.749, | |
| "eval_steps_per_second": 1.049, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 2e-05, | |
| "loss": 3843.1729, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 2e-05, | |
| "loss": 3957.4761, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 2e-05, | |
| "loss": 4018.5742, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 2e-05, | |
| "loss": 3802.7734, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "eval_loss": 4049.432373046875, | |
| "eval_runtime": 95.3586, | |
| "eval_samples_per_second": 16.737, | |
| "eval_steps_per_second": 1.049, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 2e-05, | |
| "loss": 4562.4453, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 2e-05, | |
| "loss": 3944.2036, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 2e-05, | |
| "loss": 4023.9956, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 2e-05, | |
| "loss": 4351.9863, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "eval_loss": 4015.07373046875, | |
| "eval_runtime": 95.1955, | |
| "eval_samples_per_second": 16.766, | |
| "eval_steps_per_second": 1.05, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 2e-05, | |
| "loss": 3598.9106, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 2e-05, | |
| "loss": 3748.6475, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 2e-05, | |
| "loss": 3714.1748, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 2e-05, | |
| "loss": 4423.7349, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 4013.801025390625, | |
| "eval_runtime": 95.1615, | |
| "eval_samples_per_second": 16.771, | |
| "eval_steps_per_second": 1.051, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 2e-05, | |
| "loss": 3955.9373, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 2e-05, | |
| "loss": 4049.354, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 2e-05, | |
| "loss": 4312.8247, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 2e-05, | |
| "loss": 3894.739, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "eval_loss": 4020.21240234375, | |
| "eval_runtime": 94.9862, | |
| "eval_samples_per_second": 16.802, | |
| "eval_steps_per_second": 1.053, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 2e-05, | |
| "loss": 3237.6282, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 2e-05, | |
| "loss": 4196.6562, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 2e-05, | |
| "loss": 4185.1821, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 2e-05, | |
| "loss": 3637.6782, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "eval_loss": 4004.71826171875, | |
| "eval_runtime": 95.0911, | |
| "eval_samples_per_second": 16.784, | |
| "eval_steps_per_second": 1.052, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 2e-05, | |
| "loss": 3988.9346, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 2e-05, | |
| "loss": 3972.2412, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 2e-05, | |
| "loss": 4046.356, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 2e-05, | |
| "loss": 4103.7446, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "eval_loss": 3999.879150390625, | |
| "eval_runtime": 95.151, | |
| "eval_samples_per_second": 16.773, | |
| "eval_steps_per_second": 1.051, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 2e-05, | |
| "loss": 4567.3848, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 2e-05, | |
| "loss": 4096.2393, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 2e-05, | |
| "loss": 3677.2112, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 2e-05, | |
| "loss": 3869.1951, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "eval_loss": 3975.71240234375, | |
| "eval_runtime": 95.223, | |
| "eval_samples_per_second": 16.761, | |
| "eval_steps_per_second": 1.05, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 2e-05, | |
| "loss": 4281.8516, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 2e-05, | |
| "loss": 4052.2227, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 2e-05, | |
| "loss": 4156.7637, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 2e-05, | |
| "loss": 3435.3076, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "eval_loss": 3955.1552734375, | |
| "eval_runtime": 95.1337, | |
| "eval_samples_per_second": 16.776, | |
| "eval_steps_per_second": 1.051, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 2e-05, | |
| "loss": 3932.6658, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 2e-05, | |
| "loss": 3382.2915, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 2e-05, | |
| "loss": 3378.9287, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 2e-05, | |
| "loss": 3811.2612, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "eval_loss": 3958.28759765625, | |
| "eval_runtime": 94.998, | |
| "eval_samples_per_second": 16.8, | |
| "eval_steps_per_second": 1.053, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 2e-05, | |
| "loss": 4169.3755, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 2e-05, | |
| "loss": 4260.3926, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 2e-05, | |
| "loss": 4086.002, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 2e-05, | |
| "loss": 4149.6416, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "eval_loss": 3951.014404296875, | |
| "eval_runtime": 95.1617, | |
| "eval_samples_per_second": 16.771, | |
| "eval_steps_per_second": 1.051, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 2e-05, | |
| "loss": 3471.564, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 2e-05, | |
| "loss": 3824.6528, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 2e-05, | |
| "loss": 3360.2578, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 2e-05, | |
| "loss": 3621.5127, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "eval_loss": 3957.65380859375, | |
| "eval_runtime": 95.1799, | |
| "eval_samples_per_second": 16.768, | |
| "eval_steps_per_second": 1.051, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 2e-05, | |
| "loss": 4050.9973, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 2e-05, | |
| "loss": 4221.9043, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 2e-05, | |
| "loss": 3668.5938, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 2e-05, | |
| "loss": 3374.7612, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "eval_loss": 3935.7607421875, | |
| "eval_runtime": 95.1897, | |
| "eval_samples_per_second": 16.767, | |
| "eval_steps_per_second": 1.051, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 2e-05, | |
| "loss": 3811.7754, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 2e-05, | |
| "loss": 3923.9185, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 2e-05, | |
| "loss": 3072.0181, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 2e-05, | |
| "loss": 4219.8125, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_loss": 3909.99560546875, | |
| "eval_runtime": 95.2009, | |
| "eval_samples_per_second": 16.765, | |
| "eval_steps_per_second": 1.05, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 2e-05, | |
| "loss": 4093.2798, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 2e-05, | |
| "loss": 4144.9243, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 2e-05, | |
| "loss": 3701.4731, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 2e-05, | |
| "loss": 3713.2314, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "eval_loss": 3911.078857421875, | |
| "eval_runtime": 95.0383, | |
| "eval_samples_per_second": 16.793, | |
| "eval_steps_per_second": 1.052, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 2e-05, | |
| "loss": 3543.9497, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 2e-05, | |
| "loss": 3692.1785, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 2e-05, | |
| "loss": 4061.7036, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 2e-05, | |
| "loss": 3513.0017, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "eval_loss": 3910.442626953125, | |
| "eval_runtime": 95.2387, | |
| "eval_samples_per_second": 16.758, | |
| "eval_steps_per_second": 1.05, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 2e-05, | |
| "loss": 4166.7217, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 2e-05, | |
| "loss": 3680.3262, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 2e-05, | |
| "loss": 3960.1064, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 2e-05, | |
| "loss": 3358.9592, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "eval_loss": 3899.7275390625, | |
| "eval_runtime": 95.1727, | |
| "eval_samples_per_second": 16.77, | |
| "eval_steps_per_second": 1.051, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 2e-05, | |
| "loss": 3664.8364, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 2e-05, | |
| "loss": 3645.0352, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 2e-05, | |
| "loss": 4320.4873, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 2e-05, | |
| "loss": 4029.3306, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "eval_loss": 3905.114013671875, | |
| "eval_runtime": 95.1752, | |
| "eval_samples_per_second": 16.769, | |
| "eval_steps_per_second": 1.051, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 2e-05, | |
| "loss": 4058.9121, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 2e-05, | |
| "loss": 4163.0127, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 2e-05, | |
| "loss": 3698.998, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 2e-05, | |
| "loss": 3724.9954, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "eval_loss": 3902.5595703125, | |
| "eval_runtime": 95.1954, | |
| "eval_samples_per_second": 16.766, | |
| "eval_steps_per_second": 1.05, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 2e-05, | |
| "loss": 4149.5771, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 2e-05, | |
| "loss": 3952.4429, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 2e-05, | |
| "loss": 3482.0449, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 2e-05, | |
| "loss": 3825.3076, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "eval_loss": 3882.601806640625, | |
| "eval_runtime": 95.0573, | |
| "eval_samples_per_second": 16.79, | |
| "eval_steps_per_second": 1.052, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 2e-05, | |
| "loss": 3698.0227, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 2e-05, | |
| "loss": 3797.3899, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 2e-05, | |
| "loss": 3853.0374, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 2e-05, | |
| "loss": 3591.9854, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "eval_loss": 3878.234375, | |
| "eval_runtime": 95.1839, | |
| "eval_samples_per_second": 16.768, | |
| "eval_steps_per_second": 1.051, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 2e-05, | |
| "loss": 3889.3989, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 2e-05, | |
| "loss": 3946.7024, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 2e-05, | |
| "loss": 4180.001, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 2e-05, | |
| "loss": 3440.269, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "eval_loss": 3873.271728515625, | |
| "eval_runtime": 95.2614, | |
| "eval_samples_per_second": 16.754, | |
| "eval_steps_per_second": 1.05, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 2e-05, | |
| "loss": 3619.1611, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 2e-05, | |
| "loss": 3825.2026, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 2e-05, | |
| "loss": 4002.6731, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 2e-05, | |
| "loss": 3595.2097, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "eval_loss": 3864.229248046875, | |
| "eval_runtime": 95.4953, | |
| "eval_samples_per_second": 16.713, | |
| "eval_steps_per_second": 1.047, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 2e-05, | |
| "loss": 3813.6006, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 2e-05, | |
| "loss": 4163.6484, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 2e-05, | |
| "loss": 3158.1484, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 2e-05, | |
| "loss": 3456.5925, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "eval_loss": 3866.61767578125, | |
| "eval_runtime": 95.7468, | |
| "eval_samples_per_second": 16.669, | |
| "eval_steps_per_second": 1.044, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 2e-05, | |
| "loss": 3924.3809, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 2e-05, | |
| "loss": 4106.1128, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 2e-05, | |
| "loss": 3968.1797, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 2e-05, | |
| "loss": 3913.6394, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "eval_loss": 3853.93505859375, | |
| "eval_runtime": 95.3329, | |
| "eval_samples_per_second": 16.741, | |
| "eval_steps_per_second": 1.049, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 2e-05, | |
| "loss": 3787.5688, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 2e-05, | |
| "loss": 4051.9841, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 2e-05, | |
| "loss": 3468.6104, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 2e-05, | |
| "loss": 4153.1147, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "eval_loss": 3836.56201171875, | |
| "eval_runtime": 95.4516, | |
| "eval_samples_per_second": 16.721, | |
| "eval_steps_per_second": 1.048, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 2e-05, | |
| "loss": 3588.4766, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 2e-05, | |
| "loss": 3939.7871, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 2e-05, | |
| "loss": 4142.5205, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 2e-05, | |
| "loss": 3433.5652, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "eval_loss": 3846.0400390625, | |
| "eval_runtime": 95.5865, | |
| "eval_samples_per_second": 16.697, | |
| "eval_steps_per_second": 1.046, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 2e-05, | |
| "loss": 3704.4355, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 2e-05, | |
| "loss": 3561.1382, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 2e-05, | |
| "loss": 4084.75, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 2e-05, | |
| "loss": 3592.4402, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "eval_loss": 3824.31298828125, | |
| "eval_runtime": 95.6271, | |
| "eval_samples_per_second": 16.69, | |
| "eval_steps_per_second": 1.046, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 2e-05, | |
| "loss": 3653.906, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 2e-05, | |
| "loss": 3920.9485, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 2e-05, | |
| "loss": 4010.104, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 2e-05, | |
| "loss": 4472.293, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 3811.89013671875, | |
| "eval_runtime": 95.218, | |
| "eval_samples_per_second": 16.762, | |
| "eval_steps_per_second": 1.05, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 2e-05, | |
| "loss": 4144.3301, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 2e-05, | |
| "loss": 3661.8413, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 2e-05, | |
| "loss": 4158.1958, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 2e-05, | |
| "loss": 3705.3564, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "eval_loss": 3801.527587890625, | |
| "eval_runtime": 95.4031, | |
| "eval_samples_per_second": 16.729, | |
| "eval_steps_per_second": 1.048, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 2e-05, | |
| "loss": 3678.627, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 2e-05, | |
| "loss": 3692.2642, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 2e-05, | |
| "loss": 4010.1907, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 2e-05, | |
| "loss": 3680.8633, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "eval_loss": 3794.080322265625, | |
| "eval_runtime": 95.2615, | |
| "eval_samples_per_second": 16.754, | |
| "eval_steps_per_second": 1.05, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 2e-05, | |
| "loss": 4088.3789, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 2e-05, | |
| "loss": 3263.083, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 2e-05, | |
| "loss": 3412.7646, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 2e-05, | |
| "loss": 2886.2148, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "eval_loss": 3781.141357421875, | |
| "eval_runtime": 95.4625, | |
| "eval_samples_per_second": 16.719, | |
| "eval_steps_per_second": 1.048, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 2e-05, | |
| "loss": 3421.999, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 2e-05, | |
| "loss": 4785.0142, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 2e-05, | |
| "loss": 3859.052, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 2e-05, | |
| "loss": 3919.5405, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "eval_loss": 3814.05224609375, | |
| "eval_runtime": 95.377, | |
| "eval_samples_per_second": 16.734, | |
| "eval_steps_per_second": 1.048, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 2e-05, | |
| "loss": 3466.0466, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 2e-05, | |
| "loss": 3382.6812, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 2e-05, | |
| "loss": 3554.6763, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 2e-05, | |
| "loss": 3869.5581, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "eval_loss": 3784.0302734375, | |
| "eval_runtime": 95.3698, | |
| "eval_samples_per_second": 16.735, | |
| "eval_steps_per_second": 1.049, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 2e-05, | |
| "loss": 3639.7705, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 2e-05, | |
| "loss": 3887.6313, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 2e-05, | |
| "loss": 3908.9287, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 2e-05, | |
| "loss": 3672.9302, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "eval_loss": 3771.347412109375, | |
| "eval_runtime": 95.2036, | |
| "eval_samples_per_second": 16.764, | |
| "eval_steps_per_second": 1.05, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 2e-05, | |
| "loss": 3436.8274, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 2e-05, | |
| "loss": 3314.8804, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 2e-05, | |
| "loss": 4389.9253, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 2e-05, | |
| "loss": 4018.4453, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "eval_loss": 3771.130859375, | |
| "eval_runtime": 95.3816, | |
| "eval_samples_per_second": 16.733, | |
| "eval_steps_per_second": 1.048, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 2e-05, | |
| "loss": 3510.4697, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 2e-05, | |
| "loss": 3604.1636, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 2e-05, | |
| "loss": 4791.7847, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 2e-05, | |
| "loss": 3840.9712, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "eval_loss": 3769.62744140625, | |
| "eval_runtime": 95.364, | |
| "eval_samples_per_second": 16.736, | |
| "eval_steps_per_second": 1.049, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 2e-05, | |
| "loss": 3833.2412, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 2e-05, | |
| "loss": 3851.5979, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 2e-05, | |
| "loss": 3107.7024, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 2e-05, | |
| "loss": 3598.7141, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "eval_loss": 3741.15283203125, | |
| "eval_runtime": 95.3181, | |
| "eval_samples_per_second": 16.744, | |
| "eval_steps_per_second": 1.049, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "learning_rate": 2e-05, | |
| "loss": 3801.637, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 2e-05, | |
| "loss": 3975.8054, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 2e-05, | |
| "loss": 3865.6533, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 2e-05, | |
| "loss": 4142.3828, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "eval_loss": 3735.14892578125, | |
| "eval_runtime": 95.3278, | |
| "eval_samples_per_second": 16.742, | |
| "eval_steps_per_second": 1.049, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 2e-05, | |
| "loss": 3423.9048, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 2e-05, | |
| "loss": 3500.3408, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "learning_rate": 2e-05, | |
| "loss": 3935.4355, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 2e-05, | |
| "loss": 3490.2856, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "eval_loss": 3755.257568359375, | |
| "eval_runtime": 95.3238, | |
| "eval_samples_per_second": 16.743, | |
| "eval_steps_per_second": 1.049, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 2e-05, | |
| "loss": 3251.2615, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 2e-05, | |
| "loss": 3406.0591, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 2e-05, | |
| "loss": 3306.6914, | |
| "step": 347 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 2e-05, | |
| "loss": 3858.6367, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "eval_loss": 3728.05615234375, | |
| "eval_runtime": 95.4779, | |
| "eval_samples_per_second": 16.716, | |
| "eval_steps_per_second": 1.047, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 2e-05, | |
| "loss": 2887.1479, | |
| "step": 349 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 2e-05, | |
| "loss": 3831.7244, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 2e-05, | |
| "loss": 3361.1741, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 2e-05, | |
| "loss": 3100.0488, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "eval_loss": 3719.01953125, | |
| "eval_runtime": 95.2657, | |
| "eval_samples_per_second": 16.753, | |
| "eval_steps_per_second": 1.05, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 2e-05, | |
| "loss": 3521.7913, | |
| "step": 353 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 2e-05, | |
| "loss": 3286.1931, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 2e-05, | |
| "loss": 4122.73, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 2e-05, | |
| "loss": 3818.4766, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "eval_loss": 3691.170166015625, | |
| "eval_runtime": 95.4436, | |
| "eval_samples_per_second": 16.722, | |
| "eval_steps_per_second": 1.048, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 2e-05, | |
| "loss": 3285.2466, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 2e-05, | |
| "loss": 3424.1902, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "learning_rate": 2e-05, | |
| "loss": 3263.9805, | |
| "step": 359 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 2e-05, | |
| "loss": 3721.5125, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "eval_loss": 3691.932861328125, | |
| "eval_runtime": 95.5042, | |
| "eval_samples_per_second": 16.711, | |
| "eval_steps_per_second": 1.047, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 2e-05, | |
| "loss": 3110.5813, | |
| "step": 361 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "learning_rate": 2e-05, | |
| "loss": 3151.187, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 2e-05, | |
| "loss": 3511.4319, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 2e-05, | |
| "loss": 3510.0305, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "eval_loss": 3845.365234375, | |
| "eval_runtime": 95.2618, | |
| "eval_samples_per_second": 16.754, | |
| "eval_steps_per_second": 1.05, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "learning_rate": 2e-05, | |
| "loss": 3422.686, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 2e-05, | |
| "loss": 4240.2275, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 2e-05, | |
| "loss": 3544.7195, | |
| "step": 367 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 2e-05, | |
| "loss": 3897.0737, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "eval_loss": 3735.1435546875, | |
| "eval_runtime": 95.385, | |
| "eval_samples_per_second": 16.732, | |
| "eval_steps_per_second": 1.048, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 2e-05, | |
| "loss": 3670.8647, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 2e-05, | |
| "loss": 3732.1475, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "learning_rate": 2e-05, | |
| "loss": 3360.2307, | |
| "step": 371 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 2e-05, | |
| "loss": 3394.595, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "eval_loss": 3689.341552734375, | |
| "eval_runtime": 95.4346, | |
| "eval_samples_per_second": 16.724, | |
| "eval_steps_per_second": 1.048, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 2e-05, | |
| "loss": 3888.7461, | |
| "step": 373 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 2e-05, | |
| "loss": 3887.3716, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 2e-05, | |
| "loss": 3540.4429, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 2e-05, | |
| "loss": 3279.0503, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "eval_loss": 3688.84619140625, | |
| "eval_runtime": 95.5526, | |
| "eval_samples_per_second": 16.703, | |
| "eval_steps_per_second": 1.047, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 2e-05, | |
| "loss": 3422.4468, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 3.78, | |
| "learning_rate": 2e-05, | |
| "loss": 3986.1982, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 2e-05, | |
| "loss": 3540.3237, | |
| "step": 379 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 2e-05, | |
| "loss": 3527.5225, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "eval_loss": 3675.298828125, | |
| "eval_runtime": 95.6115, | |
| "eval_samples_per_second": 16.693, | |
| "eval_steps_per_second": 1.046, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 2e-05, | |
| "loss": 3525.8005, | |
| "step": 381 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 2e-05, | |
| "loss": 3136.1785, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 2e-05, | |
| "loss": 3337.8206, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 2e-05, | |
| "loss": 3592.8411, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "eval_loss": 3678.1904296875, | |
| "eval_runtime": 95.1358, | |
| "eval_samples_per_second": 16.776, | |
| "eval_steps_per_second": 1.051, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 2e-05, | |
| "loss": 3581.0991, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "learning_rate": 2e-05, | |
| "loss": 4133.2891, | |
| "step": 386 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 2e-05, | |
| "loss": 3552.9802, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 2e-05, | |
| "loss": 3522.3882, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "eval_loss": 3674.487548828125, | |
| "eval_runtime": 95.2781, | |
| "eval_samples_per_second": 16.751, | |
| "eval_steps_per_second": 1.05, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "learning_rate": 2e-05, | |
| "loss": 3406.5796, | |
| "step": 389 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "learning_rate": 2e-05, | |
| "loss": 3628.0713, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 2e-05, | |
| "loss": 3814.6108, | |
| "step": 391 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 2e-05, | |
| "loss": 3952.0635, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "eval_loss": 3655.67919921875, | |
| "eval_runtime": 95.4463, | |
| "eval_samples_per_second": 16.721, | |
| "eval_steps_per_second": 1.048, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 2e-05, | |
| "loss": 3041.1628, | |
| "step": 393 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 2e-05, | |
| "loss": 3882.897, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "learning_rate": 2e-05, | |
| "loss": 3482.4553, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 2e-05, | |
| "loss": 3240.0728, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "eval_loss": 3666.441650390625, | |
| "eval_runtime": 95.3661, | |
| "eval_samples_per_second": 16.736, | |
| "eval_steps_per_second": 1.049, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "learning_rate": 2e-05, | |
| "loss": 3923.905, | |
| "step": 397 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 2e-05, | |
| "loss": 3575.6948, | |
| "step": 398 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 2e-05, | |
| "loss": 2891.4922, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 2e-05, | |
| "loss": 3905.6792, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 3648.62841796875, | |
| "eval_runtime": 95.4232, | |
| "eval_samples_per_second": 16.725, | |
| "eval_steps_per_second": 1.048, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "step": 400, | |
| "total_flos": 1.624099600371548e+17, | |
| "train_loss": 4450.289553833008, | |
| "train_runtime": 14295.8762, | |
| "train_samples_per_second": 1.787, | |
| "train_steps_per_second": 0.028 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 400, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 20, | |
| "total_flos": 1.624099600371548e+17, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |