| { |
| "best_metric": 0.5266188979148865, |
| "best_model_checkpoint": "./output_v2/7b_cluster00_Nous-Hermes-llama-2-7b_codellama_blob_1/checkpoint-200", |
| "epoch": 0.5614035087719298, |
| "global_step": 200, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0, |
| "learning_rate": 2e-06, |
| "loss": 0.7795, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.01, |
| "learning_rate": 4e-06, |
| "loss": 0.6789, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.01, |
| "learning_rate": 5.999999999999999e-06, |
| "loss": 0.6847, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.01, |
| "learning_rate": 8e-06, |
| "loss": 0.6876, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.01, |
| "learning_rate": 9.999999999999999e-06, |
| "loss": 0.5964, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.02, |
| "learning_rate": 1.1999999999999999e-05, |
| "loss": 0.6592, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.02, |
| "learning_rate": 1.4e-05, |
| "loss": 0.6261, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.02, |
| "learning_rate": 1.6e-05, |
| "loss": 0.6892, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.03, |
| "learning_rate": 1.7999999999999997e-05, |
| "loss": 0.538, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.03, |
| "learning_rate": 1.9999999999999998e-05, |
| "loss": 0.6015, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.03, |
| "learning_rate": 2.2e-05, |
| "loss": 0.7061, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.03, |
| "learning_rate": 2.3999999999999997e-05, |
| "loss": 0.6329, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.04, |
| "learning_rate": 2.6e-05, |
| "loss": 0.5633, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.04, |
| "learning_rate": 2.8e-05, |
| "loss": 0.5499, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.04, |
| "learning_rate": 2.9999999999999997e-05, |
| "loss": 0.5846, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.04, |
| "learning_rate": 3.2e-05, |
| "loss": 0.7056, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.05, |
| "learning_rate": 3.399999999999999e-05, |
| "loss": 0.9478, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.05, |
| "learning_rate": 3.5999999999999994e-05, |
| "loss": 0.7119, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.05, |
| "learning_rate": 3.8e-05, |
| "loss": 0.5115, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.06, |
| "learning_rate": 3.9999999999999996e-05, |
| "loss": 0.6481, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.06, |
| "learning_rate": 4.2e-05, |
| "loss": 1.0479, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.06, |
| "learning_rate": 4.4e-05, |
| "loss": 0.9266, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.06, |
| "learning_rate": 4.599999999999999e-05, |
| "loss": 0.7517, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.07, |
| "learning_rate": 4.7999999999999994e-05, |
| "loss": 0.7024, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.07, |
| "learning_rate": 4.9999999999999996e-05, |
| "loss": 0.6996, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.07, |
| "eval_loss": 0.6741535663604736, |
| "eval_runtime": 26.372, |
| "eval_samples_per_second": 7.584, |
| "eval_steps_per_second": 1.896, |
| "step": 25 |
| }, |
| { |
| "dharma_eval_accuracy": 0.47090526975371527, |
| "dharma_eval_accuracy_ARC-Challenge": 0.6296296296296297, |
| "dharma_eval_accuracy_ARC-Easy": 0.7592592592592593, |
| "dharma_eval_accuracy_BoolQ": 0.7037037037037037, |
| "dharma_eval_accuracy_MMLU": 0.4444444444444444, |
| "dharma_eval_accuracy_agieval": 0.2542372881355932, |
| "dharma_eval_accuracy_bigbench": 0.4098360655737705, |
| "dharma_eval_accuracy_openbookqa": 0.2962962962962963, |
| "dharma_eval_accuracy_truthful_qa": 0.37037037037037035, |
| "dharma_eval_accuracy_winogrande": 0.37037037037037035, |
| "dharma_loss": 3.7834435443878176, |
| "epoch": 0.07, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.07, |
| "learning_rate": 5.2e-05, |
| "loss": 0.6123, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.08, |
| "learning_rate": 5.399999999999999e-05, |
| "loss": 0.608, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.08, |
| "learning_rate": 5.6e-05, |
| "loss": 0.4845, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.08, |
| "learning_rate": 5.7999999999999994e-05, |
| "loss": 0.6026, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.08, |
| "learning_rate": 5.9999999999999995e-05, |
| "loss": 0.87, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.09, |
| "learning_rate": 6.199999999999999e-05, |
| "loss": 0.9898, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.09, |
| "learning_rate": 6.4e-05, |
| "loss": 0.7354, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.09, |
| "learning_rate": 6.599999999999999e-05, |
| "loss": 0.5053, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.1, |
| "learning_rate": 6.799999999999999e-05, |
| "loss": 0.6644, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.1, |
| "learning_rate": 7e-05, |
| "loss": 0.6932, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.1, |
| "learning_rate": 7.199999999999999e-05, |
| "loss": 0.7425, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.1, |
| "learning_rate": 7.4e-05, |
| "loss": 0.8268, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.11, |
| "learning_rate": 7.6e-05, |
| "loss": 0.5957, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.11, |
| "learning_rate": 7.8e-05, |
| "loss": 0.5579, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.11, |
| "learning_rate": 7.999999999999999e-05, |
| "loss": 0.7978, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.12, |
| "learning_rate": 8.199999999999999e-05, |
| "loss": 0.8261, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.12, |
| "learning_rate": 8.4e-05, |
| "loss": 0.7618, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.12, |
| "learning_rate": 8.6e-05, |
| "loss": 0.6062, |
| "step": 43 |
| }, |
| { |
| "epoch": 0.12, |
| "learning_rate": 8.8e-05, |
| "loss": 0.5791, |
| "step": 44 |
| }, |
| { |
| "epoch": 0.13, |
| "learning_rate": 8.999999999999999e-05, |
| "loss": 0.6008, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.13, |
| "learning_rate": 9.199999999999999e-05, |
| "loss": 0.5143, |
| "step": 46 |
| }, |
| { |
| "epoch": 0.13, |
| "learning_rate": 9.4e-05, |
| "loss": 0.5329, |
| "step": 47 |
| }, |
| { |
| "epoch": 0.13, |
| "learning_rate": 9.599999999999999e-05, |
| "loss": 0.6973, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.14, |
| "learning_rate": 9.799999999999998e-05, |
| "loss": 0.615, |
| "step": 49 |
| }, |
| { |
| "epoch": 0.14, |
| "learning_rate": 9.999999999999999e-05, |
| "loss": 0.6362, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.14, |
| "eval_loss": 0.6042094826698303, |
| "eval_runtime": 26.344, |
| "eval_samples_per_second": 7.592, |
| "eval_steps_per_second": 1.898, |
| "step": 50 |
| }, |
| { |
| "dharma_eval_accuracy": 0.4825425901342051, |
| "dharma_eval_accuracy_ARC-Challenge": 0.6666666666666666, |
| "dharma_eval_accuracy_ARC-Easy": 0.6851851851851852, |
| "dharma_eval_accuracy_BoolQ": 0.7037037037037037, |
| "dharma_eval_accuracy_MMLU": 0.42592592592592593, |
| "dharma_eval_accuracy_agieval": 0.2542372881355932, |
| "dharma_eval_accuracy_bigbench": 0.45901639344262296, |
| "dharma_eval_accuracy_openbookqa": 0.3333333333333333, |
| "dharma_eval_accuracy_truthful_qa": 0.35185185185185186, |
| "dharma_eval_accuracy_winogrande": 0.46296296296296297, |
| "dharma_loss": 2.1548793907165527, |
| "epoch": 0.14, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.14, |
| "learning_rate": 0.000102, |
| "loss": 0.6567, |
| "step": 51 |
| }, |
| { |
| "epoch": 0.15, |
| "learning_rate": 0.000104, |
| "loss": 0.9786, |
| "step": 52 |
| }, |
| { |
| "epoch": 0.15, |
| "learning_rate": 0.00010599999999999999, |
| "loss": 0.6146, |
| "step": 53 |
| }, |
| { |
| "epoch": 0.15, |
| "learning_rate": 0.00010799999999999998, |
| "loss": 0.6402, |
| "step": 54 |
| }, |
| { |
| "epoch": 0.15, |
| "learning_rate": 0.00010999999999999998, |
| "loss": 0.5906, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.16, |
| "learning_rate": 0.000112, |
| "loss": 0.6441, |
| "step": 56 |
| }, |
| { |
| "epoch": 0.16, |
| "learning_rate": 0.00011399999999999999, |
| "loss": 0.6887, |
| "step": 57 |
| }, |
| { |
| "epoch": 0.16, |
| "learning_rate": 0.00011599999999999999, |
| "loss": 0.6283, |
| "step": 58 |
| }, |
| { |
| "epoch": 0.17, |
| "learning_rate": 0.00011799999999999998, |
| "loss": 0.5929, |
| "step": 59 |
| }, |
| { |
| "epoch": 0.17, |
| "learning_rate": 0.00011999999999999999, |
| "loss": 0.6939, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.17, |
| "learning_rate": 0.000122, |
| "loss": 0.5535, |
| "step": 61 |
| }, |
| { |
| "epoch": 0.17, |
| "learning_rate": 0.00012399999999999998, |
| "loss": 0.5457, |
| "step": 62 |
| }, |
| { |
| "epoch": 0.18, |
| "learning_rate": 0.00012599999999999997, |
| "loss": 0.6425, |
| "step": 63 |
| }, |
| { |
| "epoch": 0.18, |
| "learning_rate": 0.000128, |
| "loss": 0.6855, |
| "step": 64 |
| }, |
| { |
| "epoch": 0.18, |
| "learning_rate": 0.00013, |
| "loss": 0.5396, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.19, |
| "learning_rate": 0.00013199999999999998, |
| "loss": 0.6307, |
| "step": 66 |
| }, |
| { |
| "epoch": 0.19, |
| "learning_rate": 0.00013399999999999998, |
| "loss": 0.6396, |
| "step": 67 |
| }, |
| { |
| "epoch": 0.19, |
| "learning_rate": 0.00013599999999999997, |
| "loss": 0.5727, |
| "step": 68 |
| }, |
| { |
| "epoch": 0.19, |
| "learning_rate": 0.000138, |
| "loss": 0.4812, |
| "step": 69 |
| }, |
| { |
| "epoch": 0.2, |
| "learning_rate": 0.00014, |
| "loss": 0.5658, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.2, |
| "learning_rate": 0.00014199999999999998, |
| "loss": 0.6314, |
| "step": 71 |
| }, |
| { |
| "epoch": 0.2, |
| "learning_rate": 0.00014399999999999998, |
| "loss": 0.6175, |
| "step": 72 |
| }, |
| { |
| "epoch": 0.2, |
| "learning_rate": 0.000146, |
| "loss": 0.5468, |
| "step": 73 |
| }, |
| { |
| "epoch": 0.21, |
| "learning_rate": 0.000148, |
| "loss": 0.6233, |
| "step": 74 |
| }, |
| { |
| "epoch": 0.21, |
| "learning_rate": 0.00015, |
| "loss": 0.5276, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.21, |
| "eval_loss": 0.5642657279968262, |
| "eval_runtime": 26.2701, |
| "eval_samples_per_second": 7.613, |
| "eval_steps_per_second": 1.903, |
| "step": 75 |
| }, |
| { |
| "dharma_eval_accuracy": 0.45038002097061713, |
| "dharma_eval_accuracy_ARC-Challenge": 0.6111111111111112, |
| "dharma_eval_accuracy_ARC-Easy": 0.6111111111111112, |
| "dharma_eval_accuracy_BoolQ": 0.7037037037037037, |
| "dharma_eval_accuracy_MMLU": 0.42592592592592593, |
| "dharma_eval_accuracy_agieval": 0.2033898305084746, |
| "dharma_eval_accuracy_bigbench": 0.4426229508196721, |
| "dharma_eval_accuracy_openbookqa": 0.14814814814814814, |
| "dharma_eval_accuracy_truthful_qa": 0.42592592592592593, |
| "dharma_eval_accuracy_winogrande": 0.48148148148148145, |
| "dharma_loss": 2.056876979827881, |
| "epoch": 0.21, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.21, |
| "learning_rate": 0.000152, |
| "loss": 0.5308, |
| "step": 76 |
| }, |
| { |
| "epoch": 0.22, |
| "learning_rate": 0.00015399999999999998, |
| "loss": 0.6546, |
| "step": 77 |
| }, |
| { |
| "epoch": 0.22, |
| "learning_rate": 0.000156, |
| "loss": 0.6451, |
| "step": 78 |
| }, |
| { |
| "epoch": 0.22, |
| "learning_rate": 0.00015799999999999996, |
| "loss": 0.5255, |
| "step": 79 |
| }, |
| { |
| "epoch": 0.22, |
| "learning_rate": 0.00015999999999999999, |
| "loss": 0.5629, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.23, |
| "learning_rate": 0.000162, |
| "loss": 0.6642, |
| "step": 81 |
| }, |
| { |
| "epoch": 0.23, |
| "learning_rate": 0.00016399999999999997, |
| "loss": 0.6393, |
| "step": 82 |
| }, |
| { |
| "epoch": 0.23, |
| "learning_rate": 0.000166, |
| "loss": 0.5073, |
| "step": 83 |
| }, |
| { |
| "epoch": 0.24, |
| "learning_rate": 0.000168, |
| "loss": 0.5628, |
| "step": 84 |
| }, |
| { |
| "epoch": 0.24, |
| "learning_rate": 0.00016999999999999999, |
| "loss": 0.5566, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.24, |
| "learning_rate": 0.000172, |
| "loss": 0.4653, |
| "step": 86 |
| }, |
| { |
| "epoch": 0.24, |
| "learning_rate": 0.00017399999999999997, |
| "loss": 0.5322, |
| "step": 87 |
| }, |
| { |
| "epoch": 0.25, |
| "learning_rate": 0.000176, |
| "loss": 0.7131, |
| "step": 88 |
| }, |
| { |
| "epoch": 0.25, |
| "learning_rate": 0.000178, |
| "loss": 0.5586, |
| "step": 89 |
| }, |
| { |
| "epoch": 0.25, |
| "learning_rate": 0.00017999999999999998, |
| "loss": 0.7246, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.26, |
| "learning_rate": 0.00018199999999999998, |
| "loss": 0.6527, |
| "step": 91 |
| }, |
| { |
| "epoch": 0.26, |
| "learning_rate": 0.00018399999999999997, |
| "loss": 0.8067, |
| "step": 92 |
| }, |
| { |
| "epoch": 0.26, |
| "learning_rate": 0.000186, |
| "loss": 0.6427, |
| "step": 93 |
| }, |
| { |
| "epoch": 0.26, |
| "learning_rate": 0.000188, |
| "loss": 0.6309, |
| "step": 94 |
| }, |
| { |
| "epoch": 0.27, |
| "learning_rate": 0.00018999999999999998, |
| "loss": 0.6111, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.27, |
| "learning_rate": 0.00019199999999999998, |
| "loss": 0.5911, |
| "step": 96 |
| }, |
| { |
| "epoch": 0.27, |
| "learning_rate": 0.00019399999999999997, |
| "loss": 0.6372, |
| "step": 97 |
| }, |
| { |
| "epoch": 0.28, |
| "learning_rate": 0.00019599999999999997, |
| "loss": 0.5664, |
| "step": 98 |
| }, |
| { |
| "epoch": 0.28, |
| "learning_rate": 0.000198, |
| "loss": 0.5618, |
| "step": 99 |
| }, |
| { |
| "epoch": 0.28, |
| "learning_rate": 0.00019999999999999998, |
| "loss": 0.7154, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.28, |
| "eval_loss": 0.5470997095108032, |
| "eval_runtime": 26.3144, |
| "eval_samples_per_second": 7.6, |
| "eval_steps_per_second": 1.9, |
| "step": 100 |
| }, |
| { |
| "dharma_eval_accuracy": 0.398478315307064, |
| "dharma_eval_accuracy_ARC-Challenge": 0.5740740740740741, |
| "dharma_eval_accuracy_ARC-Easy": 0.48148148148148145, |
| "dharma_eval_accuracy_BoolQ": 0.7037037037037037, |
| "dharma_eval_accuracy_MMLU": 0.4074074074074074, |
| "dharma_eval_accuracy_agieval": 0.2711864406779661, |
| "dharma_eval_accuracy_bigbench": 0.4262295081967213, |
| "dharma_eval_accuracy_openbookqa": 0.07407407407407407, |
| "dharma_eval_accuracy_truthful_qa": 0.3888888888888889, |
| "dharma_eval_accuracy_winogrande": 0.25925925925925924, |
| "dharma_loss": 2.5759267053604127, |
| "epoch": 0.28, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.28, |
| "learning_rate": 0.00020199999999999998, |
| "loss": 0.5837, |
| "step": 101 |
| }, |
| { |
| "epoch": 0.29, |
| "learning_rate": 0.000204, |
| "loss": 0.5707, |
| "step": 102 |
| }, |
| { |
| "epoch": 0.29, |
| "learning_rate": 0.00020599999999999997, |
| "loss": 0.7798, |
| "step": 103 |
| }, |
| { |
| "epoch": 0.29, |
| "learning_rate": 0.000208, |
| "loss": 0.4922, |
| "step": 104 |
| }, |
| { |
| "epoch": 0.29, |
| "learning_rate": 0.00020999999999999998, |
| "loss": 0.7033, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.3, |
| "learning_rate": 0.00021199999999999998, |
| "loss": 0.7297, |
| "step": 106 |
| }, |
| { |
| "epoch": 0.3, |
| "learning_rate": 0.000214, |
| "loss": 0.5376, |
| "step": 107 |
| }, |
| { |
| "epoch": 0.3, |
| "learning_rate": 0.00021599999999999996, |
| "loss": 0.5372, |
| "step": 108 |
| }, |
| { |
| "epoch": 0.31, |
| "learning_rate": 0.00021799999999999999, |
| "loss": 0.7453, |
| "step": 109 |
| }, |
| { |
| "epoch": 0.31, |
| "learning_rate": 0.00021999999999999995, |
| "loss": 0.4582, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.31, |
| "learning_rate": 0.00022199999999999998, |
| "loss": 0.54, |
| "step": 111 |
| }, |
| { |
| "epoch": 0.31, |
| "learning_rate": 0.000224, |
| "loss": 0.643, |
| "step": 112 |
| }, |
| { |
| "epoch": 0.32, |
| "learning_rate": 0.00022599999999999996, |
| "loss": 0.5972, |
| "step": 113 |
| }, |
| { |
| "epoch": 0.32, |
| "learning_rate": 0.00022799999999999999, |
| "loss": 0.5765, |
| "step": 114 |
| }, |
| { |
| "epoch": 0.32, |
| "learning_rate": 0.00023, |
| "loss": 0.6007, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.33, |
| "learning_rate": 0.00023199999999999997, |
| "loss": 0.5343, |
| "step": 116 |
| }, |
| { |
| "epoch": 0.33, |
| "learning_rate": 0.000234, |
| "loss": 0.8235, |
| "step": 117 |
| }, |
| { |
| "epoch": 0.33, |
| "learning_rate": 0.00023599999999999996, |
| "loss": 0.6687, |
| "step": 118 |
| }, |
| { |
| "epoch": 0.33, |
| "learning_rate": 0.00023799999999999998, |
| "loss": 0.6696, |
| "step": 119 |
| }, |
| { |
| "epoch": 0.34, |
| "learning_rate": 0.00023999999999999998, |
| "loss": 0.77, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.34, |
| "learning_rate": 0.00024199999999999997, |
| "loss": 0.5792, |
| "step": 121 |
| }, |
| { |
| "epoch": 0.34, |
| "learning_rate": 0.000244, |
| "loss": 0.3653, |
| "step": 122 |
| }, |
| { |
| "epoch": 0.35, |
| "learning_rate": 0.00024599999999999996, |
| "loss": 0.5344, |
| "step": 123 |
| }, |
| { |
| "epoch": 0.35, |
| "learning_rate": 0.00024799999999999996, |
| "loss": 0.5772, |
| "step": 124 |
| }, |
| { |
| "epoch": 0.35, |
| "learning_rate": 0.00025, |
| "loss": 0.7189, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.35, |
| "eval_loss": 0.5514405369758606, |
| "eval_runtime": 26.3447, |
| "eval_samples_per_second": 7.592, |
| "eval_steps_per_second": 1.898, |
| "step": 125 |
| }, |
| { |
| "dharma_eval_accuracy": 0.3371043854202756, |
| "dharma_eval_accuracy_ARC-Challenge": 0.37037037037037035, |
| "dharma_eval_accuracy_ARC-Easy": 0.42592592592592593, |
| "dharma_eval_accuracy_BoolQ": 0.37037037037037035, |
| "dharma_eval_accuracy_MMLU": 0.35185185185185186, |
| "dharma_eval_accuracy_agieval": 0.22033898305084745, |
| "dharma_eval_accuracy_bigbench": 0.29508196721311475, |
| "dharma_eval_accuracy_openbookqa": 0.18518518518518517, |
| "dharma_eval_accuracy_truthful_qa": 0.3888888888888889, |
| "dharma_eval_accuracy_winogrande": 0.42592592592592593, |
| "dharma_loss": 2.1871530780792234, |
| "epoch": 0.35, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.35, |
| "learning_rate": 0.00025199999999999995, |
| "loss": 0.5891, |
| "step": 126 |
| }, |
| { |
| "epoch": 0.36, |
| "learning_rate": 0.000254, |
| "loss": 0.8225, |
| "step": 127 |
| }, |
| { |
| "epoch": 0.36, |
| "learning_rate": 0.000256, |
| "loss": 0.6104, |
| "step": 128 |
| }, |
| { |
| "epoch": 0.36, |
| "learning_rate": 0.000258, |
| "loss": 0.6571, |
| "step": 129 |
| }, |
| { |
| "epoch": 0.36, |
| "learning_rate": 0.00026, |
| "loss": 0.7562, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.37, |
| "learning_rate": 0.00026199999999999997, |
| "loss": 0.7172, |
| "step": 131 |
| }, |
| { |
| "epoch": 0.37, |
| "learning_rate": 0.00026399999999999997, |
| "loss": 0.4353, |
| "step": 132 |
| }, |
| { |
| "epoch": 0.37, |
| "learning_rate": 0.000266, |
| "loss": 0.5576, |
| "step": 133 |
| }, |
| { |
| "epoch": 0.38, |
| "learning_rate": 0.00026799999999999995, |
| "loss": 0.553, |
| "step": 134 |
| }, |
| { |
| "epoch": 0.38, |
| "learning_rate": 0.00027, |
| "loss": 0.5062, |
| "step": 135 |
| }, |
| { |
| "epoch": 0.38, |
| "learning_rate": 0.00027199999999999994, |
| "loss": 0.4819, |
| "step": 136 |
| }, |
| { |
| "epoch": 0.38, |
| "learning_rate": 0.000274, |
| "loss": 0.6195, |
| "step": 137 |
| }, |
| { |
| "epoch": 0.39, |
| "learning_rate": 0.000276, |
| "loss": 0.7592, |
| "step": 138 |
| }, |
| { |
| "epoch": 0.39, |
| "learning_rate": 0.000278, |
| "loss": 0.6118, |
| "step": 139 |
| }, |
| { |
| "epoch": 0.39, |
| "learning_rate": 0.00028, |
| "loss": 0.7897, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.4, |
| "learning_rate": 0.00028199999999999997, |
| "loss": 0.5879, |
| "step": 141 |
| }, |
| { |
| "epoch": 0.4, |
| "learning_rate": 0.00028399999999999996, |
| "loss": 0.6055, |
| "step": 142 |
| }, |
| { |
| "epoch": 0.4, |
| "learning_rate": 0.00028599999999999996, |
| "loss": 0.541, |
| "step": 143 |
| }, |
| { |
| "epoch": 0.4, |
| "learning_rate": 0.00028799999999999995, |
| "loss": 0.7665, |
| "step": 144 |
| }, |
| { |
| "epoch": 0.41, |
| "learning_rate": 0.00029, |
| "loss": 0.612, |
| "step": 145 |
| }, |
| { |
| "epoch": 0.41, |
| "learning_rate": 0.000292, |
| "loss": 0.5397, |
| "step": 146 |
| }, |
| { |
| "epoch": 0.41, |
| "learning_rate": 0.000294, |
| "loss": 0.5727, |
| "step": 147 |
| }, |
| { |
| "epoch": 0.42, |
| "learning_rate": 0.000296, |
| "loss": 1.1184, |
| "step": 148 |
| }, |
| { |
| "epoch": 0.42, |
| "learning_rate": 0.000298, |
| "loss": 0.5912, |
| "step": 149 |
| }, |
| { |
| "epoch": 0.42, |
| "learning_rate": 0.0003, |
| "loss": 0.5581, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.42, |
| "eval_loss": 0.5423073768615723, |
| "eval_runtime": 26.3108, |
| "eval_samples_per_second": 7.601, |
| "eval_steps_per_second": 1.9, |
| "step": 150 |
| }, |
| { |
| "dharma_eval_accuracy": 0.3860708907481159, |
| "dharma_eval_accuracy_ARC-Challenge": 0.42592592592592593, |
| "dharma_eval_accuracy_ARC-Easy": 0.4444444444444444, |
| "dharma_eval_accuracy_BoolQ": 0.7037037037037037, |
| "dharma_eval_accuracy_MMLU": 0.37037037037037035, |
| "dharma_eval_accuracy_agieval": 0.2542372881355932, |
| "dharma_eval_accuracy_bigbench": 0.4426229508196721, |
| "dharma_eval_accuracy_openbookqa": 0.18518518518518517, |
| "dharma_eval_accuracy_truthful_qa": 0.2962962962962963, |
| "dharma_eval_accuracy_winogrande": 0.35185185185185186, |
| "dharma_loss": 2.471666145801544, |
| "epoch": 0.42, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.42, |
| "learning_rate": 0.0002999999685313931, |
| "loss": 0.656, |
| "step": 151 |
| }, |
| { |
| "epoch": 0.43, |
| "learning_rate": 0.00029999987412558584, |
| "loss": 0.5075, |
| "step": 152 |
| }, |
| { |
| "epoch": 0.43, |
| "learning_rate": 0.0002999997167826177, |
| "loss": 0.4696, |
| "step": 153 |
| }, |
| { |
| "epoch": 0.43, |
| "learning_rate": 0.00029999949650255474, |
| "loss": 0.7349, |
| "step": 154 |
| }, |
| { |
| "epoch": 0.44, |
| "learning_rate": 0.0002999992132854894, |
| "loss": 0.5935, |
| "step": 155 |
| }, |
| { |
| "epoch": 0.44, |
| "learning_rate": 0.0002999988671315404, |
| "loss": 0.4127, |
| "step": 156 |
| }, |
| { |
| "epoch": 0.44, |
| "learning_rate": 0.0002999984580408531, |
| "loss": 0.5503, |
| "step": 157 |
| }, |
| { |
| "epoch": 0.44, |
| "learning_rate": 0.00029999798601359915, |
| "loss": 0.5742, |
| "step": 158 |
| }, |
| { |
| "epoch": 0.45, |
| "learning_rate": 0.00029999745104997654, |
| "loss": 0.5606, |
| "step": 159 |
| }, |
| { |
| "epoch": 0.45, |
| "learning_rate": 0.0002999968531502098, |
| "loss": 0.6209, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.45, |
| "learning_rate": 0.0002999961923145497, |
| "loss": 0.4977, |
| "step": 161 |
| }, |
| { |
| "epoch": 0.45, |
| "learning_rate": 0.0002999954685432736, |
| "loss": 0.7474, |
| "step": 162 |
| }, |
| { |
| "epoch": 0.46, |
| "learning_rate": 0.0002999946818366852, |
| "loss": 0.574, |
| "step": 163 |
| }, |
| { |
| "epoch": 0.46, |
| "learning_rate": 0.00029999383219511444, |
| "loss": 0.3991, |
| "step": 164 |
| }, |
| { |
| "epoch": 0.46, |
| "learning_rate": 0.0002999929196189179, |
| "loss": 0.6335, |
| "step": 165 |
| }, |
| { |
| "epoch": 0.47, |
| "learning_rate": 0.0002999919441084786, |
| "loss": 0.6144, |
| "step": 166 |
| }, |
| { |
| "epoch": 0.47, |
| "learning_rate": 0.0002999909056642057, |
| "loss": 0.4695, |
| "step": 167 |
| }, |
| { |
| "epoch": 0.47, |
| "learning_rate": 0.00029998980428653496, |
| "loss": 0.5322, |
| "step": 168 |
| }, |
| { |
| "epoch": 0.47, |
| "learning_rate": 0.00029998863997592843, |
| "loss": 0.6111, |
| "step": 169 |
| }, |
| { |
| "epoch": 0.48, |
| "learning_rate": 0.00029998741273287477, |
| "loss": 0.5517, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.48, |
| "learning_rate": 0.0002999861225578888, |
| "loss": 0.5407, |
| "step": 171 |
| }, |
| { |
| "epoch": 0.48, |
| "learning_rate": 0.00029998476945151183, |
| "loss": 0.4942, |
| "step": 172 |
| }, |
| { |
| "epoch": 0.49, |
| "learning_rate": 0.00029998335341431174, |
| "loss": 0.4563, |
| "step": 173 |
| }, |
| { |
| "epoch": 0.49, |
| "learning_rate": 0.0002999818744468825, |
| "loss": 0.4406, |
| "step": 174 |
| }, |
| { |
| "epoch": 0.49, |
| "learning_rate": 0.0002999803325498448, |
| "loss": 0.5319, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.49, |
| "eval_loss": 0.5312690734863281, |
| "eval_runtime": 26.3302, |
| "eval_samples_per_second": 7.596, |
| "eval_steps_per_second": 1.899, |
| "step": 175 |
| }, |
| { |
| "dharma_eval_accuracy": 0.40200352864364475, |
| "dharma_eval_accuracy_ARC-Challenge": 0.42592592592592593, |
| "dharma_eval_accuracy_ARC-Easy": 0.5, |
| "dharma_eval_accuracy_BoolQ": 0.7592592592592593, |
| "dharma_eval_accuracy_MMLU": 0.4074074074074074, |
| "dharma_eval_accuracy_agieval": 0.22033898305084745, |
| "dharma_eval_accuracy_bigbench": 0.36065573770491804, |
| "dharma_eval_accuracy_openbookqa": 0.2222222222222222, |
| "dharma_eval_accuracy_truthful_qa": 0.2962962962962963, |
| "dharma_eval_accuracy_winogrande": 0.42592592592592593, |
| "dharma_loss": 2.2439456572532652, |
| "epoch": 0.49, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.49, |
| "learning_rate": 0.0002999787277238455, |
| "loss": 0.7389, |
| "step": 176 |
| }, |
| { |
| "epoch": 0.5, |
| "learning_rate": 0.000299977059969558, |
| "loss": 0.6848, |
| "step": 177 |
| }, |
| { |
| "epoch": 0.5, |
| "learning_rate": 0.00029997532928768204, |
| "loss": 0.5144, |
| "step": 178 |
| }, |
| { |
| "epoch": 0.5, |
| "learning_rate": 0.00029997353567894384, |
| "loss": 0.5707, |
| "step": 179 |
| }, |
| { |
| "epoch": 0.51, |
| "learning_rate": 0.0002999716791440959, |
| "loss": 0.668, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.51, |
| "learning_rate": 0.00029996975968391715, |
| "loss": 0.4851, |
| "step": 181 |
| }, |
| { |
| "epoch": 0.51, |
| "learning_rate": 0.000299967777299213, |
| "loss": 0.725, |
| "step": 182 |
| }, |
| { |
| "epoch": 0.51, |
| "learning_rate": 0.0002999657319908153, |
| "loss": 0.6281, |
| "step": 183 |
| }, |
| { |
| "epoch": 0.52, |
| "learning_rate": 0.0002999636237595821, |
| "loss": 0.6357, |
| "step": 184 |
| }, |
| { |
| "epoch": 0.52, |
| "learning_rate": 0.00029996145260639806, |
| "loss": 0.5517, |
| "step": 185 |
| }, |
| { |
| "epoch": 0.52, |
| "learning_rate": 0.0002999592185321741, |
| "loss": 0.6792, |
| "step": 186 |
| }, |
| { |
| "epoch": 0.52, |
| "learning_rate": 0.0002999569215378477, |
| "loss": 0.619, |
| "step": 187 |
| }, |
| { |
| "epoch": 0.53, |
| "learning_rate": 0.0002999545616243825, |
| "loss": 0.5693, |
| "step": 188 |
| }, |
| { |
| "epoch": 0.53, |
| "learning_rate": 0.00029995213879276876, |
| "loss": 0.5759, |
| "step": 189 |
| }, |
| { |
| "epoch": 0.53, |
| "learning_rate": 0.000299949653044023, |
| "loss": 0.4382, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.54, |
| "learning_rate": 0.00029994710437918824, |
| "loss": 0.7183, |
| "step": 191 |
| }, |
| { |
| "epoch": 0.54, |
| "learning_rate": 0.0002999444927993338, |
| "loss": 0.7328, |
| "step": 192 |
| }, |
| { |
| "epoch": 0.54, |
| "learning_rate": 0.00029994181830555555, |
| "loss": 0.645, |
| "step": 193 |
| }, |
| { |
| "epoch": 0.54, |
| "learning_rate": 0.00029993908089897555, |
| "loss": 0.5784, |
| "step": 194 |
| }, |
| { |
| "epoch": 0.55, |
| "learning_rate": 0.00029993628058074245, |
| "loss": 0.4547, |
| "step": 195 |
| }, |
| { |
| "epoch": 0.55, |
| "learning_rate": 0.00029993341735203114, |
| "loss": 0.5243, |
| "step": 196 |
| }, |
| { |
| "epoch": 0.55, |
| "learning_rate": 0.00029993049121404303, |
| "loss": 0.5059, |
| "step": 197 |
| }, |
| { |
| "epoch": 0.56, |
| "learning_rate": 0.0002999275021680058, |
| "loss": 0.6225, |
| "step": 198 |
| }, |
| { |
| "epoch": 0.56, |
| "learning_rate": 0.0002999244502151737, |
| "loss": 0.5956, |
| "step": 199 |
| }, |
| { |
| "epoch": 0.56, |
| "learning_rate": 0.00029992133535682725, |
| "loss": 0.553, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.56, |
| "eval_loss": 0.5266188979148865, |
| "eval_runtime": 26.3, |
| "eval_samples_per_second": 7.605, |
| "eval_steps_per_second": 1.901, |
| "step": 200 |
| }, |
| { |
| "dharma_eval_accuracy": 0.4282802607491564, |
| "dharma_eval_accuracy_ARC-Challenge": 0.5185185185185185, |
| "dharma_eval_accuracy_ARC-Easy": 0.5740740740740741, |
| "dharma_eval_accuracy_BoolQ": 0.7037037037037037, |
| "dharma_eval_accuracy_MMLU": 0.4074074074074074, |
| "dharma_eval_accuracy_agieval": 0.22033898305084745, |
| "dharma_eval_accuracy_bigbench": 0.39344262295081966, |
| "dharma_eval_accuracy_openbookqa": 0.14814814814814814, |
| "dharma_eval_accuracy_truthful_qa": 0.3148148148148148, |
| "dharma_eval_accuracy_winogrande": 0.5740740740740741, |
| "dharma_loss": 2.507861177444458, |
| "epoch": 0.56, |
| "step": 200 |
| } |
| ], |
| "max_steps": 5000, |
| "num_train_epochs": 15, |
| "total_flos": 6.277915233887846e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
