| { | |
| "best_metric": 0.12461505830287933, | |
| "best_model_checkpoint": "strategytransitionplanv1/checkpoint-155", | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 155, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03225806451612903, | |
| "grad_norm": 1.7076008319854736, | |
| "learning_rate": 6.25e-07, | |
| "loss": 1.0981, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06451612903225806, | |
| "grad_norm": 1.3594564199447632, | |
| "learning_rate": 1.25e-06, | |
| "loss": 1.0979, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0967741935483871, | |
| "grad_norm": 4.986942768096924, | |
| "learning_rate": 1.8750000000000003e-06, | |
| "loss": 1.12, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.12903225806451613, | |
| "grad_norm": 3.718357563018799, | |
| "learning_rate": 2.5e-06, | |
| "loss": 1.1224, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.16129032258064516, | |
| "grad_norm": 3.902071952819824, | |
| "learning_rate": 3.125e-06, | |
| "loss": 1.1079, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1935483870967742, | |
| "grad_norm": 1.6320927143096924, | |
| "learning_rate": 3.7500000000000005e-06, | |
| "loss": 1.1149, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.22580645161290322, | |
| "grad_norm": 2.3765382766723633, | |
| "learning_rate": 4.3750000000000005e-06, | |
| "loss": 1.1274, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.25806451612903225, | |
| "grad_norm": 1.9507699012756348, | |
| "learning_rate": 5e-06, | |
| "loss": 1.0572, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.2903225806451613, | |
| "grad_norm": 2.0720622539520264, | |
| "learning_rate": 5.625e-06, | |
| "loss": 1.0771, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3225806451612903, | |
| "grad_norm": 3.6346395015716553, | |
| "learning_rate": 6.25e-06, | |
| "loss": 1.0732, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3548387096774194, | |
| "grad_norm": 3.3288047313690186, | |
| "learning_rate": 6.875e-06, | |
| "loss": 1.0486, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.3870967741935484, | |
| "grad_norm": 3.1521379947662354, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 1.0992, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.41935483870967744, | |
| "grad_norm": 5.848731994628906, | |
| "learning_rate": 8.125000000000001e-06, | |
| "loss": 1.0845, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.45161290322580644, | |
| "grad_norm": 4.110851287841797, | |
| "learning_rate": 8.750000000000001e-06, | |
| "loss": 1.093, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.4838709677419355, | |
| "grad_norm": 1.617586374282837, | |
| "learning_rate": 9.375000000000001e-06, | |
| "loss": 1.0811, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5161290322580645, | |
| "grad_norm": 2.5444748401641846, | |
| "learning_rate": 1e-05, | |
| "loss": 1.0869, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.5483870967741935, | |
| "grad_norm": 2.050872802734375, | |
| "learning_rate": 9.928057553956835e-06, | |
| "loss": 1.0879, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.5806451612903226, | |
| "grad_norm": 4.142770290374756, | |
| "learning_rate": 9.85611510791367e-06, | |
| "loss": 1.0807, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.6129032258064516, | |
| "grad_norm": 2.6557066440582275, | |
| "learning_rate": 9.784172661870505e-06, | |
| "loss": 1.0831, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.6451612903225806, | |
| "grad_norm": 2.187577724456787, | |
| "learning_rate": 9.712230215827338e-06, | |
| "loss": 1.0701, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6774193548387096, | |
| "grad_norm": 2.1984810829162598, | |
| "learning_rate": 9.640287769784174e-06, | |
| "loss": 1.0397, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.7096774193548387, | |
| "grad_norm": 2.2228214740753174, | |
| "learning_rate": 9.568345323741008e-06, | |
| "loss": 1.0466, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.7419354838709677, | |
| "grad_norm": 2.3713221549987793, | |
| "learning_rate": 9.496402877697842e-06, | |
| "loss": 1.0695, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.7741935483870968, | |
| "grad_norm": 3.8912224769592285, | |
| "learning_rate": 9.424460431654678e-06, | |
| "loss": 1.0865, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.8064516129032258, | |
| "grad_norm": 4.4668869972229, | |
| "learning_rate": 9.35251798561151e-06, | |
| "loss": 1.087, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8387096774193549, | |
| "grad_norm": 4.023162364959717, | |
| "learning_rate": 9.280575539568346e-06, | |
| "loss": 1.075, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.8709677419354839, | |
| "grad_norm": 2.8331081867218018, | |
| "learning_rate": 9.20863309352518e-06, | |
| "loss": 1.0941, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.9032258064516129, | |
| "grad_norm": 3.602895498275757, | |
| "learning_rate": 9.136690647482015e-06, | |
| "loss": 1.0431, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.9354838709677419, | |
| "grad_norm": 3.7651658058166504, | |
| "learning_rate": 9.064748201438849e-06, | |
| "loss": 1.0362, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.967741935483871, | |
| "grad_norm": 1.5405668020248413, | |
| "learning_rate": 8.992805755395683e-06, | |
| "loss": 1.0579, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 4.124188423156738, | |
| "learning_rate": 8.92086330935252e-06, | |
| "loss": 1.0354, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8387096774193549, | |
| "eval_f1_macro": 0.8319607843137254, | |
| "eval_f1_micro": 0.8387096774193549, | |
| "eval_f1_weighted": 0.8339943074003796, | |
| "eval_loss": 1.025422215461731, | |
| "eval_precision_macro": 0.8604269293924466, | |
| "eval_precision_micro": 0.8387096774193549, | |
| "eval_precision_weighted": 0.8604798982996981, | |
| "eval_recall_macro": 0.834920634920635, | |
| "eval_recall_micro": 0.8387096774193549, | |
| "eval_recall_weighted": 0.8387096774193549, | |
| "eval_runtime": 0.3641, | |
| "eval_samples_per_second": 170.282, | |
| "eval_steps_per_second": 10.986, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.032258064516129, | |
| "grad_norm": 4.104296684265137, | |
| "learning_rate": 8.848920863309353e-06, | |
| "loss": 0.9849, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.064516129032258, | |
| "grad_norm": 3.3923492431640625, | |
| "learning_rate": 8.776978417266188e-06, | |
| "loss": 1.0266, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.096774193548387, | |
| "grad_norm": 5.368731498718262, | |
| "learning_rate": 8.705035971223022e-06, | |
| "loss": 0.9705, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.129032258064516, | |
| "grad_norm": 5.603680610656738, | |
| "learning_rate": 8.633093525179856e-06, | |
| "loss": 1.0303, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.1612903225806452, | |
| "grad_norm": 2.2851974964141846, | |
| "learning_rate": 8.561151079136692e-06, | |
| "loss": 0.9739, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.1935483870967742, | |
| "grad_norm": 4.70708703994751, | |
| "learning_rate": 8.489208633093526e-06, | |
| "loss": 0.9742, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.2258064516129032, | |
| "grad_norm": 7.92202091217041, | |
| "learning_rate": 8.41726618705036e-06, | |
| "loss": 0.957, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.2580645161290323, | |
| "grad_norm": 4.823170185089111, | |
| "learning_rate": 8.345323741007195e-06, | |
| "loss": 0.9731, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.2903225806451613, | |
| "grad_norm": 3.4790797233581543, | |
| "learning_rate": 8.273381294964029e-06, | |
| "loss": 0.9411, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.3225806451612903, | |
| "grad_norm": 4.450028419494629, | |
| "learning_rate": 8.201438848920865e-06, | |
| "loss": 0.9636, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.3548387096774195, | |
| "grad_norm": 3.824451446533203, | |
| "learning_rate": 8.129496402877699e-06, | |
| "loss": 0.938, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.3870967741935485, | |
| "grad_norm": 4.1180419921875, | |
| "learning_rate": 8.057553956834533e-06, | |
| "loss": 0.8856, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.4193548387096775, | |
| "grad_norm": 6.481126308441162, | |
| "learning_rate": 7.985611510791367e-06, | |
| "loss": 0.9327, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.4516129032258065, | |
| "grad_norm": 3.7428112030029297, | |
| "learning_rate": 7.913669064748202e-06, | |
| "loss": 0.8892, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.4838709677419355, | |
| "grad_norm": 5.0267791748046875, | |
| "learning_rate": 7.841726618705036e-06, | |
| "loss": 0.8205, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.5161290322580645, | |
| "grad_norm": 5.348020553588867, | |
| "learning_rate": 7.769784172661872e-06, | |
| "loss": 0.8093, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.5483870967741935, | |
| "grad_norm": 7.635085582733154, | |
| "learning_rate": 7.697841726618706e-06, | |
| "loss": 0.8342, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.5806451612903225, | |
| "grad_norm": 5.7552056312561035, | |
| "learning_rate": 7.62589928057554e-06, | |
| "loss": 0.8389, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.6129032258064515, | |
| "grad_norm": 6.611269950866699, | |
| "learning_rate": 7.5539568345323745e-06, | |
| "loss": 0.9106, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.6451612903225805, | |
| "grad_norm": 4.329951286315918, | |
| "learning_rate": 7.48201438848921e-06, | |
| "loss": 0.7197, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 1.6774193548387095, | |
| "grad_norm": 5.155747890472412, | |
| "learning_rate": 7.410071942446043e-06, | |
| "loss": 0.6425, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.7096774193548387, | |
| "grad_norm": 5.479297637939453, | |
| "learning_rate": 7.338129496402878e-06, | |
| "loss": 0.7609, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 1.7419354838709677, | |
| "grad_norm": 5.481513977050781, | |
| "learning_rate": 7.266187050359713e-06, | |
| "loss": 0.8313, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.7741935483870968, | |
| "grad_norm": 5.614933967590332, | |
| "learning_rate": 7.194244604316547e-06, | |
| "loss": 0.7208, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.8064516129032258, | |
| "grad_norm": 4.680207252502441, | |
| "learning_rate": 7.122302158273382e-06, | |
| "loss": 0.6751, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.838709677419355, | |
| "grad_norm": 5.295926094055176, | |
| "learning_rate": 7.050359712230216e-06, | |
| "loss": 0.8244, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 1.870967741935484, | |
| "grad_norm": 4.341407775878906, | |
| "learning_rate": 6.978417266187051e-06, | |
| "loss": 0.6805, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 1.903225806451613, | |
| "grad_norm": 5.317811489105225, | |
| "learning_rate": 6.906474820143886e-06, | |
| "loss": 0.6056, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 1.935483870967742, | |
| "grad_norm": 5.420223236083984, | |
| "learning_rate": 6.834532374100719e-06, | |
| "loss": 0.6867, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.967741935483871, | |
| "grad_norm": 7.248617649078369, | |
| "learning_rate": 6.762589928057554e-06, | |
| "loss": 0.7531, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 9.447990417480469, | |
| "learning_rate": 6.6906474820143886e-06, | |
| "loss": 0.5974, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.967741935483871, | |
| "eval_f1_macro": 0.967304625199362, | |
| "eval_f1_micro": 0.967741935483871, | |
| "eval_f1_weighted": 0.967626176879148, | |
| "eval_loss": 0.5691941380500793, | |
| "eval_precision_macro": 0.9710144927536232, | |
| "eval_precision_micro": 0.967741935483871, | |
| "eval_precision_weighted": 0.97054698457223, | |
| "eval_recall_macro": 0.9666666666666667, | |
| "eval_recall_micro": 0.967741935483871, | |
| "eval_recall_weighted": 0.967741935483871, | |
| "eval_runtime": 0.3633, | |
| "eval_samples_per_second": 170.675, | |
| "eval_steps_per_second": 11.011, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.032258064516129, | |
| "grad_norm": 3.9469432830810547, | |
| "learning_rate": 6.618705035971224e-06, | |
| "loss": 0.6395, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.064516129032258, | |
| "grad_norm": 4.58109188079834, | |
| "learning_rate": 6.546762589928059e-06, | |
| "loss": 0.5742, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.096774193548387, | |
| "grad_norm": 5.2513933181762695, | |
| "learning_rate": 6.474820143884892e-06, | |
| "loss": 0.665, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.129032258064516, | |
| "grad_norm": 4.5661301612854, | |
| "learning_rate": 6.402877697841727e-06, | |
| "loss": 0.5077, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.161290322580645, | |
| "grad_norm": 6.208225727081299, | |
| "learning_rate": 6.330935251798561e-06, | |
| "loss": 0.5777, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.193548387096774, | |
| "grad_norm": 5.244273662567139, | |
| "learning_rate": 6.2589928057553964e-06, | |
| "loss": 0.6024, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.225806451612903, | |
| "grad_norm": 6.400041580200195, | |
| "learning_rate": 6.1870503597122315e-06, | |
| "loss": 0.7029, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.258064516129032, | |
| "grad_norm": 3.543893575668335, | |
| "learning_rate": 6.115107913669065e-06, | |
| "loss": 0.4423, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.2903225806451615, | |
| "grad_norm": 4.5264787673950195, | |
| "learning_rate": 6.0431654676259e-06, | |
| "loss": 0.4439, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.3225806451612905, | |
| "grad_norm": 6.25119686126709, | |
| "learning_rate": 5.971223021582734e-06, | |
| "loss": 0.5624, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.3548387096774195, | |
| "grad_norm": 3.226388931274414, | |
| "learning_rate": 5.899280575539568e-06, | |
| "loss": 0.3964, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 2.3870967741935485, | |
| "grad_norm": 3.7347843647003174, | |
| "learning_rate": 5.8273381294964035e-06, | |
| "loss": 0.5466, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 2.4193548387096775, | |
| "grad_norm": 3.9312491416931152, | |
| "learning_rate": 5.755395683453238e-06, | |
| "loss": 0.5006, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 2.4516129032258065, | |
| "grad_norm": 5.62445592880249, | |
| "learning_rate": 5.683453237410073e-06, | |
| "loss": 0.3485, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 2.4838709677419355, | |
| "grad_norm": 3.4454846382141113, | |
| "learning_rate": 5.611510791366906e-06, | |
| "loss": 0.399, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 2.5161290322580645, | |
| "grad_norm": 3.8090169429779053, | |
| "learning_rate": 5.539568345323741e-06, | |
| "loss": 0.3801, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 2.5483870967741935, | |
| "grad_norm": 3.244086742401123, | |
| "learning_rate": 5.467625899280576e-06, | |
| "loss": 0.3907, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 2.5806451612903225, | |
| "grad_norm": 4.637303352355957, | |
| "learning_rate": 5.3956834532374105e-06, | |
| "loss": 0.4531, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.6129032258064515, | |
| "grad_norm": 3.3718318939208984, | |
| "learning_rate": 5.3237410071942456e-06, | |
| "loss": 0.3218, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 2.6451612903225805, | |
| "grad_norm": 3.9827523231506348, | |
| "learning_rate": 5.251798561151079e-06, | |
| "loss": 0.3826, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 2.6774193548387095, | |
| "grad_norm": 4.160843372344971, | |
| "learning_rate": 5.179856115107914e-06, | |
| "loss": 0.3748, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 2.709677419354839, | |
| "grad_norm": 3.411928653717041, | |
| "learning_rate": 5.107913669064749e-06, | |
| "loss": 0.353, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 2.741935483870968, | |
| "grad_norm": 5.943264007568359, | |
| "learning_rate": 5.035971223021583e-06, | |
| "loss": 0.2906, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 2.774193548387097, | |
| "grad_norm": 4.6810150146484375, | |
| "learning_rate": 4.9640287769784175e-06, | |
| "loss": 0.2362, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 2.806451612903226, | |
| "grad_norm": 3.2993741035461426, | |
| "learning_rate": 4.892086330935253e-06, | |
| "loss": 0.2516, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 2.838709677419355, | |
| "grad_norm": 2.4518892765045166, | |
| "learning_rate": 4.820143884892087e-06, | |
| "loss": 0.2009, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 2.870967741935484, | |
| "grad_norm": 6.592429161071777, | |
| "learning_rate": 4.748201438848921e-06, | |
| "loss": 0.5157, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 2.903225806451613, | |
| "grad_norm": 2.818664312362671, | |
| "learning_rate": 4.676258992805755e-06, | |
| "loss": 0.2421, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.935483870967742, | |
| "grad_norm": 4.569883346557617, | |
| "learning_rate": 4.60431654676259e-06, | |
| "loss": 0.2791, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 2.967741935483871, | |
| "grad_norm": 5.113462924957275, | |
| "learning_rate": 4.5323741007194245e-06, | |
| "loss": 0.2892, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 4.380687713623047, | |
| "learning_rate": 4.46043165467626e-06, | |
| "loss": 0.3231, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.967741935483871, | |
| "eval_f1_macro": 0.967304625199362, | |
| "eval_f1_micro": 0.967741935483871, | |
| "eval_f1_weighted": 0.967626176879148, | |
| "eval_loss": 0.23027083277702332, | |
| "eval_precision_macro": 0.9710144927536232, | |
| "eval_precision_micro": 0.967741935483871, | |
| "eval_precision_weighted": 0.97054698457223, | |
| "eval_recall_macro": 0.9666666666666667, | |
| "eval_recall_micro": 0.967741935483871, | |
| "eval_recall_weighted": 0.967741935483871, | |
| "eval_runtime": 0.3631, | |
| "eval_samples_per_second": 170.75, | |
| "eval_steps_per_second": 11.016, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 3.032258064516129, | |
| "grad_norm": 3.396799087524414, | |
| "learning_rate": 4.388489208633094e-06, | |
| "loss": 0.2294, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 3.064516129032258, | |
| "grad_norm": 2.6190600395202637, | |
| "learning_rate": 4.316546762589928e-06, | |
| "loss": 0.2166, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 3.096774193548387, | |
| "grad_norm": 4.4704060554504395, | |
| "learning_rate": 4.244604316546763e-06, | |
| "loss": 0.3076, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 3.129032258064516, | |
| "grad_norm": 3.570626974105835, | |
| "learning_rate": 4.172661870503597e-06, | |
| "loss": 0.2187, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 3.161290322580645, | |
| "grad_norm": 3.120173931121826, | |
| "learning_rate": 4.100719424460432e-06, | |
| "loss": 0.4226, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 3.193548387096774, | |
| "grad_norm": 2.8124935626983643, | |
| "learning_rate": 4.028776978417267e-06, | |
| "loss": 0.2103, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 3.225806451612903, | |
| "grad_norm": 3.7060863971710205, | |
| "learning_rate": 3.956834532374101e-06, | |
| "loss": 0.2506, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.258064516129032, | |
| "grad_norm": 2.422107458114624, | |
| "learning_rate": 3.884892086330936e-06, | |
| "loss": 0.174, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 3.2903225806451615, | |
| "grad_norm": 2.4062161445617676, | |
| "learning_rate": 3.81294964028777e-06, | |
| "loss": 0.2021, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 3.3225806451612905, | |
| "grad_norm": 2.4910507202148438, | |
| "learning_rate": 3.741007194244605e-06, | |
| "loss": 0.1937, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 3.3548387096774195, | |
| "grad_norm": 2.2566051483154297, | |
| "learning_rate": 3.669064748201439e-06, | |
| "loss": 0.1584, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 3.3870967741935485, | |
| "grad_norm": 2.0386288166046143, | |
| "learning_rate": 3.5971223021582737e-06, | |
| "loss": 0.1443, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 3.4193548387096775, | |
| "grad_norm": 2.2671079635620117, | |
| "learning_rate": 3.525179856115108e-06, | |
| "loss": 0.181, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 3.4516129032258065, | |
| "grad_norm": 1.894828200340271, | |
| "learning_rate": 3.453237410071943e-06, | |
| "loss": 0.1515, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 3.4838709677419355, | |
| "grad_norm": 4.2288384437561035, | |
| "learning_rate": 3.381294964028777e-06, | |
| "loss": 0.272, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 3.5161290322580645, | |
| "grad_norm": 3.274885416030884, | |
| "learning_rate": 3.309352517985612e-06, | |
| "loss": 0.172, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 3.5483870967741935, | |
| "grad_norm": 3.967803955078125, | |
| "learning_rate": 3.237410071942446e-06, | |
| "loss": 0.4134, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 3.5806451612903225, | |
| "grad_norm": 3.1320571899414062, | |
| "learning_rate": 3.1654676258992807e-06, | |
| "loss": 0.2018, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 3.6129032258064515, | |
| "grad_norm": 2.877068519592285, | |
| "learning_rate": 3.0935251798561158e-06, | |
| "loss": 0.1946, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 3.6451612903225805, | |
| "grad_norm": 2.552804470062256, | |
| "learning_rate": 3.02158273381295e-06, | |
| "loss": 0.1403, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 3.6774193548387095, | |
| "grad_norm": 5.13293981552124, | |
| "learning_rate": 2.949640287769784e-06, | |
| "loss": 0.3705, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 3.709677419354839, | |
| "grad_norm": 1.5643055438995361, | |
| "learning_rate": 2.877697841726619e-06, | |
| "loss": 0.1245, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 3.741935483870968, | |
| "grad_norm": 1.7311073541641235, | |
| "learning_rate": 2.805755395683453e-06, | |
| "loss": 0.1252, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 3.774193548387097, | |
| "grad_norm": 1.9834305047988892, | |
| "learning_rate": 2.733812949640288e-06, | |
| "loss": 0.1294, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 3.806451612903226, | |
| "grad_norm": 1.7714146375656128, | |
| "learning_rate": 2.6618705035971228e-06, | |
| "loss": 0.1248, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 3.838709677419355, | |
| "grad_norm": 2.352647304534912, | |
| "learning_rate": 2.589928057553957e-06, | |
| "loss": 0.3432, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 3.870967741935484, | |
| "grad_norm": 1.8365036249160767, | |
| "learning_rate": 2.5179856115107916e-06, | |
| "loss": 0.1135, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 3.903225806451613, | |
| "grad_norm": 9.964637756347656, | |
| "learning_rate": 2.4460431654676263e-06, | |
| "loss": 0.6474, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 3.935483870967742, | |
| "grad_norm": 2.3334484100341797, | |
| "learning_rate": 2.3741007194244605e-06, | |
| "loss": 0.1629, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 3.967741935483871, | |
| "grad_norm": 4.90928316116333, | |
| "learning_rate": 2.302158273381295e-06, | |
| "loss": 0.1706, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": Infinity, | |
| "learning_rate": 2.302158273381295e-06, | |
| "loss": 0.4531, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.967741935483871, | |
| "eval_f1_macro": 0.967304625199362, | |
| "eval_f1_micro": 0.967741935483871, | |
| "eval_f1_weighted": 0.967626176879148, | |
| "eval_loss": 0.1408514678478241, | |
| "eval_precision_macro": 0.9710144927536232, | |
| "eval_precision_micro": 0.967741935483871, | |
| "eval_precision_weighted": 0.97054698457223, | |
| "eval_recall_macro": 0.9666666666666667, | |
| "eval_recall_micro": 0.967741935483871, | |
| "eval_recall_weighted": 0.967741935483871, | |
| "eval_runtime": 0.364, | |
| "eval_samples_per_second": 170.325, | |
| "eval_steps_per_second": 10.989, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 4.032258064516129, | |
| "grad_norm": 1.4911006689071655, | |
| "learning_rate": 2.23021582733813e-06, | |
| "loss": 0.1036, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 4.064516129032258, | |
| "grad_norm": 1.8918758630752563, | |
| "learning_rate": 2.158273381294964e-06, | |
| "loss": 0.1496, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 4.096774193548387, | |
| "grad_norm": 7.057977199554443, | |
| "learning_rate": 2.0863309352517987e-06, | |
| "loss": 0.4655, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 4.129032258064516, | |
| "grad_norm": 1.8621776103973389, | |
| "learning_rate": 2.0143884892086333e-06, | |
| "loss": 0.1149, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 4.161290322580645, | |
| "grad_norm": 1.6348507404327393, | |
| "learning_rate": 1.942446043165468e-06, | |
| "loss": 0.0879, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 4.193548387096774, | |
| "grad_norm": 2.331972360610962, | |
| "learning_rate": 1.8705035971223024e-06, | |
| "loss": 0.1251, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 4.225806451612903, | |
| "grad_norm": 1.8028337955474854, | |
| "learning_rate": 1.7985611510791368e-06, | |
| "loss": 0.1074, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 4.258064516129032, | |
| "grad_norm": 1.5170693397521973, | |
| "learning_rate": 1.7266187050359715e-06, | |
| "loss": 0.0963, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 4.290322580645161, | |
| "grad_norm": 1.7213988304138184, | |
| "learning_rate": 1.654676258992806e-06, | |
| "loss": 0.1002, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 4.32258064516129, | |
| "grad_norm": 1.1244333982467651, | |
| "learning_rate": 1.5827338129496403e-06, | |
| "loss": 0.0825, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 4.354838709677419, | |
| "grad_norm": 1.8200867176055908, | |
| "learning_rate": 1.510791366906475e-06, | |
| "loss": 0.1212, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 4.387096774193548, | |
| "grad_norm": 1.1631309986114502, | |
| "learning_rate": 1.4388489208633094e-06, | |
| "loss": 0.0765, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 4.419354838709677, | |
| "grad_norm": 1.3975659608840942, | |
| "learning_rate": 1.366906474820144e-06, | |
| "loss": 0.1039, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 4.451612903225806, | |
| "grad_norm": 3.7922534942626953, | |
| "learning_rate": 1.2949640287769785e-06, | |
| "loss": 0.434, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 4.483870967741936, | |
| "grad_norm": 1.495962381362915, | |
| "learning_rate": 1.2230215827338131e-06, | |
| "loss": 0.0988, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 4.516129032258064, | |
| "grad_norm": 6.633321285247803, | |
| "learning_rate": 1.1510791366906476e-06, | |
| "loss": 0.3248, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 4.548387096774194, | |
| "grad_norm": 0.9505869746208191, | |
| "learning_rate": 1.079136690647482e-06, | |
| "loss": 0.0635, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 4.580645161290323, | |
| "grad_norm": 4.179118633270264, | |
| "learning_rate": 1.0071942446043167e-06, | |
| "loss": 0.4312, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 4.612903225806452, | |
| "grad_norm": 4.571844100952148, | |
| "learning_rate": 9.352517985611512e-07, | |
| "loss": 0.4026, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 4.645161290322581, | |
| "grad_norm": 6.533665180206299, | |
| "learning_rate": 8.633093525179857e-07, | |
| "loss": 0.2858, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 4.67741935483871, | |
| "grad_norm": 1.06562077999115, | |
| "learning_rate": 7.913669064748202e-07, | |
| "loss": 0.0803, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 4.709677419354839, | |
| "grad_norm": 1.3917797803878784, | |
| "learning_rate": 7.194244604316547e-07, | |
| "loss": 0.0883, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 4.741935483870968, | |
| "grad_norm": 2.7961225509643555, | |
| "learning_rate": 6.474820143884893e-07, | |
| "loss": 0.1603, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 4.774193548387097, | |
| "grad_norm": 2.315228223800659, | |
| "learning_rate": 5.755395683453238e-07, | |
| "loss": 0.1078, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 4.806451612903226, | |
| "grad_norm": 1.2167779207229614, | |
| "learning_rate": 5.035971223021583e-07, | |
| "loss": 0.0807, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 4.838709677419355, | |
| "grad_norm": 3.9313344955444336, | |
| "learning_rate": 4.3165467625899287e-07, | |
| "loss": 0.1382, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 4.870967741935484, | |
| "grad_norm": 1.4970654249191284, | |
| "learning_rate": 3.5971223021582736e-07, | |
| "loss": 0.1097, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 4.903225806451613, | |
| "grad_norm": 2.4545068740844727, | |
| "learning_rate": 2.877697841726619e-07, | |
| "loss": 0.1327, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 4.935483870967742, | |
| "grad_norm": 5.53891134262085, | |
| "learning_rate": 2.1582733812949643e-07, | |
| "loss": 0.1897, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 4.967741935483871, | |
| "grad_norm": 1.297095537185669, | |
| "learning_rate": 1.4388489208633095e-07, | |
| "loss": 0.0874, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 8.026548385620117, | |
| "learning_rate": 7.194244604316547e-08, | |
| "loss": 0.7796, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9838709677419355, | |
| "eval_f1_macro": 0.9837010534684953, | |
| "eval_f1_micro": 0.9838709677419355, | |
| "eval_f1_weighted": 0.9838517321638102, | |
| "eval_loss": 0.12461505830287933, | |
| "eval_precision_macro": 0.9848484848484849, | |
| "eval_precision_micro": 0.9838709677419355, | |
| "eval_precision_weighted": 0.9846041055718475, | |
| "eval_recall_macro": 0.9833333333333334, | |
| "eval_recall_micro": 0.9838709677419355, | |
| "eval_recall_weighted": 0.9838709677419355, | |
| "eval_runtime": 0.3625, | |
| "eval_samples_per_second": 171.046, | |
| "eval_steps_per_second": 11.035, | |
| "step": 155 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 155, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "total_flos": 161613108449280.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |