| { | |
| "best_metric": 0.10599859803915024, | |
| "best_model_checkpoint": "riskmanagementv1/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": 1.648207187652588, | |
| "learning_rate": 6.25e-07, | |
| "loss": 1.0951, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06451612903225806, | |
| "grad_norm": 1.5398106575012207, | |
| "learning_rate": 1.25e-06, | |
| "loss": 1.116, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0967741935483871, | |
| "grad_norm": 4.653311729431152, | |
| "learning_rate": 1.8750000000000003e-06, | |
| "loss": 1.0443, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.12903225806451613, | |
| "grad_norm": 3.8882646560668945, | |
| "learning_rate": 2.5e-06, | |
| "loss": 1.113, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.16129032258064516, | |
| "grad_norm": 3.754126787185669, | |
| "learning_rate": 3.125e-06, | |
| "loss": 1.1012, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1935483870967742, | |
| "grad_norm": 1.5717527866363525, | |
| "learning_rate": 3.7500000000000005e-06, | |
| "loss": 1.0946, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.22580645161290322, | |
| "grad_norm": 2.106679677963257, | |
| "learning_rate": 4.3750000000000005e-06, | |
| "loss": 1.0793, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.25806451612903225, | |
| "grad_norm": 2.2854700088500977, | |
| "learning_rate": 5e-06, | |
| "loss": 1.1227, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.2903225806451613, | |
| "grad_norm": 2.0785741806030273, | |
| "learning_rate": 5.625e-06, | |
| "loss": 1.0784, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3225806451612903, | |
| "grad_norm": 3.856192111968994, | |
| "learning_rate": 6.25e-06, | |
| "loss": 1.1229, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3548387096774194, | |
| "grad_norm": 2.9804818630218506, | |
| "learning_rate": 6.875e-06, | |
| "loss": 1.0941, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.3870967741935484, | |
| "grad_norm": 2.701162099838257, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 1.0792, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.41935483870967744, | |
| "grad_norm": 5.755159854888916, | |
| "learning_rate": 8.125000000000001e-06, | |
| "loss": 1.08, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.45161290322580644, | |
| "grad_norm": 4.275572299957275, | |
| "learning_rate": 8.750000000000001e-06, | |
| "loss": 1.0991, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.4838709677419355, | |
| "grad_norm": 1.5670201778411865, | |
| "learning_rate": 9.375000000000001e-06, | |
| "loss": 1.0728, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5161290322580645, | |
| "grad_norm": 2.7937171459198, | |
| "learning_rate": 1e-05, | |
| "loss": 1.1006, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.5483870967741935, | |
| "grad_norm": 2.048818349838257, | |
| "learning_rate": 9.928057553956835e-06, | |
| "loss": 1.0779, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.5806451612903226, | |
| "grad_norm": 4.063783168792725, | |
| "learning_rate": 9.85611510791367e-06, | |
| "loss": 1.0858, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.6129032258064516, | |
| "grad_norm": 2.6299703121185303, | |
| "learning_rate": 9.784172661870505e-06, | |
| "loss": 1.0715, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.6451612903225806, | |
| "grad_norm": 2.324522018432617, | |
| "learning_rate": 9.712230215827338e-06, | |
| "loss": 1.0964, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6774193548387096, | |
| "grad_norm": 2.1976382732391357, | |
| "learning_rate": 9.640287769784174e-06, | |
| "loss": 1.032, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.7096774193548387, | |
| "grad_norm": 2.2792370319366455, | |
| "learning_rate": 9.568345323741008e-06, | |
| "loss": 1.0902, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.7419354838709677, | |
| "grad_norm": 1.996429204940796, | |
| "learning_rate": 9.496402877697842e-06, | |
| "loss": 1.0665, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.7741935483870968, | |
| "grad_norm": 4.1794891357421875, | |
| "learning_rate": 9.424460431654678e-06, | |
| "loss": 1.0737, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.8064516129032258, | |
| "grad_norm": 4.505804061889648, | |
| "learning_rate": 9.35251798561151e-06, | |
| "loss": 1.0948, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8387096774193549, | |
| "grad_norm": 3.4325923919677734, | |
| "learning_rate": 9.280575539568346e-06, | |
| "loss": 1.0494, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.8709677419354839, | |
| "grad_norm": 2.4758219718933105, | |
| "learning_rate": 9.20863309352518e-06, | |
| "loss": 1.052, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.9032258064516129, | |
| "grad_norm": 3.858365297317505, | |
| "learning_rate": 9.136690647482015e-06, | |
| "loss": 1.051, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.9354838709677419, | |
| "grad_norm": 2.598480701446533, | |
| "learning_rate": 9.064748201438849e-06, | |
| "loss": 1.0568, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.967741935483871, | |
| "grad_norm": 1.8019946813583374, | |
| "learning_rate": 8.992805755395683e-06, | |
| "loss": 1.0231, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 3.940290927886963, | |
| "learning_rate": 8.92086330935252e-06, | |
| "loss": 1.0415, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9032258064516129, | |
| "eval_f1_macro": 0.9035612535612536, | |
| "eval_f1_micro": 0.9032258064516129, | |
| "eval_f1_weighted": 0.9040736145574856, | |
| "eval_loss": 1.0341954231262207, | |
| "eval_precision_macro": 0.9093567251461989, | |
| "eval_precision_micro": 0.9032258064516129, | |
| "eval_precision_weighted": 0.9095925297113752, | |
| "eval_recall_macro": 0.9023809523809523, | |
| "eval_recall_micro": 0.9032258064516129, | |
| "eval_recall_weighted": 0.9032258064516129, | |
| "eval_runtime": 0.3613, | |
| "eval_samples_per_second": 171.597, | |
| "eval_steps_per_second": 11.071, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.032258064516129, | |
| "grad_norm": 4.133128643035889, | |
| "learning_rate": 8.848920863309353e-06, | |
| "loss": 1.0548, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.064516129032258, | |
| "grad_norm": 3.782399892807007, | |
| "learning_rate": 8.776978417266188e-06, | |
| "loss": 1.0703, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.096774193548387, | |
| "grad_norm": 4.876072883605957, | |
| "learning_rate": 8.705035971223022e-06, | |
| "loss": 1.0334, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.129032258064516, | |
| "grad_norm": 4.667634963989258, | |
| "learning_rate": 8.633093525179856e-06, | |
| "loss": 0.9948, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.1612903225806452, | |
| "grad_norm": 2.1760268211364746, | |
| "learning_rate": 8.561151079136692e-06, | |
| "loss": 0.972, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.1935483870967742, | |
| "grad_norm": 4.767606735229492, | |
| "learning_rate": 8.489208633093526e-06, | |
| "loss": 0.9336, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.2258064516129032, | |
| "grad_norm": 7.815669536590576, | |
| "learning_rate": 8.41726618705036e-06, | |
| "loss": 0.9686, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.2580645161290323, | |
| "grad_norm": 4.481734752655029, | |
| "learning_rate": 8.345323741007195e-06, | |
| "loss": 0.9709, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.2903225806451613, | |
| "grad_norm": 2.848688840866089, | |
| "learning_rate": 8.273381294964029e-06, | |
| "loss": 0.962, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.3225806451612903, | |
| "grad_norm": 4.002137184143066, | |
| "learning_rate": 8.201438848920865e-06, | |
| "loss": 0.937, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.3548387096774195, | |
| "grad_norm": 4.138007640838623, | |
| "learning_rate": 8.129496402877699e-06, | |
| "loss": 0.9601, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.3870967741935485, | |
| "grad_norm": 4.144357681274414, | |
| "learning_rate": 8.057553956834533e-06, | |
| "loss": 0.9457, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.4193548387096775, | |
| "grad_norm": 5.553256034851074, | |
| "learning_rate": 7.985611510791367e-06, | |
| "loss": 0.9491, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.4516129032258065, | |
| "grad_norm": 3.699176549911499, | |
| "learning_rate": 7.913669064748202e-06, | |
| "loss": 0.9378, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.4838709677419355, | |
| "grad_norm": 4.687703609466553, | |
| "learning_rate": 7.841726618705036e-06, | |
| "loss": 0.8746, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.5161290322580645, | |
| "grad_norm": 4.312544822692871, | |
| "learning_rate": 7.769784172661872e-06, | |
| "loss": 0.9033, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.5483870967741935, | |
| "grad_norm": 7.0601067543029785, | |
| "learning_rate": 7.697841726618706e-06, | |
| "loss": 0.7922, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.5806451612903225, | |
| "grad_norm": 5.145197868347168, | |
| "learning_rate": 7.62589928057554e-06, | |
| "loss": 0.7994, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.6129032258064515, | |
| "grad_norm": 7.315432071685791, | |
| "learning_rate": 7.5539568345323745e-06, | |
| "loss": 0.9052, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.6451612903225805, | |
| "grad_norm": 5.903252601623535, | |
| "learning_rate": 7.48201438848921e-06, | |
| "loss": 0.7659, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 1.6774193548387095, | |
| "grad_norm": 6.903425216674805, | |
| "learning_rate": 7.410071942446043e-06, | |
| "loss": 0.6835, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.7096774193548387, | |
| "grad_norm": 5.649851322174072, | |
| "learning_rate": 7.338129496402878e-06, | |
| "loss": 0.7886, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 1.7419354838709677, | |
| "grad_norm": 7.038477420806885, | |
| "learning_rate": 7.266187050359713e-06, | |
| "loss": 0.8199, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.7741935483870968, | |
| "grad_norm": 5.405828475952148, | |
| "learning_rate": 7.194244604316547e-06, | |
| "loss": 0.7793, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.8064516129032258, | |
| "grad_norm": 4.914242744445801, | |
| "learning_rate": 7.122302158273382e-06, | |
| "loss": 0.6027, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.838709677419355, | |
| "grad_norm": 3.8369204998016357, | |
| "learning_rate": 7.050359712230216e-06, | |
| "loss": 0.6166, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 1.870967741935484, | |
| "grad_norm": 5.300614356994629, | |
| "learning_rate": 6.978417266187051e-06, | |
| "loss": 0.5933, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 1.903225806451613, | |
| "grad_norm": 6.020833969116211, | |
| "learning_rate": 6.906474820143886e-06, | |
| "loss": 0.6644, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 1.935483870967742, | |
| "grad_norm": 7.810927867889404, | |
| "learning_rate": 6.834532374100719e-06, | |
| "loss": 0.6088, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.967741935483871, | |
| "grad_norm": 4.888729572296143, | |
| "learning_rate": 6.762589928057554e-06, | |
| "loss": 0.601, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 9.534357070922852, | |
| "learning_rate": 6.6906474820143886e-06, | |
| "loss": 0.5048, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9032258064516129, | |
| "eval_f1_macro": 0.9009661835748792, | |
| "eval_f1_micro": 0.9032258064516129, | |
| "eval_f1_weighted": 0.90205703599813, | |
| "eval_loss": 0.5168083310127258, | |
| "eval_precision_macro": 0.9125, | |
| "eval_precision_micro": 0.9032258064516129, | |
| "eval_precision_weighted": 0.9120967741935483, | |
| "eval_recall_macro": 0.9007936507936508, | |
| "eval_recall_micro": 0.9032258064516129, | |
| "eval_recall_weighted": 0.9032258064516129, | |
| "eval_runtime": 0.362, | |
| "eval_samples_per_second": 171.293, | |
| "eval_steps_per_second": 11.051, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.032258064516129, | |
| "grad_norm": 5.264218807220459, | |
| "learning_rate": 6.618705035971224e-06, | |
| "loss": 0.5298, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.064516129032258, | |
| "grad_norm": 4.860868453979492, | |
| "learning_rate": 6.546762589928059e-06, | |
| "loss": 0.4793, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.096774193548387, | |
| "grad_norm": 4.750568389892578, | |
| "learning_rate": 6.474820143884892e-06, | |
| "loss": 0.6173, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.129032258064516, | |
| "grad_norm": 6.425321102142334, | |
| "learning_rate": 6.402877697841727e-06, | |
| "loss": 0.6019, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.161290322580645, | |
| "grad_norm": 9.132750511169434, | |
| "learning_rate": 6.330935251798561e-06, | |
| "loss": 0.5513, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.193548387096774, | |
| "grad_norm": 3.2714285850524902, | |
| "learning_rate": 6.2589928057553964e-06, | |
| "loss": 0.5036, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.225806451612903, | |
| "grad_norm": 6.814634323120117, | |
| "learning_rate": 6.1870503597122315e-06, | |
| "loss": 0.537, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.258064516129032, | |
| "grad_norm": 3.728926420211792, | |
| "learning_rate": 6.115107913669065e-06, | |
| "loss": 0.4946, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.2903225806451615, | |
| "grad_norm": 6.5363545417785645, | |
| "learning_rate": 6.0431654676259e-06, | |
| "loss": 0.4285, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.3225806451612905, | |
| "grad_norm": 3.544241428375244, | |
| "learning_rate": 5.971223021582734e-06, | |
| "loss": 0.5499, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.3548387096774195, | |
| "grad_norm": 4.439380168914795, | |
| "learning_rate": 5.899280575539568e-06, | |
| "loss": 0.4158, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 2.3870967741935485, | |
| "grad_norm": 3.382199287414551, | |
| "learning_rate": 5.8273381294964035e-06, | |
| "loss": 0.5042, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 2.4193548387096775, | |
| "grad_norm": 3.844313144683838, | |
| "learning_rate": 5.755395683453238e-06, | |
| "loss": 0.4456, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 2.4516129032258065, | |
| "grad_norm": 6.994678497314453, | |
| "learning_rate": 5.683453237410073e-06, | |
| "loss": 0.3322, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 2.4838709677419355, | |
| "grad_norm": 3.745391845703125, | |
| "learning_rate": 5.611510791366906e-06, | |
| "loss": 0.4974, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 2.5161290322580645, | |
| "grad_norm": 3.9794974327087402, | |
| "learning_rate": 5.539568345323741e-06, | |
| "loss": 0.6066, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 2.5483870967741935, | |
| "grad_norm": 4.3371901512146, | |
| "learning_rate": 5.467625899280576e-06, | |
| "loss": 0.3384, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 2.5806451612903225, | |
| "grad_norm": 3.778343915939331, | |
| "learning_rate": 5.3956834532374105e-06, | |
| "loss": 0.3747, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.6129032258064515, | |
| "grad_norm": 5.110599994659424, | |
| "learning_rate": 5.3237410071942456e-06, | |
| "loss": 0.3761, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 2.6451612903225805, | |
| "grad_norm": 4.0779128074646, | |
| "learning_rate": 5.251798561151079e-06, | |
| "loss": 0.3718, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 2.6774193548387095, | |
| "grad_norm": 3.576948881149292, | |
| "learning_rate": 5.179856115107914e-06, | |
| "loss": 0.3232, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 2.709677419354839, | |
| "grad_norm": 4.824243068695068, | |
| "learning_rate": 5.107913669064749e-06, | |
| "loss": 0.3021, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 2.741935483870968, | |
| "grad_norm": 7.285948276519775, | |
| "learning_rate": 5.035971223021583e-06, | |
| "loss": 0.3227, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 2.774193548387097, | |
| "grad_norm": 4.5859246253967285, | |
| "learning_rate": 4.9640287769784175e-06, | |
| "loss": 0.2029, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 2.806451612903226, | |
| "grad_norm": 3.3746910095214844, | |
| "learning_rate": 4.892086330935253e-06, | |
| "loss": 0.3087, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 2.838709677419355, | |
| "grad_norm": 5.0139875411987305, | |
| "learning_rate": 4.820143884892087e-06, | |
| "loss": 0.3919, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 2.870967741935484, | |
| "grad_norm": 3.168724775314331, | |
| "learning_rate": 4.748201438848921e-06, | |
| "loss": 0.2469, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 2.903225806451613, | |
| "grad_norm": 6.2994914054870605, | |
| "learning_rate": 4.676258992805755e-06, | |
| "loss": 0.2812, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.935483870967742, | |
| "grad_norm": 1.8329119682312012, | |
| "learning_rate": 4.60431654676259e-06, | |
| "loss": 0.148, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 2.967741935483871, | |
| "grad_norm": 3.138279914855957, | |
| "learning_rate": 4.5323741007194245e-06, | |
| "loss": 0.1359, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 4.396747589111328, | |
| "learning_rate": 4.46043165467626e-06, | |
| "loss": 0.1879, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.967741935483871, | |
| "eval_f1_macro": 0.9674603174603175, | |
| "eval_f1_micro": 0.967741935483871, | |
| "eval_f1_weighted": 0.967741935483871, | |
| "eval_loss": 0.22156503796577454, | |
| "eval_precision_macro": 0.9674603174603175, | |
| "eval_precision_micro": 0.967741935483871, | |
| "eval_precision_weighted": 0.967741935483871, | |
| "eval_recall_macro": 0.9674603174603175, | |
| "eval_recall_micro": 0.967741935483871, | |
| "eval_recall_weighted": 0.967741935483871, | |
| "eval_runtime": 0.3612, | |
| "eval_samples_per_second": 171.656, | |
| "eval_steps_per_second": 11.075, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 3.032258064516129, | |
| "grad_norm": 2.482665538787842, | |
| "learning_rate": 4.388489208633094e-06, | |
| "loss": 0.203, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 3.064516129032258, | |
| "grad_norm": 3.7393405437469482, | |
| "learning_rate": 4.316546762589928e-06, | |
| "loss": 0.4162, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 3.096774193548387, | |
| "grad_norm": 4.992405414581299, | |
| "learning_rate": 4.244604316546763e-06, | |
| "loss": 0.272, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 3.129032258064516, | |
| "grad_norm": 5.053823471069336, | |
| "learning_rate": 4.172661870503597e-06, | |
| "loss": 0.3839, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 3.161290322580645, | |
| "grad_norm": 9.411662101745605, | |
| "learning_rate": 4.100719424460432e-06, | |
| "loss": 0.2929, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 3.193548387096774, | |
| "grad_norm": 3.2983734607696533, | |
| "learning_rate": 4.028776978417267e-06, | |
| "loss": 0.1844, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 3.225806451612903, | |
| "grad_norm": 9.005085945129395, | |
| "learning_rate": 3.956834532374101e-06, | |
| "loss": 0.2335, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.258064516129032, | |
| "grad_norm": 2.7752511501312256, | |
| "learning_rate": 3.884892086330936e-06, | |
| "loss": 0.1636, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 3.2903225806451615, | |
| "grad_norm": 2.129927635192871, | |
| "learning_rate": 3.81294964028777e-06, | |
| "loss": 0.1674, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 3.3225806451612905, | |
| "grad_norm": 3.201385736465454, | |
| "learning_rate": 3.741007194244605e-06, | |
| "loss": 0.2321, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 3.3548387096774195, | |
| "grad_norm": 6.4212775230407715, | |
| "learning_rate": 3.669064748201439e-06, | |
| "loss": 0.3104, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 3.3870967741935485, | |
| "grad_norm": 9.587445259094238, | |
| "learning_rate": 3.5971223021582737e-06, | |
| "loss": 0.3252, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 3.4193548387096775, | |
| "grad_norm": 4.780144214630127, | |
| "learning_rate": 3.525179856115108e-06, | |
| "loss": 0.2342, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 3.4516129032258065, | |
| "grad_norm": 6.432891845703125, | |
| "learning_rate": 3.453237410071943e-06, | |
| "loss": 0.3754, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 3.4838709677419355, | |
| "grad_norm": 1.6028318405151367, | |
| "learning_rate": 3.381294964028777e-06, | |
| "loss": 0.0951, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 3.5161290322580645, | |
| "grad_norm": 3.9140098094940186, | |
| "learning_rate": 3.309352517985612e-06, | |
| "loss": 0.1739, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 3.5483870967741935, | |
| "grad_norm": 5.9437785148620605, | |
| "learning_rate": 3.237410071942446e-06, | |
| "loss": 0.3609, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 3.5806451612903225, | |
| "grad_norm": 2.725947380065918, | |
| "learning_rate": 3.1654676258992807e-06, | |
| "loss": 0.2015, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 3.6129032258064515, | |
| "grad_norm": 5.769122123718262, | |
| "learning_rate": 3.0935251798561158e-06, | |
| "loss": 0.2124, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 3.6451612903225805, | |
| "grad_norm": 3.645589590072632, | |
| "learning_rate": 3.02158273381295e-06, | |
| "loss": 0.157, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 3.6774193548387095, | |
| "grad_norm": 2.2191619873046875, | |
| "learning_rate": 2.949640287769784e-06, | |
| "loss": 0.1301, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 3.709677419354839, | |
| "grad_norm": 2.9101061820983887, | |
| "learning_rate": 2.877697841726619e-06, | |
| "loss": 0.1281, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 3.741935483870968, | |
| "grad_norm": 8.459104537963867, | |
| "learning_rate": 2.805755395683453e-06, | |
| "loss": 0.2189, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 3.774193548387097, | |
| "grad_norm": 4.622738361358643, | |
| "learning_rate": 2.733812949640288e-06, | |
| "loss": 0.1275, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 3.806451612903226, | |
| "grad_norm": 5.437811374664307, | |
| "learning_rate": 2.6618705035971228e-06, | |
| "loss": 0.2634, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 3.838709677419355, | |
| "grad_norm": 1.6734240055084229, | |
| "learning_rate": 2.589928057553957e-06, | |
| "loss": 0.1186, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 3.870967741935484, | |
| "grad_norm": 1.7176499366760254, | |
| "learning_rate": 2.5179856115107916e-06, | |
| "loss": 0.1065, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 3.903225806451613, | |
| "grad_norm": Infinity, | |
| "learning_rate": 2.5179856115107916e-06, | |
| "loss": 0.2718, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 3.935483870967742, | |
| "grad_norm": 5.398061752319336, | |
| "learning_rate": 2.4460431654676263e-06, | |
| "loss": 0.1756, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 3.967741935483871, | |
| "grad_norm": 5.624890327453613, | |
| "learning_rate": 2.3741007194244605e-06, | |
| "loss": 0.177, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 2.5228195190429688, | |
| "learning_rate": 2.302158273381295e-06, | |
| "loss": 0.1125, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9838709677419355, | |
| "eval_f1_macro": 0.983739837398374, | |
| "eval_f1_micro": 0.9838709677419355, | |
| "eval_f1_weighted": 0.9838709677419355, | |
| "eval_loss": 0.12518411874771118, | |
| "eval_precision_macro": 0.9841269841269842, | |
| "eval_precision_micro": 0.9838709677419355, | |
| "eval_precision_weighted": 0.9846390168970814, | |
| "eval_recall_macro": 0.9841269841269842, | |
| "eval_recall_micro": 0.9838709677419355, | |
| "eval_recall_weighted": 0.9838709677419355, | |
| "eval_runtime": 0.361, | |
| "eval_samples_per_second": 171.764, | |
| "eval_steps_per_second": 11.082, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 4.032258064516129, | |
| "grad_norm": 7.587864398956299, | |
| "learning_rate": 2.23021582733813e-06, | |
| "loss": 0.3132, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 4.064516129032258, | |
| "grad_norm": 9.148059844970703, | |
| "learning_rate": 2.158273381294964e-06, | |
| "loss": 0.3178, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 4.096774193548387, | |
| "grad_norm": 1.7947614192962646, | |
| "learning_rate": 2.0863309352517987e-06, | |
| "loss": 0.112, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 4.129032258064516, | |
| "grad_norm": 1.4539235830307007, | |
| "learning_rate": 2.0143884892086333e-06, | |
| "loss": 0.0894, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 4.161290322580645, | |
| "grad_norm": 3.562119245529175, | |
| "learning_rate": 1.942446043165468e-06, | |
| "loss": 0.1412, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 4.193548387096774, | |
| "grad_norm": 3.7732717990875244, | |
| "learning_rate": 1.8705035971223024e-06, | |
| "loss": 0.1285, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 4.225806451612903, | |
| "grad_norm": 8.253504753112793, | |
| "learning_rate": 1.7985611510791368e-06, | |
| "loss": 0.1619, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 4.258064516129032, | |
| "grad_norm": 1.0998966693878174, | |
| "learning_rate": 1.7266187050359715e-06, | |
| "loss": 0.0796, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 4.290322580645161, | |
| "grad_norm": 1.808113694190979, | |
| "learning_rate": 1.654676258992806e-06, | |
| "loss": 0.0901, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 4.32258064516129, | |
| "grad_norm": 1.456236720085144, | |
| "learning_rate": 1.5827338129496403e-06, | |
| "loss": 0.0853, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 4.354838709677419, | |
| "grad_norm": 8.323379516601562, | |
| "learning_rate": 1.510791366906475e-06, | |
| "loss": 0.2426, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 4.387096774193548, | |
| "grad_norm": 6.862564563751221, | |
| "learning_rate": 1.4388489208633094e-06, | |
| "loss": 0.179, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 4.419354838709677, | |
| "grad_norm": 8.144110679626465, | |
| "learning_rate": 1.366906474820144e-06, | |
| "loss": 0.2786, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 4.451612903225806, | |
| "grad_norm": 1.4601564407348633, | |
| "learning_rate": 1.2949640287769785e-06, | |
| "loss": 0.0765, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 4.483870967741936, | |
| "grad_norm": 8.350536346435547, | |
| "learning_rate": 1.2230215827338131e-06, | |
| "loss": 0.1893, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 4.516129032258064, | |
| "grad_norm": 6.004292011260986, | |
| "learning_rate": 1.1510791366906476e-06, | |
| "loss": 0.1283, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 4.548387096774194, | |
| "grad_norm": 4.625925540924072, | |
| "learning_rate": 1.079136690647482e-06, | |
| "loss": 0.1, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 4.580645161290323, | |
| "grad_norm": 4.438725471496582, | |
| "learning_rate": 1.0071942446043167e-06, | |
| "loss": 0.1802, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 4.612903225806452, | |
| "grad_norm": 15.338831901550293, | |
| "learning_rate": 9.352517985611512e-07, | |
| "loss": 0.2354, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 4.645161290322581, | |
| "grad_norm": 4.097437381744385, | |
| "learning_rate": 8.633093525179857e-07, | |
| "loss": 0.1042, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 4.67741935483871, | |
| "grad_norm": 4.476722240447998, | |
| "learning_rate": 7.913669064748202e-07, | |
| "loss": 0.1137, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 4.709677419354839, | |
| "grad_norm": 8.289087295532227, | |
| "learning_rate": 7.194244604316547e-07, | |
| "loss": 0.273, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 4.741935483870968, | |
| "grad_norm": 1.9783574342727661, | |
| "learning_rate": 6.474820143884893e-07, | |
| "loss": 0.1018, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 4.774193548387097, | |
| "grad_norm": 4.377150535583496, | |
| "learning_rate": 5.755395683453238e-07, | |
| "loss": 0.1195, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 4.806451612903226, | |
| "grad_norm": 3.9018876552581787, | |
| "learning_rate": 5.035971223021583e-07, | |
| "loss": 0.1093, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 4.838709677419355, | |
| "grad_norm": 13.00845718383789, | |
| "learning_rate": 4.3165467625899287e-07, | |
| "loss": 0.3638, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 4.870967741935484, | |
| "grad_norm": 4.976847171783447, | |
| "learning_rate": 3.5971223021582736e-07, | |
| "loss": 0.0991, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 4.903225806451613, | |
| "grad_norm": 10.16610336303711, | |
| "learning_rate": 2.877697841726619e-07, | |
| "loss": 0.1559, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 4.935483870967742, | |
| "grad_norm": 1.9939817190170288, | |
| "learning_rate": 2.1582733812949643e-07, | |
| "loss": 0.1162, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 4.967741935483871, | |
| "grad_norm": 5.235056400299072, | |
| "learning_rate": 1.4388489208633095e-07, | |
| "loss": 0.133, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 2.054269790649414, | |
| "learning_rate": 7.194244604316547e-08, | |
| "loss": 0.0845, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9838709677419355, | |
| "eval_f1_macro": 0.983739837398374, | |
| "eval_f1_micro": 0.9838709677419355, | |
| "eval_f1_weighted": 0.9838709677419355, | |
| "eval_loss": 0.10599859803915024, | |
| "eval_precision_macro": 0.9841269841269842, | |
| "eval_precision_micro": 0.9838709677419355, | |
| "eval_precision_weighted": 0.9846390168970814, | |
| "eval_recall_macro": 0.9841269841269842, | |
| "eval_recall_micro": 0.9838709677419355, | |
| "eval_recall_weighted": 0.9838709677419355, | |
| "eval_runtime": 0.3592, | |
| "eval_samples_per_second": 172.607, | |
| "eval_steps_per_second": 11.136, | |
| "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 | |
| } | |