| { | |
| "best_metric": 0.0851063829787234, | |
| "best_model_checkpoint": "xtreme_s_xlsr_300m_mt5-small_minds14.en-US/checkpoint-20", | |
| "epoch": 49.95238095238095, | |
| "global_step": 250, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 2.9999999999999997e-06, | |
| "loss": 2.6237, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 5.999999999999999e-06, | |
| "loss": 2.6431, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 8.999999999999999e-06, | |
| "loss": 2.6487, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.1999999999999999e-05, | |
| "loss": 2.6581, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.4999999999999999e-05, | |
| "loss": 2.6703, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 1.7999999999999997e-05, | |
| "loss": 3.3039, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 2.1e-05, | |
| "loss": 2.6422, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 2.3999999999999997e-05, | |
| "loss": 2.6526, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 2.6999999999999996e-05, | |
| "loss": 2.6371, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 2.6353, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 3.2999999999999996e-05, | |
| "loss": 3.3038, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 3.5999999999999994e-05, | |
| "loss": 2.6328, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 3.9e-05, | |
| "loss": 2.6081, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 4.2e-05, | |
| "loss": 2.6003, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 4.4999999999999996e-05, | |
| "loss": 2.6218, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 4.7999999999999994e-05, | |
| "loss": 3.2488, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 5.1e-05, | |
| "loss": 2.6038, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 5.399999999999999e-05, | |
| "loss": 2.6556, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 5.6999999999999996e-05, | |
| "loss": 2.5489, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 2.6067, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "eval_accuracy": 0.0851063829787234, | |
| "eval_f1": 0.011204481792717087, | |
| "eval_loss": 2.6500837802886963, | |
| "eval_runtime": 22.888, | |
| "eval_samples_per_second": 12.321, | |
| "eval_steps_per_second": 0.218, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 6.299999999999999e-05, | |
| "loss": 3.3092, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 6.599999999999999e-05, | |
| "loss": 2.5702, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 6.9e-05, | |
| "loss": 2.6135, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 4.76, | |
| "learning_rate": 7.199999999999999e-05, | |
| "loss": 2.5806, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "learning_rate": 7.5e-05, | |
| "loss": 2.54, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 5.19, | |
| "learning_rate": 7.8e-05, | |
| "loss": 3.2317, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 5.38, | |
| "learning_rate": 8.1e-05, | |
| "loss": 2.5439, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 5.57, | |
| "learning_rate": 8.4e-05, | |
| "loss": 2.5509, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 5.76, | |
| "learning_rate": 8.699999999999999e-05, | |
| "loss": 2.5222, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 5.95, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 2.5358, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 6.19, | |
| "learning_rate": 9.3e-05, | |
| "loss": 3.1367, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 6.38, | |
| "learning_rate": 9.599999999999999e-05, | |
| "loss": 2.4961, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 6.57, | |
| "learning_rate": 9.9e-05, | |
| "loss": 2.386, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 6.76, | |
| "learning_rate": 0.000102, | |
| "loss": 2.5143, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 6.95, | |
| "learning_rate": 0.00010499999999999999, | |
| "loss": 2.5108, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 7.19, | |
| "learning_rate": 0.00010799999999999998, | |
| "loss": 3.0678, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 7.38, | |
| "learning_rate": 0.00011099999999999999, | |
| "loss": 2.3575, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 7.57, | |
| "learning_rate": 0.00011399999999999999, | |
| "loss": 2.5258, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 7.76, | |
| "learning_rate": 0.000117, | |
| "loss": 2.4514, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 7.95, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 2.5614, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 7.95, | |
| "eval_accuracy": 0.06028368794326241, | |
| "eval_f1": 0.013335536643807322, | |
| "eval_loss": 2.801831007003784, | |
| "eval_runtime": 22.1671, | |
| "eval_samples_per_second": 12.722, | |
| "eval_steps_per_second": 0.226, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 8.19, | |
| "learning_rate": 0.00012299999999999998, | |
| "loss": 2.9978, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 8.38, | |
| "learning_rate": 0.00012599999999999997, | |
| "loss": 2.378, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 8.57, | |
| "learning_rate": 0.000129, | |
| "loss": 2.4547, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 8.76, | |
| "learning_rate": 0.00013199999999999998, | |
| "loss": 2.3469, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 8.95, | |
| "learning_rate": 0.000135, | |
| "loss": 2.3036, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 9.19, | |
| "learning_rate": 0.000138, | |
| "loss": 3.0764, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 9.38, | |
| "learning_rate": 0.00014099999999999998, | |
| "loss": 2.2139, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 9.57, | |
| "learning_rate": 0.00014399999999999998, | |
| "loss": 2.1505, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 9.76, | |
| "learning_rate": 0.000147, | |
| "loss": 2.2935, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 9.95, | |
| "learning_rate": 0.00015, | |
| "loss": 2.3409, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 10.19, | |
| "learning_rate": 0.00015299999999999998, | |
| "loss": 2.9912, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 10.38, | |
| "learning_rate": 0.000156, | |
| "loss": 2.2506, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 10.57, | |
| "learning_rate": 0.000159, | |
| "loss": 2.1813, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 10.76, | |
| "learning_rate": 0.000162, | |
| "loss": 2.2503, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 10.95, | |
| "learning_rate": 0.000165, | |
| "loss": 2.2379, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 11.19, | |
| "learning_rate": 0.000168, | |
| "loss": 2.9891, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 11.38, | |
| "learning_rate": 0.00017099999999999998, | |
| "loss": 2.1612, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 11.57, | |
| "learning_rate": 0.00017399999999999997, | |
| "loss": 2.1393, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 11.76, | |
| "learning_rate": 0.00017699999999999997, | |
| "loss": 2.0967, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 11.95, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 2.2836, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 11.95, | |
| "eval_accuracy": 0.06028368794326241, | |
| "eval_f1": 0.008374384236453201, | |
| "eval_loss": 3.078601360321045, | |
| "eval_runtime": 21.8372, | |
| "eval_samples_per_second": 12.914, | |
| "eval_steps_per_second": 0.229, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 12.19, | |
| "learning_rate": 0.00018299999999999998, | |
| "loss": 2.5805, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 12.38, | |
| "learning_rate": 0.000186, | |
| "loss": 2.1918, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 12.57, | |
| "learning_rate": 0.00018899999999999999, | |
| "loss": 2.0755, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 12.76, | |
| "learning_rate": 0.00019199999999999998, | |
| "loss": 2.1025, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 12.95, | |
| "learning_rate": 0.000195, | |
| "loss": 2.0926, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 13.19, | |
| "learning_rate": 0.000198, | |
| "loss": 2.6881, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 13.38, | |
| "learning_rate": 0.000201, | |
| "loss": 2.0654, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 13.57, | |
| "learning_rate": 0.000204, | |
| "loss": 1.8003, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 13.76, | |
| "learning_rate": 0.00020699999999999996, | |
| "loss": 1.7717, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 13.95, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 2.1953, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 14.19, | |
| "learning_rate": 0.00021299999999999997, | |
| "loss": 2.4275, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 14.38, | |
| "learning_rate": 0.00021599999999999996, | |
| "loss": 1.9666, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 14.57, | |
| "learning_rate": 0.00021899999999999998, | |
| "loss": 1.8635, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 14.76, | |
| "learning_rate": 0.00022199999999999998, | |
| "loss": 1.9375, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 14.95, | |
| "learning_rate": 0.000225, | |
| "loss": 1.7644, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 15.19, | |
| "learning_rate": 0.00022799999999999999, | |
| "loss": 2.3216, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 15.38, | |
| "learning_rate": 0.00023099999999999998, | |
| "loss": 1.7671, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 15.57, | |
| "learning_rate": 0.000234, | |
| "loss": 2.0365, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 15.76, | |
| "learning_rate": 0.000237, | |
| "loss": 2.0866, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 15.95, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 1.9597, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 15.95, | |
| "eval_accuracy": 0.06382978723404255, | |
| "eval_f1": 0.012634220354808589, | |
| "eval_loss": 3.2287864685058594, | |
| "eval_runtime": 22.1138, | |
| "eval_samples_per_second": 12.752, | |
| "eval_steps_per_second": 0.226, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 16.19, | |
| "learning_rate": 0.000243, | |
| "loss": 2.2081, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 16.38, | |
| "learning_rate": 0.00024599999999999996, | |
| "loss": 1.5558, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 16.57, | |
| "learning_rate": 0.000249, | |
| "loss": 1.7294, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 16.76, | |
| "learning_rate": 0.00025199999999999995, | |
| "loss": 1.4959, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 16.95, | |
| "learning_rate": 0.00025499999999999996, | |
| "loss": 1.9221, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 17.19, | |
| "learning_rate": 0.000258, | |
| "loss": 1.939, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 17.38, | |
| "learning_rate": 0.000261, | |
| "loss": 1.6908, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 17.57, | |
| "learning_rate": 0.00026399999999999997, | |
| "loss": 1.7953, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 17.76, | |
| "learning_rate": 0.000267, | |
| "loss": 1.557, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 17.95, | |
| "learning_rate": 0.00027, | |
| "loss": 1.8179, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 18.19, | |
| "learning_rate": 0.00027299999999999997, | |
| "loss": 1.8706, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 18.38, | |
| "learning_rate": 0.000276, | |
| "loss": 1.4066, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 18.57, | |
| "learning_rate": 0.000279, | |
| "loss": 1.7786, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 18.76, | |
| "learning_rate": 0.00028199999999999997, | |
| "loss": 1.5466, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 18.95, | |
| "learning_rate": 0.000285, | |
| "loss": 1.7946, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 19.19, | |
| "learning_rate": 0.00028799999999999995, | |
| "loss": 1.6017, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 19.38, | |
| "learning_rate": 0.00029099999999999997, | |
| "loss": 1.4677, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 19.57, | |
| "learning_rate": 0.000294, | |
| "loss": 1.3462, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 19.76, | |
| "learning_rate": 0.00029699999999999996, | |
| "loss": 1.6485, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 19.95, | |
| "learning_rate": 0.0003, | |
| "loss": 1.5566, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 19.95, | |
| "eval_accuracy": 0.05673758865248227, | |
| "eval_f1": 0.017791123605077095, | |
| "eval_loss": 3.6933910846710205, | |
| "eval_runtime": 22.0004, | |
| "eval_samples_per_second": 12.818, | |
| "eval_steps_per_second": 0.227, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 20.19, | |
| "learning_rate": 0.000298, | |
| "loss": 1.8716, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 20.38, | |
| "learning_rate": 0.000296, | |
| "loss": 1.2853, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 20.57, | |
| "learning_rate": 0.000294, | |
| "loss": 1.6498, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 20.76, | |
| "learning_rate": 0.000292, | |
| "loss": 1.3141, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 20.95, | |
| "learning_rate": 0.00029, | |
| "loss": 1.3928, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 21.19, | |
| "learning_rate": 0.00028799999999999995, | |
| "loss": 1.719, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 21.38, | |
| "learning_rate": 0.00028599999999999996, | |
| "loss": 1.6084, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 21.57, | |
| "learning_rate": 0.00028399999999999996, | |
| "loss": 1.4534, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 21.76, | |
| "learning_rate": 0.00028199999999999997, | |
| "loss": 1.34, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 21.95, | |
| "learning_rate": 0.00028, | |
| "loss": 1.2225, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 22.19, | |
| "learning_rate": 0.000278, | |
| "loss": 1.8928, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 22.38, | |
| "learning_rate": 0.000276, | |
| "loss": 1.1772, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 22.57, | |
| "learning_rate": 0.000274, | |
| "loss": 1.2046, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 22.76, | |
| "learning_rate": 0.00027199999999999994, | |
| "loss": 1.2977, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 22.95, | |
| "learning_rate": 0.00027, | |
| "loss": 1.3624, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 23.19, | |
| "learning_rate": 0.00026799999999999995, | |
| "loss": 1.3893, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 23.38, | |
| "learning_rate": 0.000266, | |
| "loss": 1.0624, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 23.57, | |
| "learning_rate": 0.00026399999999999997, | |
| "loss": 1.069, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 23.76, | |
| "learning_rate": 0.00026199999999999997, | |
| "loss": 1.4328, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 23.95, | |
| "learning_rate": 0.00026, | |
| "loss": 1.3168, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 23.95, | |
| "eval_accuracy": 0.06382978723404255, | |
| "eval_f1": 0.015014809751651858, | |
| "eval_loss": 3.913482666015625, | |
| "eval_runtime": 21.9303, | |
| "eval_samples_per_second": 12.859, | |
| "eval_steps_per_second": 0.228, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 24.19, | |
| "learning_rate": 0.000258, | |
| "loss": 1.3535, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 24.38, | |
| "learning_rate": 0.000256, | |
| "loss": 1.225, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 24.57, | |
| "learning_rate": 0.000254, | |
| "loss": 1.382, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 24.76, | |
| "learning_rate": 0.00025199999999999995, | |
| "loss": 0.9501, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 24.95, | |
| "learning_rate": 0.00025, | |
| "loss": 1.2305, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 25.19, | |
| "learning_rate": 0.00024799999999999996, | |
| "loss": 1.3317, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 25.38, | |
| "learning_rate": 0.00024599999999999996, | |
| "loss": 1.0909, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 25.57, | |
| "learning_rate": 0.000244, | |
| "loss": 1.3626, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 25.76, | |
| "learning_rate": 0.00024199999999999997, | |
| "loss": 1.4076, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 25.95, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 1.178, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 26.19, | |
| "learning_rate": 0.00023799999999999998, | |
| "loss": 1.4365, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 26.38, | |
| "learning_rate": 0.00023599999999999996, | |
| "loss": 1.2742, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 26.57, | |
| "learning_rate": 0.000234, | |
| "loss": 0.9605, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 26.76, | |
| "learning_rate": 0.00023199999999999997, | |
| "loss": 1.3498, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 26.95, | |
| "learning_rate": 0.00023, | |
| "loss": 1.2505, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 27.19, | |
| "learning_rate": 0.00022799999999999999, | |
| "loss": 1.5257, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 27.38, | |
| "learning_rate": 0.00022599999999999996, | |
| "loss": 0.9837, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 27.57, | |
| "learning_rate": 0.000224, | |
| "loss": 0.9088, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 27.76, | |
| "learning_rate": 0.00022199999999999998, | |
| "loss": 1.0888, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 27.95, | |
| "learning_rate": 0.00021999999999999995, | |
| "loss": 1.0598, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 27.95, | |
| "eval_accuracy": 0.06028368794326241, | |
| "eval_f1": 0.008403361344537815, | |
| "eval_loss": 4.261812210083008, | |
| "eval_runtime": 22.0694, | |
| "eval_samples_per_second": 12.778, | |
| "eval_steps_per_second": 0.227, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 28.19, | |
| "learning_rate": 0.00021799999999999999, | |
| "loss": 1.2825, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 28.38, | |
| "learning_rate": 0.00021599999999999996, | |
| "loss": 0.9134, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 28.57, | |
| "learning_rate": 0.000214, | |
| "loss": 0.8605, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 28.76, | |
| "learning_rate": 0.00021199999999999998, | |
| "loss": 0.977, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 28.95, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 0.9525, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 29.19, | |
| "learning_rate": 0.000208, | |
| "loss": 0.9748, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 29.38, | |
| "learning_rate": 0.00020599999999999997, | |
| "loss": 0.9609, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 29.57, | |
| "learning_rate": 0.000204, | |
| "loss": 0.8758, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 29.76, | |
| "learning_rate": 0.00020199999999999998, | |
| "loss": 0.9648, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 29.95, | |
| "learning_rate": 0.00019999999999999998, | |
| "loss": 0.9435, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 30.19, | |
| "learning_rate": 0.000198, | |
| "loss": 0.8495, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 30.38, | |
| "learning_rate": 0.00019599999999999997, | |
| "loss": 0.7653, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 30.57, | |
| "learning_rate": 0.00019399999999999997, | |
| "loss": 0.5764, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 30.76, | |
| "learning_rate": 0.00019199999999999998, | |
| "loss": 0.6918, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 30.95, | |
| "learning_rate": 0.00018999999999999998, | |
| "loss": 0.9413, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 31.19, | |
| "learning_rate": 0.000188, | |
| "loss": 1.0015, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 31.38, | |
| "learning_rate": 0.000186, | |
| "loss": 0.7529, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 31.57, | |
| "learning_rate": 0.00018399999999999997, | |
| "loss": 0.8388, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 31.76, | |
| "learning_rate": 0.00018199999999999998, | |
| "loss": 0.6467, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 31.95, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 0.5721, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 31.95, | |
| "eval_accuracy": 0.07801418439716312, | |
| "eval_f1": 0.035389118125809506, | |
| "eval_loss": 3.7973175048828125, | |
| "eval_runtime": 22.0436, | |
| "eval_samples_per_second": 12.793, | |
| "eval_steps_per_second": 0.227, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 32.19, | |
| "learning_rate": 0.000178, | |
| "loss": 1.0825, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 32.38, | |
| "learning_rate": 0.000176, | |
| "loss": 0.5634, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 32.57, | |
| "learning_rate": 0.00017399999999999997, | |
| "loss": 0.8141, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 32.76, | |
| "learning_rate": 0.000172, | |
| "loss": 1.0187, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 32.95, | |
| "learning_rate": 0.00016999999999999999, | |
| "loss": 0.724, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 33.19, | |
| "learning_rate": 0.000168, | |
| "loss": 1.0303, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 33.38, | |
| "learning_rate": 0.000166, | |
| "loss": 0.7125, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 33.57, | |
| "learning_rate": 0.00016399999999999997, | |
| "loss": 0.6681, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 33.76, | |
| "learning_rate": 0.000162, | |
| "loss": 0.5326, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 33.95, | |
| "learning_rate": 0.00015999999999999999, | |
| "loss": 0.5521, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 34.19, | |
| "learning_rate": 0.00015799999999999996, | |
| "loss": 0.5982, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 34.38, | |
| "learning_rate": 0.000156, | |
| "loss": 0.5877, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 34.57, | |
| "learning_rate": 0.00015399999999999998, | |
| "loss": 0.7232, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 34.76, | |
| "learning_rate": 0.000152, | |
| "loss": 0.7139, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 34.95, | |
| "learning_rate": 0.00015, | |
| "loss": 0.4435, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 35.19, | |
| "learning_rate": 0.000148, | |
| "loss": 0.5186, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 35.38, | |
| "learning_rate": 0.000146, | |
| "loss": 0.501, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 35.57, | |
| "learning_rate": 0.00014399999999999998, | |
| "loss": 0.6495, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 35.76, | |
| "learning_rate": 0.00014199999999999998, | |
| "loss": 0.6904, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 35.95, | |
| "learning_rate": 0.00014, | |
| "loss": 0.4402, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 35.95, | |
| "eval_accuracy": 0.06382978723404255, | |
| "eval_f1": 0.017911912648754753, | |
| "eval_loss": 4.623348712921143, | |
| "eval_runtime": 21.8741, | |
| "eval_samples_per_second": 12.892, | |
| "eval_steps_per_second": 0.229, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 36.19, | |
| "learning_rate": 0.000138, | |
| "loss": 0.5381, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 36.38, | |
| "learning_rate": 0.00013599999999999997, | |
| "loss": 0.3591, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 36.57, | |
| "learning_rate": 0.00013399999999999998, | |
| "loss": 0.9615, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 36.76, | |
| "learning_rate": 0.00013199999999999998, | |
| "loss": 0.8523, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 36.95, | |
| "learning_rate": 0.00013, | |
| "loss": 0.5768, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 37.19, | |
| "learning_rate": 0.000128, | |
| "loss": 0.8723, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 37.38, | |
| "learning_rate": 0.00012599999999999997, | |
| "loss": 0.5213, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 37.57, | |
| "learning_rate": 0.00012399999999999998, | |
| "loss": 0.4604, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 37.76, | |
| "learning_rate": 0.000122, | |
| "loss": 0.3154, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 37.95, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 0.8434, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 38.19, | |
| "learning_rate": 0.00011799999999999998, | |
| "loss": 0.6779, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 38.38, | |
| "learning_rate": 0.00011599999999999999, | |
| "loss": 0.394, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 38.57, | |
| "learning_rate": 0.00011399999999999999, | |
| "loss": 0.6969, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 38.76, | |
| "learning_rate": 0.000112, | |
| "loss": 0.729, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 38.95, | |
| "learning_rate": 0.00010999999999999998, | |
| "loss": 0.5887, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 39.19, | |
| "learning_rate": 0.00010799999999999998, | |
| "loss": 0.5589, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 39.38, | |
| "learning_rate": 0.00010599999999999999, | |
| "loss": 0.4659, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 39.57, | |
| "learning_rate": 0.000104, | |
| "loss": 0.3563, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 39.76, | |
| "learning_rate": 0.000102, | |
| "loss": 0.5006, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 39.95, | |
| "learning_rate": 9.999999999999999e-05, | |
| "loss": 0.6113, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 39.95, | |
| "eval_accuracy": 0.0673758865248227, | |
| "eval_f1": 0.020788735074449362, | |
| "eval_loss": 4.614910125732422, | |
| "eval_runtime": 22.0677, | |
| "eval_samples_per_second": 12.779, | |
| "eval_steps_per_second": 0.227, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 40.19, | |
| "learning_rate": 9.799999999999998e-05, | |
| "loss": 0.5995, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 40.38, | |
| "learning_rate": 9.599999999999999e-05, | |
| "loss": 0.3788, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 40.57, | |
| "learning_rate": 9.4e-05, | |
| "loss": 0.4077, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 40.76, | |
| "learning_rate": 9.199999999999999e-05, | |
| "loss": 0.6014, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 40.95, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 0.4386, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 41.19, | |
| "learning_rate": 8.8e-05, | |
| "loss": 0.6344, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 41.38, | |
| "learning_rate": 8.6e-05, | |
| "loss": 0.4539, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 41.57, | |
| "learning_rate": 8.4e-05, | |
| "loss": 0.5215, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 41.76, | |
| "learning_rate": 8.199999999999999e-05, | |
| "loss": 0.3119, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 41.95, | |
| "learning_rate": 7.999999999999999e-05, | |
| "loss": 0.605, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 42.19, | |
| "learning_rate": 7.8e-05, | |
| "loss": 0.6575, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 42.38, | |
| "learning_rate": 7.6e-05, | |
| "loss": 0.3662, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 42.57, | |
| "learning_rate": 7.4e-05, | |
| "loss": 0.2629, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 42.76, | |
| "learning_rate": 7.199999999999999e-05, | |
| "loss": 0.4347, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 42.95, | |
| "learning_rate": 7e-05, | |
| "loss": 0.5917, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 43.19, | |
| "learning_rate": 6.799999999999999e-05, | |
| "loss": 0.7379, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 43.38, | |
| "learning_rate": 6.599999999999999e-05, | |
| "loss": 0.5227, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 43.57, | |
| "learning_rate": 6.4e-05, | |
| "loss": 0.2489, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 43.76, | |
| "learning_rate": 6.199999999999999e-05, | |
| "loss": 0.4983, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 43.95, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 0.3938, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 43.95, | |
| "eval_accuracy": 0.06382978723404255, | |
| "eval_f1": 0.015878725590955805, | |
| "eval_loss": 4.788589954376221, | |
| "eval_runtime": 21.8918, | |
| "eval_samples_per_second": 12.882, | |
| "eval_steps_per_second": 0.228, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 44.19, | |
| "learning_rate": 5.7999999999999994e-05, | |
| "loss": 0.3637, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 44.38, | |
| "learning_rate": 5.6e-05, | |
| "loss": 0.4839, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 44.57, | |
| "learning_rate": 5.399999999999999e-05, | |
| "loss": 0.3104, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 44.76, | |
| "learning_rate": 5.2e-05, | |
| "loss": 0.2964, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 44.95, | |
| "learning_rate": 4.9999999999999996e-05, | |
| "loss": 0.3151, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 45.19, | |
| "learning_rate": 4.7999999999999994e-05, | |
| "loss": 0.3447, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 45.38, | |
| "learning_rate": 4.599999999999999e-05, | |
| "loss": 0.276, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 45.57, | |
| "learning_rate": 4.4e-05, | |
| "loss": 0.4807, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 45.76, | |
| "learning_rate": 4.2e-05, | |
| "loss": 0.4292, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 45.95, | |
| "learning_rate": 3.9999999999999996e-05, | |
| "loss": 0.438, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 46.19, | |
| "learning_rate": 3.8e-05, | |
| "loss": 0.5133, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 46.38, | |
| "learning_rate": 3.5999999999999994e-05, | |
| "loss": 0.4525, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 46.57, | |
| "learning_rate": 3.399999999999999e-05, | |
| "loss": 0.3549, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 46.76, | |
| "learning_rate": 3.2e-05, | |
| "loss": 0.2801, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 46.95, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 0.2622, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 47.19, | |
| "learning_rate": 2.8e-05, | |
| "loss": 0.5435, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 47.38, | |
| "learning_rate": 2.6e-05, | |
| "loss": 0.221, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 47.57, | |
| "learning_rate": 2.3999999999999997e-05, | |
| "loss": 0.2311, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 47.76, | |
| "learning_rate": 2.2e-05, | |
| "loss": 0.2953, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 47.95, | |
| "learning_rate": 1.9999999999999998e-05, | |
| "loss": 0.2473, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 47.95, | |
| "eval_accuracy": 0.06382978723404255, | |
| "eval_f1": 0.01542207792207792, | |
| "eval_loss": 4.732133388519287, | |
| "eval_runtime": 21.9819, | |
| "eval_samples_per_second": 12.829, | |
| "eval_steps_per_second": 0.227, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 48.19, | |
| "learning_rate": 1.7999999999999997e-05, | |
| "loss": 0.3288, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 48.38, | |
| "learning_rate": 1.6e-05, | |
| "loss": 0.4118, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 48.57, | |
| "learning_rate": 1.4e-05, | |
| "loss": 0.2015, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 48.76, | |
| "learning_rate": 1.1999999999999999e-05, | |
| "loss": 0.1637, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 48.95, | |
| "learning_rate": 9.999999999999999e-06, | |
| "loss": 0.533, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 49.19, | |
| "learning_rate": 8e-06, | |
| "loss": 0.4164, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 49.38, | |
| "learning_rate": 5.999999999999999e-06, | |
| "loss": 0.2681, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 49.57, | |
| "learning_rate": 4e-06, | |
| "loss": 0.2715, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 49.76, | |
| "learning_rate": 2e-06, | |
| "loss": 0.2028, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 49.95, | |
| "learning_rate": 0.0, | |
| "loss": 0.2395, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 49.95, | |
| "step": 250, | |
| "total_flos": 2.497996718910248e+18, | |
| "train_loss": 1.3846193885803222, | |
| "train_runtime": 2065.3687, | |
| "train_samples_per_second": 3.97, | |
| "train_steps_per_second": 0.121 | |
| } | |
| ], | |
| "max_steps": 250, | |
| "num_train_epochs": 50, | |
| "total_flos": 2.497996718910248e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |