| { | |
| "best_metric": 0.875886524822695, | |
| "best_model_checkpoint": "xtreme_s_xlsr_300m_minds14.en-US_2/checkpoint-180", | |
| "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": 2.6385, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 5.999999999999999e-06, | |
| "loss": 2.6393, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 8.999999999999999e-06, | |
| "loss": 2.6383, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.1999999999999999e-05, | |
| "loss": 2.6341, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.4999999999999999e-05, | |
| "loss": 2.6426, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 1.7999999999999997e-05, | |
| "loss": 3.2976, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 2.1e-05, | |
| "loss": 2.6427, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 2.3999999999999997e-05, | |
| "loss": 2.638, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 2.6999999999999996e-05, | |
| "loss": 2.6369, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 2.6352, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 3.2999999999999996e-05, | |
| "loss": 3.2899, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 3.5999999999999994e-05, | |
| "loss": 2.6354, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 3.9e-05, | |
| "loss": 2.6296, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 4.2e-05, | |
| "loss": 2.6469, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 4.4999999999999996e-05, | |
| "loss": 2.6332, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 4.7999999999999994e-05, | |
| "loss": 3.2997, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 5.1e-05, | |
| "loss": 2.6299, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 5.399999999999999e-05, | |
| "loss": 2.6381, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 5.6999999999999996e-05, | |
| "loss": 2.637, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 2.6195, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "eval_accuracy": 0.08156028368794327, | |
| "eval_f1": 0.017200191113234592, | |
| "eval_loss": 2.6347639560699463, | |
| "eval_runtime": 17.0067, | |
| "eval_samples_per_second": 16.582, | |
| "eval_steps_per_second": 1.058, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 6.299999999999999e-05, | |
| "loss": 3.2793, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 6.599999999999999e-05, | |
| "loss": 2.6309, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 6.9e-05, | |
| "loss": 2.6306, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 4.76, | |
| "learning_rate": 7.199999999999999e-05, | |
| "loss": 2.6235, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "learning_rate": 7.5e-05, | |
| "loss": 2.6328, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 5.19, | |
| "learning_rate": 7.8e-05, | |
| "loss": 3.2753, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 5.38, | |
| "learning_rate": 8.1e-05, | |
| "loss": 2.6277, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 5.57, | |
| "learning_rate": 8.4e-05, | |
| "loss": 2.624, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 5.76, | |
| "learning_rate": 8.699999999999999e-05, | |
| "loss": 2.6107, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 5.95, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 2.6068, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 6.19, | |
| "learning_rate": 9.3e-05, | |
| "loss": 3.2691, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 6.38, | |
| "learning_rate": 9.599999999999999e-05, | |
| "loss": 2.6094, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 6.57, | |
| "learning_rate": 9.9e-05, | |
| "loss": 2.6068, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 6.76, | |
| "learning_rate": 0.000102, | |
| "loss": 2.5809, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 6.95, | |
| "learning_rate": 0.00010499999999999999, | |
| "loss": 2.5934, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 7.19, | |
| "learning_rate": 0.00010799999999999998, | |
| "loss": 3.192, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 7.38, | |
| "learning_rate": 0.00011099999999999999, | |
| "loss": 2.5513, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 7.57, | |
| "learning_rate": 0.00011399999999999999, | |
| "loss": 2.6196, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 7.76, | |
| "learning_rate": 0.000117, | |
| "loss": 2.5949, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 7.95, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 2.5925, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 7.95, | |
| "eval_accuracy": 0.0851063829787234, | |
| "eval_f1": 0.035230613984724324, | |
| "eval_loss": 2.611875295639038, | |
| "eval_runtime": 16.3097, | |
| "eval_samples_per_second": 17.29, | |
| "eval_steps_per_second": 1.104, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 8.19, | |
| "learning_rate": 0.00012299999999999998, | |
| "loss": 3.205, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 8.38, | |
| "learning_rate": 0.00012599999999999997, | |
| "loss": 2.5316, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 8.57, | |
| "learning_rate": 0.000129, | |
| "loss": 2.5142, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 8.76, | |
| "learning_rate": 0.00013199999999999998, | |
| "loss": 2.4874, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 8.95, | |
| "learning_rate": 0.000135, | |
| "loss": 2.5622, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 9.19, | |
| "learning_rate": 0.000138, | |
| "loss": 3.1398, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 9.38, | |
| "learning_rate": 0.00014099999999999998, | |
| "loss": 2.4462, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 9.57, | |
| "learning_rate": 0.00014399999999999998, | |
| "loss": 2.4995, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 9.76, | |
| "learning_rate": 0.000147, | |
| "loss": 2.4876, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 9.95, | |
| "learning_rate": 0.00015, | |
| "loss": 2.377, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 10.19, | |
| "learning_rate": 0.00015299999999999998, | |
| "loss": 2.9698, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 10.38, | |
| "learning_rate": 0.000156, | |
| "loss": 2.3821, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 10.57, | |
| "learning_rate": 0.000159, | |
| "loss": 2.2798, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 10.76, | |
| "learning_rate": 0.000162, | |
| "loss": 2.2958, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 10.95, | |
| "learning_rate": 0.000165, | |
| "loss": 2.3266, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 11.19, | |
| "learning_rate": 0.000168, | |
| "loss": 2.8351, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 11.38, | |
| "learning_rate": 0.00017099999999999998, | |
| "loss": 2.2491, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 11.57, | |
| "learning_rate": 0.00017399999999999997, | |
| "loss": 2.1973, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 11.76, | |
| "learning_rate": 0.00017699999999999997, | |
| "loss": 2.0763, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 11.95, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 2.1271, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 11.95, | |
| "eval_accuracy": 0.19858156028368795, | |
| "eval_f1": 0.15555698930698927, | |
| "eval_loss": 2.3066093921661377, | |
| "eval_runtime": 16.1461, | |
| "eval_samples_per_second": 17.466, | |
| "eval_steps_per_second": 1.115, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 12.19, | |
| "learning_rate": 0.00018299999999999998, | |
| "loss": 2.5432, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 12.38, | |
| "learning_rate": 0.000186, | |
| "loss": 2.0774, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 12.57, | |
| "learning_rate": 0.00018899999999999999, | |
| "loss": 2.0708, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 12.76, | |
| "learning_rate": 0.00019199999999999998, | |
| "loss": 1.898, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 12.95, | |
| "learning_rate": 0.000195, | |
| "loss": 1.8782, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 13.19, | |
| "learning_rate": 0.000198, | |
| "loss": 2.3485, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 13.38, | |
| "learning_rate": 0.000201, | |
| "loss": 1.7709, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 13.57, | |
| "learning_rate": 0.000204, | |
| "loss": 1.8035, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 13.76, | |
| "learning_rate": 0.00020699999999999996, | |
| "loss": 1.657, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 13.95, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 1.6485, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 14.19, | |
| "learning_rate": 0.00021299999999999997, | |
| "loss": 1.92, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 14.38, | |
| "learning_rate": 0.00021599999999999996, | |
| "loss": 1.5454, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 14.57, | |
| "learning_rate": 0.00021899999999999998, | |
| "loss": 1.5563, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 14.76, | |
| "learning_rate": 0.00022199999999999998, | |
| "loss": 1.5107, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 14.95, | |
| "learning_rate": 0.000225, | |
| "loss": 1.5645, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 15.19, | |
| "learning_rate": 0.00022799999999999999, | |
| "loss": 1.6461, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 15.38, | |
| "learning_rate": 0.00023099999999999998, | |
| "loss": 1.2531, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 15.57, | |
| "learning_rate": 0.000234, | |
| "loss": 1.3016, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 15.76, | |
| "learning_rate": 0.000237, | |
| "loss": 1.154, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 15.95, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 1.2618, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 15.95, | |
| "eval_accuracy": 0.7127659574468085, | |
| "eval_f1": 0.6877481849792252, | |
| "eval_loss": 1.381032109260559, | |
| "eval_runtime": 16.3482, | |
| "eval_samples_per_second": 17.25, | |
| "eval_steps_per_second": 1.101, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 16.19, | |
| "learning_rate": 0.000243, | |
| "loss": 1.3269, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 16.38, | |
| "learning_rate": 0.00024599999999999996, | |
| "loss": 1.267, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 16.57, | |
| "learning_rate": 0.000249, | |
| "loss": 1.3008, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 16.76, | |
| "learning_rate": 0.00025199999999999995, | |
| "loss": 1.1131, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 16.95, | |
| "learning_rate": 0.00025499999999999996, | |
| "loss": 1.1345, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 17.19, | |
| "learning_rate": 0.000258, | |
| "loss": 1.1702, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 17.38, | |
| "learning_rate": 0.000261, | |
| "loss": 0.8821, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 17.57, | |
| "learning_rate": 0.00026399999999999997, | |
| "loss": 1.1497, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 17.76, | |
| "learning_rate": 0.000267, | |
| "loss": 1.1509, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 17.95, | |
| "learning_rate": 0.00027, | |
| "loss": 1.0648, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 18.19, | |
| "learning_rate": 0.00027299999999999997, | |
| "loss": 1.2844, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 18.38, | |
| "learning_rate": 0.000276, | |
| "loss": 0.9621, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 18.57, | |
| "learning_rate": 0.000279, | |
| "loss": 0.8527, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 18.76, | |
| "learning_rate": 0.00028199999999999997, | |
| "loss": 1.0502, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 18.95, | |
| "learning_rate": 0.000285, | |
| "loss": 0.6719, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 19.19, | |
| "learning_rate": 0.00028799999999999995, | |
| "loss": 0.8417, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 19.38, | |
| "learning_rate": 0.00029099999999999997, | |
| "loss": 0.7657, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 19.57, | |
| "learning_rate": 0.000294, | |
| "loss": 0.724, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 19.76, | |
| "learning_rate": 0.00029699999999999996, | |
| "loss": 0.4878, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 19.95, | |
| "learning_rate": 0.0003, | |
| "loss": 0.5455, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 19.95, | |
| "eval_accuracy": 0.7269503546099291, | |
| "eval_f1": 0.6991854490807772, | |
| "eval_loss": 1.0403251647949219, | |
| "eval_runtime": 16.2432, | |
| "eval_samples_per_second": 17.361, | |
| "eval_steps_per_second": 1.108, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 20.19, | |
| "learning_rate": 0.000298, | |
| "loss": 0.7783, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 20.38, | |
| "learning_rate": 0.000296, | |
| "loss": 0.6694, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 20.57, | |
| "learning_rate": 0.000294, | |
| "loss": 0.504, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 20.76, | |
| "learning_rate": 0.000292, | |
| "loss": 0.3801, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 20.95, | |
| "learning_rate": 0.00029, | |
| "loss": 0.7225, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 21.19, | |
| "learning_rate": 0.00028799999999999995, | |
| "loss": 0.8528, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 21.38, | |
| "learning_rate": 0.00028599999999999996, | |
| "loss": 1.0327, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 21.57, | |
| "learning_rate": 0.00028399999999999996, | |
| "loss": 1.0904, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 21.76, | |
| "learning_rate": 0.00028199999999999997, | |
| "loss": 0.6435, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 21.95, | |
| "learning_rate": 0.00028, | |
| "loss": 0.5316, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 22.19, | |
| "learning_rate": 0.000278, | |
| "loss": 0.5442, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 22.38, | |
| "learning_rate": 0.000276, | |
| "loss": 0.4732, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 22.57, | |
| "learning_rate": 0.000274, | |
| "loss": 0.3529, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 22.76, | |
| "learning_rate": 0.00027199999999999994, | |
| "loss": 0.4958, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 22.95, | |
| "learning_rate": 0.00027, | |
| "loss": 0.6046, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 23.19, | |
| "learning_rate": 0.00026799999999999995, | |
| "loss": 0.4016, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 23.38, | |
| "learning_rate": 0.000266, | |
| "loss": 0.5724, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 23.57, | |
| "learning_rate": 0.00026399999999999997, | |
| "loss": 0.3282, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 23.76, | |
| "learning_rate": 0.00026199999999999997, | |
| "loss": 0.3314, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 23.95, | |
| "learning_rate": 0.00026, | |
| "loss": 0.2571, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 23.95, | |
| "eval_accuracy": 0.8120567375886525, | |
| "eval_f1": 0.81601355118773, | |
| "eval_loss": 0.8423281311988831, | |
| "eval_runtime": 16.3321, | |
| "eval_samples_per_second": 17.267, | |
| "eval_steps_per_second": 1.102, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 24.19, | |
| "learning_rate": 0.000258, | |
| "loss": 0.3314, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 24.38, | |
| "learning_rate": 0.000256, | |
| "loss": 0.214, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 24.57, | |
| "learning_rate": 0.000254, | |
| "loss": 0.2825, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 24.76, | |
| "learning_rate": 0.00025199999999999995, | |
| "loss": 0.5121, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 24.95, | |
| "learning_rate": 0.00025, | |
| "loss": 0.3832, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 25.19, | |
| "learning_rate": 0.00024799999999999996, | |
| "loss": 0.5013, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 25.38, | |
| "learning_rate": 0.00024599999999999996, | |
| "loss": 0.3286, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 25.57, | |
| "learning_rate": 0.000244, | |
| "loss": 0.2521, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 25.76, | |
| "learning_rate": 0.00024199999999999997, | |
| "loss": 0.2546, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 25.95, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 0.1844, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 26.19, | |
| "learning_rate": 0.00023799999999999998, | |
| "loss": 0.3035, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 26.38, | |
| "learning_rate": 0.00023599999999999996, | |
| "loss": 0.2392, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 26.57, | |
| "learning_rate": 0.000234, | |
| "loss": 0.5093, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 26.76, | |
| "learning_rate": 0.00023199999999999997, | |
| "loss": 0.8045, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 26.95, | |
| "learning_rate": 0.00023, | |
| "loss": 0.1891, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 27.19, | |
| "learning_rate": 0.00022799999999999999, | |
| "loss": 0.2445, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 27.38, | |
| "learning_rate": 0.00022599999999999996, | |
| "loss": 0.2789, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 27.57, | |
| "learning_rate": 0.000224, | |
| "loss": 0.179, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 27.76, | |
| "learning_rate": 0.00022199999999999998, | |
| "loss": 0.2237, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 27.95, | |
| "learning_rate": 0.00021999999999999995, | |
| "loss": 0.3478, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 27.95, | |
| "eval_accuracy": 0.8439716312056738, | |
| "eval_f1": 0.851591970396411, | |
| "eval_loss": 0.6499652862548828, | |
| "eval_runtime": 16.333, | |
| "eval_samples_per_second": 17.266, | |
| "eval_steps_per_second": 1.102, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 28.19, | |
| "learning_rate": 0.00021799999999999999, | |
| "loss": 0.4559, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 28.38, | |
| "learning_rate": 0.00021599999999999996, | |
| "loss": 0.2259, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 28.57, | |
| "learning_rate": 0.000214, | |
| "loss": 0.412, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 28.76, | |
| "learning_rate": 0.00021199999999999998, | |
| "loss": 0.4065, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 28.95, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 0.1336, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 29.19, | |
| "learning_rate": 0.000208, | |
| "loss": 0.1519, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 29.38, | |
| "learning_rate": 0.00020599999999999997, | |
| "loss": 0.2387, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 29.57, | |
| "learning_rate": 0.000204, | |
| "loss": 0.1746, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 29.76, | |
| "learning_rate": 0.00020199999999999998, | |
| "loss": 0.5495, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 29.95, | |
| "learning_rate": 0.00019999999999999998, | |
| "loss": 0.3561, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 30.19, | |
| "learning_rate": 0.000198, | |
| "loss": 0.1945, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 30.38, | |
| "learning_rate": 0.00019599999999999997, | |
| "loss": 0.1289, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 30.57, | |
| "learning_rate": 0.00019399999999999997, | |
| "loss": 0.133, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 30.76, | |
| "learning_rate": 0.00019199999999999998, | |
| "loss": 0.1371, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 30.95, | |
| "learning_rate": 0.00018999999999999998, | |
| "loss": 0.1858, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 31.19, | |
| "learning_rate": 0.000188, | |
| "loss": 0.1205, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 31.38, | |
| "learning_rate": 0.000186, | |
| "loss": 0.1084, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 31.57, | |
| "learning_rate": 0.00018399999999999997, | |
| "loss": 0.125, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 31.76, | |
| "learning_rate": 0.00018199999999999998, | |
| "loss": 0.2521, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 31.95, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 0.0732, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 31.95, | |
| "eval_accuracy": 0.8156028368794326, | |
| "eval_f1": 0.812294475915318, | |
| "eval_loss": 0.7066314816474915, | |
| "eval_runtime": 16.2944, | |
| "eval_samples_per_second": 17.307, | |
| "eval_steps_per_second": 1.105, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 32.19, | |
| "learning_rate": 0.000178, | |
| "loss": 0.1074, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 32.38, | |
| "learning_rate": 0.000176, | |
| "loss": 0.0687, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 32.57, | |
| "learning_rate": 0.00017399999999999997, | |
| "loss": 0.2088, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 32.76, | |
| "learning_rate": 0.000172, | |
| "loss": 0.0658, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 32.95, | |
| "learning_rate": 0.00016999999999999999, | |
| "loss": 0.1021, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 33.19, | |
| "learning_rate": 0.000168, | |
| "loss": 0.0714, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 33.38, | |
| "learning_rate": 0.000166, | |
| "loss": 0.055, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 33.57, | |
| "learning_rate": 0.00016399999999999997, | |
| "loss": 0.0711, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 33.76, | |
| "learning_rate": 0.000162, | |
| "loss": 0.1285, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 33.95, | |
| "learning_rate": 0.00015999999999999999, | |
| "loss": 0.0777, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 34.19, | |
| "learning_rate": 0.00015799999999999996, | |
| "loss": 0.0951, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 34.38, | |
| "learning_rate": 0.000156, | |
| "loss": 0.1975, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 34.57, | |
| "learning_rate": 0.00015399999999999998, | |
| "loss": 0.0395, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 34.76, | |
| "learning_rate": 0.000152, | |
| "loss": 0.0471, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 34.95, | |
| "learning_rate": 0.00015, | |
| "loss": 0.1489, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 35.19, | |
| "learning_rate": 0.000148, | |
| "loss": 0.0512, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 35.38, | |
| "learning_rate": 0.000146, | |
| "loss": 0.3909, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 35.57, | |
| "learning_rate": 0.00014399999999999998, | |
| "loss": 0.0396, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 35.76, | |
| "learning_rate": 0.00014199999999999998, | |
| "loss": 0.0473, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 35.95, | |
| "learning_rate": 0.00014199999999999998, | |
| "loss": 0.1092, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 35.95, | |
| "eval_accuracy": 0.875886524822695, | |
| "eval_f1": 0.8766602604385049, | |
| "eval_loss": 0.5878153443336487, | |
| "eval_runtime": 16.268, | |
| "eval_samples_per_second": 17.335, | |
| "eval_steps_per_second": 1.106, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 36.19, | |
| "learning_rate": 0.00014, | |
| "loss": 0.0433, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 36.38, | |
| "learning_rate": 0.000138, | |
| "loss": 0.0424, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 36.57, | |
| "learning_rate": 0.00013599999999999997, | |
| "loss": 0.0325, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 36.76, | |
| "learning_rate": 0.00013399999999999998, | |
| "loss": 0.0357, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 36.95, | |
| "learning_rate": 0.00013199999999999998, | |
| "loss": 0.043, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 37.19, | |
| "learning_rate": 0.00013, | |
| "loss": 0.1738, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 37.38, | |
| "learning_rate": 0.000128, | |
| "loss": 0.1993, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 37.57, | |
| "learning_rate": 0.00012599999999999997, | |
| "loss": 0.061, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 37.76, | |
| "learning_rate": 0.00012399999999999998, | |
| "loss": 0.0337, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 37.95, | |
| "learning_rate": 0.000122, | |
| "loss": 0.0306, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 38.19, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 0.041, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 38.38, | |
| "learning_rate": 0.00011799999999999998, | |
| "loss": 0.1831, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 38.57, | |
| "learning_rate": 0.00011599999999999999, | |
| "loss": 0.0457, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 38.76, | |
| "learning_rate": 0.00011399999999999999, | |
| "loss": 0.2698, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 38.95, | |
| "learning_rate": 0.000112, | |
| "loss": 0.1268, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 39.19, | |
| "learning_rate": 0.00010999999999999998, | |
| "loss": 0.0408, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 39.38, | |
| "learning_rate": 0.00010799999999999998, | |
| "loss": 0.1086, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 39.57, | |
| "learning_rate": 0.00010599999999999999, | |
| "loss": 0.0435, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 39.76, | |
| "learning_rate": 0.000104, | |
| "loss": 0.1343, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 39.95, | |
| "learning_rate": 0.000102, | |
| "loss": 0.0271, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 39.95, | |
| "eval_accuracy": 0.8617021276595744, | |
| "eval_f1": 0.8578022762116569, | |
| "eval_loss": 0.5993813872337341, | |
| "eval_runtime": 16.2429, | |
| "eval_samples_per_second": 17.361, | |
| "eval_steps_per_second": 1.108, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 40.19, | |
| "learning_rate": 9.999999999999999e-05, | |
| "loss": 0.0756, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 40.38, | |
| "learning_rate": 9.799999999999998e-05, | |
| "loss": 0.0385, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 40.57, | |
| "learning_rate": 9.599999999999999e-05, | |
| "loss": 0.0659, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 40.76, | |
| "learning_rate": 9.4e-05, | |
| "loss": 0.0579, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 40.95, | |
| "learning_rate": 9.199999999999999e-05, | |
| "loss": 0.031, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 41.19, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 0.0363, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 41.38, | |
| "learning_rate": 8.8e-05, | |
| "loss": 0.0857, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 41.57, | |
| "learning_rate": 8.6e-05, | |
| "loss": 0.0338, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 41.76, | |
| "learning_rate": 8.4e-05, | |
| "loss": 0.0378, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 41.95, | |
| "learning_rate": 8.199999999999999e-05, | |
| "loss": 0.0263, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 42.19, | |
| "learning_rate": 7.999999999999999e-05, | |
| "loss": 0.0433, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 42.38, | |
| "learning_rate": 7.8e-05, | |
| "loss": 0.0274, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 42.57, | |
| "learning_rate": 7.6e-05, | |
| "loss": 0.0433, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 42.76, | |
| "learning_rate": 7.4e-05, | |
| "loss": 0.0698, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 42.95, | |
| "learning_rate": 7.199999999999999e-05, | |
| "loss": 0.0217, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 43.19, | |
| "learning_rate": 7e-05, | |
| "loss": 0.0471, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 43.38, | |
| "learning_rate": 6.799999999999999e-05, | |
| "loss": 0.0226, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 43.57, | |
| "learning_rate": 6.599999999999999e-05, | |
| "loss": 0.0224, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 43.76, | |
| "learning_rate": 6.4e-05, | |
| "loss": 0.0214, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 43.95, | |
| "learning_rate": 6.199999999999999e-05, | |
| "loss": 0.4664, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 43.95, | |
| "eval_accuracy": 0.8439716312056738, | |
| "eval_f1": 0.8402871437379335, | |
| "eval_loss": 0.7830185890197754, | |
| "eval_runtime": 16.2374, | |
| "eval_samples_per_second": 17.367, | |
| "eval_steps_per_second": 1.109, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 44.19, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 0.3105, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 44.38, | |
| "learning_rate": 5.7999999999999994e-05, | |
| "loss": 0.081, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 44.57, | |
| "learning_rate": 5.6e-05, | |
| "loss": 0.0277, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 44.76, | |
| "learning_rate": 5.399999999999999e-05, | |
| "loss": 0.0273, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 44.95, | |
| "learning_rate": 5.2e-05, | |
| "loss": 0.0269, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 45.19, | |
| "learning_rate": 4.9999999999999996e-05, | |
| "loss": 0.0394, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 45.38, | |
| "learning_rate": 4.7999999999999994e-05, | |
| "loss": 0.0699, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 45.57, | |
| "learning_rate": 4.599999999999999e-05, | |
| "loss": 0.0639, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 45.76, | |
| "learning_rate": 4.4e-05, | |
| "loss": 0.02, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 45.95, | |
| "learning_rate": 4.2e-05, | |
| "loss": 0.0237, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 46.19, | |
| "learning_rate": 3.9999999999999996e-05, | |
| "loss": 0.0268, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 46.38, | |
| "learning_rate": 3.8e-05, | |
| "loss": 0.0195, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 46.57, | |
| "learning_rate": 3.5999999999999994e-05, | |
| "loss": 0.0199, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 46.76, | |
| "learning_rate": 3.399999999999999e-05, | |
| "loss": 0.0205, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 46.95, | |
| "learning_rate": 3.2e-05, | |
| "loss": 0.0231, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 47.19, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 0.0242, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 47.38, | |
| "learning_rate": 2.8e-05, | |
| "loss": 0.0219, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 47.57, | |
| "learning_rate": 2.6e-05, | |
| "loss": 0.0226, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 47.76, | |
| "learning_rate": 2.3999999999999997e-05, | |
| "loss": 0.0213, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 47.95, | |
| "learning_rate": 2.2e-05, | |
| "loss": 0.0192, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 47.95, | |
| "eval_accuracy": 0.875886524822695, | |
| "eval_f1": 0.874718376861234, | |
| "eval_loss": 0.5684738159179688, | |
| "eval_runtime": 16.3149, | |
| "eval_samples_per_second": 17.285, | |
| "eval_steps_per_second": 1.103, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 48.19, | |
| "learning_rate": 1.9999999999999998e-05, | |
| "loss": 0.022, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 48.38, | |
| "learning_rate": 1.7999999999999997e-05, | |
| "loss": 0.02, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 48.57, | |
| "learning_rate": 1.6e-05, | |
| "loss": 0.0185, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 48.76, | |
| "learning_rate": 1.4e-05, | |
| "loss": 0.0185, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 48.95, | |
| "learning_rate": 1.1999999999999999e-05, | |
| "loss": 0.0207, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 49.19, | |
| "learning_rate": 9.999999999999999e-06, | |
| "loss": 0.1504, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 49.38, | |
| "learning_rate": 8e-06, | |
| "loss": 0.0932, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 49.57, | |
| "learning_rate": 5.999999999999999e-06, | |
| "loss": 0.0191, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 49.76, | |
| "learning_rate": 4e-06, | |
| "loss": 0.0204, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 49.95, | |
| "learning_rate": 2e-06, | |
| "loss": 0.0192, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 49.95, | |
| "step": 250, | |
| "total_flos": 2.2169595227007877e+18, | |
| "train_loss": 0.970869776725769, | |
| "train_runtime": 888.1973, | |
| "train_samples_per_second": 9.401, | |
| "train_steps_per_second": 0.281 | |
| } | |
| ], | |
| "max_steps": 250, | |
| "num_train_epochs": 50, | |
| "total_flos": 2.2169595227007877e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |