| { | |
| "best_metric": 2.19789457321167, | |
| "best_model_checkpoint": "models\\DinoAmoros-small-2025_05_06_36794-prova_bs16_freeze_monolabel\\checkpoint-47", | |
| "epoch": 57.0, | |
| "eval_steps": 500, | |
| "global_step": 57, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.0, | |
| "eval_f1_macro": 0.0, | |
| "eval_f1_micro": 0.0, | |
| "eval_loss": 3.198047161102295, | |
| "eval_runtime": 0.2491, | |
| "eval_samples_per_second": 40.14, | |
| "eval_steps_per_second": 4.014, | |
| "learning_rate": 0.001, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.0, | |
| "eval_f1_macro": 0.0, | |
| "eval_f1_micro": 0.0, | |
| "eval_loss": 3.131640911102295, | |
| "eval_runtime": 0.1122, | |
| "eval_samples_per_second": 89.154, | |
| "eval_steps_per_second": 8.915, | |
| "learning_rate": 0.001, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.0, | |
| "eval_f1_macro": 0.0, | |
| "eval_f1_micro": 0.0, | |
| "eval_loss": 3.125, | |
| "eval_runtime": 0.1717, | |
| "eval_samples_per_second": 58.232, | |
| "eval_steps_per_second": 5.823, | |
| "learning_rate": 0.001, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.0, | |
| "eval_f1_macro": 0.0, | |
| "eval_f1_micro": 0.0, | |
| "eval_loss": 3.1275391578674316, | |
| "eval_runtime": 0.1416, | |
| "eval_samples_per_second": 70.64, | |
| "eval_steps_per_second": 7.064, | |
| "learning_rate": 0.001, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.1, | |
| "eval_f1_macro": 0.05714285714285715, | |
| "eval_f1_micro": 0.1, | |
| "eval_loss": 3.067577838897705, | |
| "eval_runtime": 0.1405, | |
| "eval_samples_per_second": 71.164, | |
| "eval_steps_per_second": 7.116, | |
| "learning_rate": 0.001, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.1, | |
| "eval_f1_macro": 0.05714285714285715, | |
| "eval_f1_micro": 0.1, | |
| "eval_loss": 3.065624713897705, | |
| "eval_runtime": 0.173, | |
| "eval_samples_per_second": 57.811, | |
| "eval_steps_per_second": 5.781, | |
| "learning_rate": 0.001, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.1, | |
| "eval_f1_macro": 0.05, | |
| "eval_f1_micro": 0.1, | |
| "eval_loss": 3.0042967796325684, | |
| "eval_runtime": 0.1325, | |
| "eval_samples_per_second": 75.457, | |
| "eval_steps_per_second": 7.546, | |
| "learning_rate": 0.001, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.3, | |
| "eval_f1_macro": 0.15306122448979592, | |
| "eval_f1_micro": 0.3, | |
| "eval_loss": 2.9486327171325684, | |
| "eval_runtime": 0.1302, | |
| "eval_samples_per_second": 76.779, | |
| "eval_steps_per_second": 7.678, | |
| "learning_rate": 0.001, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.4, | |
| "eval_f1_macro": 0.2816326530612245, | |
| "eval_f1_micro": 0.4, | |
| "eval_loss": 2.8736329078674316, | |
| "eval_runtime": 0.1384, | |
| "eval_samples_per_second": 72.254, | |
| "eval_steps_per_second": 7.225, | |
| "learning_rate": 0.001, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.4, | |
| "eval_f1_macro": 0.2816326530612245, | |
| "eval_f1_micro": 0.4, | |
| "eval_loss": 2.8121094703674316, | |
| "eval_runtime": 0.1367, | |
| "eval_samples_per_second": 73.148, | |
| "eval_steps_per_second": 7.315, | |
| "learning_rate": 0.001, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.6, | |
| "eval_f1_macro": 0.40277777777777773, | |
| "eval_f1_micro": 0.6, | |
| "eval_loss": 2.754101276397705, | |
| "eval_runtime": 0.164, | |
| "eval_samples_per_second": 60.964, | |
| "eval_steps_per_second": 6.096, | |
| "learning_rate": 0.001, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.6, | |
| "eval_f1_macro": 0.40277777777777773, | |
| "eval_f1_micro": 0.6, | |
| "eval_loss": 2.6966795921325684, | |
| "eval_runtime": 0.1396, | |
| "eval_samples_per_second": 71.647, | |
| "eval_steps_per_second": 7.165, | |
| "learning_rate": 0.001, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.6, | |
| "eval_f1_macro": 0.484126984126984, | |
| "eval_f1_micro": 0.6, | |
| "eval_loss": 2.6595702171325684, | |
| "eval_runtime": 0.1263, | |
| "eval_samples_per_second": 79.178, | |
| "eval_steps_per_second": 7.918, | |
| "learning_rate": 0.001, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.5, | |
| "eval_f1_macro": 0.35714285714285715, | |
| "eval_f1_micro": 0.5, | |
| "eval_loss": 2.6483397483825684, | |
| "eval_runtime": 0.1255, | |
| "eval_samples_per_second": 79.679, | |
| "eval_steps_per_second": 7.968, | |
| "learning_rate": 0.001, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.5, | |
| "eval_f1_macro": 0.35714285714285715, | |
| "eval_f1_micro": 0.5, | |
| "eval_loss": 2.6143555641174316, | |
| "eval_runtime": 0.1245, | |
| "eval_samples_per_second": 80.34, | |
| "eval_steps_per_second": 8.034, | |
| "learning_rate": 0.001, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.5, | |
| "eval_f1_macro": 0.35714285714285715, | |
| "eval_f1_micro": 0.5, | |
| "eval_loss": 2.5909180641174316, | |
| "eval_runtime": 0.141, | |
| "eval_samples_per_second": 70.936, | |
| "eval_steps_per_second": 7.094, | |
| "learning_rate": 0.001, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.5, | |
| "eval_f1_macro": 0.42857142857142855, | |
| "eval_f1_micro": 0.5, | |
| "eval_loss": 2.548144817352295, | |
| "eval_runtime": 0.1409, | |
| "eval_samples_per_second": 70.958, | |
| "eval_steps_per_second": 7.096, | |
| "learning_rate": 0.001, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.5, | |
| "eval_f1_macro": 0.3619047619047619, | |
| "eval_f1_micro": 0.5, | |
| "eval_loss": 2.5125975608825684, | |
| "eval_runtime": 0.1285, | |
| "eval_samples_per_second": 77.801, | |
| "eval_steps_per_second": 7.78, | |
| "learning_rate": 0.001, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.5, | |
| "eval_f1_macro": 0.42857142857142855, | |
| "eval_f1_micro": 0.5, | |
| "eval_loss": 2.4791016578674316, | |
| "eval_runtime": 0.1252, | |
| "eval_samples_per_second": 79.893, | |
| "eval_steps_per_second": 7.989, | |
| "learning_rate": 0.001, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.5, | |
| "eval_f1_macro": 0.42857142857142855, | |
| "eval_f1_micro": 0.5, | |
| "eval_loss": 2.473827838897705, | |
| "eval_runtime": 0.1649, | |
| "eval_samples_per_second": 60.639, | |
| "eval_steps_per_second": 6.064, | |
| "learning_rate": 0.001, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.5, | |
| "eval_f1_macro": 0.42857142857142855, | |
| "eval_f1_micro": 0.5, | |
| "eval_loss": 2.4310059547424316, | |
| "eval_runtime": 0.1318, | |
| "eval_samples_per_second": 75.857, | |
| "eval_steps_per_second": 7.586, | |
| "learning_rate": 0.001, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.5, | |
| "eval_f1_macro": 0.42857142857142855, | |
| "eval_f1_micro": 0.5, | |
| "eval_loss": 2.403027057647705, | |
| "eval_runtime": 0.1782, | |
| "eval_samples_per_second": 56.119, | |
| "eval_steps_per_second": 5.612, | |
| "learning_rate": 0.001, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.5, | |
| "eval_f1_macro": 0.42857142857142855, | |
| "eval_f1_micro": 0.5, | |
| "eval_loss": 2.400097370147705, | |
| "eval_runtime": 0.1295, | |
| "eval_samples_per_second": 77.208, | |
| "eval_steps_per_second": 7.721, | |
| "learning_rate": 0.001, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.5, | |
| "eval_f1_macro": 0.42857142857142855, | |
| "eval_f1_micro": 0.5, | |
| "eval_loss": 2.3993163108825684, | |
| "eval_runtime": 0.1217, | |
| "eval_samples_per_second": 82.203, | |
| "eval_steps_per_second": 8.22, | |
| "learning_rate": 0.001, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.5, | |
| "eval_f1_macro": 0.42857142857142855, | |
| "eval_f1_micro": 0.5, | |
| "eval_loss": 2.392773151397705, | |
| "eval_runtime": 0.1217, | |
| "eval_samples_per_second": 82.192, | |
| "eval_steps_per_second": 8.219, | |
| "learning_rate": 0.001, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.5, | |
| "eval_f1_macro": 0.42857142857142855, | |
| "eval_f1_micro": 0.5, | |
| "eval_loss": 2.3896484375, | |
| "eval_runtime": 0.1371, | |
| "eval_samples_per_second": 72.942, | |
| "eval_steps_per_second": 7.294, | |
| "learning_rate": 0.001, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.5, | |
| "eval_f1_macro": 0.42857142857142855, | |
| "eval_f1_micro": 0.5, | |
| "eval_loss": 2.390869140625, | |
| "eval_runtime": 0.1358, | |
| "eval_samples_per_second": 73.642, | |
| "eval_steps_per_second": 7.364, | |
| "learning_rate": 0.001, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.5, | |
| "eval_f1_macro": 0.42857142857142855, | |
| "eval_f1_micro": 0.5, | |
| "eval_loss": 2.377246379852295, | |
| "eval_runtime": 0.1254, | |
| "eval_samples_per_second": 79.747, | |
| "eval_steps_per_second": 7.975, | |
| "learning_rate": 0.001, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.5, | |
| "eval_f1_macro": 0.42857142857142855, | |
| "eval_f1_micro": 0.5, | |
| "eval_loss": 2.3432374000549316, | |
| "eval_runtime": 0.1266, | |
| "eval_samples_per_second": 78.973, | |
| "eval_steps_per_second": 7.897, | |
| "learning_rate": 0.001, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.5, | |
| "eval_f1_macro": 0.42857142857142855, | |
| "eval_f1_micro": 0.5, | |
| "eval_loss": 2.3191895484924316, | |
| "eval_runtime": 0.1195, | |
| "eval_samples_per_second": 83.69, | |
| "eval_steps_per_second": 8.369, | |
| "learning_rate": 0.001, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.6, | |
| "eval_f1_macro": 0.5476190476190477, | |
| "eval_f1_micro": 0.6, | |
| "eval_loss": 2.308764934539795, | |
| "eval_runtime": 0.1395, | |
| "eval_samples_per_second": 71.709, | |
| "eval_steps_per_second": 7.171, | |
| "learning_rate": 0.001, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.6, | |
| "eval_f1_macro": 0.5476190476190477, | |
| "eval_f1_micro": 0.6, | |
| "eval_loss": 2.3003783226013184, | |
| "eval_runtime": 0.1233, | |
| "eval_samples_per_second": 81.112, | |
| "eval_steps_per_second": 8.111, | |
| "learning_rate": 0.001, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.6, | |
| "eval_f1_macro": 0.5476190476190477, | |
| "eval_f1_micro": 0.6, | |
| "eval_loss": 2.304394245147705, | |
| "eval_runtime": 0.1231, | |
| "eval_samples_per_second": 81.231, | |
| "eval_steps_per_second": 8.123, | |
| "learning_rate": 0.001, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.6, | |
| "eval_f1_macro": 0.5476190476190477, | |
| "eval_f1_micro": 0.6, | |
| "eval_loss": 2.297924518585205, | |
| "eval_runtime": 0.136, | |
| "eval_samples_per_second": 73.545, | |
| "eval_steps_per_second": 7.355, | |
| "learning_rate": 0.001, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.6, | |
| "eval_f1_macro": 0.5476190476190477, | |
| "eval_f1_micro": 0.6, | |
| "eval_loss": 2.304821491241455, | |
| "eval_runtime": 0.1332, | |
| "eval_samples_per_second": 75.078, | |
| "eval_steps_per_second": 7.508, | |
| "learning_rate": 0.001, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.6, | |
| "eval_f1_macro": 0.5476190476190477, | |
| "eval_f1_micro": 0.6, | |
| "eval_loss": 2.2987122535705566, | |
| "eval_runtime": 0.1444, | |
| "eval_samples_per_second": 69.246, | |
| "eval_steps_per_second": 6.925, | |
| "learning_rate": 0.001, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.6, | |
| "eval_f1_macro": 0.5476190476190477, | |
| "eval_f1_micro": 0.6, | |
| "eval_loss": 2.299713134765625, | |
| "eval_runtime": 0.175, | |
| "eval_samples_per_second": 57.129, | |
| "eval_steps_per_second": 5.713, | |
| "learning_rate": 0.001, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.6, | |
| "eval_f1_macro": 0.5476190476190477, | |
| "eval_f1_micro": 0.6, | |
| "eval_loss": 2.319528102874756, | |
| "eval_runtime": 0.1336, | |
| "eval_samples_per_second": 74.854, | |
| "eval_steps_per_second": 7.485, | |
| "learning_rate": 0.001, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.5, | |
| "eval_f1_macro": 0.42857142857142855, | |
| "eval_f1_micro": 0.5, | |
| "eval_loss": 2.3158326148986816, | |
| "eval_runtime": 0.1144, | |
| "eval_samples_per_second": 87.426, | |
| "eval_steps_per_second": 8.743, | |
| "learning_rate": 0.001, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.5, | |
| "eval_f1_macro": 0.42857142857142855, | |
| "eval_f1_micro": 0.5, | |
| "eval_loss": 2.3082613945007324, | |
| "eval_runtime": 0.144, | |
| "eval_samples_per_second": 69.427, | |
| "eval_steps_per_second": 6.943, | |
| "learning_rate": 0.001, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.5, | |
| "eval_f1_macro": 0.42857142857142855, | |
| "eval_f1_micro": 0.5, | |
| "eval_loss": 2.28303861618042, | |
| "eval_runtime": 0.1397, | |
| "eval_samples_per_second": 71.6, | |
| "eval_steps_per_second": 7.16, | |
| "learning_rate": 0.0001, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.5, | |
| "eval_f1_macro": 0.42857142857142855, | |
| "eval_f1_micro": 0.5, | |
| "eval_loss": 2.2719388008117676, | |
| "eval_runtime": 0.1221, | |
| "eval_samples_per_second": 81.871, | |
| "eval_steps_per_second": 8.187, | |
| "learning_rate": 0.0001, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.5, | |
| "eval_f1_macro": 0.42857142857142855, | |
| "eval_f1_micro": 0.5, | |
| "eval_loss": 2.240405559539795, | |
| "eval_runtime": 0.1323, | |
| "eval_samples_per_second": 75.566, | |
| "eval_steps_per_second": 7.557, | |
| "learning_rate": 0.0001, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.5, | |
| "eval_f1_macro": 0.42857142857142855, | |
| "eval_f1_micro": 0.5, | |
| "eval_loss": 2.2438597679138184, | |
| "eval_runtime": 0.1759, | |
| "eval_samples_per_second": 56.864, | |
| "eval_steps_per_second": 5.686, | |
| "learning_rate": 0.0001, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.5, | |
| "eval_f1_macro": 0.42857142857142855, | |
| "eval_f1_micro": 0.5, | |
| "eval_loss": 2.22489595413208, | |
| "eval_runtime": 0.1278, | |
| "eval_samples_per_second": 78.272, | |
| "eval_steps_per_second": 7.827, | |
| "learning_rate": 0.0001, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.5, | |
| "eval_f1_macro": 0.42857142857142855, | |
| "eval_f1_micro": 0.5, | |
| "eval_loss": 2.21156644821167, | |
| "eval_runtime": 0.1529, | |
| "eval_samples_per_second": 65.404, | |
| "eval_steps_per_second": 6.54, | |
| "learning_rate": 0.0001, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.5, | |
| "eval_f1_macro": 0.42857142857142855, | |
| "eval_f1_micro": 0.5, | |
| "eval_loss": 2.19789457321167, | |
| "eval_runtime": 0.1469, | |
| "eval_samples_per_second": 68.081, | |
| "eval_steps_per_second": 6.808, | |
| "learning_rate": 0.0001, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.5, | |
| "eval_f1_macro": 0.42857142857142855, | |
| "eval_f1_micro": 0.5, | |
| "eval_loss": 2.208752155303955, | |
| "eval_runtime": 0.1318, | |
| "eval_samples_per_second": 75.849, | |
| "eval_steps_per_second": 7.585, | |
| "learning_rate": 0.0001, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.5, | |
| "eval_f1_macro": 0.42857142857142855, | |
| "eval_f1_micro": 0.5, | |
| "eval_loss": 2.2074952125549316, | |
| "eval_runtime": 0.1432, | |
| "eval_samples_per_second": 69.811, | |
| "eval_steps_per_second": 6.981, | |
| "learning_rate": 0.0001, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.5, | |
| "eval_f1_macro": 0.42857142857142855, | |
| "eval_f1_micro": 0.5, | |
| "eval_loss": 2.2066588401794434, | |
| "eval_runtime": 0.1397, | |
| "eval_samples_per_second": 71.588, | |
| "eval_steps_per_second": 7.159, | |
| "learning_rate": 0.0001, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.5, | |
| "eval_f1_macro": 0.42857142857142855, | |
| "eval_f1_micro": 0.5, | |
| "eval_loss": 2.218231201171875, | |
| "eval_runtime": 0.1212, | |
| "eval_samples_per_second": 82.531, | |
| "eval_steps_per_second": 8.253, | |
| "learning_rate": 0.0001, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.5, | |
| "eval_f1_macro": 0.42857142857142855, | |
| "eval_f1_micro": 0.5, | |
| "eval_loss": 2.2242674827575684, | |
| "eval_runtime": 0.17, | |
| "eval_samples_per_second": 58.815, | |
| "eval_steps_per_second": 5.881, | |
| "learning_rate": 0.0001, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.5, | |
| "eval_f1_macro": 0.42857142857142855, | |
| "eval_f1_micro": 0.5, | |
| "eval_loss": 2.23439359664917, | |
| "eval_runtime": 0.1367, | |
| "eval_samples_per_second": 73.138, | |
| "eval_steps_per_second": 7.314, | |
| "learning_rate": 0.0001, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.5, | |
| "eval_f1_macro": 0.42857142857142855, | |
| "eval_f1_micro": 0.5, | |
| "eval_loss": 2.2221617698669434, | |
| "eval_runtime": 0.1651, | |
| "eval_samples_per_second": 60.581, | |
| "eval_steps_per_second": 6.058, | |
| "learning_rate": 1e-05, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.5, | |
| "eval_f1_macro": 0.42857142857142855, | |
| "eval_f1_micro": 0.5, | |
| "eval_loss": 2.2211365699768066, | |
| "eval_runtime": 0.1366, | |
| "eval_samples_per_second": 73.229, | |
| "eval_steps_per_second": 7.323, | |
| "learning_rate": 1e-05, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.5, | |
| "eval_f1_macro": 0.42857142857142855, | |
| "eval_f1_micro": 0.5, | |
| "eval_loss": 2.207244873046875, | |
| "eval_runtime": 0.1238, | |
| "eval_samples_per_second": 80.78, | |
| "eval_steps_per_second": 8.078, | |
| "learning_rate": 1e-05, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.5, | |
| "eval_f1_macro": 0.42857142857142855, | |
| "eval_f1_micro": 0.5, | |
| "eval_loss": 2.2094483375549316, | |
| "eval_runtime": 0.1349, | |
| "eval_samples_per_second": 74.14, | |
| "eval_steps_per_second": 7.414, | |
| "learning_rate": 1e-05, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "learning_rate": 1e-05, | |
| "step": 57, | |
| "total_flos": 1.132788066729984e+16, | |
| "train_loss": 1.0105553342584979, | |
| "train_runtime": 99.3744, | |
| "train_samples_per_second": 15.094, | |
| "train_steps_per_second": 1.509 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 150, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 150, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 10, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 10 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.132788066729984e+16, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |