| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "global_step": 1750, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0, |
| "learning_rate": 4.9971428571428576e-05, |
| "loss": 13.0691, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.02, |
| "learning_rate": 4.9e-05, |
| "loss": 14.048, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.02, |
| "eval_accuracy": 0.5, |
| "eval_f1": 0.6666666666666666, |
| "eval_loss": 7.880705833435059, |
| "eval_precision": 0.5, |
| "eval_recall": 1.0, |
| "eval_runtime": 80.7039, |
| "eval_samples_per_second": 37.173, |
| "eval_steps_per_second": 4.647, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.04, |
| "learning_rate": 4.8e-05, |
| "loss": 2.2656, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.04, |
| "eval_accuracy": 0.5016666666666667, |
| "eval_f1": 0.6674082313681868, |
| "eval_loss": 3.2190163135528564, |
| "eval_precision": 0.5008347245409015, |
| "eval_recall": 1.0, |
| "eval_runtime": 80.4061, |
| "eval_samples_per_second": 37.311, |
| "eval_steps_per_second": 4.664, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.06, |
| "learning_rate": 4.7e-05, |
| "loss": 2.1548, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.06, |
| "eval_accuracy": 0.6906666666666667, |
| "eval_f1": 0.7371104815864024, |
| "eval_loss": 0.5703864097595215, |
| "eval_precision": 0.6408866995073892, |
| "eval_recall": 0.8673333333333333, |
| "eval_runtime": 80.8676, |
| "eval_samples_per_second": 37.098, |
| "eval_steps_per_second": 4.637, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.08, |
| "learning_rate": 4.600000000000001e-05, |
| "loss": 1.3819, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.08, |
| "eval_accuracy": 0.5, |
| "eval_f1": 0.0, |
| "eval_loss": 0.9337035417556763, |
| "eval_precision": 0.0, |
| "eval_recall": 0.0, |
| "eval_runtime": 80.5811, |
| "eval_samples_per_second": 37.23, |
| "eval_steps_per_second": 4.654, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.1, |
| "learning_rate": 4.5e-05, |
| "loss": 1.1309, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.1, |
| "eval_accuracy": 0.5, |
| "eval_f1": 0.6666666666666666, |
| "eval_loss": 2.4655497074127197, |
| "eval_precision": 0.5, |
| "eval_recall": 1.0, |
| "eval_runtime": 80.4828, |
| "eval_samples_per_second": 37.275, |
| "eval_steps_per_second": 4.659, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.12, |
| "learning_rate": 4.4000000000000006e-05, |
| "loss": 0.9397, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.12, |
| "eval_accuracy": 0.6686666666666666, |
| "eval_f1": 0.7317862924986509, |
| "eval_loss": 0.6442784667015076, |
| "eval_precision": 0.614687216681777, |
| "eval_recall": 0.904, |
| "eval_runtime": 80.537, |
| "eval_samples_per_second": 37.25, |
| "eval_steps_per_second": 4.656, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.14, |
| "learning_rate": 4.3e-05, |
| "loss": 0.8193, |
| "step": 245 |
| }, |
| { |
| "epoch": 0.14, |
| "eval_accuracy": 0.6676666666666666, |
| "eval_f1": 0.7155492154065621, |
| "eval_loss": 1.0818308591842651, |
| "eval_precision": 0.6254364089775561, |
| "eval_recall": 0.836, |
| "eval_runtime": 81.1642, |
| "eval_samples_per_second": 36.962, |
| "eval_steps_per_second": 4.62, |
| "step": 245 |
| }, |
| { |
| "epoch": 0.16, |
| "learning_rate": 4.2e-05, |
| "loss": 0.6235, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.16, |
| "eval_accuracy": 0.5413333333333333, |
| "eval_f1": 0.685413808870599, |
| "eval_loss": 1.136587381362915, |
| "eval_precision": 0.5215727209464162, |
| "eval_recall": 0.9993333333333333, |
| "eval_runtime": 81.1897, |
| "eval_samples_per_second": 36.951, |
| "eval_steps_per_second": 4.619, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.18, |
| "learning_rate": 4.1e-05, |
| "loss": 0.6828, |
| "step": 315 |
| }, |
| { |
| "epoch": 0.18, |
| "eval_accuracy": 0.7913333333333333, |
| "eval_f1": 0.7481898632341111, |
| "eval_loss": 0.5717737674713135, |
| "eval_precision": 0.9432048681541582, |
| "eval_recall": 0.62, |
| "eval_runtime": 80.6162, |
| "eval_samples_per_second": 37.213, |
| "eval_steps_per_second": 4.652, |
| "step": 315 |
| }, |
| { |
| "epoch": 0.2, |
| "learning_rate": 4e-05, |
| "loss": 0.5375, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.2, |
| "eval_accuracy": 0.6203333333333333, |
| "eval_f1": 0.7234765719834911, |
| "eval_loss": 1.3898557424545288, |
| "eval_precision": 0.5689194348988164, |
| "eval_recall": 0.9933333333333333, |
| "eval_runtime": 80.8767, |
| "eval_samples_per_second": 37.094, |
| "eval_steps_per_second": 4.637, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.22, |
| "learning_rate": 3.9000000000000006e-05, |
| "loss": 0.8008, |
| "step": 385 |
| }, |
| { |
| "epoch": 0.22, |
| "eval_accuracy": 0.6446666666666667, |
| "eval_f1": 0.7352210630899155, |
| "eval_loss": 1.3506994247436523, |
| "eval_precision": 0.5859065716547902, |
| "eval_recall": 0.9866666666666667, |
| "eval_runtime": 80.9272, |
| "eval_samples_per_second": 37.07, |
| "eval_steps_per_second": 4.634, |
| "step": 385 |
| }, |
| { |
| "epoch": 0.24, |
| "learning_rate": 3.8e-05, |
| "loss": 0.5408, |
| "step": 420 |
| }, |
| { |
| "epoch": 0.24, |
| "eval_accuracy": 0.5, |
| "eval_f1": 0.6666666666666666, |
| "eval_loss": 5.448528289794922, |
| "eval_precision": 0.5, |
| "eval_recall": 1.0, |
| "eval_runtime": 80.3832, |
| "eval_samples_per_second": 37.321, |
| "eval_steps_per_second": 4.665, |
| "step": 420 |
| }, |
| { |
| "epoch": 0.26, |
| "learning_rate": 3.7e-05, |
| "loss": 1.5679, |
| "step": 455 |
| }, |
| { |
| "epoch": 0.26, |
| "eval_accuracy": 0.5303333333333333, |
| "eval_f1": 0.6804264005443411, |
| "eval_loss": 2.9407122135162354, |
| "eval_precision": 0.5156411137848058, |
| "eval_recall": 1.0, |
| "eval_runtime": 80.4322, |
| "eval_samples_per_second": 37.298, |
| "eval_steps_per_second": 4.662, |
| "step": 455 |
| }, |
| { |
| "epoch": 0.28, |
| "learning_rate": 3.6e-05, |
| "loss": 0.7113, |
| "step": 490 |
| }, |
| { |
| "epoch": 0.28, |
| "eval_accuracy": 0.5003333333333333, |
| "eval_f1": 0.6668148477439431, |
| "eval_loss": 4.913637638092041, |
| "eval_precision": 0.5001667222407469, |
| "eval_recall": 1.0, |
| "eval_runtime": 80.9405, |
| "eval_samples_per_second": 37.064, |
| "eval_steps_per_second": 4.633, |
| "step": 490 |
| }, |
| { |
| "epoch": 0.3, |
| "learning_rate": 3.5e-05, |
| "loss": 0.5356, |
| "step": 525 |
| }, |
| { |
| "epoch": 0.3, |
| "eval_accuracy": 0.6223333333333333, |
| "eval_f1": 0.724933236222384, |
| "eval_loss": 1.4003673791885376, |
| "eval_precision": 0.5700649102710958, |
| "eval_recall": 0.9953333333333333, |
| "eval_runtime": 80.635, |
| "eval_samples_per_second": 37.205, |
| "eval_steps_per_second": 4.651, |
| "step": 525 |
| }, |
| { |
| "epoch": 0.32, |
| "learning_rate": 3.4000000000000007e-05, |
| "loss": 0.4847, |
| "step": 560 |
| }, |
| { |
| "epoch": 0.32, |
| "eval_accuracy": 0.5016666666666667, |
| "eval_f1": 0.6674082313681868, |
| "eval_loss": 6.015239715576172, |
| "eval_precision": 0.5008347245409015, |
| "eval_recall": 1.0, |
| "eval_runtime": 80.7702, |
| "eval_samples_per_second": 37.142, |
| "eval_steps_per_second": 4.643, |
| "step": 560 |
| }, |
| { |
| "epoch": 0.34, |
| "learning_rate": 3.3e-05, |
| "loss": 0.319, |
| "step": 595 |
| }, |
| { |
| "epoch": 0.34, |
| "eval_accuracy": 0.8496666666666667, |
| "eval_f1": 0.8543752018082015, |
| "eval_loss": 0.6166228652000427, |
| "eval_precision": 0.828428303068253, |
| "eval_recall": 0.882, |
| "eval_runtime": 80.8211, |
| "eval_samples_per_second": 37.119, |
| "eval_steps_per_second": 4.64, |
| "step": 595 |
| }, |
| { |
| "epoch": 0.36, |
| "learning_rate": 3.2000000000000005e-05, |
| "loss": 0.822, |
| "step": 630 |
| }, |
| { |
| "epoch": 0.36, |
| "eval_accuracy": 0.8383333333333334, |
| "eval_f1": 0.820967146548542, |
| "eval_loss": 0.41078850626945496, |
| "eval_precision": 0.9197684036393714, |
| "eval_recall": 0.7413333333333333, |
| "eval_runtime": 80.9973, |
| "eval_samples_per_second": 37.038, |
| "eval_steps_per_second": 4.63, |
| "step": 630 |
| }, |
| { |
| "epoch": 0.38, |
| "learning_rate": 3.1e-05, |
| "loss": 0.4746, |
| "step": 665 |
| }, |
| { |
| "epoch": 0.38, |
| "eval_accuracy": 0.8246666666666667, |
| "eval_f1": 0.830213040671401, |
| "eval_loss": 0.3808746337890625, |
| "eval_precision": 0.804755944931164, |
| "eval_recall": 0.8573333333333333, |
| "eval_runtime": 80.4252, |
| "eval_samples_per_second": 37.302, |
| "eval_steps_per_second": 4.663, |
| "step": 665 |
| }, |
| { |
| "epoch": 0.4, |
| "learning_rate": 3e-05, |
| "loss": 0.2913, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.4, |
| "eval_accuracy": 0.747, |
| "eval_f1": 0.7941415785191213, |
| "eval_loss": 0.7681821584701538, |
| "eval_precision": 0.6694101508916324, |
| "eval_recall": 0.976, |
| "eval_runtime": 80.4193, |
| "eval_samples_per_second": 37.304, |
| "eval_steps_per_second": 4.663, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.42, |
| "learning_rate": 2.9e-05, |
| "loss": 0.3153, |
| "step": 735 |
| }, |
| { |
| "epoch": 0.42, |
| "eval_accuracy": 0.8356666666666667, |
| "eval_f1": 0.8523510032943996, |
| "eval_loss": 0.4611086845397949, |
| "eval_precision": 0.7737901033170201, |
| "eval_recall": 0.9486666666666667, |
| "eval_runtime": 80.4421, |
| "eval_samples_per_second": 37.294, |
| "eval_steps_per_second": 4.662, |
| "step": 735 |
| }, |
| { |
| "epoch": 0.44, |
| "learning_rate": 2.8000000000000003e-05, |
| "loss": 0.4953, |
| "step": 770 |
| }, |
| { |
| "epoch": 0.44, |
| "eval_accuracy": 0.5146666666666667, |
| "eval_f1": 0.6732495511669659, |
| "eval_loss": 1.9276390075683594, |
| "eval_precision": 0.5074424898511503, |
| "eval_recall": 1.0, |
| "eval_runtime": 80.6277, |
| "eval_samples_per_second": 37.208, |
| "eval_steps_per_second": 4.651, |
| "step": 770 |
| }, |
| { |
| "epoch": 0.46, |
| "learning_rate": 2.7000000000000002e-05, |
| "loss": 0.8238, |
| "step": 805 |
| }, |
| { |
| "epoch": 0.46, |
| "eval_accuracy": 0.8233333333333334, |
| "eval_f1": 0.789515488482923, |
| "eval_loss": 0.758985698223114, |
| "eval_precision": 0.9764243614931237, |
| "eval_recall": 0.6626666666666666, |
| "eval_runtime": 80.4659, |
| "eval_samples_per_second": 37.283, |
| "eval_steps_per_second": 4.66, |
| "step": 805 |
| }, |
| { |
| "epoch": 0.48, |
| "learning_rate": 2.6000000000000002e-05, |
| "loss": 0.6315, |
| "step": 840 |
| }, |
| { |
| "epoch": 0.48, |
| "eval_accuracy": 0.5013333333333333, |
| "eval_f1": 0.6672597864768683, |
| "eval_loss": 5.900465965270996, |
| "eval_precision": 0.5006675567423231, |
| "eval_recall": 1.0, |
| "eval_runtime": 80.4747, |
| "eval_samples_per_second": 37.279, |
| "eval_steps_per_second": 4.66, |
| "step": 840 |
| }, |
| { |
| "epoch": 0.5, |
| "learning_rate": 2.5e-05, |
| "loss": 0.4659, |
| "step": 875 |
| }, |
| { |
| "epoch": 0.5, |
| "eval_accuracy": 0.879, |
| "eval_f1": 0.875214850464077, |
| "eval_loss": 0.2947004735469818, |
| "eval_precision": 0.9034776437189496, |
| "eval_recall": 0.8486666666666667, |
| "eval_runtime": 80.8565, |
| "eval_samples_per_second": 37.103, |
| "eval_steps_per_second": 4.638, |
| "step": 875 |
| }, |
| { |
| "epoch": 0.52, |
| "learning_rate": 2.4e-05, |
| "loss": 0.2773, |
| "step": 910 |
| }, |
| { |
| "epoch": 0.52, |
| "eval_accuracy": 0.5133333333333333, |
| "eval_f1": 0.672645739910314, |
| "eval_loss": 3.5455527305603027, |
| "eval_precision": 0.5067567567567568, |
| "eval_recall": 1.0, |
| "eval_runtime": 80.4994, |
| "eval_samples_per_second": 37.267, |
| "eval_steps_per_second": 4.658, |
| "step": 910 |
| }, |
| { |
| "epoch": 0.54, |
| "learning_rate": 2.3000000000000003e-05, |
| "loss": 0.371, |
| "step": 945 |
| }, |
| { |
| "epoch": 0.54, |
| "eval_accuracy": 0.5043333333333333, |
| "eval_f1": 0.6685981724983284, |
| "eval_loss": 3.9809491634368896, |
| "eval_precision": 0.5021760964178105, |
| "eval_recall": 1.0, |
| "eval_runtime": 80.5845, |
| "eval_samples_per_second": 37.228, |
| "eval_steps_per_second": 4.654, |
| "step": 945 |
| }, |
| { |
| "epoch": 0.56, |
| "learning_rate": 2.2000000000000003e-05, |
| "loss": 0.4968, |
| "step": 980 |
| }, |
| { |
| "epoch": 0.56, |
| "eval_accuracy": 0.713, |
| "eval_f1": 0.7757228444907528, |
| "eval_loss": 1.2047169208526611, |
| "eval_precision": 0.6365968362548098, |
| "eval_recall": 0.9926666666666667, |
| "eval_runtime": 80.9051, |
| "eval_samples_per_second": 37.08, |
| "eval_steps_per_second": 4.635, |
| "step": 980 |
| }, |
| { |
| "epoch": 0.58, |
| "learning_rate": 2.1e-05, |
| "loss": 0.5577, |
| "step": 1015 |
| }, |
| { |
| "epoch": 0.58, |
| "eval_accuracy": 0.9123333333333333, |
| "eval_f1": 0.9118337244384848, |
| "eval_loss": 0.24421826004981995, |
| "eval_precision": 0.9170600134861767, |
| "eval_recall": 0.9066666666666666, |
| "eval_runtime": 80.8404, |
| "eval_samples_per_second": 37.11, |
| "eval_steps_per_second": 4.639, |
| "step": 1015 |
| }, |
| { |
| "epoch": 0.6, |
| "learning_rate": 2e-05, |
| "loss": 0.2212, |
| "step": 1050 |
| }, |
| { |
| "epoch": 0.6, |
| "eval_accuracy": 0.8366666666666667, |
| "eval_f1": 0.8556275780789628, |
| "eval_loss": 0.44433295726776123, |
| "eval_precision": 0.7666314677930306, |
| "eval_recall": 0.968, |
| "eval_runtime": 80.4427, |
| "eval_samples_per_second": 37.294, |
| "eval_steps_per_second": 4.662, |
| "step": 1050 |
| }, |
| { |
| "epoch": 0.62, |
| "learning_rate": 1.9e-05, |
| "loss": 0.2668, |
| "step": 1085 |
| }, |
| { |
| "epoch": 0.62, |
| "eval_accuracy": 0.56, |
| "eval_f1": 0.6943029180176007, |
| "eval_loss": 2.2121241092681885, |
| "eval_precision": 0.5319375443577005, |
| "eval_recall": 0.9993333333333333, |
| "eval_runtime": 80.772, |
| "eval_samples_per_second": 37.142, |
| "eval_steps_per_second": 4.643, |
| "step": 1085 |
| }, |
| { |
| "epoch": 0.64, |
| "learning_rate": 1.8e-05, |
| "loss": 0.2392, |
| "step": 1120 |
| }, |
| { |
| "epoch": 0.64, |
| "eval_accuracy": 0.617, |
| "eval_f1": 0.7223967141821697, |
| "eval_loss": 1.7039114236831665, |
| "eval_precision": 0.5665024630541872, |
| "eval_recall": 0.9966666666666667, |
| "eval_runtime": 81.2102, |
| "eval_samples_per_second": 36.941, |
| "eval_steps_per_second": 4.618, |
| "step": 1120 |
| }, |
| { |
| "epoch": 0.66, |
| "learning_rate": 1.7000000000000003e-05, |
| "loss": 0.4237, |
| "step": 1155 |
| }, |
| { |
| "epoch": 0.66, |
| "eval_accuracy": 0.5113333333333333, |
| "eval_f1": 0.6717420510523958, |
| "eval_loss": 3.3159143924713135, |
| "eval_precision": 0.5057316250842886, |
| "eval_recall": 1.0, |
| "eval_runtime": 80.4636, |
| "eval_samples_per_second": 37.284, |
| "eval_steps_per_second": 4.66, |
| "step": 1155 |
| }, |
| { |
| "epoch": 0.68, |
| "learning_rate": 1.6000000000000003e-05, |
| "loss": 0.4353, |
| "step": 1190 |
| }, |
| { |
| "epoch": 0.68, |
| "eval_accuracy": 0.82, |
| "eval_f1": 0.8432055749128919, |
| "eval_loss": 0.5704355239868164, |
| "eval_precision": 0.7469135802469136, |
| "eval_recall": 0.968, |
| "eval_runtime": 80.5065, |
| "eval_samples_per_second": 37.264, |
| "eval_steps_per_second": 4.658, |
| "step": 1190 |
| }, |
| { |
| "epoch": 0.7, |
| "learning_rate": 1.5e-05, |
| "loss": 0.3109, |
| "step": 1225 |
| }, |
| { |
| "epoch": 0.7, |
| "eval_accuracy": 0.6846666666666666, |
| "eval_f1": 0.7591649694501018, |
| "eval_loss": 1.1700917482376099, |
| "eval_precision": 0.6140856672158155, |
| "eval_recall": 0.994, |
| "eval_runtime": 80.6642, |
| "eval_samples_per_second": 37.191, |
| "eval_steps_per_second": 4.649, |
| "step": 1225 |
| }, |
| { |
| "epoch": 0.72, |
| "learning_rate": 1.4000000000000001e-05, |
| "loss": 0.2154, |
| "step": 1260 |
| }, |
| { |
| "epoch": 0.72, |
| "eval_accuracy": 0.817, |
| "eval_f1": 0.8419234091563489, |
| "eval_loss": 0.48465803265571594, |
| "eval_precision": 0.7410035478966042, |
| "eval_recall": 0.9746666666666667, |
| "eval_runtime": 80.8924, |
| "eval_samples_per_second": 37.086, |
| "eval_steps_per_second": 4.636, |
| "step": 1260 |
| }, |
| { |
| "epoch": 0.74, |
| "learning_rate": 1.3000000000000001e-05, |
| "loss": 0.2415, |
| "step": 1295 |
| }, |
| { |
| "epoch": 0.74, |
| "eval_accuracy": 0.8613333333333333, |
| "eval_f1": 0.87363304981774, |
| "eval_loss": 0.36877182126045227, |
| "eval_precision": 0.8024553571428571, |
| "eval_recall": 0.9586666666666667, |
| "eval_runtime": 80.8409, |
| "eval_samples_per_second": 37.11, |
| "eval_steps_per_second": 4.639, |
| "step": 1295 |
| }, |
| { |
| "epoch": 0.76, |
| "learning_rate": 1.2e-05, |
| "loss": 0.2014, |
| "step": 1330 |
| }, |
| { |
| "epoch": 0.76, |
| "eval_accuracy": 0.7543333333333333, |
| "eval_f1": 0.8008646311807619, |
| "eval_loss": 0.6940145492553711, |
| "eval_precision": 0.6733303044070876, |
| "eval_recall": 0.988, |
| "eval_runtime": 86.2109, |
| "eval_samples_per_second": 34.798, |
| "eval_steps_per_second": 4.35, |
| "step": 1330 |
| }, |
| { |
| "epoch": 0.78, |
| "learning_rate": 1.1000000000000001e-05, |
| "loss": 0.2165, |
| "step": 1365 |
| }, |
| { |
| "epoch": 0.78, |
| "eval_accuracy": 0.611, |
| "eval_f1": 0.7195385724585437, |
| "eval_loss": 1.6025038957595825, |
| "eval_precision": 0.5625704622322435, |
| "eval_recall": 0.998, |
| "eval_runtime": 81.0854, |
| "eval_samples_per_second": 36.998, |
| "eval_steps_per_second": 4.625, |
| "step": 1365 |
| }, |
| { |
| "epoch": 0.8, |
| "learning_rate": 1e-05, |
| "loss": 0.2487, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.8, |
| "eval_accuracy": 0.73, |
| "eval_f1": 0.7856008470089996, |
| "eval_loss": 0.8998059630393982, |
| "eval_precision": 0.6514486391571555, |
| "eval_recall": 0.9893333333333333, |
| "eval_runtime": 80.4427, |
| "eval_samples_per_second": 37.294, |
| "eval_steps_per_second": 4.662, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.82, |
| "learning_rate": 9e-06, |
| "loss": 0.2204, |
| "step": 1435 |
| }, |
| { |
| "epoch": 0.82, |
| "eval_accuracy": 0.8493333333333334, |
| "eval_f1": 0.8598884066955982, |
| "eval_loss": 0.3596617579460144, |
| "eval_precision": 0.8035921205098494, |
| "eval_recall": 0.9246666666666666, |
| "eval_runtime": 80.5841, |
| "eval_samples_per_second": 37.228, |
| "eval_steps_per_second": 4.654, |
| "step": 1435 |
| }, |
| { |
| "epoch": 0.84, |
| "learning_rate": 8.000000000000001e-06, |
| "loss": 0.1436, |
| "step": 1470 |
| }, |
| { |
| "epoch": 0.84, |
| "eval_accuracy": 0.5616666666666666, |
| "eval_f1": 0.6951078135868306, |
| "eval_loss": 2.4785938262939453, |
| "eval_precision": 0.5328830430145752, |
| "eval_recall": 0.9993333333333333, |
| "eval_runtime": 80.9085, |
| "eval_samples_per_second": 37.079, |
| "eval_steps_per_second": 4.635, |
| "step": 1470 |
| }, |
| { |
| "epoch": 0.86, |
| "learning_rate": 7.000000000000001e-06, |
| "loss": 0.1431, |
| "step": 1505 |
| }, |
| { |
| "epoch": 0.86, |
| "eval_accuracy": 0.7606666666666667, |
| "eval_f1": 0.8035030103995622, |
| "eval_loss": 0.7645860314369202, |
| "eval_precision": 0.6815227483751161, |
| "eval_recall": 0.9786666666666667, |
| "eval_runtime": 80.9077, |
| "eval_samples_per_second": 37.079, |
| "eval_steps_per_second": 4.635, |
| "step": 1505 |
| }, |
| { |
| "epoch": 0.88, |
| "learning_rate": 6e-06, |
| "loss": 0.2083, |
| "step": 1540 |
| }, |
| { |
| "epoch": 0.88, |
| "eval_accuracy": 0.645, |
| "eval_f1": 0.7372316802368615, |
| "eval_loss": 1.5643061399459839, |
| "eval_precision": 0.5851938895417156, |
| "eval_recall": 0.996, |
| "eval_runtime": 80.4452, |
| "eval_samples_per_second": 37.292, |
| "eval_steps_per_second": 4.662, |
| "step": 1540 |
| }, |
| { |
| "epoch": 0.9, |
| "learning_rate": 5e-06, |
| "loss": 0.218, |
| "step": 1575 |
| }, |
| { |
| "epoch": 0.9, |
| "eval_accuracy": 0.6816666666666666, |
| "eval_f1": 0.7570592724497585, |
| "eval_loss": 1.3131792545318604, |
| "eval_precision": 0.6120937885643768, |
| "eval_recall": 0.992, |
| "eval_runtime": 80.8361, |
| "eval_samples_per_second": 37.112, |
| "eval_steps_per_second": 4.639, |
| "step": 1575 |
| }, |
| { |
| "epoch": 0.92, |
| "learning_rate": 4.000000000000001e-06, |
| "loss": 0.2679, |
| "step": 1610 |
| }, |
| { |
| "epoch": 0.92, |
| "eval_accuracy": 0.8243333333333334, |
| "eval_f1": 0.845771144278607, |
| "eval_loss": 0.4741792678833008, |
| "eval_precision": 0.7537819509650495, |
| "eval_recall": 0.9633333333333334, |
| "eval_runtime": 80.8168, |
| "eval_samples_per_second": 37.121, |
| "eval_steps_per_second": 4.64, |
| "step": 1610 |
| }, |
| { |
| "epoch": 0.94, |
| "learning_rate": 3e-06, |
| "loss": 0.2218, |
| "step": 1645 |
| }, |
| { |
| "epoch": 0.94, |
| "eval_accuracy": 0.753, |
| "eval_f1": 0.7996755879967559, |
| "eval_loss": 0.7849438190460205, |
| "eval_precision": 0.6725784447476125, |
| "eval_recall": 0.986, |
| "eval_runtime": 80.4264, |
| "eval_samples_per_second": 37.301, |
| "eval_steps_per_second": 4.663, |
| "step": 1645 |
| }, |
| { |
| "epoch": 0.96, |
| "learning_rate": 2.0000000000000003e-06, |
| "loss": 0.1489, |
| "step": 1680 |
| }, |
| { |
| "epoch": 0.96, |
| "eval_accuracy": 0.6353333333333333, |
| "eval_f1": 0.7322564855604503, |
| "eval_loss": 1.6629990339279175, |
| "eval_precision": 0.5784996133023975, |
| "eval_recall": 0.9973333333333333, |
| "eval_runtime": 80.5542, |
| "eval_samples_per_second": 37.242, |
| "eval_steps_per_second": 4.655, |
| "step": 1680 |
| }, |
| { |
| "epoch": 0.98, |
| "learning_rate": 1.0000000000000002e-06, |
| "loss": 0.2119, |
| "step": 1715 |
| }, |
| { |
| "epoch": 0.98, |
| "eval_accuracy": 0.6753333333333333, |
| "eval_f1": 0.7536671724835609, |
| "eval_loss": 1.2936441898345947, |
| "eval_precision": 0.6071719641401793, |
| "eval_recall": 0.9933333333333333, |
| "eval_runtime": 80.4726, |
| "eval_samples_per_second": 37.28, |
| "eval_steps_per_second": 4.66, |
| "step": 1715 |
| }, |
| { |
| "epoch": 1.0, |
| "learning_rate": 0.0, |
| "loss": 0.1341, |
| "step": 1750 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.6686666666666666, |
| "eval_f1": 0.7500000000000001, |
| "eval_loss": 1.3422788381576538, |
| "eval_precision": 0.6021809369951535, |
| "eval_recall": 0.994, |
| "eval_runtime": 80.4399, |
| "eval_samples_per_second": 37.295, |
| "eval_steps_per_second": 4.662, |
| "step": 1750 |
| } |
| ], |
| "max_steps": 1750, |
| "num_train_epochs": 1, |
| "total_flos": 1.300198588416e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
