| { |
| "best_metric": 0.29240357875823975, |
| "best_model_checkpoint": "loras/EMOTION-lora-t5/emotion-cause/checkpoint-100", |
| "epoch": 9.868421052631579, |
| "eval_steps": 100, |
| "global_step": 1500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.07, |
| "learning_rate": 1e-05, |
| "loss": 0.5001, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.13, |
| "learning_rate": 2e-05, |
| "loss": 0.5744, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.2, |
| "learning_rate": 3e-05, |
| "loss": 0.4812, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.26, |
| "learning_rate": 4e-05, |
| "loss": 0.5855, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.33, |
| "learning_rate": 5e-05, |
| "loss": 0.5075, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.39, |
| "learning_rate": 4.965986394557823e-05, |
| "loss": 0.4734, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.46, |
| "learning_rate": 4.931972789115647e-05, |
| "loss": 0.5369, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.53, |
| "learning_rate": 4.89795918367347e-05, |
| "loss": 0.3672, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.59, |
| "learning_rate": 4.8639455782312926e-05, |
| "loss": 0.6244, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.66, |
| "learning_rate": 4.8299319727891155e-05, |
| "loss": 0.4228, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.66, |
| "eval_accuracy": 0.8105726872246696, |
| "eval_f1-score": 0.7275025985200415, |
| "eval_loss": 0.29240357875823975, |
| "eval_runtime": 13.0638, |
| "eval_samples_per_second": 34.752, |
| "eval_steps_per_second": 1.454, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.72, |
| "learning_rate": 4.795918367346939e-05, |
| "loss": 0.4818, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.79, |
| "learning_rate": 4.761904761904762e-05, |
| "loss": 0.4353, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.86, |
| "learning_rate": 4.7278911564625856e-05, |
| "loss": 0.4118, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.92, |
| "learning_rate": 4.6938775510204086e-05, |
| "loss": 0.4053, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.99, |
| "learning_rate": 4.6598639455782315e-05, |
| "loss": 0.3474, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.05, |
| "learning_rate": 4.625850340136055e-05, |
| "loss": 0.5243, |
| "step": 160 |
| }, |
| { |
| "epoch": 1.12, |
| "learning_rate": 4.591836734693878e-05, |
| "loss": 0.3005, |
| "step": 170 |
| }, |
| { |
| "epoch": 1.18, |
| "learning_rate": 4.557823129251701e-05, |
| "loss": 0.4622, |
| "step": 180 |
| }, |
| { |
| "epoch": 1.25, |
| "learning_rate": 4.523809523809524e-05, |
| "loss": 0.2778, |
| "step": 190 |
| }, |
| { |
| "epoch": 1.32, |
| "learning_rate": 4.4897959183673474e-05, |
| "loss": 0.3463, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.32, |
| "eval_accuracy": 0.8546255506607929, |
| "eval_f1-score": 0.8025695020785344, |
| "eval_loss": 0.22088070213794708, |
| "eval_runtime": 12.9451, |
| "eval_samples_per_second": 35.071, |
| "eval_steps_per_second": 1.468, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.38, |
| "learning_rate": 4.4557823129251704e-05, |
| "loss": 0.3723, |
| "step": 210 |
| }, |
| { |
| "epoch": 1.45, |
| "learning_rate": 4.421768707482993e-05, |
| "loss": 0.2966, |
| "step": 220 |
| }, |
| { |
| "epoch": 1.51, |
| "learning_rate": 4.387755102040816e-05, |
| "loss": 0.4132, |
| "step": 230 |
| }, |
| { |
| "epoch": 1.58, |
| "learning_rate": 4.35374149659864e-05, |
| "loss": 0.2603, |
| "step": 240 |
| }, |
| { |
| "epoch": 1.64, |
| "learning_rate": 4.319727891156463e-05, |
| "loss": 0.2222, |
| "step": 250 |
| }, |
| { |
| "epoch": 1.71, |
| "learning_rate": 4.2857142857142856e-05, |
| "loss": 0.3696, |
| "step": 260 |
| }, |
| { |
| "epoch": 1.78, |
| "learning_rate": 4.2517006802721085e-05, |
| "loss": 0.2462, |
| "step": 270 |
| }, |
| { |
| "epoch": 1.84, |
| "learning_rate": 4.217687074829932e-05, |
| "loss": 0.345, |
| "step": 280 |
| }, |
| { |
| "epoch": 1.91, |
| "learning_rate": 4.183673469387756e-05, |
| "loss": 0.3124, |
| "step": 290 |
| }, |
| { |
| "epoch": 1.97, |
| "learning_rate": 4.149659863945579e-05, |
| "loss": 0.2485, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.97, |
| "eval_accuracy": 0.8920704845814978, |
| "eval_f1-score": 0.8408289468524668, |
| "eval_loss": 0.1788729727268219, |
| "eval_runtime": 13.0955, |
| "eval_samples_per_second": 34.668, |
| "eval_steps_per_second": 1.451, |
| "step": 300 |
| }, |
| { |
| "epoch": 2.04, |
| "learning_rate": 4.1156462585034016e-05, |
| "loss": 0.3078, |
| "step": 310 |
| }, |
| { |
| "epoch": 2.11, |
| "learning_rate": 4.0816326530612245e-05, |
| "loss": 0.3344, |
| "step": 320 |
| }, |
| { |
| "epoch": 2.17, |
| "learning_rate": 4.047619047619048e-05, |
| "loss": 0.2398, |
| "step": 330 |
| }, |
| { |
| "epoch": 2.24, |
| "learning_rate": 4.013605442176871e-05, |
| "loss": 0.3078, |
| "step": 340 |
| }, |
| { |
| "epoch": 2.3, |
| "learning_rate": 3.979591836734694e-05, |
| "loss": 0.2606, |
| "step": 350 |
| }, |
| { |
| "epoch": 2.37, |
| "learning_rate": 3.945578231292517e-05, |
| "loss": 0.3745, |
| "step": 360 |
| }, |
| { |
| "epoch": 2.43, |
| "learning_rate": 3.9115646258503405e-05, |
| "loss": 0.2106, |
| "step": 370 |
| }, |
| { |
| "epoch": 2.5, |
| "learning_rate": 3.8775510204081634e-05, |
| "loss": 0.2621, |
| "step": 380 |
| }, |
| { |
| "epoch": 2.57, |
| "learning_rate": 3.843537414965986e-05, |
| "loss": 0.3514, |
| "step": 390 |
| }, |
| { |
| "epoch": 2.63, |
| "learning_rate": 3.809523809523809e-05, |
| "loss": 0.2793, |
| "step": 400 |
| }, |
| { |
| "epoch": 2.63, |
| "eval_accuracy": 0.9074889867841409, |
| "eval_f1-score": 0.8577574066072332, |
| "eval_loss": 0.14204789698123932, |
| "eval_runtime": 12.9399, |
| "eval_samples_per_second": 35.085, |
| "eval_steps_per_second": 1.468, |
| "step": 400 |
| }, |
| { |
| "epoch": 2.7, |
| "learning_rate": 3.775510204081633e-05, |
| "loss": 0.1728, |
| "step": 410 |
| }, |
| { |
| "epoch": 2.76, |
| "learning_rate": 3.7414965986394564e-05, |
| "loss": 0.2235, |
| "step": 420 |
| }, |
| { |
| "epoch": 2.83, |
| "learning_rate": 3.707482993197279e-05, |
| "loss": 0.2273, |
| "step": 430 |
| }, |
| { |
| "epoch": 2.89, |
| "learning_rate": 3.673469387755102e-05, |
| "loss": 0.2575, |
| "step": 440 |
| }, |
| { |
| "epoch": 2.96, |
| "learning_rate": 3.639455782312925e-05, |
| "loss": 0.2349, |
| "step": 450 |
| }, |
| { |
| "epoch": 3.03, |
| "learning_rate": 3.605442176870749e-05, |
| "loss": 0.2168, |
| "step": 460 |
| }, |
| { |
| "epoch": 3.09, |
| "learning_rate": 3.571428571428572e-05, |
| "loss": 0.2227, |
| "step": 470 |
| }, |
| { |
| "epoch": 3.16, |
| "learning_rate": 3.5374149659863946e-05, |
| "loss": 0.2163, |
| "step": 480 |
| }, |
| { |
| "epoch": 3.22, |
| "learning_rate": 3.5034013605442175e-05, |
| "loss": 0.2502, |
| "step": 490 |
| }, |
| { |
| "epoch": 3.29, |
| "learning_rate": 3.469387755102041e-05, |
| "loss": 0.1867, |
| "step": 500 |
| }, |
| { |
| "epoch": 3.29, |
| "eval_accuracy": 0.9074889867841409, |
| "eval_f1-score": 0.8446423629439122, |
| "eval_loss": 0.128860205411911, |
| "eval_runtime": 12.9292, |
| "eval_samples_per_second": 35.114, |
| "eval_steps_per_second": 1.47, |
| "step": 500 |
| }, |
| { |
| "epoch": 3.36, |
| "learning_rate": 3.435374149659864e-05, |
| "loss": 0.2496, |
| "step": 510 |
| }, |
| { |
| "epoch": 3.42, |
| "learning_rate": 3.401360544217687e-05, |
| "loss": 0.2187, |
| "step": 520 |
| }, |
| { |
| "epoch": 3.49, |
| "learning_rate": 3.36734693877551e-05, |
| "loss": 0.1452, |
| "step": 530 |
| }, |
| { |
| "epoch": 3.55, |
| "learning_rate": 3.3333333333333335e-05, |
| "loss": 0.2326, |
| "step": 540 |
| }, |
| { |
| "epoch": 3.62, |
| "learning_rate": 3.2993197278911564e-05, |
| "loss": 0.1313, |
| "step": 550 |
| }, |
| { |
| "epoch": 3.68, |
| "learning_rate": 3.265306122448979e-05, |
| "loss": 0.209, |
| "step": 560 |
| }, |
| { |
| "epoch": 3.75, |
| "learning_rate": 3.231292517006803e-05, |
| "loss": 0.1826, |
| "step": 570 |
| }, |
| { |
| "epoch": 3.82, |
| "learning_rate": 3.1972789115646265e-05, |
| "loss": 0.172, |
| "step": 580 |
| }, |
| { |
| "epoch": 3.88, |
| "learning_rate": 3.1632653061224494e-05, |
| "loss": 0.1203, |
| "step": 590 |
| }, |
| { |
| "epoch": 3.95, |
| "learning_rate": 3.1292517006802724e-05, |
| "loss": 0.0756, |
| "step": 600 |
| }, |
| { |
| "epoch": 3.95, |
| "eval_accuracy": 0.920704845814978, |
| "eval_f1-score": 0.8556357345248059, |
| "eval_loss": 0.12136897444725037, |
| "eval_runtime": 12.9239, |
| "eval_samples_per_second": 35.129, |
| "eval_steps_per_second": 1.47, |
| "step": 600 |
| }, |
| { |
| "epoch": 4.01, |
| "learning_rate": 3.095238095238095e-05, |
| "loss": 0.2299, |
| "step": 610 |
| }, |
| { |
| "epoch": 4.08, |
| "learning_rate": 3.061224489795919e-05, |
| "loss": 0.2127, |
| "step": 620 |
| }, |
| { |
| "epoch": 4.14, |
| "learning_rate": 3.0272108843537418e-05, |
| "loss": 0.1885, |
| "step": 630 |
| }, |
| { |
| "epoch": 4.21, |
| "learning_rate": 2.9931972789115647e-05, |
| "loss": 0.1989, |
| "step": 640 |
| }, |
| { |
| "epoch": 4.28, |
| "learning_rate": 2.959183673469388e-05, |
| "loss": 0.1996, |
| "step": 650 |
| }, |
| { |
| "epoch": 4.34, |
| "learning_rate": 2.925170068027211e-05, |
| "loss": 0.2487, |
| "step": 660 |
| }, |
| { |
| "epoch": 4.41, |
| "learning_rate": 2.891156462585034e-05, |
| "loss": 0.1545, |
| "step": 670 |
| }, |
| { |
| "epoch": 4.47, |
| "learning_rate": 2.857142857142857e-05, |
| "loss": 0.1984, |
| "step": 680 |
| }, |
| { |
| "epoch": 4.54, |
| "learning_rate": 2.8231292517006803e-05, |
| "loss": 0.1019, |
| "step": 690 |
| }, |
| { |
| "epoch": 4.61, |
| "learning_rate": 2.7891156462585033e-05, |
| "loss": 0.1726, |
| "step": 700 |
| }, |
| { |
| "epoch": 4.61, |
| "eval_accuracy": 0.9427312775330396, |
| "eval_f1-score": 0.905022087808422, |
| "eval_loss": 0.09442051500082016, |
| "eval_runtime": 12.9181, |
| "eval_samples_per_second": 35.145, |
| "eval_steps_per_second": 1.471, |
| "step": 700 |
| }, |
| { |
| "epoch": 4.67, |
| "learning_rate": 2.7551020408163265e-05, |
| "loss": 0.1956, |
| "step": 710 |
| }, |
| { |
| "epoch": 4.74, |
| "learning_rate": 2.72108843537415e-05, |
| "loss": 0.1377, |
| "step": 720 |
| }, |
| { |
| "epoch": 4.8, |
| "learning_rate": 2.687074829931973e-05, |
| "loss": 0.1619, |
| "step": 730 |
| }, |
| { |
| "epoch": 4.87, |
| "learning_rate": 2.6530612244897963e-05, |
| "loss": 0.232, |
| "step": 740 |
| }, |
| { |
| "epoch": 4.93, |
| "learning_rate": 2.6190476190476192e-05, |
| "loss": 0.1959, |
| "step": 750 |
| }, |
| { |
| "epoch": 5.0, |
| "learning_rate": 2.5850340136054425e-05, |
| "loss": 0.3134, |
| "step": 760 |
| }, |
| { |
| "epoch": 5.07, |
| "learning_rate": 2.5510204081632654e-05, |
| "loss": 0.1413, |
| "step": 770 |
| }, |
| { |
| "epoch": 5.13, |
| "learning_rate": 2.5170068027210887e-05, |
| "loss": 0.2147, |
| "step": 780 |
| }, |
| { |
| "epoch": 5.2, |
| "learning_rate": 2.4829931972789116e-05, |
| "loss": 0.117, |
| "step": 790 |
| }, |
| { |
| "epoch": 5.26, |
| "learning_rate": 2.448979591836735e-05, |
| "loss": 0.1787, |
| "step": 800 |
| }, |
| { |
| "epoch": 5.26, |
| "eval_accuracy": 0.9383259911894273, |
| "eval_f1-score": 0.8826692817781815, |
| "eval_loss": 0.09425372630357742, |
| "eval_runtime": 13.0626, |
| "eval_samples_per_second": 34.756, |
| "eval_steps_per_second": 1.455, |
| "step": 800 |
| }, |
| { |
| "epoch": 5.33, |
| "learning_rate": 2.4149659863945578e-05, |
| "loss": 0.2422, |
| "step": 810 |
| }, |
| { |
| "epoch": 5.39, |
| "learning_rate": 2.380952380952381e-05, |
| "loss": 0.0996, |
| "step": 820 |
| }, |
| { |
| "epoch": 5.46, |
| "learning_rate": 2.3469387755102043e-05, |
| "loss": 0.1417, |
| "step": 830 |
| }, |
| { |
| "epoch": 5.53, |
| "learning_rate": 2.3129251700680275e-05, |
| "loss": 0.1196, |
| "step": 840 |
| }, |
| { |
| "epoch": 5.59, |
| "learning_rate": 2.2789115646258505e-05, |
| "loss": 0.1073, |
| "step": 850 |
| }, |
| { |
| "epoch": 5.66, |
| "learning_rate": 2.2448979591836737e-05, |
| "loss": 0.1313, |
| "step": 860 |
| }, |
| { |
| "epoch": 5.72, |
| "learning_rate": 2.2108843537414966e-05, |
| "loss": 0.1194, |
| "step": 870 |
| }, |
| { |
| "epoch": 5.79, |
| "learning_rate": 2.17687074829932e-05, |
| "loss": 0.1899, |
| "step": 880 |
| }, |
| { |
| "epoch": 5.86, |
| "learning_rate": 2.1428571428571428e-05, |
| "loss": 0.1734, |
| "step": 890 |
| }, |
| { |
| "epoch": 5.92, |
| "learning_rate": 2.108843537414966e-05, |
| "loss": 0.0906, |
| "step": 900 |
| }, |
| { |
| "epoch": 5.92, |
| "eval_accuracy": 0.947136563876652, |
| "eval_f1-score": 0.9084929106281839, |
| "eval_loss": 0.08273177593946457, |
| "eval_runtime": 13.0573, |
| "eval_samples_per_second": 34.77, |
| "eval_steps_per_second": 1.455, |
| "step": 900 |
| }, |
| { |
| "epoch": 5.99, |
| "learning_rate": 2.0748299319727893e-05, |
| "loss": 0.1864, |
| "step": 910 |
| }, |
| { |
| "epoch": 6.05, |
| "learning_rate": 2.0408163265306123e-05, |
| "loss": 0.1042, |
| "step": 920 |
| }, |
| { |
| "epoch": 6.12, |
| "learning_rate": 2.0068027210884355e-05, |
| "loss": 0.1157, |
| "step": 930 |
| }, |
| { |
| "epoch": 6.18, |
| "learning_rate": 1.9727891156462584e-05, |
| "loss": 0.198, |
| "step": 940 |
| }, |
| { |
| "epoch": 6.25, |
| "learning_rate": 1.9387755102040817e-05, |
| "loss": 0.1205, |
| "step": 950 |
| }, |
| { |
| "epoch": 6.32, |
| "learning_rate": 1.9047619047619046e-05, |
| "loss": 0.1314, |
| "step": 960 |
| }, |
| { |
| "epoch": 6.38, |
| "learning_rate": 1.8707482993197282e-05, |
| "loss": 0.0886, |
| "step": 970 |
| }, |
| { |
| "epoch": 6.45, |
| "learning_rate": 1.836734693877551e-05, |
| "loss": 0.2477, |
| "step": 980 |
| }, |
| { |
| "epoch": 6.51, |
| "learning_rate": 1.8027210884353744e-05, |
| "loss": 0.157, |
| "step": 990 |
| }, |
| { |
| "epoch": 6.58, |
| "learning_rate": 1.7687074829931973e-05, |
| "loss": 0.1209, |
| "step": 1000 |
| }, |
| { |
| "epoch": 6.58, |
| "eval_accuracy": 0.947136563876652, |
| "eval_f1-score": 0.9084929106281839, |
| "eval_loss": 0.08069759607315063, |
| "eval_runtime": 13.0503, |
| "eval_samples_per_second": 34.788, |
| "eval_steps_per_second": 1.456, |
| "step": 1000 |
| }, |
| { |
| "epoch": 6.64, |
| "learning_rate": 1.7346938775510206e-05, |
| "loss": 0.1683, |
| "step": 1010 |
| }, |
| { |
| "epoch": 6.71, |
| "learning_rate": 1.7006802721088435e-05, |
| "loss": 0.2253, |
| "step": 1020 |
| }, |
| { |
| "epoch": 6.78, |
| "learning_rate": 1.6666666666666667e-05, |
| "loss": 0.1202, |
| "step": 1030 |
| }, |
| { |
| "epoch": 6.84, |
| "learning_rate": 1.6326530612244897e-05, |
| "loss": 0.1373, |
| "step": 1040 |
| }, |
| { |
| "epoch": 6.91, |
| "learning_rate": 1.5986394557823133e-05, |
| "loss": 0.0931, |
| "step": 1050 |
| }, |
| { |
| "epoch": 6.97, |
| "learning_rate": 1.5646258503401362e-05, |
| "loss": 0.237, |
| "step": 1060 |
| }, |
| { |
| "epoch": 7.04, |
| "learning_rate": 1.5306122448979594e-05, |
| "loss": 0.1104, |
| "step": 1070 |
| }, |
| { |
| "epoch": 7.11, |
| "learning_rate": 1.4965986394557824e-05, |
| "loss": 0.1043, |
| "step": 1080 |
| }, |
| { |
| "epoch": 7.17, |
| "learning_rate": 1.4625850340136055e-05, |
| "loss": 0.1085, |
| "step": 1090 |
| }, |
| { |
| "epoch": 7.24, |
| "learning_rate": 1.4285714285714285e-05, |
| "loss": 0.0559, |
| "step": 1100 |
| }, |
| { |
| "epoch": 7.24, |
| "eval_accuracy": 0.9515418502202643, |
| "eval_f1-score": 0.9121499814738822, |
| "eval_loss": 0.08020388334989548, |
| "eval_runtime": 13.1367, |
| "eval_samples_per_second": 34.56, |
| "eval_steps_per_second": 1.446, |
| "step": 1100 |
| }, |
| { |
| "epoch": 7.3, |
| "learning_rate": 1.3945578231292516e-05, |
| "loss": 0.1583, |
| "step": 1110 |
| }, |
| { |
| "epoch": 7.37, |
| "learning_rate": 1.360544217687075e-05, |
| "loss": 0.1031, |
| "step": 1120 |
| }, |
| { |
| "epoch": 7.43, |
| "learning_rate": 1.3265306122448982e-05, |
| "loss": 0.1965, |
| "step": 1130 |
| }, |
| { |
| "epoch": 7.5, |
| "learning_rate": 1.2925170068027212e-05, |
| "loss": 0.1119, |
| "step": 1140 |
| }, |
| { |
| "epoch": 7.57, |
| "learning_rate": 1.2585034013605443e-05, |
| "loss": 0.1384, |
| "step": 1150 |
| }, |
| { |
| "epoch": 7.63, |
| "learning_rate": 1.2244897959183674e-05, |
| "loss": 0.0558, |
| "step": 1160 |
| }, |
| { |
| "epoch": 7.7, |
| "learning_rate": 1.1904761904761905e-05, |
| "loss": 0.1149, |
| "step": 1170 |
| }, |
| { |
| "epoch": 7.76, |
| "learning_rate": 1.1564625850340138e-05, |
| "loss": 0.1152, |
| "step": 1180 |
| }, |
| { |
| "epoch": 7.83, |
| "learning_rate": 1.1224489795918369e-05, |
| "loss": 0.1665, |
| "step": 1190 |
| }, |
| { |
| "epoch": 7.89, |
| "learning_rate": 1.08843537414966e-05, |
| "loss": 0.121, |
| "step": 1200 |
| }, |
| { |
| "epoch": 7.89, |
| "eval_accuracy": 0.9493392070484582, |
| "eval_f1-score": 0.9182148906727446, |
| "eval_loss": 0.07849086821079254, |
| "eval_runtime": 12.9069, |
| "eval_samples_per_second": 35.175, |
| "eval_steps_per_second": 1.472, |
| "step": 1200 |
| }, |
| { |
| "epoch": 7.96, |
| "learning_rate": 1.054421768707483e-05, |
| "loss": 0.2109, |
| "step": 1210 |
| }, |
| { |
| "epoch": 8.03, |
| "learning_rate": 1.0204081632653061e-05, |
| "loss": 0.1204, |
| "step": 1220 |
| }, |
| { |
| "epoch": 8.09, |
| "learning_rate": 9.863945578231292e-06, |
| "loss": 0.169, |
| "step": 1230 |
| }, |
| { |
| "epoch": 8.16, |
| "learning_rate": 9.523809523809523e-06, |
| "loss": 0.0848, |
| "step": 1240 |
| }, |
| { |
| "epoch": 8.22, |
| "learning_rate": 9.183673469387756e-06, |
| "loss": 0.1149, |
| "step": 1250 |
| }, |
| { |
| "epoch": 8.29, |
| "learning_rate": 8.843537414965987e-06, |
| "loss": 0.1162, |
| "step": 1260 |
| }, |
| { |
| "epoch": 8.36, |
| "learning_rate": 8.503401360544217e-06, |
| "loss": 0.0564, |
| "step": 1270 |
| }, |
| { |
| "epoch": 8.42, |
| "learning_rate": 8.163265306122448e-06, |
| "loss": 0.1447, |
| "step": 1280 |
| }, |
| { |
| "epoch": 8.49, |
| "learning_rate": 7.823129251700681e-06, |
| "loss": 0.2075, |
| "step": 1290 |
| }, |
| { |
| "epoch": 8.55, |
| "learning_rate": 7.482993197278912e-06, |
| "loss": 0.1551, |
| "step": 1300 |
| }, |
| { |
| "epoch": 8.55, |
| "eval_accuracy": 0.9493392070484582, |
| "eval_f1-score": 0.9182148906727446, |
| "eval_loss": 0.07675673067569733, |
| "eval_runtime": 12.9164, |
| "eval_samples_per_second": 35.149, |
| "eval_steps_per_second": 1.471, |
| "step": 1300 |
| }, |
| { |
| "epoch": 8.62, |
| "learning_rate": 7.142857142857143e-06, |
| "loss": 0.0894, |
| "step": 1310 |
| }, |
| { |
| "epoch": 8.68, |
| "learning_rate": 6.802721088435375e-06, |
| "loss": 0.1112, |
| "step": 1320 |
| }, |
| { |
| "epoch": 8.75, |
| "learning_rate": 6.462585034013606e-06, |
| "loss": 0.084, |
| "step": 1330 |
| }, |
| { |
| "epoch": 8.82, |
| "learning_rate": 6.122448979591837e-06, |
| "loss": 0.075, |
| "step": 1340 |
| }, |
| { |
| "epoch": 8.88, |
| "learning_rate": 5.782312925170069e-06, |
| "loss": 0.1516, |
| "step": 1350 |
| }, |
| { |
| "epoch": 8.95, |
| "learning_rate": 5.4421768707483e-06, |
| "loss": 0.1858, |
| "step": 1360 |
| }, |
| { |
| "epoch": 9.01, |
| "learning_rate": 5.102040816326531e-06, |
| "loss": 0.0845, |
| "step": 1370 |
| }, |
| { |
| "epoch": 9.08, |
| "learning_rate": 4.7619047619047615e-06, |
| "loss": 0.1114, |
| "step": 1380 |
| }, |
| { |
| "epoch": 9.14, |
| "learning_rate": 4.421768707482993e-06, |
| "loss": 0.1629, |
| "step": 1390 |
| }, |
| { |
| "epoch": 9.21, |
| "learning_rate": 4.081632653061224e-06, |
| "loss": 0.2564, |
| "step": 1400 |
| }, |
| { |
| "epoch": 9.21, |
| "eval_accuracy": 0.9493392070484582, |
| "eval_f1-score": 0.9182148906727446, |
| "eval_loss": 0.0777244046330452, |
| "eval_runtime": 12.9181, |
| "eval_samples_per_second": 35.145, |
| "eval_steps_per_second": 1.471, |
| "step": 1400 |
| }, |
| { |
| "epoch": 9.28, |
| "learning_rate": 3.741496598639456e-06, |
| "loss": 0.1501, |
| "step": 1410 |
| }, |
| { |
| "epoch": 9.34, |
| "learning_rate": 3.4013605442176877e-06, |
| "loss": 0.1026, |
| "step": 1420 |
| }, |
| { |
| "epoch": 9.41, |
| "learning_rate": 3.0612244897959185e-06, |
| "loss": 0.154, |
| "step": 1430 |
| }, |
| { |
| "epoch": 9.47, |
| "learning_rate": 2.72108843537415e-06, |
| "loss": 0.1399, |
| "step": 1440 |
| }, |
| { |
| "epoch": 9.54, |
| "learning_rate": 2.3809523809523808e-06, |
| "loss": 0.0634, |
| "step": 1450 |
| }, |
| { |
| "epoch": 9.61, |
| "learning_rate": 2.040816326530612e-06, |
| "loss": 0.1792, |
| "step": 1460 |
| }, |
| { |
| "epoch": 9.67, |
| "learning_rate": 1.7006802721088438e-06, |
| "loss": 0.0527, |
| "step": 1470 |
| }, |
| { |
| "epoch": 9.74, |
| "learning_rate": 1.360544217687075e-06, |
| "loss": 0.0934, |
| "step": 1480 |
| }, |
| { |
| "epoch": 9.8, |
| "learning_rate": 1.020408163265306e-06, |
| "loss": 0.0909, |
| "step": 1490 |
| }, |
| { |
| "epoch": 9.87, |
| "learning_rate": 6.802721088435375e-07, |
| "loss": 0.0888, |
| "step": 1500 |
| }, |
| { |
| "epoch": 9.87, |
| "eval_accuracy": 0.9493392070484582, |
| "eval_f1-score": 0.9182148906727446, |
| "eval_loss": 0.07651279121637344, |
| "eval_runtime": 12.9126, |
| "eval_samples_per_second": 35.16, |
| "eval_steps_per_second": 1.471, |
| "step": 1500 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 1520, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "save_steps": 100, |
| "total_flos": 1.16460566249472e+16, |
| "train_batch_size": 12, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
