| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 3590, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 2e-05, | |
| "loss": 95.2205, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 2e-05, | |
| "loss": 48.3233, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 2e-05, | |
| "loss": 13.9954, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 2e-05, | |
| "loss": 2.0884, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 2e-05, | |
| "loss": 1.5549, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 2e-05, | |
| "loss": 2.0528, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 2e-05, | |
| "loss": 3.102, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 2e-05, | |
| "loss": 1.2929, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_f1": 0.1941564561734213, | |
| "eval_loss": 13.452169418334961, | |
| "eval_runtime": 23.1921, | |
| "eval_samples_per_second": 82.614, | |
| "eval_steps_per_second": 1.294, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5906, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3674, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5531, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2448, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1894, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2385, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2773, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1879, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1541, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_f1": 0.1941564561734213, | |
| "eval_loss": 8.468379020690918, | |
| "eval_runtime": 22.9961, | |
| "eval_samples_per_second": 83.318, | |
| "eval_steps_per_second": 1.305, | |
| "step": 359 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1381, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1464, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2856, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3727, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2145, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0867, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 2e-05, | |
| "loss": 0.232, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1407, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1257, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_f1": 0.1941564561734213, | |
| "eval_loss": 7.637044906616211, | |
| "eval_runtime": 22.6323, | |
| "eval_samples_per_second": 84.658, | |
| "eval_steps_per_second": 1.326, | |
| "step": 538 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1963, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1485, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1373, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0971, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2036, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2205, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0547, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0957, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1684, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_f1": 0.6376360808709176, | |
| "eval_loss": 0.7054294943809509, | |
| "eval_runtime": 22.968, | |
| "eval_samples_per_second": 83.42, | |
| "eval_steps_per_second": 1.306, | |
| "step": 718 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 2e-05, | |
| "loss": 0.145, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1186, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0227, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0556, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "learning_rate": 2e-05, | |
| "loss": 0.141, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1328, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0992, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1691, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0911, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_f1": 0.1941564561734213, | |
| "eval_loss": 5.119464874267578, | |
| "eval_runtime": 22.7812, | |
| "eval_samples_per_second": 84.104, | |
| "eval_steps_per_second": 1.317, | |
| "step": 897 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0993, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 5.13, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0972, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0389, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 5.35, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1366, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 5.46, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0833, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 5.57, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1634, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 5.68, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0691, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 5.79, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1487, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "learning_rate": 2e-05, | |
| "loss": 0.145, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_f1": 0.7984031936127745, | |
| "eval_loss": 0.2693595290184021, | |
| "eval_runtime": 22.9118, | |
| "eval_samples_per_second": 83.625, | |
| "eval_steps_per_second": 1.309, | |
| "step": 1077 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0373, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0409, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 6.24, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0714, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 6.35, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0915, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 6.46, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1359, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 6.57, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1016, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 6.69, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0346, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 6.8, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0437, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 6.91, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1191, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_f1": 0.20265617314313825, | |
| "eval_loss": 2.941455602645874, | |
| "eval_runtime": 22.6391, | |
| "eval_samples_per_second": 84.632, | |
| "eval_steps_per_second": 1.325, | |
| "step": 1256 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "learning_rate": 2e-05, | |
| "loss": 0.069, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 7.13, | |
| "learning_rate": 2e-05, | |
| "loss": 0.009, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 7.24, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0485, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 7.35, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0105, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 7.47, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0835, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 7.58, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1458, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0553, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 7.8, | |
| "learning_rate": 2e-05, | |
| "loss": 0.005, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 7.91, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1008, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_f1": 0.9023255813953488, | |
| "eval_loss": 0.17851048707962036, | |
| "eval_runtime": 22.8798, | |
| "eval_samples_per_second": 83.742, | |
| "eval_steps_per_second": 1.311, | |
| "step": 1436 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0414, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 8.13, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0351, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 8.25, | |
| "learning_rate": 2e-05, | |
| "loss": 0.115, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 8.36, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0453, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "learning_rate": 0.001, | |
| "loss": 18.7223, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 0.001, | |
| "loss": 5.5701, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 0.001, | |
| "loss": 1.2935, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 0.001, | |
| "loss": 0.6161, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "learning_rate": 0.001, | |
| "loss": 0.757, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "learning_rate": 0.001, | |
| "loss": 0.6241, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 0.001, | |
| "loss": 0.5211, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 0.001, | |
| "loss": 0.4467, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 0.001, | |
| "loss": 0.424, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 0.001, | |
| "loss": 0.3741, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "learning_rate": 0.001, | |
| "loss": 0.3276, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "learning_rate": 0.001, | |
| "loss": 0.3692, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "learning_rate": 0.001, | |
| "loss": 0.3626, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "learning_rate": 0.001, | |
| "loss": 0.3698, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.3513816297054291, | |
| "eval_runtime": 20.8512, | |
| "eval_samples_per_second": 91.889, | |
| "eval_steps_per_second": 1.439, | |
| "step": 1795 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 0.001, | |
| "loss": 0.3672, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "learning_rate": 0.001, | |
| "loss": 0.3879, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 5.13, | |
| "learning_rate": 0.001, | |
| "loss": 0.458, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 5.18, | |
| "learning_rate": 0.001, | |
| "loss": 0.3949, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "learning_rate": 0.001, | |
| "loss": 0.372, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 5.29, | |
| "learning_rate": 0.001, | |
| "loss": 0.3578, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 5.35, | |
| "learning_rate": 0.001, | |
| "loss": 0.3906, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 5.4, | |
| "learning_rate": 0.001, | |
| "loss": 0.3888, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 5.46, | |
| "learning_rate": 0.001, | |
| "loss": 0.4049, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 5.52, | |
| "learning_rate": 0.001, | |
| "loss": 0.3692, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 5.57, | |
| "learning_rate": 0.001, | |
| "loss": 0.3299, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 5.63, | |
| "learning_rate": 0.001, | |
| "loss": 0.3714, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 5.68, | |
| "learning_rate": 0.001, | |
| "loss": 0.3423, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 5.74, | |
| "learning_rate": 0.001, | |
| "loss": 0.3534, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 5.79, | |
| "learning_rate": 0.001, | |
| "loss": 0.3426, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 5.85, | |
| "learning_rate": 0.001, | |
| "loss": 0.3684, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "learning_rate": 0.001, | |
| "loss": 0.3472, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 5.96, | |
| "learning_rate": 0.001, | |
| "loss": 0.299, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.3469391465187073, | |
| "eval_runtime": 20.5335, | |
| "eval_samples_per_second": 93.311, | |
| "eval_steps_per_second": 1.461, | |
| "step": 2154 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 0.001, | |
| "loss": 0.3336, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 6.07, | |
| "learning_rate": 0.001, | |
| "loss": 0.4366, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "learning_rate": 0.001, | |
| "loss": 0.3709, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 6.18, | |
| "learning_rate": 0.001, | |
| "loss": 0.3357, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 6.24, | |
| "learning_rate": 0.001, | |
| "loss": 0.4034, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 6.3, | |
| "learning_rate": 0.001, | |
| "loss": 0.3868, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 6.35, | |
| "learning_rate": 0.001, | |
| "loss": 0.3328, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "learning_rate": 0.001, | |
| "loss": 0.3974, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 6.46, | |
| "learning_rate": 0.001, | |
| "loss": 0.3707, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 6.52, | |
| "learning_rate": 0.001, | |
| "loss": 0.3753, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 6.57, | |
| "learning_rate": 0.001, | |
| "loss": 0.3255, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 6.63, | |
| "learning_rate": 0.001, | |
| "loss": 0.4284, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 6.69, | |
| "learning_rate": 0.001, | |
| "loss": 0.3699, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 6.74, | |
| "learning_rate": 0.001, | |
| "loss": 0.3705, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 6.8, | |
| "learning_rate": 0.001, | |
| "loss": 0.2841, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 6.85, | |
| "learning_rate": 0.001, | |
| "loss": 0.2687, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 6.91, | |
| "learning_rate": 0.001, | |
| "loss": 0.3294, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 6.96, | |
| "learning_rate": 0.001, | |
| "loss": 0.3531, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.3420043885707855, | |
| "eval_runtime": 20.5195, | |
| "eval_samples_per_second": 93.374, | |
| "eval_steps_per_second": 1.462, | |
| "step": 2513 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "learning_rate": 0.001, | |
| "loss": 0.3396, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 7.08, | |
| "learning_rate": 0.001, | |
| "loss": 0.3824, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 7.13, | |
| "learning_rate": 0.001, | |
| "loss": 0.2518, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 7.19, | |
| "learning_rate": 0.001, | |
| "loss": 0.3822, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 7.24, | |
| "learning_rate": 0.001, | |
| "loss": 0.3969, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 7.3, | |
| "learning_rate": 0.001, | |
| "loss": 0.2551, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 7.35, | |
| "learning_rate": 0.001, | |
| "loss": 0.3387, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 7.41, | |
| "learning_rate": 0.001, | |
| "loss": 0.3761, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 7.47, | |
| "learning_rate": 0.001, | |
| "loss": 0.3899, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 7.52, | |
| "learning_rate": 0.001, | |
| "loss": 0.3691, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 7.58, | |
| "learning_rate": 0.001, | |
| "loss": 0.3172, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 7.63, | |
| "learning_rate": 0.001, | |
| "loss": 0.3358, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "learning_rate": 0.001, | |
| "loss": 0.3459, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 7.74, | |
| "learning_rate": 0.001, | |
| "loss": 0.3347, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 7.8, | |
| "learning_rate": 0.001, | |
| "loss": 0.3459, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 7.86, | |
| "learning_rate": 0.001, | |
| "loss": 0.3797, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 7.91, | |
| "learning_rate": 0.001, | |
| "loss": 0.3721, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 7.97, | |
| "learning_rate": 0.001, | |
| "loss": 0.3892, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.34283891320228577, | |
| "eval_runtime": 20.5477, | |
| "eval_samples_per_second": 93.247, | |
| "eval_steps_per_second": 1.46, | |
| "step": 2872 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "learning_rate": 0.001, | |
| "loss": 0.3234, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 8.08, | |
| "learning_rate": 0.001, | |
| "loss": 0.3979, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 8.13, | |
| "learning_rate": 0.001, | |
| "loss": 0.4032, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 8.19, | |
| "learning_rate": 0.001, | |
| "loss": 0.3787, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 8.25, | |
| "learning_rate": 0.001, | |
| "loss": 0.3144, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 8.3, | |
| "learning_rate": 0.001, | |
| "loss": 0.4071, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 8.36, | |
| "learning_rate": 0.001, | |
| "loss": 0.3192, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 8.41, | |
| "learning_rate": 0.001, | |
| "loss": 0.3194, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 8.47, | |
| "learning_rate": 0.001, | |
| "loss": 0.3468, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 8.52, | |
| "learning_rate": 0.001, | |
| "loss": 0.325, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 8.58, | |
| "learning_rate": 0.001, | |
| "loss": 0.3631, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 8.64, | |
| "learning_rate": 0.001, | |
| "loss": 0.3464, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 8.69, | |
| "learning_rate": 0.001, | |
| "loss": 0.3378, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 8.75, | |
| "learning_rate": 0.001, | |
| "loss": 0.3808, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "learning_rate": 0.001, | |
| "loss": 0.3668, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 8.86, | |
| "learning_rate": 0.001, | |
| "loss": 0.3045, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 8.91, | |
| "learning_rate": 0.001, | |
| "loss": 0.2805, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 8.97, | |
| "learning_rate": 0.001, | |
| "loss": 0.3706, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.3420598804950714, | |
| "eval_runtime": 20.5266, | |
| "eval_samples_per_second": 93.342, | |
| "eval_steps_per_second": 1.462, | |
| "step": 3231 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "learning_rate": 0.001, | |
| "loss": 0.3502, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 9.08, | |
| "learning_rate": 0.001, | |
| "loss": 0.3414, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 9.14, | |
| "learning_rate": 0.001, | |
| "loss": 0.4037, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 9.19, | |
| "learning_rate": 0.001, | |
| "loss": 0.3548, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 9.25, | |
| "learning_rate": 0.001, | |
| "loss": 0.3426, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 9.3, | |
| "learning_rate": 0.001, | |
| "loss": 0.3614, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 9.36, | |
| "learning_rate": 0.001, | |
| "loss": 0.2505, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 9.42, | |
| "learning_rate": 0.001, | |
| "loss": 0.402, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 9.47, | |
| "learning_rate": 0.001, | |
| "loss": 0.3029, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 9.53, | |
| "learning_rate": 0.001, | |
| "loss": 0.2799, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 9.58, | |
| "learning_rate": 0.001, | |
| "loss": 0.3046, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 9.64, | |
| "learning_rate": 0.001, | |
| "loss": 0.3707, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 9.69, | |
| "learning_rate": 0.001, | |
| "loss": 0.3417, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 9.75, | |
| "learning_rate": 0.001, | |
| "loss": 0.3826, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 9.81, | |
| "learning_rate": 0.001, | |
| "loss": 0.3658, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 9.86, | |
| "learning_rate": 0.001, | |
| "loss": 0.3185, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 9.92, | |
| "learning_rate": 0.001, | |
| "loss": 0.3596, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 9.97, | |
| "learning_rate": 0.001, | |
| "loss": 0.3863, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.34448280930519104, | |
| "eval_runtime": 20.4875, | |
| "eval_samples_per_second": 93.52, | |
| "eval_steps_per_second": 1.464, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 3590, | |
| "total_flos": 3792562624069632.0, | |
| "train_loss": 0.3510875488058106, | |
| "train_runtime": 3949.5247, | |
| "train_samples_per_second": 14.541, | |
| "train_steps_per_second": 0.909 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 3590, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 3792562624069632.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |