| { | |
| "best_metric": 0.894333004951477, | |
| "best_model_checkpoint": "bert-base-arabertv2_1/checkpoint-1000", | |
| "epoch": 22.831050228310502, | |
| "eval_steps": 1000, | |
| "global_step": 5000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.200000000000001e-07, | |
| "loss": 1.0908, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.8400000000000002e-06, | |
| "loss": 1.0474, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 2.7600000000000003e-06, | |
| "loss": 0.9963, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 3.7600000000000004e-06, | |
| "loss": 1.0041, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.76e-06, | |
| "loss": 1.0071, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 5.76e-06, | |
| "loss": 0.9659, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 6.760000000000001e-06, | |
| "loss": 0.9522, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 7.76e-06, | |
| "loss": 0.9335, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 8.76e-06, | |
| "loss": 0.9048, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 9.760000000000001e-06, | |
| "loss": 0.8749, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 1.0760000000000002e-05, | |
| "loss": 0.9108, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 1.1760000000000001e-05, | |
| "loss": 0.8703, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 1.2760000000000001e-05, | |
| "loss": 0.8957, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 1.376e-05, | |
| "loss": 0.8933, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 1.4760000000000001e-05, | |
| "loss": 0.8811, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 1.576e-05, | |
| "loss": 0.8982, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 1.6760000000000002e-05, | |
| "loss": 0.857, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 1.7760000000000003e-05, | |
| "loss": 0.8538, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 1.876e-05, | |
| "loss": 0.8573, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 1.976e-05, | |
| "loss": 0.766, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 1.9915555555555557e-05, | |
| "loss": 0.7945, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 1.9804444444444445e-05, | |
| "loss": 0.8713, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 1.9693333333333337e-05, | |
| "loss": 0.8652, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 1.9582222222222225e-05, | |
| "loss": 0.8292, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 1.9471111111111113e-05, | |
| "loss": 0.7645, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 1.936e-05, | |
| "loss": 0.7594, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 1.924888888888889e-05, | |
| "loss": 0.7144, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 1.913777777777778e-05, | |
| "loss": 0.6814, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 1.902666666666667e-05, | |
| "loss": 0.7054, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 1.8915555555555557e-05, | |
| "loss": 0.7027, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 1.8804444444444445e-05, | |
| "loss": 0.678, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "learning_rate": 1.8693333333333333e-05, | |
| "loss": 0.7418, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 1.8582222222222224e-05, | |
| "loss": 0.7237, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 1.8471111111111112e-05, | |
| "loss": 0.688, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 1.8360000000000004e-05, | |
| "loss": 0.7115, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 1.824888888888889e-05, | |
| "loss": 0.6277, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 1.813777777777778e-05, | |
| "loss": 0.6007, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 4.34, | |
| "learning_rate": 1.8026666666666668e-05, | |
| "loss": 0.5753, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 4.45, | |
| "learning_rate": 1.7915555555555556e-05, | |
| "loss": 0.5818, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 1.7804444444444448e-05, | |
| "loss": 0.6125, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "eval_accuracy": 0.65, | |
| "eval_loss": 0.894333004951477, | |
| "eval_runtime": 2.6838, | |
| "eval_samples_per_second": 372.609, | |
| "eval_steps_per_second": 46.576, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 1.7693333333333336e-05, | |
| "loss": 0.5496, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "learning_rate": 1.7582222222222224e-05, | |
| "loss": 0.5603, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 4.91, | |
| "learning_rate": 1.7471111111111112e-05, | |
| "loss": 0.5716, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 1.736e-05, | |
| "loss": 0.5522, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 5.14, | |
| "learning_rate": 1.724888888888889e-05, | |
| "loss": 0.4755, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 5.25, | |
| "learning_rate": 1.713777777777778e-05, | |
| "loss": 0.4464, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 5.37, | |
| "learning_rate": 1.702666666666667e-05, | |
| "loss": 0.4405, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 5.48, | |
| "learning_rate": 1.6915555555555555e-05, | |
| "loss": 0.4359, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 5.59, | |
| "learning_rate": 1.6804444444444447e-05, | |
| "loss": 0.463, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "learning_rate": 1.6693333333333335e-05, | |
| "loss": 0.4788, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 5.82, | |
| "learning_rate": 1.6582222222222223e-05, | |
| "loss": 0.4673, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 5.94, | |
| "learning_rate": 1.6471111111111115e-05, | |
| "loss": 0.4315, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 6.05, | |
| "learning_rate": 1.636e-05, | |
| "loss": 0.4113, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 6.16, | |
| "learning_rate": 1.624888888888889e-05, | |
| "loss": 0.3585, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 6.28, | |
| "learning_rate": 1.613777777777778e-05, | |
| "loss": 0.3595, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 6.39, | |
| "learning_rate": 1.6026666666666667e-05, | |
| "loss": 0.3161, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 6.51, | |
| "learning_rate": 1.5915555555555558e-05, | |
| "loss": 0.3476, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 6.62, | |
| "learning_rate": 1.5804444444444446e-05, | |
| "loss": 0.3784, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 6.74, | |
| "learning_rate": 1.5693333333333334e-05, | |
| "loss": 0.3336, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 6.85, | |
| "learning_rate": 1.5582222222222222e-05, | |
| "loss": 0.3314, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 6.96, | |
| "learning_rate": 1.5471111111111114e-05, | |
| "loss": 0.3501, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 7.08, | |
| "learning_rate": 1.5360000000000002e-05, | |
| "loss": 0.274, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 7.19, | |
| "learning_rate": 1.524888888888889e-05, | |
| "loss": 0.2473, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 7.31, | |
| "learning_rate": 1.513777777777778e-05, | |
| "loss": 0.237, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 7.42, | |
| "learning_rate": 1.5026666666666668e-05, | |
| "loss": 0.2742, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 7.53, | |
| "learning_rate": 1.4915555555555556e-05, | |
| "loss": 0.2906, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 7.65, | |
| "learning_rate": 1.4804444444444446e-05, | |
| "loss": 0.2499, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 7.76, | |
| "learning_rate": 1.4693333333333336e-05, | |
| "loss": 0.2694, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 7.88, | |
| "learning_rate": 1.4582222222222224e-05, | |
| "loss": 0.2465, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 7.99, | |
| "learning_rate": 1.4471111111111112e-05, | |
| "loss": 0.2739, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 8.11, | |
| "learning_rate": 1.4360000000000001e-05, | |
| "loss": 0.1963, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 8.22, | |
| "learning_rate": 1.424888888888889e-05, | |
| "loss": 0.1694, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 8.33, | |
| "learning_rate": 1.413777777777778e-05, | |
| "loss": 0.1532, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 8.45, | |
| "learning_rate": 1.4026666666666669e-05, | |
| "loss": 0.1692, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 8.56, | |
| "learning_rate": 1.3915555555555557e-05, | |
| "loss": 0.1687, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 8.68, | |
| "learning_rate": 1.3804444444444445e-05, | |
| "loss": 0.2099, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 8.79, | |
| "learning_rate": 1.3693333333333333e-05, | |
| "loss": 0.1927, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 8.9, | |
| "learning_rate": 1.3582222222222223e-05, | |
| "loss": 0.2065, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "learning_rate": 1.3471111111111113e-05, | |
| "loss": 0.2312, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 9.13, | |
| "learning_rate": 1.3360000000000003e-05, | |
| "loss": 0.1438, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 9.13, | |
| "eval_accuracy": 0.622, | |
| "eval_loss": 1.4417067766189575, | |
| "eval_runtime": 2.6482, | |
| "eval_samples_per_second": 377.613, | |
| "eval_steps_per_second": 47.202, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 9.25, | |
| "learning_rate": 1.3248888888888889e-05, | |
| "loss": 0.1875, | |
| "step": 2025 | |
| }, | |
| { | |
| "epoch": 9.36, | |
| "learning_rate": 1.3137777777777779e-05, | |
| "loss": 0.1359, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 9.47, | |
| "learning_rate": 1.3026666666666667e-05, | |
| "loss": 0.1177, | |
| "step": 2075 | |
| }, | |
| { | |
| "epoch": 9.59, | |
| "learning_rate": 1.2915555555555557e-05, | |
| "loss": 0.1494, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 9.7, | |
| "learning_rate": 1.2804444444444446e-05, | |
| "loss": 0.1313, | |
| "step": 2125 | |
| }, | |
| { | |
| "epoch": 9.82, | |
| "learning_rate": 1.2693333333333336e-05, | |
| "loss": 0.1571, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 9.93, | |
| "learning_rate": 1.2582222222222222e-05, | |
| "loss": 0.1671, | |
| "step": 2175 | |
| }, | |
| { | |
| "epoch": 10.05, | |
| "learning_rate": 1.2471111111111112e-05, | |
| "loss": 0.1264, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 10.16, | |
| "learning_rate": 1.236e-05, | |
| "loss": 0.0969, | |
| "step": 2225 | |
| }, | |
| { | |
| "epoch": 10.27, | |
| "learning_rate": 1.224888888888889e-05, | |
| "loss": 0.0971, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 10.39, | |
| "learning_rate": 1.213777777777778e-05, | |
| "loss": 0.1435, | |
| "step": 2275 | |
| }, | |
| { | |
| "epoch": 10.5, | |
| "learning_rate": 1.202666666666667e-05, | |
| "loss": 0.0938, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 10.62, | |
| "learning_rate": 1.1915555555555556e-05, | |
| "loss": 0.0844, | |
| "step": 2325 | |
| }, | |
| { | |
| "epoch": 10.73, | |
| "learning_rate": 1.1804444444444446e-05, | |
| "loss": 0.109, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 10.84, | |
| "learning_rate": 1.1693333333333334e-05, | |
| "loss": 0.0935, | |
| "step": 2375 | |
| }, | |
| { | |
| "epoch": 10.96, | |
| "learning_rate": 1.1582222222222224e-05, | |
| "loss": 0.1274, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 11.07, | |
| "learning_rate": 1.1471111111111113e-05, | |
| "loss": 0.0904, | |
| "step": 2425 | |
| }, | |
| { | |
| "epoch": 11.19, | |
| "learning_rate": 1.136e-05, | |
| "loss": 0.0675, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 11.3, | |
| "learning_rate": 1.124888888888889e-05, | |
| "loss": 0.0875, | |
| "step": 2475 | |
| }, | |
| { | |
| "epoch": 11.42, | |
| "learning_rate": 1.113777777777778e-05, | |
| "loss": 0.0729, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 11.53, | |
| "learning_rate": 1.1026666666666667e-05, | |
| "loss": 0.0708, | |
| "step": 2525 | |
| }, | |
| { | |
| "epoch": 11.64, | |
| "learning_rate": 1.0915555555555557e-05, | |
| "loss": 0.0948, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 11.76, | |
| "learning_rate": 1.0804444444444447e-05, | |
| "loss": 0.0795, | |
| "step": 2575 | |
| }, | |
| { | |
| "epoch": 11.87, | |
| "learning_rate": 1.0693333333333333e-05, | |
| "loss": 0.0761, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 11.99, | |
| "learning_rate": 1.0582222222222223e-05, | |
| "loss": 0.0987, | |
| "step": 2625 | |
| }, | |
| { | |
| "epoch": 12.1, | |
| "learning_rate": 1.0471111111111113e-05, | |
| "loss": 0.0723, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 12.21, | |
| "learning_rate": 1.036e-05, | |
| "loss": 0.054, | |
| "step": 2675 | |
| }, | |
| { | |
| "epoch": 12.33, | |
| "learning_rate": 1.024888888888889e-05, | |
| "loss": 0.0688, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 12.44, | |
| "learning_rate": 1.013777777777778e-05, | |
| "loss": 0.079, | |
| "step": 2725 | |
| }, | |
| { | |
| "epoch": 12.56, | |
| "learning_rate": 1.0026666666666667e-05, | |
| "loss": 0.0457, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 12.67, | |
| "learning_rate": 9.915555555555556e-06, | |
| "loss": 0.0554, | |
| "step": 2775 | |
| }, | |
| { | |
| "epoch": 12.79, | |
| "learning_rate": 9.804444444444444e-06, | |
| "loss": 0.066, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 12.9, | |
| "learning_rate": 9.693333333333334e-06, | |
| "loss": 0.0432, | |
| "step": 2825 | |
| }, | |
| { | |
| "epoch": 13.01, | |
| "learning_rate": 9.582222222222222e-06, | |
| "loss": 0.0783, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 13.13, | |
| "learning_rate": 9.471111111111112e-06, | |
| "loss": 0.0645, | |
| "step": 2875 | |
| }, | |
| { | |
| "epoch": 13.24, | |
| "learning_rate": 9.360000000000002e-06, | |
| "loss": 0.0483, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 13.36, | |
| "learning_rate": 9.24888888888889e-06, | |
| "loss": 0.0524, | |
| "step": 2925 | |
| }, | |
| { | |
| "epoch": 13.47, | |
| "learning_rate": 9.137777777777778e-06, | |
| "loss": 0.0497, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 13.58, | |
| "learning_rate": 9.026666666666666e-06, | |
| "loss": 0.0492, | |
| "step": 2975 | |
| }, | |
| { | |
| "epoch": 13.7, | |
| "learning_rate": 8.915555555555556e-06, | |
| "loss": 0.0537, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 13.7, | |
| "eval_accuracy": 0.62, | |
| "eval_loss": 2.1143836975097656, | |
| "eval_runtime": 2.8406, | |
| "eval_samples_per_second": 352.038, | |
| "eval_steps_per_second": 44.005, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 13.81, | |
| "learning_rate": 8.804444444444446e-06, | |
| "loss": 0.0493, | |
| "step": 3025 | |
| }, | |
| { | |
| "epoch": 13.93, | |
| "learning_rate": 8.693333333333334e-06, | |
| "loss": 0.0601, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 14.04, | |
| "learning_rate": 8.582222222222223e-06, | |
| "loss": 0.0522, | |
| "step": 3075 | |
| }, | |
| { | |
| "epoch": 14.16, | |
| "learning_rate": 8.471111111111112e-06, | |
| "loss": 0.024, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 14.27, | |
| "learning_rate": 8.36e-06, | |
| "loss": 0.0418, | |
| "step": 3125 | |
| }, | |
| { | |
| "epoch": 14.38, | |
| "learning_rate": 8.24888888888889e-06, | |
| "loss": 0.0578, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 14.5, | |
| "learning_rate": 8.137777777777779e-06, | |
| "loss": 0.0423, | |
| "step": 3175 | |
| }, | |
| { | |
| "epoch": 14.61, | |
| "learning_rate": 8.026666666666667e-06, | |
| "loss": 0.0478, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 14.73, | |
| "learning_rate": 7.915555555555557e-06, | |
| "loss": 0.0447, | |
| "step": 3225 | |
| }, | |
| { | |
| "epoch": 14.84, | |
| "learning_rate": 7.804444444444445e-06, | |
| "loss": 0.0416, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 14.95, | |
| "learning_rate": 7.693333333333333e-06, | |
| "loss": 0.0473, | |
| "step": 3275 | |
| }, | |
| { | |
| "epoch": 15.07, | |
| "learning_rate": 7.582222222222223e-06, | |
| "loss": 0.0459, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 15.18, | |
| "learning_rate": 7.471111111111111e-06, | |
| "loss": 0.0151, | |
| "step": 3325 | |
| }, | |
| { | |
| "epoch": 15.3, | |
| "learning_rate": 7.360000000000001e-06, | |
| "loss": 0.0403, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 15.41, | |
| "learning_rate": 7.24888888888889e-06, | |
| "loss": 0.0601, | |
| "step": 3375 | |
| }, | |
| { | |
| "epoch": 15.53, | |
| "learning_rate": 7.137777777777778e-06, | |
| "loss": 0.03, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 15.64, | |
| "learning_rate": 7.0266666666666674e-06, | |
| "loss": 0.0176, | |
| "step": 3425 | |
| }, | |
| { | |
| "epoch": 15.75, | |
| "learning_rate": 6.915555555555556e-06, | |
| "loss": 0.0169, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 15.87, | |
| "learning_rate": 6.8044444444444444e-06, | |
| "loss": 0.0351, | |
| "step": 3475 | |
| }, | |
| { | |
| "epoch": 15.98, | |
| "learning_rate": 6.693333333333334e-06, | |
| "loss": 0.0477, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 16.1, | |
| "learning_rate": 6.582222222222223e-06, | |
| "loss": 0.0474, | |
| "step": 3525 | |
| }, | |
| { | |
| "epoch": 16.21, | |
| "learning_rate": 6.471111111111111e-06, | |
| "loss": 0.0317, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 16.32, | |
| "learning_rate": 6.360000000000001e-06, | |
| "loss": 0.0216, | |
| "step": 3575 | |
| }, | |
| { | |
| "epoch": 16.44, | |
| "learning_rate": 6.24888888888889e-06, | |
| "loss": 0.0238, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 16.55, | |
| "learning_rate": 6.137777777777778e-06, | |
| "loss": 0.0458, | |
| "step": 3625 | |
| }, | |
| { | |
| "epoch": 16.67, | |
| "learning_rate": 6.026666666666668e-06, | |
| "loss": 0.0273, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 16.78, | |
| "learning_rate": 5.915555555555556e-06, | |
| "loss": 0.0058, | |
| "step": 3675 | |
| }, | |
| { | |
| "epoch": 16.89, | |
| "learning_rate": 5.804444444444445e-06, | |
| "loss": 0.0289, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 17.01, | |
| "learning_rate": 5.6933333333333344e-06, | |
| "loss": 0.0227, | |
| "step": 3725 | |
| }, | |
| { | |
| "epoch": 17.12, | |
| "learning_rate": 5.5822222222222225e-06, | |
| "loss": 0.0245, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 17.24, | |
| "learning_rate": 5.4711111111111114e-06, | |
| "loss": 0.0073, | |
| "step": 3775 | |
| }, | |
| { | |
| "epoch": 17.35, | |
| "learning_rate": 5.36e-06, | |
| "loss": 0.024, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 17.47, | |
| "learning_rate": 5.248888888888889e-06, | |
| "loss": 0.0094, | |
| "step": 3825 | |
| }, | |
| { | |
| "epoch": 17.58, | |
| "learning_rate": 5.137777777777778e-06, | |
| "loss": 0.0309, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 17.69, | |
| "learning_rate": 5.026666666666667e-06, | |
| "loss": 0.07, | |
| "step": 3875 | |
| }, | |
| { | |
| "epoch": 17.81, | |
| "learning_rate": 4.915555555555556e-06, | |
| "loss": 0.027, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 17.92, | |
| "learning_rate": 4.804444444444445e-06, | |
| "loss": 0.034, | |
| "step": 3925 | |
| }, | |
| { | |
| "epoch": 18.04, | |
| "learning_rate": 4.693333333333334e-06, | |
| "loss": 0.0337, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 18.15, | |
| "learning_rate": 4.582222222222223e-06, | |
| "loss": 0.0173, | |
| "step": 3975 | |
| }, | |
| { | |
| "epoch": 18.26, | |
| "learning_rate": 4.471111111111112e-06, | |
| "loss": 0.0346, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 18.26, | |
| "eval_accuracy": 0.643, | |
| "eval_loss": 2.5202674865722656, | |
| "eval_runtime": 2.6541, | |
| "eval_samples_per_second": 376.769, | |
| "eval_steps_per_second": 47.096, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 18.38, | |
| "learning_rate": 4.360000000000001e-06, | |
| "loss": 0.0392, | |
| "step": 4025 | |
| }, | |
| { | |
| "epoch": 18.49, | |
| "learning_rate": 4.248888888888889e-06, | |
| "loss": 0.0405, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 18.61, | |
| "learning_rate": 4.1377777777777784e-06, | |
| "loss": 0.018, | |
| "step": 4075 | |
| }, | |
| { | |
| "epoch": 18.72, | |
| "learning_rate": 4.026666666666667e-06, | |
| "loss": 0.0129, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 18.84, | |
| "learning_rate": 3.9155555555555554e-06, | |
| "loss": 0.0188, | |
| "step": 4125 | |
| }, | |
| { | |
| "epoch": 18.95, | |
| "learning_rate": 3.8044444444444443e-06, | |
| "loss": 0.0141, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 19.06, | |
| "learning_rate": 3.6933333333333337e-06, | |
| "loss": 0.0237, | |
| "step": 4175 | |
| }, | |
| { | |
| "epoch": 19.18, | |
| "learning_rate": 3.5822222222222226e-06, | |
| "loss": 0.0135, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 19.29, | |
| "learning_rate": 3.471111111111111e-06, | |
| "loss": 0.0152, | |
| "step": 4225 | |
| }, | |
| { | |
| "epoch": 19.41, | |
| "learning_rate": 3.3600000000000004e-06, | |
| "loss": 0.0286, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 19.52, | |
| "learning_rate": 3.2488888888888894e-06, | |
| "loss": 0.0106, | |
| "step": 4275 | |
| }, | |
| { | |
| "epoch": 19.63, | |
| "learning_rate": 3.137777777777778e-06, | |
| "loss": 0.0184, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 19.75, | |
| "learning_rate": 3.0266666666666668e-06, | |
| "loss": 0.019, | |
| "step": 4325 | |
| }, | |
| { | |
| "epoch": 19.86, | |
| "learning_rate": 2.915555555555556e-06, | |
| "loss": 0.0084, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 19.98, | |
| "learning_rate": 2.8044444444444446e-06, | |
| "loss": 0.0092, | |
| "step": 4375 | |
| }, | |
| { | |
| "epoch": 20.09, | |
| "learning_rate": 2.6933333333333335e-06, | |
| "loss": 0.0138, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 20.21, | |
| "learning_rate": 2.5822222222222224e-06, | |
| "loss": 0.0052, | |
| "step": 4425 | |
| }, | |
| { | |
| "epoch": 20.32, | |
| "learning_rate": 2.4711111111111114e-06, | |
| "loss": 0.0093, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 20.43, | |
| "learning_rate": 2.3600000000000003e-06, | |
| "loss": 0.0114, | |
| "step": 4475 | |
| }, | |
| { | |
| "epoch": 20.55, | |
| "learning_rate": 2.248888888888889e-06, | |
| "loss": 0.0047, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 20.66, | |
| "learning_rate": 2.137777777777778e-06, | |
| "loss": 0.0304, | |
| "step": 4525 | |
| }, | |
| { | |
| "epoch": 20.78, | |
| "learning_rate": 2.0266666666666666e-06, | |
| "loss": 0.0076, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 20.89, | |
| "learning_rate": 1.915555555555556e-06, | |
| "loss": 0.0075, | |
| "step": 4575 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "learning_rate": 1.8044444444444444e-06, | |
| "loss": 0.0178, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 21.12, | |
| "learning_rate": 1.6933333333333336e-06, | |
| "loss": 0.0104, | |
| "step": 4625 | |
| }, | |
| { | |
| "epoch": 21.23, | |
| "learning_rate": 1.5822222222222223e-06, | |
| "loss": 0.0152, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 21.35, | |
| "learning_rate": 1.4711111111111112e-06, | |
| "loss": 0.0134, | |
| "step": 4675 | |
| }, | |
| { | |
| "epoch": 21.46, | |
| "learning_rate": 1.3600000000000001e-06, | |
| "loss": 0.0252, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 21.58, | |
| "learning_rate": 1.248888888888889e-06, | |
| "loss": 0.022, | |
| "step": 4725 | |
| }, | |
| { | |
| "epoch": 21.69, | |
| "learning_rate": 1.137777777777778e-06, | |
| "loss": 0.006, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 21.8, | |
| "learning_rate": 1.0266666666666669e-06, | |
| "loss": 0.0187, | |
| "step": 4775 | |
| }, | |
| { | |
| "epoch": 21.92, | |
| "learning_rate": 9.155555555555557e-07, | |
| "loss": 0.0115, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 22.03, | |
| "learning_rate": 8.044444444444445e-07, | |
| "loss": 0.0129, | |
| "step": 4825 | |
| }, | |
| { | |
| "epoch": 22.15, | |
| "learning_rate": 6.933333333333334e-07, | |
| "loss": 0.0066, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 22.26, | |
| "learning_rate": 5.822222222222223e-07, | |
| "loss": 0.0174, | |
| "step": 4875 | |
| }, | |
| { | |
| "epoch": 22.37, | |
| "learning_rate": 4.7111111111111113e-07, | |
| "loss": 0.0181, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 22.49, | |
| "learning_rate": 3.6e-07, | |
| "loss": 0.0089, | |
| "step": 4925 | |
| }, | |
| { | |
| "epoch": 22.6, | |
| "learning_rate": 2.488888888888889e-07, | |
| "loss": 0.0157, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 22.72, | |
| "learning_rate": 1.3777777777777778e-07, | |
| "loss": 0.0219, | |
| "step": 4975 | |
| }, | |
| { | |
| "epoch": 22.83, | |
| "learning_rate": 2.6666666666666667e-08, | |
| "loss": 0.0013, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 22.83, | |
| "eval_accuracy": 0.636, | |
| "eval_loss": 2.6798980236053467, | |
| "eval_runtime": 2.8534, | |
| "eval_samples_per_second": 350.458, | |
| "eval_steps_per_second": 43.807, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 22.83, | |
| "step": 5000, | |
| "total_flos": 1.0512959718739968e+16, | |
| "train_loss": 0.2579876671291888, | |
| "train_runtime": 1594.4621, | |
| "train_samples_per_second": 100.347, | |
| "train_steps_per_second": 3.136 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 5000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 23, | |
| "save_steps": 1000, | |
| "total_flos": 1.0512959718739968e+16, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |