| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 20.0, | |
| "eval_steps": 500, | |
| "global_step": 371860, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 3.125e-05, | |
| "loss": 6.2324, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 6.25e-05, | |
| "loss": 5.004, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.375e-05, | |
| "loss": 4.6782, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.000125, | |
| "loss": 4.451, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00015625, | |
| "loss": 4.2941, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0001875, | |
| "loss": 4.1772, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00021875, | |
| "loss": 4.0706, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00025, | |
| "loss": 3.9803, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00028121875, | |
| "loss": 3.9093, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.00031246875000000003, | |
| "loss": 3.8551, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00034368749999999997, | |
| "loss": 3.8101, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.0003749375, | |
| "loss": 3.7743, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.00040615625, | |
| "loss": 3.7316, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.00043737500000000005, | |
| "loss": 3.7002, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.00046859375, | |
| "loss": 3.6744, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.00049984375, | |
| "loss": 3.6446, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.00053109375, | |
| "loss": 3.6324, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.00056234375, | |
| "loss": 3.6079, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.35758257053339554, | |
| "eval_loss": 3.814922332763672, | |
| "eval_runtime": 152.0015, | |
| "eval_samples_per_second": 381.042, | |
| "eval_steps_per_second": 5.954, | |
| "step": 18593 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.00059359375, | |
| "loss": 3.5787, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.0006248437500000001, | |
| "loss": 3.5479, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.0006560625, | |
| "loss": 3.5427, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.0006873125, | |
| "loss": 3.5347, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.00071853125, | |
| "loss": 3.5129, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.00074978125, | |
| "loss": 3.5089, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.0007810312499999999, | |
| "loss": 3.496, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.00081225, | |
| "loss": 3.4853, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.00084346875, | |
| "loss": 3.4794, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 0.00087471875, | |
| "loss": 3.471, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 0.00090596875, | |
| "loss": 3.4613, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 0.0009371875, | |
| "loss": 3.4515, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.0009684375, | |
| "loss": 3.4459, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 0.0009996875, | |
| "loss": 3.4398, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.0009970899782263285, | |
| "loss": 3.4285, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 0.0009941475901841935, | |
| "loss": 3.4208, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.0009912052021420585, | |
| "loss": 3.406, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 0.0009882628140999235, | |
| "loss": 3.3979, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 0.0009853233684458307, | |
| "loss": 3.3841, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.37915455926877084, | |
| "eval_loss": 3.590174436569214, | |
| "eval_runtime": 153.5121, | |
| "eval_samples_per_second": 377.293, | |
| "eval_steps_per_second": 5.895, | |
| "step": 37186 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 0.0009823809804036957, | |
| "loss": 3.3374, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 0.0009794415347496028, | |
| "loss": 3.3261, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 0.0009764991467074677, | |
| "loss": 3.3249, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 0.0009735567586653328, | |
| "loss": 3.3187, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 0.0009706143706231978, | |
| "loss": 3.3172, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 0.0009676719825810628, | |
| "loss": 3.3078, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 0.0009647325369269699, | |
| "loss": 3.31, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 0.000961793091272877, | |
| "loss": 3.3027, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 0.0009588507032307421, | |
| "loss": 3.2934, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 0.0009559083151886071, | |
| "loss": 3.2863, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 0.0009529659271464721, | |
| "loss": 3.291, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 0.0009500235391043372, | |
| "loss": 3.2837, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 0.0009470840934502442, | |
| "loss": 3.2791, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 0.0009441417054081093, | |
| "loss": 3.2756, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 0.0009412022597540164, | |
| "loss": 3.273, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 0.0009382598717118814, | |
| "loss": 3.2648, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 0.0009353204260577886, | |
| "loss": 3.2609, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 0.0009323780380156535, | |
| "loss": 3.2548, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.3917531951068388, | |
| "eval_loss": 3.4806971549987793, | |
| "eval_runtime": 153.7786, | |
| "eval_samples_per_second": 376.639, | |
| "eval_steps_per_second": 5.885, | |
| "step": 55779 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 0.0009294356499735185, | |
| "loss": 3.2367, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 0.0009264962043194257, | |
| "loss": 3.1899, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 0.0009235538162772906, | |
| "loss": 3.1955, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 0.00092061731301124, | |
| "loss": 3.1993, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 0.0009176749249691049, | |
| "loss": 3.1937, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 0.0009147325369269699, | |
| "loss": 3.196, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 0.0009117930912728771, | |
| "loss": 3.1964, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 0.0009088507032307421, | |
| "loss": 3.2007, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 0.0009059083151886071, | |
| "loss": 3.1925, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 0.000902965927146472, | |
| "loss": 3.193, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 0.0009000264814923792, | |
| "loss": 3.1927, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 0.0008970840934502442, | |
| "loss": 3.1868, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 0.0008941446477961514, | |
| "loss": 3.1813, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "learning_rate": 0.0008912022597540164, | |
| "loss": 3.1868, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 0.0008882628140999234, | |
| "loss": 3.1849, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 0.0008853204260577885, | |
| "loss": 3.1809, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 0.0008823809804036956, | |
| "loss": 3.1804, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 0.0008794385923615607, | |
| "loss": 3.1842, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 0.0008764991467074678, | |
| "loss": 3.1845, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.3967745643436161, | |
| "eval_loss": 3.4469034671783447, | |
| "eval_runtime": 153.5493, | |
| "eval_samples_per_second": 377.201, | |
| "eval_steps_per_second": 5.894, | |
| "step": 74372 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 0.0008735567586653328, | |
| "loss": 3.1352, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 0.0008706143706231978, | |
| "loss": 3.1097, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 0.0008676719825810628, | |
| "loss": 3.1133, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 0.0008647354793150121, | |
| "loss": 3.1205, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 0.0008617930912728771, | |
| "loss": 3.1258, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 0.0008588536456187842, | |
| "loss": 3.1284, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "learning_rate": 0.0008559112575766492, | |
| "loss": 3.1247, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 0.0008529688695345142, | |
| "loss": 3.1244, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "learning_rate": 0.0008500264814923793, | |
| "loss": 3.1273, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "learning_rate": 0.0008470870358382864, | |
| "loss": 3.1249, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 0.0008441446477961514, | |
| "loss": 3.1289, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "learning_rate": 0.0008412022597540165, | |
| "loss": 3.1241, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 0.0008382657564879656, | |
| "loss": 3.1304, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 0.0008353233684458307, | |
| "loss": 3.1271, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "learning_rate": 0.0008323839227917378, | |
| "loss": 3.1215, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "learning_rate": 0.0008294415347496028, | |
| "loss": 3.1234, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 0.0008264991467074679, | |
| "loss": 3.1243, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "learning_rate": 0.0008235567586653327, | |
| "loss": 3.1246, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.40143053666186035, | |
| "eval_loss": 3.416903018951416, | |
| "eval_runtime": 153.8466, | |
| "eval_samples_per_second": 376.472, | |
| "eval_steps_per_second": 5.882, | |
| "step": 92965 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.00082061731301124, | |
| "loss": 3.1216, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 5.06, | |
| "learning_rate": 0.0008176749249691049, | |
| "loss": 3.0534, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "learning_rate": 0.0008147325369269699, | |
| "loss": 3.0622, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 5.16, | |
| "learning_rate": 0.000811790148884835, | |
| "loss": 3.0629, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "learning_rate": 0.000808850703230742, | |
| "loss": 3.0635, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "learning_rate": 0.0008059112575766492, | |
| "loss": 3.0733, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 5.32, | |
| "learning_rate": 0.0008029688695345142, | |
| "loss": 3.0755, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 5.38, | |
| "learning_rate": 0.0008000264814923792, | |
| "loss": 3.0766, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 5.43, | |
| "learning_rate": 0.0007970840934502443, | |
| "loss": 3.0731, | |
| "step": 101000 | |
| }, | |
| { | |
| "epoch": 5.49, | |
| "learning_rate": 0.0007941417054081093, | |
| "loss": 3.078, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 5.54, | |
| "learning_rate": 0.0007911993173659742, | |
| "loss": 3.0757, | |
| "step": 103000 | |
| }, | |
| { | |
| "epoch": 5.59, | |
| "learning_rate": 0.0007882598717118814, | |
| "loss": 3.0787, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 5.65, | |
| "learning_rate": 0.0007853204260577885, | |
| "loss": 3.0817, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 5.7, | |
| "learning_rate": 0.0007823780380156536, | |
| "loss": 3.0789, | |
| "step": 106000 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "learning_rate": 0.0007794385923615607, | |
| "loss": 3.0801, | |
| "step": 107000 | |
| }, | |
| { | |
| "epoch": 5.81, | |
| "learning_rate": 0.0007764962043194257, | |
| "loss": 3.0792, | |
| "step": 108000 | |
| }, | |
| { | |
| "epoch": 5.86, | |
| "learning_rate": 0.0007735538162772907, | |
| "loss": 3.0791, | |
| "step": 109000 | |
| }, | |
| { | |
| "epoch": 5.92, | |
| "learning_rate": 0.0007706143706231978, | |
| "loss": 3.0793, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 5.97, | |
| "learning_rate": 0.0007676719825810629, | |
| "loss": 3.0823, | |
| "step": 111000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.40345429411247413, | |
| "eval_loss": 3.3872547149658203, | |
| "eval_runtime": 153.6203, | |
| "eval_samples_per_second": 377.027, | |
| "eval_steps_per_second": 5.891, | |
| "step": 111558 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 0.0007647295945389278, | |
| "loss": 3.0473, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "learning_rate": 0.0007617872064967927, | |
| "loss": 3.0106, | |
| "step": 113000 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "learning_rate": 0.0007588507032307421, | |
| "loss": 3.0174, | |
| "step": 114000 | |
| }, | |
| { | |
| "epoch": 6.19, | |
| "learning_rate": 0.0007559083151886071, | |
| "loss": 3.0203, | |
| "step": 115000 | |
| }, | |
| { | |
| "epoch": 6.24, | |
| "learning_rate": 0.0007529659271464721, | |
| "loss": 3.0278, | |
| "step": 116000 | |
| }, | |
| { | |
| "epoch": 6.29, | |
| "learning_rate": 0.0007500235391043371, | |
| "loss": 3.0312, | |
| "step": 117000 | |
| }, | |
| { | |
| "epoch": 6.35, | |
| "learning_rate": 0.000747081151062202, | |
| "loss": 3.0315, | |
| "step": 118000 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 0.0007441417054081092, | |
| "loss": 3.0355, | |
| "step": 119000 | |
| }, | |
| { | |
| "epoch": 6.45, | |
| "learning_rate": 0.0007412022597540163, | |
| "loss": 3.0334, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 6.51, | |
| "learning_rate": 0.0007382598717118814, | |
| "loss": 3.0394, | |
| "step": 121000 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "learning_rate": 0.0007353174836697464, | |
| "loss": 3.039, | |
| "step": 122000 | |
| }, | |
| { | |
| "epoch": 6.62, | |
| "learning_rate": 0.0007323780380156535, | |
| "loss": 3.039, | |
| "step": 123000 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 0.0007294356499735185, | |
| "loss": 3.0429, | |
| "step": 124000 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "learning_rate": 0.0007264932619313835, | |
| "loss": 3.0438, | |
| "step": 125000 | |
| }, | |
| { | |
| "epoch": 6.78, | |
| "learning_rate": 0.0007235538162772907, | |
| "loss": 3.0439, | |
| "step": 126000 | |
| }, | |
| { | |
| "epoch": 6.83, | |
| "learning_rate": 0.0007206114282351557, | |
| "loss": 3.0431, | |
| "step": 127000 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "learning_rate": 0.0007176690401930207, | |
| "loss": 3.0421, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 6.94, | |
| "learning_rate": 0.0007147266521508858, | |
| "loss": 3.044, | |
| "step": 129000 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "learning_rate": 0.000711793091272877, | |
| "loss": 3.0457, | |
| "step": 130000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.40529780520669445, | |
| "eval_loss": 3.3856544494628906, | |
| "eval_runtime": 153.5426, | |
| "eval_samples_per_second": 377.218, | |
| "eval_steps_per_second": 5.894, | |
| "step": 130151 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "learning_rate": 0.0007088507032307421, | |
| "loss": 2.9788, | |
| "step": 131000 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "learning_rate": 0.0007059083151886071, | |
| "loss": 2.9803, | |
| "step": 132000 | |
| }, | |
| { | |
| "epoch": 7.15, | |
| "learning_rate": 0.0007029659271464721, | |
| "loss": 2.9871, | |
| "step": 133000 | |
| }, | |
| { | |
| "epoch": 7.21, | |
| "learning_rate": 0.0007000235391043372, | |
| "loss": 2.9897, | |
| "step": 134000 | |
| }, | |
| { | |
| "epoch": 7.26, | |
| "learning_rate": 0.000697081151062202, | |
| "loss": 2.9932, | |
| "step": 135000 | |
| }, | |
| { | |
| "epoch": 7.31, | |
| "learning_rate": 0.0006941417054081093, | |
| "loss": 2.9984, | |
| "step": 136000 | |
| }, | |
| { | |
| "epoch": 7.37, | |
| "learning_rate": 0.0006911993173659742, | |
| "loss": 2.9945, | |
| "step": 137000 | |
| }, | |
| { | |
| "epoch": 7.42, | |
| "learning_rate": 0.0006882598717118814, | |
| "loss": 3.0014, | |
| "step": 138000 | |
| }, | |
| { | |
| "epoch": 7.48, | |
| "learning_rate": 0.0006853174836697464, | |
| "loss": 3.004, | |
| "step": 139000 | |
| }, | |
| { | |
| "epoch": 7.53, | |
| "learning_rate": 0.0006823750956276113, | |
| "loss": 3.0046, | |
| "step": 140000 | |
| }, | |
| { | |
| "epoch": 7.58, | |
| "learning_rate": 0.0006794356499735185, | |
| "loss": 3.0085, | |
| "step": 141000 | |
| }, | |
| { | |
| "epoch": 7.64, | |
| "learning_rate": 0.0006764932619313835, | |
| "loss": 3.0102, | |
| "step": 142000 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "learning_rate": 0.0006735508738892485, | |
| "loss": 3.0089, | |
| "step": 143000 | |
| }, | |
| { | |
| "epoch": 7.74, | |
| "learning_rate": 0.0006706084858471136, | |
| "loss": 3.0119, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 7.8, | |
| "learning_rate": 0.0006676690401930206, | |
| "loss": 3.0145, | |
| "step": 145000 | |
| }, | |
| { | |
| "epoch": 7.85, | |
| "learning_rate": 0.0006647266521508856, | |
| "loss": 3.0094, | |
| "step": 146000 | |
| }, | |
| { | |
| "epoch": 7.91, | |
| "learning_rate": 0.0006617872064967928, | |
| "loss": 3.013, | |
| "step": 147000 | |
| }, | |
| { | |
| "epoch": 7.96, | |
| "learning_rate": 0.0006588477608426999, | |
| "loss": 3.0112, | |
| "step": 148000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.40697128144141725, | |
| "eval_loss": 3.351954936981201, | |
| "eval_runtime": 153.9341, | |
| "eval_samples_per_second": 376.258, | |
| "eval_steps_per_second": 5.879, | |
| "step": 148744 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 0.000655905372800565, | |
| "loss": 2.9938, | |
| "step": 149000 | |
| }, | |
| { | |
| "epoch": 8.07, | |
| "learning_rate": 0.00065296298475843, | |
| "loss": 2.9454, | |
| "step": 150000 | |
| }, | |
| { | |
| "epoch": 8.12, | |
| "learning_rate": 0.0006500205967162949, | |
| "loss": 2.9538, | |
| "step": 151000 | |
| }, | |
| { | |
| "epoch": 8.18, | |
| "learning_rate": 0.0006470811510622021, | |
| "loss": 2.957, | |
| "step": 152000 | |
| }, | |
| { | |
| "epoch": 8.23, | |
| "learning_rate": 0.0006441417054081092, | |
| "loss": 2.959, | |
| "step": 153000 | |
| }, | |
| { | |
| "epoch": 8.28, | |
| "learning_rate": 0.0006411993173659743, | |
| "loss": 2.9678, | |
| "step": 154000 | |
| }, | |
| { | |
| "epoch": 8.34, | |
| "learning_rate": 0.0006382569293238393, | |
| "loss": 2.9651, | |
| "step": 155000 | |
| }, | |
| { | |
| "epoch": 8.39, | |
| "learning_rate": 0.0006353145412817042, | |
| "loss": 2.9725, | |
| "step": 156000 | |
| }, | |
| { | |
| "epoch": 8.44, | |
| "learning_rate": 0.0006323750956276114, | |
| "loss": 2.9723, | |
| "step": 157000 | |
| }, | |
| { | |
| "epoch": 8.5, | |
| "learning_rate": 0.0006294327075854764, | |
| "loss": 2.9785, | |
| "step": 158000 | |
| }, | |
| { | |
| "epoch": 8.55, | |
| "learning_rate": 0.0006264903195433414, | |
| "loss": 2.9773, | |
| "step": 159000 | |
| }, | |
| { | |
| "epoch": 8.61, | |
| "learning_rate": 0.0006235508738892486, | |
| "loss": 2.9782, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 8.66, | |
| "learning_rate": 0.0006206084858471134, | |
| "loss": 2.9797, | |
| "step": 161000 | |
| }, | |
| { | |
| "epoch": 8.71, | |
| "learning_rate": 0.0006176690401930206, | |
| "loss": 2.9821, | |
| "step": 162000 | |
| }, | |
| { | |
| "epoch": 8.77, | |
| "learning_rate": 0.0006147266521508856, | |
| "loss": 2.9781, | |
| "step": 163000 | |
| }, | |
| { | |
| "epoch": 8.82, | |
| "learning_rate": 0.0006117872064967928, | |
| "loss": 2.9783, | |
| "step": 164000 | |
| }, | |
| { | |
| "epoch": 8.87, | |
| "learning_rate": 0.0006088448184546578, | |
| "loss": 2.9839, | |
| "step": 165000 | |
| }, | |
| { | |
| "epoch": 8.93, | |
| "learning_rate": 0.0006059024304125227, | |
| "loss": 2.9802, | |
| "step": 166000 | |
| }, | |
| { | |
| "epoch": 8.98, | |
| "learning_rate": 0.0006029629847584299, | |
| "loss": 2.9878, | |
| "step": 167000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.40724766366661397, | |
| "eval_loss": 3.373262882232666, | |
| "eval_runtime": 153.9138, | |
| "eval_samples_per_second": 376.308, | |
| "eval_steps_per_second": 5.88, | |
| "step": 167337 | |
| }, | |
| { | |
| "epoch": 9.04, | |
| "learning_rate": 0.000600023539104337, | |
| "loss": 2.9425, | |
| "step": 168000 | |
| }, | |
| { | |
| "epoch": 9.09, | |
| "learning_rate": 0.0005970811510622021, | |
| "loss": 2.9186, | |
| "step": 169000 | |
| }, | |
| { | |
| "epoch": 9.14, | |
| "learning_rate": 0.0005941387630200671, | |
| "loss": 2.9267, | |
| "step": 170000 | |
| }, | |
| { | |
| "epoch": 9.2, | |
| "learning_rate": 0.0005911963749779321, | |
| "loss": 2.9365, | |
| "step": 171000 | |
| }, | |
| { | |
| "epoch": 9.25, | |
| "learning_rate": 0.0005882539869357971, | |
| "loss": 2.936, | |
| "step": 172000 | |
| }, | |
| { | |
| "epoch": 9.3, | |
| "learning_rate": 0.0005853115988936621, | |
| "loss": 2.9392, | |
| "step": 173000 | |
| }, | |
| { | |
| "epoch": 9.36, | |
| "learning_rate": 0.0005823721532395693, | |
| "loss": 2.9433, | |
| "step": 174000 | |
| }, | |
| { | |
| "epoch": 9.41, | |
| "learning_rate": 0.0005794327075854764, | |
| "loss": 2.9456, | |
| "step": 175000 | |
| }, | |
| { | |
| "epoch": 9.47, | |
| "learning_rate": 0.0005764903195433414, | |
| "loss": 2.9453, | |
| "step": 176000 | |
| }, | |
| { | |
| "epoch": 9.52, | |
| "learning_rate": 0.0005735479315012065, | |
| "loss": 2.95, | |
| "step": 177000 | |
| }, | |
| { | |
| "epoch": 9.57, | |
| "learning_rate": 0.0005706055434590713, | |
| "loss": 2.9531, | |
| "step": 178000 | |
| }, | |
| { | |
| "epoch": 9.63, | |
| "learning_rate": 0.0005676660978049786, | |
| "loss": 2.9517, | |
| "step": 179000 | |
| }, | |
| { | |
| "epoch": 9.68, | |
| "learning_rate": 0.0005647237097628435, | |
| "loss": 2.9523, | |
| "step": 180000 | |
| }, | |
| { | |
| "epoch": 9.73, | |
| "learning_rate": 0.0005617813217207085, | |
| "loss": 2.9557, | |
| "step": 181000 | |
| }, | |
| { | |
| "epoch": 9.79, | |
| "learning_rate": 0.0005588418760666157, | |
| "loss": 2.9531, | |
| "step": 182000 | |
| }, | |
| { | |
| "epoch": 9.84, | |
| "learning_rate": 0.0005559024304125228, | |
| "loss": 2.9572, | |
| "step": 183000 | |
| }, | |
| { | |
| "epoch": 9.9, | |
| "learning_rate": 0.0005529600423703878, | |
| "loss": 2.9587, | |
| "step": 184000 | |
| }, | |
| { | |
| "epoch": 9.95, | |
| "learning_rate": 0.0005500176543282528, | |
| "loss": 2.96, | |
| "step": 185000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.4083363301613423, | |
| "eval_loss": 3.3502931594848633, | |
| "eval_runtime": 153.7858, | |
| "eval_samples_per_second": 376.621, | |
| "eval_steps_per_second": 5.885, | |
| "step": 185930 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 0.0005470782086741599, | |
| "loss": 2.9556, | |
| "step": 186000 | |
| }, | |
| { | |
| "epoch": 10.06, | |
| "learning_rate": 0.000544135820632025, | |
| "loss": 2.8933, | |
| "step": 187000 | |
| }, | |
| { | |
| "epoch": 10.11, | |
| "learning_rate": 0.0005411934325898899, | |
| "loss": 2.9007, | |
| "step": 188000 | |
| }, | |
| { | |
| "epoch": 10.17, | |
| "learning_rate": 0.0005382510445477549, | |
| "loss": 2.9058, | |
| "step": 189000 | |
| }, | |
| { | |
| "epoch": 10.22, | |
| "learning_rate": 0.0005353145412817042, | |
| "loss": 2.9129, | |
| "step": 190000 | |
| }, | |
| { | |
| "epoch": 10.27, | |
| "learning_rate": 0.0005323721532395692, | |
| "loss": 2.9168, | |
| "step": 191000 | |
| }, | |
| { | |
| "epoch": 10.33, | |
| "learning_rate": 0.0005294297651974343, | |
| "loss": 2.9153, | |
| "step": 192000 | |
| }, | |
| { | |
| "epoch": 10.38, | |
| "learning_rate": 0.0005264873771552992, | |
| "loss": 2.9197, | |
| "step": 193000 | |
| }, | |
| { | |
| "epoch": 10.43, | |
| "learning_rate": 0.0005235479315012064, | |
| "loss": 2.9233, | |
| "step": 194000 | |
| }, | |
| { | |
| "epoch": 10.49, | |
| "learning_rate": 0.0005206084858471135, | |
| "loss": 2.9206, | |
| "step": 195000 | |
| }, | |
| { | |
| "epoch": 10.54, | |
| "learning_rate": 0.0005176690401930207, | |
| "loss": 2.923, | |
| "step": 196000 | |
| }, | |
| { | |
| "epoch": 10.6, | |
| "learning_rate": 0.0005147266521508857, | |
| "loss": 2.9268, | |
| "step": 197000 | |
| }, | |
| { | |
| "epoch": 10.65, | |
| "learning_rate": 0.0005117842641087506, | |
| "loss": 2.9284, | |
| "step": 198000 | |
| }, | |
| { | |
| "epoch": 10.7, | |
| "learning_rate": 0.0005088418760666157, | |
| "loss": 2.9327, | |
| "step": 199000 | |
| }, | |
| { | |
| "epoch": 10.76, | |
| "learning_rate": 0.0005058994880244807, | |
| "loss": 2.9307, | |
| "step": 200000 | |
| }, | |
| { | |
| "epoch": 10.81, | |
| "learning_rate": 0.0005029570999823457, | |
| "loss": 2.9309, | |
| "step": 201000 | |
| }, | |
| { | |
| "epoch": 10.86, | |
| "learning_rate": 0.0005000147119402107, | |
| "loss": 2.9368, | |
| "step": 202000 | |
| }, | |
| { | |
| "epoch": 10.92, | |
| "learning_rate": 0.0004970752662861179, | |
| "loss": 2.9346, | |
| "step": 203000 | |
| }, | |
| { | |
| "epoch": 10.97, | |
| "learning_rate": 0.0004941358206320249, | |
| "loss": 2.938, | |
| "step": 204000 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.40840062228324636, | |
| "eval_loss": 3.3663504123687744, | |
| "eval_runtime": 153.6763, | |
| "eval_samples_per_second": 376.89, | |
| "eval_steps_per_second": 5.889, | |
| "step": 204523 | |
| }, | |
| { | |
| "epoch": 11.03, | |
| "learning_rate": 0.0004911934325898899, | |
| "loss": 2.9043, | |
| "step": 205000 | |
| }, | |
| { | |
| "epoch": 11.08, | |
| "learning_rate": 0.0004882539869357971, | |
| "loss": 2.8785, | |
| "step": 206000 | |
| }, | |
| { | |
| "epoch": 11.13, | |
| "learning_rate": 0.00048531159889366214, | |
| "loss": 2.881, | |
| "step": 207000 | |
| }, | |
| { | |
| "epoch": 11.19, | |
| "learning_rate": 0.0004823692108515271, | |
| "loss": 2.8844, | |
| "step": 208000 | |
| }, | |
| { | |
| "epoch": 11.24, | |
| "learning_rate": 0.00047942976519743425, | |
| "loss": 2.8866, | |
| "step": 209000 | |
| }, | |
| { | |
| "epoch": 11.29, | |
| "learning_rate": 0.0004764873771552993, | |
| "loss": 2.8919, | |
| "step": 210000 | |
| }, | |
| { | |
| "epoch": 11.35, | |
| "learning_rate": 0.00047354498911316426, | |
| "loss": 2.8931, | |
| "step": 211000 | |
| }, | |
| { | |
| "epoch": 11.4, | |
| "learning_rate": 0.00047060260107102924, | |
| "loss": 2.8974, | |
| "step": 212000 | |
| }, | |
| { | |
| "epoch": 11.46, | |
| "learning_rate": 0.00046766315541693637, | |
| "loss": 2.8975, | |
| "step": 213000 | |
| }, | |
| { | |
| "epoch": 11.51, | |
| "learning_rate": 0.0004647207673748014, | |
| "loss": 2.9048, | |
| "step": 214000 | |
| }, | |
| { | |
| "epoch": 11.56, | |
| "learning_rate": 0.00046178132172070853, | |
| "loss": 2.9042, | |
| "step": 215000 | |
| }, | |
| { | |
| "epoch": 11.62, | |
| "learning_rate": 0.00045883893367857357, | |
| "loss": 2.9049, | |
| "step": 216000 | |
| }, | |
| { | |
| "epoch": 11.67, | |
| "learning_rate": 0.00045589654563643855, | |
| "loss": 2.91, | |
| "step": 217000 | |
| }, | |
| { | |
| "epoch": 11.72, | |
| "learning_rate": 0.00045295415759430353, | |
| "loss": 2.9081, | |
| "step": 218000 | |
| }, | |
| { | |
| "epoch": 11.78, | |
| "learning_rate": 0.0004500176543282528, | |
| "loss": 2.9122, | |
| "step": 219000 | |
| }, | |
| { | |
| "epoch": 11.83, | |
| "learning_rate": 0.00044707526628611784, | |
| "loss": 2.9081, | |
| "step": 220000 | |
| }, | |
| { | |
| "epoch": 11.89, | |
| "learning_rate": 0.0004441328782439829, | |
| "loss": 2.9113, | |
| "step": 221000 | |
| }, | |
| { | |
| "epoch": 11.94, | |
| "learning_rate": 0.00044119343258988995, | |
| "loss": 2.9173, | |
| "step": 222000 | |
| }, | |
| { | |
| "epoch": 11.99, | |
| "learning_rate": 0.00043825104454775493, | |
| "loss": 2.9158, | |
| "step": 223000 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.409260269087723, | |
| "eval_loss": 3.3659985065460205, | |
| "eval_runtime": 153.6366, | |
| "eval_samples_per_second": 376.987, | |
| "eval_steps_per_second": 5.891, | |
| "step": 223116 | |
| }, | |
| { | |
| "epoch": 12.05, | |
| "learning_rate": 0.0004353115988936621, | |
| "loss": 2.8563, | |
| "step": 224000 | |
| }, | |
| { | |
| "epoch": 12.1, | |
| "learning_rate": 0.0004323692108515271, | |
| "loss": 2.8596, | |
| "step": 225000 | |
| }, | |
| { | |
| "epoch": 12.16, | |
| "learning_rate": 0.0004294268228093921, | |
| "loss": 2.8624, | |
| "step": 226000 | |
| }, | |
| { | |
| "epoch": 12.21, | |
| "learning_rate": 0.0004264873771552992, | |
| "loss": 2.8647, | |
| "step": 227000 | |
| }, | |
| { | |
| "epoch": 12.26, | |
| "learning_rate": 0.00042354498911316424, | |
| "loss": 2.8693, | |
| "step": 228000 | |
| }, | |
| { | |
| "epoch": 12.32, | |
| "learning_rate": 0.0004206026010710293, | |
| "loss": 2.8721, | |
| "step": 229000 | |
| }, | |
| { | |
| "epoch": 12.37, | |
| "learning_rate": 0.0004176602130288943, | |
| "loss": 2.8762, | |
| "step": 230000 | |
| }, | |
| { | |
| "epoch": 12.42, | |
| "learning_rate": 0.0004147207673748014, | |
| "loss": 2.8763, | |
| "step": 231000 | |
| }, | |
| { | |
| "epoch": 12.48, | |
| "learning_rate": 0.00041177837933266637, | |
| "loss": 2.8808, | |
| "step": 232000 | |
| }, | |
| { | |
| "epoch": 12.53, | |
| "learning_rate": 0.0004088359912905314, | |
| "loss": 2.8784, | |
| "step": 233000 | |
| }, | |
| { | |
| "epoch": 12.59, | |
| "learning_rate": 0.00040589360324839644, | |
| "loss": 2.8828, | |
| "step": 234000 | |
| }, | |
| { | |
| "epoch": 12.64, | |
| "learning_rate": 0.00040295415759430357, | |
| "loss": 2.8865, | |
| "step": 235000 | |
| }, | |
| { | |
| "epoch": 12.69, | |
| "learning_rate": 0.00040001176955216855, | |
| "loss": 2.8932, | |
| "step": 236000 | |
| }, | |
| { | |
| "epoch": 12.75, | |
| "learning_rate": 0.0003970723238980757, | |
| "loss": 2.8908, | |
| "step": 237000 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "learning_rate": 0.0003941328782439828, | |
| "loss": 2.8887, | |
| "step": 238000 | |
| }, | |
| { | |
| "epoch": 12.85, | |
| "learning_rate": 0.00039119049020184784, | |
| "loss": 2.8927, | |
| "step": 239000 | |
| }, | |
| { | |
| "epoch": 12.91, | |
| "learning_rate": 0.00038824810215971287, | |
| "loss": 2.8926, | |
| "step": 240000 | |
| }, | |
| { | |
| "epoch": 12.96, | |
| "learning_rate": 0.00038530865650561995, | |
| "loss": 2.8919, | |
| "step": 241000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.41007524059327993, | |
| "eval_loss": 3.356402635574341, | |
| "eval_runtime": 153.9338, | |
| "eval_samples_per_second": 376.259, | |
| "eval_steps_per_second": 5.879, | |
| "step": 241709 | |
| }, | |
| { | |
| "epoch": 13.02, | |
| "learning_rate": 0.000382366268463485, | |
| "loss": 2.8744, | |
| "step": 242000 | |
| }, | |
| { | |
| "epoch": 13.07, | |
| "learning_rate": 0.00037942388042134996, | |
| "loss": 2.8308, | |
| "step": 243000 | |
| }, | |
| { | |
| "epoch": 13.12, | |
| "learning_rate": 0.00037648443476725714, | |
| "loss": 2.8409, | |
| "step": 244000 | |
| }, | |
| { | |
| "epoch": 13.18, | |
| "learning_rate": 0.00037354204672512207, | |
| "loss": 2.8463, | |
| "step": 245000 | |
| }, | |
| { | |
| "epoch": 13.23, | |
| "learning_rate": 0.0003705996586829871, | |
| "loss": 2.8508, | |
| "step": 246000 | |
| }, | |
| { | |
| "epoch": 13.28, | |
| "learning_rate": 0.00036765727064085214, | |
| "loss": 2.8527, | |
| "step": 247000 | |
| }, | |
| { | |
| "epoch": 13.34, | |
| "learning_rate": 0.0003647148825987171, | |
| "loss": 2.8531, | |
| "step": 248000 | |
| }, | |
| { | |
| "epoch": 13.39, | |
| "learning_rate": 0.0003617754369446243, | |
| "loss": 2.8581, | |
| "step": 249000 | |
| }, | |
| { | |
| "epoch": 13.45, | |
| "learning_rate": 0.0003588359912905314, | |
| "loss": 2.8592, | |
| "step": 250000 | |
| }, | |
| { | |
| "epoch": 13.5, | |
| "learning_rate": 0.0003558936032483964, | |
| "loss": 2.8585, | |
| "step": 251000 | |
| }, | |
| { | |
| "epoch": 13.55, | |
| "learning_rate": 0.0003529512152062614, | |
| "loss": 2.8675, | |
| "step": 252000 | |
| }, | |
| { | |
| "epoch": 13.61, | |
| "learning_rate": 0.00035000882716412643, | |
| "loss": 2.8613, | |
| "step": 253000 | |
| }, | |
| { | |
| "epoch": 13.66, | |
| "learning_rate": 0.00034706938151003356, | |
| "loss": 2.867, | |
| "step": 254000 | |
| }, | |
| { | |
| "epoch": 13.71, | |
| "learning_rate": 0.0003441299358559407, | |
| "loss": 2.8679, | |
| "step": 255000 | |
| }, | |
| { | |
| "epoch": 13.77, | |
| "learning_rate": 0.00034118754781380567, | |
| "loss": 2.8687, | |
| "step": 256000 | |
| }, | |
| { | |
| "epoch": 13.82, | |
| "learning_rate": 0.0003382451597716707, | |
| "loss": 2.8717, | |
| "step": 257000 | |
| }, | |
| { | |
| "epoch": 13.88, | |
| "learning_rate": 0.00033530277172953574, | |
| "loss": 2.8678, | |
| "step": 258000 | |
| }, | |
| { | |
| "epoch": 13.93, | |
| "learning_rate": 0.00033236038368740067, | |
| "loss": 2.87, | |
| "step": 259000 | |
| }, | |
| { | |
| "epoch": 13.98, | |
| "learning_rate": 0.0003294179956452657, | |
| "loss": 2.8735, | |
| "step": 260000 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.4106870570553281, | |
| "eval_loss": 3.3567473888397217, | |
| "eval_runtime": 153.9192, | |
| "eval_samples_per_second": 376.295, | |
| "eval_steps_per_second": 5.88, | |
| "step": 260302 | |
| }, | |
| { | |
| "epoch": 14.04, | |
| "learning_rate": 0.00032647854999117283, | |
| "loss": 2.8363, | |
| "step": 261000 | |
| }, | |
| { | |
| "epoch": 14.09, | |
| "learning_rate": 0.00032353616194903787, | |
| "loss": 2.8187, | |
| "step": 262000 | |
| }, | |
| { | |
| "epoch": 14.15, | |
| "learning_rate": 0.00032059377390690285, | |
| "loss": 2.8209, | |
| "step": 263000 | |
| }, | |
| { | |
| "epoch": 14.2, | |
| "learning_rate": 0.00031765432825281, | |
| "loss": 2.8269, | |
| "step": 264000 | |
| }, | |
| { | |
| "epoch": 14.25, | |
| "learning_rate": 0.000314711940210675, | |
| "loss": 2.8333, | |
| "step": 265000 | |
| }, | |
| { | |
| "epoch": 14.31, | |
| "learning_rate": 0.00031177249455658214, | |
| "loss": 2.8345, | |
| "step": 266000 | |
| }, | |
| { | |
| "epoch": 14.36, | |
| "learning_rate": 0.0003088301065144472, | |
| "loss": 2.8346, | |
| "step": 267000 | |
| }, | |
| { | |
| "epoch": 14.41, | |
| "learning_rate": 0.0003058877184723121, | |
| "loss": 2.8415, | |
| "step": 268000 | |
| }, | |
| { | |
| "epoch": 14.47, | |
| "learning_rate": 0.00030294533043017714, | |
| "loss": 2.8395, | |
| "step": 269000 | |
| }, | |
| { | |
| "epoch": 14.52, | |
| "learning_rate": 0.00030000588477608426, | |
| "loss": 2.8446, | |
| "step": 270000 | |
| }, | |
| { | |
| "epoch": 14.58, | |
| "learning_rate": 0.00029706643912199145, | |
| "loss": 2.8475, | |
| "step": 271000 | |
| }, | |
| { | |
| "epoch": 14.63, | |
| "learning_rate": 0.00029412405107985643, | |
| "loss": 2.8464, | |
| "step": 272000 | |
| }, | |
| { | |
| "epoch": 14.68, | |
| "learning_rate": 0.0002911816630377214, | |
| "loss": 2.8431, | |
| "step": 273000 | |
| }, | |
| { | |
| "epoch": 14.74, | |
| "learning_rate": 0.00028823927499558645, | |
| "loss": 2.8475, | |
| "step": 274000 | |
| }, | |
| { | |
| "epoch": 14.79, | |
| "learning_rate": 0.00028529982934149357, | |
| "loss": 2.8491, | |
| "step": 275000 | |
| }, | |
| { | |
| "epoch": 14.84, | |
| "learning_rate": 0.0002823603836874007, | |
| "loss": 2.854, | |
| "step": 276000 | |
| }, | |
| { | |
| "epoch": 14.9, | |
| "learning_rate": 0.00027941799564526574, | |
| "loss": 2.8498, | |
| "step": 277000 | |
| }, | |
| { | |
| "epoch": 14.95, | |
| "learning_rate": 0.0002764756076031307, | |
| "loss": 2.8562, | |
| "step": 278000 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.4100232425761914, | |
| "eval_loss": 3.3675010204315186, | |
| "eval_runtime": 153.998, | |
| "eval_samples_per_second": 376.102, | |
| "eval_steps_per_second": 5.877, | |
| "step": 278895 | |
| }, | |
| { | |
| "epoch": 15.01, | |
| "learning_rate": 0.0002735332195609957, | |
| "loss": 2.8471, | |
| "step": 279000 | |
| }, | |
| { | |
| "epoch": 15.06, | |
| "learning_rate": 0.0002705937739069029, | |
| "loss": 2.805, | |
| "step": 280000 | |
| }, | |
| { | |
| "epoch": 15.11, | |
| "learning_rate": 0.00026765138586476786, | |
| "loss": 2.8089, | |
| "step": 281000 | |
| }, | |
| { | |
| "epoch": 15.17, | |
| "learning_rate": 0.00026470899782263284, | |
| "loss": 2.8092, | |
| "step": 282000 | |
| }, | |
| { | |
| "epoch": 15.22, | |
| "learning_rate": 0.00026176955216853997, | |
| "loss": 2.8135, | |
| "step": 283000 | |
| }, | |
| { | |
| "epoch": 15.27, | |
| "learning_rate": 0.000258827164126405, | |
| "loss": 2.8146, | |
| "step": 284000 | |
| }, | |
| { | |
| "epoch": 15.33, | |
| "learning_rate": 0.00025588477608427004, | |
| "loss": 2.8197, | |
| "step": 285000 | |
| }, | |
| { | |
| "epoch": 15.38, | |
| "learning_rate": 0.00025294533043017717, | |
| "loss": 2.8212, | |
| "step": 286000 | |
| }, | |
| { | |
| "epoch": 15.44, | |
| "learning_rate": 0.00025000294238804215, | |
| "loss": 2.8213, | |
| "step": 287000 | |
| }, | |
| { | |
| "epoch": 15.49, | |
| "learning_rate": 0.00024706055434590713, | |
| "loss": 2.8222, | |
| "step": 288000 | |
| }, | |
| { | |
| "epoch": 15.54, | |
| "learning_rate": 0.0002441211086918143, | |
| "loss": 2.8197, | |
| "step": 289000 | |
| }, | |
| { | |
| "epoch": 15.6, | |
| "learning_rate": 0.00024117872064967927, | |
| "loss": 2.825, | |
| "step": 290000 | |
| }, | |
| { | |
| "epoch": 15.65, | |
| "learning_rate": 0.0002382363326075443, | |
| "loss": 2.8267, | |
| "step": 291000 | |
| }, | |
| { | |
| "epoch": 15.7, | |
| "learning_rate": 0.0002352968869534514, | |
| "loss": 2.826, | |
| "step": 292000 | |
| }, | |
| { | |
| "epoch": 15.76, | |
| "learning_rate": 0.00023235449891131644, | |
| "loss": 2.8306, | |
| "step": 293000 | |
| }, | |
| { | |
| "epoch": 15.81, | |
| "learning_rate": 0.00022941211086918142, | |
| "loss": 2.8308, | |
| "step": 294000 | |
| }, | |
| { | |
| "epoch": 15.87, | |
| "learning_rate": 0.00022646972282704646, | |
| "loss": 2.8306, | |
| "step": 295000 | |
| }, | |
| { | |
| "epoch": 15.92, | |
| "learning_rate": 0.00022353027717295358, | |
| "loss": 2.8337, | |
| "step": 296000 | |
| }, | |
| { | |
| "epoch": 15.97, | |
| "learning_rate": 0.00022058788913081857, | |
| "loss": 2.8344, | |
| "step": 297000 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.4103203836996831, | |
| "eval_loss": 3.3702094554901123, | |
| "eval_runtime": 154.2186, | |
| "eval_samples_per_second": 375.564, | |
| "eval_steps_per_second": 5.868, | |
| "step": 297488 | |
| }, | |
| { | |
| "epoch": 16.03, | |
| "learning_rate": 0.00021764550108868357, | |
| "loss": 2.8099, | |
| "step": 298000 | |
| }, | |
| { | |
| "epoch": 16.08, | |
| "learning_rate": 0.0002147060554345907, | |
| "loss": 2.7897, | |
| "step": 299000 | |
| }, | |
| { | |
| "epoch": 16.14, | |
| "learning_rate": 0.00021176366739245574, | |
| "loss": 2.7917, | |
| "step": 300000 | |
| }, | |
| { | |
| "epoch": 16.19, | |
| "learning_rate": 0.00020882127935032072, | |
| "loss": 2.7953, | |
| "step": 301000 | |
| }, | |
| { | |
| "epoch": 16.24, | |
| "learning_rate": 0.00020588183369622787, | |
| "loss": 2.7966, | |
| "step": 302000 | |
| }, | |
| { | |
| "epoch": 16.3, | |
| "learning_rate": 0.00020293944565409286, | |
| "loss": 2.8025, | |
| "step": 303000 | |
| }, | |
| { | |
| "epoch": 16.35, | |
| "learning_rate": 0.0002, | |
| "loss": 2.8022, | |
| "step": 304000 | |
| }, | |
| { | |
| "epoch": 16.4, | |
| "learning_rate": 0.00019705761195786502, | |
| "loss": 2.8053, | |
| "step": 305000 | |
| }, | |
| { | |
| "epoch": 16.46, | |
| "learning_rate": 0.00019411522391573, | |
| "loss": 2.8051, | |
| "step": 306000 | |
| }, | |
| { | |
| "epoch": 16.51, | |
| "learning_rate": 0.000191172835873595, | |
| "loss": 2.8114, | |
| "step": 307000 | |
| }, | |
| { | |
| "epoch": 16.57, | |
| "learning_rate": 0.00018823044783146002, | |
| "loss": 2.8063, | |
| "step": 308000 | |
| }, | |
| { | |
| "epoch": 16.62, | |
| "learning_rate": 0.0001852939445654093, | |
| "loss": 2.8062, | |
| "step": 309000 | |
| }, | |
| { | |
| "epoch": 16.67, | |
| "learning_rate": 0.0001823515565232743, | |
| "loss": 2.8081, | |
| "step": 310000 | |
| }, | |
| { | |
| "epoch": 16.73, | |
| "learning_rate": 0.0001794091684811393, | |
| "loss": 2.8049, | |
| "step": 311000 | |
| }, | |
| { | |
| "epoch": 16.78, | |
| "learning_rate": 0.0001764667804390043, | |
| "loss": 2.8113, | |
| "step": 312000 | |
| }, | |
| { | |
| "epoch": 16.83, | |
| "learning_rate": 0.00017352733478491144, | |
| "loss": 2.8138, | |
| "step": 313000 | |
| }, | |
| { | |
| "epoch": 16.89, | |
| "learning_rate": 0.00017058494674277645, | |
| "loss": 2.8114, | |
| "step": 314000 | |
| }, | |
| { | |
| "epoch": 16.94, | |
| "learning_rate": 0.00016764550108868358, | |
| "loss": 2.8168, | |
| "step": 315000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "learning_rate": 0.0001647031130465486, | |
| "loss": 2.814, | |
| "step": 316000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.4100904906577232, | |
| "eval_loss": 3.380819797515869, | |
| "eval_runtime": 153.6931, | |
| "eval_samples_per_second": 376.848, | |
| "eval_steps_per_second": 5.888, | |
| "step": 316081 | |
| }, | |
| { | |
| "epoch": 17.05, | |
| "learning_rate": 0.00016176072500441357, | |
| "loss": 2.7806, | |
| "step": 317000 | |
| }, | |
| { | |
| "epoch": 17.1, | |
| "learning_rate": 0.00015882422173836287, | |
| "loss": 2.7806, | |
| "step": 318000 | |
| }, | |
| { | |
| "epoch": 17.16, | |
| "learning_rate": 0.00015588183369622785, | |
| "loss": 2.7804, | |
| "step": 319000 | |
| }, | |
| { | |
| "epoch": 17.21, | |
| "learning_rate": 0.0001529394456540929, | |
| "loss": 2.7796, | |
| "step": 320000 | |
| }, | |
| { | |
| "epoch": 17.26, | |
| "learning_rate": 0.00014999705761195787, | |
| "loss": 2.7818, | |
| "step": 321000 | |
| }, | |
| { | |
| "epoch": 17.32, | |
| "learning_rate": 0.00014705761195786502, | |
| "loss": 2.7842, | |
| "step": 322000 | |
| }, | |
| { | |
| "epoch": 17.37, | |
| "learning_rate": 0.00014411816630377215, | |
| "loss": 2.7866, | |
| "step": 323000 | |
| }, | |
| { | |
| "epoch": 17.43, | |
| "learning_rate": 0.0001411787206496793, | |
| "loss": 2.7849, | |
| "step": 324000 | |
| }, | |
| { | |
| "epoch": 17.48, | |
| "learning_rate": 0.00013823633260754429, | |
| "loss": 2.7858, | |
| "step": 325000 | |
| }, | |
| { | |
| "epoch": 17.53, | |
| "learning_rate": 0.00013529394456540927, | |
| "loss": 2.7908, | |
| "step": 326000 | |
| }, | |
| { | |
| "epoch": 17.59, | |
| "learning_rate": 0.0001323515565232743, | |
| "loss": 2.7868, | |
| "step": 327000 | |
| }, | |
| { | |
| "epoch": 17.64, | |
| "learning_rate": 0.00012940916848113928, | |
| "loss": 2.7918, | |
| "step": 328000 | |
| }, | |
| { | |
| "epoch": 17.69, | |
| "learning_rate": 0.00012646972282704644, | |
| "loss": 2.7926, | |
| "step": 329000 | |
| }, | |
| { | |
| "epoch": 17.75, | |
| "learning_rate": 0.00012352733478491142, | |
| "loss": 2.7943, | |
| "step": 330000 | |
| }, | |
| { | |
| "epoch": 17.8, | |
| "learning_rate": 0.00012058494674277644, | |
| "loss": 2.7906, | |
| "step": 331000 | |
| }, | |
| { | |
| "epoch": 17.86, | |
| "learning_rate": 0.00011764255870064144, | |
| "loss": 2.796, | |
| "step": 332000 | |
| }, | |
| { | |
| "epoch": 17.91, | |
| "learning_rate": 0.00011470017065850645, | |
| "loss": 2.7958, | |
| "step": 333000 | |
| }, | |
| { | |
| "epoch": 17.96, | |
| "learning_rate": 0.00011175778261637146, | |
| "loss": 2.7973, | |
| "step": 334000 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.4098012096996053, | |
| "eval_loss": 3.3934710025787354, | |
| "eval_runtime": 153.7409, | |
| "eval_samples_per_second": 376.731, | |
| "eval_steps_per_second": 5.887, | |
| "step": 334674 | |
| }, | |
| { | |
| "epoch": 18.02, | |
| "learning_rate": 0.0001088183369622786, | |
| "loss": 2.7829, | |
| "step": 335000 | |
| }, | |
| { | |
| "epoch": 18.07, | |
| "learning_rate": 0.00010587889130818574, | |
| "loss": 2.7617, | |
| "step": 336000 | |
| }, | |
| { | |
| "epoch": 18.13, | |
| "learning_rate": 0.00010293650326605072, | |
| "loss": 2.7652, | |
| "step": 337000 | |
| }, | |
| { | |
| "epoch": 18.18, | |
| "learning_rate": 9.999411522391573e-05, | |
| "loss": 2.7735, | |
| "step": 338000 | |
| }, | |
| { | |
| "epoch": 18.23, | |
| "learning_rate": 9.705172718178074e-05, | |
| "loss": 2.7722, | |
| "step": 339000 | |
| }, | |
| { | |
| "epoch": 18.29, | |
| "learning_rate": 9.411228152768788e-05, | |
| "loss": 2.7673, | |
| "step": 340000 | |
| }, | |
| { | |
| "epoch": 18.34, | |
| "learning_rate": 9.116989348555289e-05, | |
| "loss": 2.7696, | |
| "step": 341000 | |
| }, | |
| { | |
| "epoch": 18.39, | |
| "learning_rate": 8.822750544341788e-05, | |
| "loss": 2.7708, | |
| "step": 342000 | |
| }, | |
| { | |
| "epoch": 18.45, | |
| "learning_rate": 8.528805978932502e-05, | |
| "loss": 2.7714, | |
| "step": 343000 | |
| }, | |
| { | |
| "epoch": 18.5, | |
| "learning_rate": 8.234567174719002e-05, | |
| "loss": 2.7757, | |
| "step": 344000 | |
| }, | |
| { | |
| "epoch": 18.56, | |
| "learning_rate": 7.940622609309716e-05, | |
| "loss": 2.7743, | |
| "step": 345000 | |
| }, | |
| { | |
| "epoch": 18.61, | |
| "learning_rate": 7.646383805096215e-05, | |
| "loss": 2.7707, | |
| "step": 346000 | |
| }, | |
| { | |
| "epoch": 18.66, | |
| "learning_rate": 7.35243923968693e-05, | |
| "loss": 2.7734, | |
| "step": 347000 | |
| }, | |
| { | |
| "epoch": 18.72, | |
| "learning_rate": 7.05820043547343e-05, | |
| "loss": 2.7749, | |
| "step": 348000 | |
| }, | |
| { | |
| "epoch": 18.77, | |
| "learning_rate": 6.764255870064144e-05, | |
| "loss": 2.7769, | |
| "step": 349000 | |
| }, | |
| { | |
| "epoch": 18.82, | |
| "learning_rate": 6.470017065850645e-05, | |
| "loss": 2.7797, | |
| "step": 350000 | |
| }, | |
| { | |
| "epoch": 18.88, | |
| "learning_rate": 6.175778261637145e-05, | |
| "loss": 2.7753, | |
| "step": 351000 | |
| }, | |
| { | |
| "epoch": 18.93, | |
| "learning_rate": 5.881833696227858e-05, | |
| "loss": 2.7806, | |
| "step": 352000 | |
| }, | |
| { | |
| "epoch": 18.99, | |
| "learning_rate": 5.587889130818573e-05, | |
| "loss": 2.7732, | |
| "step": 353000 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.4104149744077718, | |
| "eval_loss": 3.3887417316436768, | |
| "eval_runtime": 153.8157, | |
| "eval_samples_per_second": 376.548, | |
| "eval_steps_per_second": 5.884, | |
| "step": 353267 | |
| }, | |
| { | |
| "epoch": 19.04, | |
| "learning_rate": 5.293650326605073e-05, | |
| "loss": 2.7578, | |
| "step": 354000 | |
| }, | |
| { | |
| "epoch": 19.09, | |
| "learning_rate": 4.999411522391573e-05, | |
| "loss": 2.7527, | |
| "step": 355000 | |
| }, | |
| { | |
| "epoch": 19.15, | |
| "learning_rate": 4.7051727181780734e-05, | |
| "loss": 2.7525, | |
| "step": 356000 | |
| }, | |
| { | |
| "epoch": 19.2, | |
| "learning_rate": 4.411228152768787e-05, | |
| "loss": 2.7595, | |
| "step": 357000 | |
| }, | |
| { | |
| "epoch": 19.25, | |
| "learning_rate": 4.1169893485552876e-05, | |
| "loss": 2.7602, | |
| "step": 358000 | |
| }, | |
| { | |
| "epoch": 19.31, | |
| "learning_rate": 3.823044783146001e-05, | |
| "loss": 2.7569, | |
| "step": 359000 | |
| }, | |
| { | |
| "epoch": 19.36, | |
| "learning_rate": 3.528805978932502e-05, | |
| "loss": 2.7605, | |
| "step": 360000 | |
| }, | |
| { | |
| "epoch": 19.42, | |
| "learning_rate": 3.234567174719002e-05, | |
| "loss": 2.758, | |
| "step": 361000 | |
| }, | |
| { | |
| "epoch": 19.47, | |
| "learning_rate": 2.940622609309716e-05, | |
| "loss": 2.7595, | |
| "step": 362000 | |
| }, | |
| { | |
| "epoch": 19.52, | |
| "learning_rate": 2.6463838050962164e-05, | |
| "loss": 2.7584, | |
| "step": 363000 | |
| }, | |
| { | |
| "epoch": 19.58, | |
| "learning_rate": 2.35243923968693e-05, | |
| "loss": 2.7612, | |
| "step": 364000 | |
| }, | |
| { | |
| "epoch": 19.63, | |
| "learning_rate": 2.0584946742776438e-05, | |
| "loss": 2.7626, | |
| "step": 365000 | |
| }, | |
| { | |
| "epoch": 19.68, | |
| "learning_rate": 1.764255870064144e-05, | |
| "loss": 2.7573, | |
| "step": 366000 | |
| }, | |
| { | |
| "epoch": 19.74, | |
| "learning_rate": 1.4700170658506444e-05, | |
| "loss": 2.7586, | |
| "step": 367000 | |
| }, | |
| { | |
| "epoch": 19.79, | |
| "learning_rate": 1.1757782616371448e-05, | |
| "loss": 2.7569, | |
| "step": 368000 | |
| }, | |
| { | |
| "epoch": 19.85, | |
| "learning_rate": 8.815394574236451e-06, | |
| "loss": 2.761, | |
| "step": 369000 | |
| }, | |
| { | |
| "epoch": 19.9, | |
| "learning_rate": 5.8759489201435885e-06, | |
| "loss": 2.7599, | |
| "step": 370000 | |
| }, | |
| { | |
| "epoch": 19.95, | |
| "learning_rate": 2.933560878008592e-06, | |
| "loss": 2.7585, | |
| "step": 371000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.40999993080367236, | |
| "eval_loss": 3.400653839111328, | |
| "eval_runtime": 153.6941, | |
| "eval_samples_per_second": 376.846, | |
| "eval_steps_per_second": 5.888, | |
| "step": 371860 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "step": 371860, | |
| "total_flos": 1.56669402051072e+18, | |
| "train_loss": 3.027651528302192, | |
| "train_runtime": 81113.4919, | |
| "train_samples_per_second": 146.695, | |
| "train_steps_per_second": 4.584 | |
| } | |
| ], | |
| "logging_steps": 1000, | |
| "max_steps": 371860, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 20, | |
| "save_steps": 5000, | |
| "total_flos": 1.56669402051072e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |