| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 69.3769684356573, | |
| "global_step": 500000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 2.9999999999999997e-06, | |
| "loss": 0.4842, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 5.999999999999999e-06, | |
| "loss": 0.4793, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 0.45401322841644287, | |
| "eval_runtime": 1.5264, | |
| "eval_samples_per_second": 121.199, | |
| "eval_steps_per_second": 7.862, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 8.999999999999999e-06, | |
| "loss": 0.4743, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1.1999999999999999e-05, | |
| "loss": 0.4701, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 0.4466768801212311, | |
| "eval_runtime": 1.2467, | |
| "eval_samples_per_second": 148.397, | |
| "eval_steps_per_second": 9.626, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1.4999999999999999e-05, | |
| "loss": 0.4687, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.7999999999999997e-05, | |
| "loss": 0.4673, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 0.4303785264492035, | |
| "eval_runtime": 1.4639, | |
| "eval_samples_per_second": 126.371, | |
| "eval_steps_per_second": 8.197, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 2.1e-05, | |
| "loss": 0.4669, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 2.3999999999999997e-05, | |
| "loss": 0.4669, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 0.44127601385116577, | |
| "eval_runtime": 1.4871, | |
| "eval_samples_per_second": 124.403, | |
| "eval_steps_per_second": 8.069, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 2.6999999999999996e-05, | |
| "loss": 0.4663, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 0.4668, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 0.4368070960044861, | |
| "eval_runtime": 1.5671, | |
| "eval_samples_per_second": 118.051, | |
| "eval_steps_per_second": 7.657, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 3.2999999999999996e-05, | |
| "loss": 0.467, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 3.5999999999999994e-05, | |
| "loss": 0.4676, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_loss": 0.4358096420764923, | |
| "eval_runtime": 1.613, | |
| "eval_samples_per_second": 114.696, | |
| "eval_steps_per_second": 7.44, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.9e-05, | |
| "loss": 0.4683, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 4.2e-05, | |
| "loss": 0.4691, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_loss": 0.43669232726097107, | |
| "eval_runtime": 1.3117, | |
| "eval_samples_per_second": 141.037, | |
| "eval_steps_per_second": 9.148, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 4.4999999999999996e-05, | |
| "loss": 0.4697, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 4.7999999999999994e-05, | |
| "loss": 0.4693, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "eval_loss": 0.4429354965686798, | |
| "eval_runtime": 1.2244, | |
| "eval_samples_per_second": 151.099, | |
| "eval_steps_per_second": 9.801, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 5.1e-05, | |
| "loss": 0.4703, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 5.399999999999999e-05, | |
| "loss": 0.4709, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_loss": 0.43878915905952454, | |
| "eval_runtime": 1.2254, | |
| "eval_samples_per_second": 150.966, | |
| "eval_steps_per_second": 9.792, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 5.6999999999999996e-05, | |
| "loss": 0.4711, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 5.9981999999999996e-05, | |
| "loss": 0.4722, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "eval_loss": 0.44534820318222046, | |
| "eval_runtime": 1.1709, | |
| "eval_samples_per_second": 157.999, | |
| "eval_steps_per_second": 10.249, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 6.298199999999999e-05, | |
| "loss": 0.4713, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 6.598199999999999e-05, | |
| "loss": 0.4729, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "eval_loss": 0.4415363073348999, | |
| "eval_runtime": 1.2422, | |
| "eval_samples_per_second": 148.934, | |
| "eval_steps_per_second": 9.661, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 6.8982e-05, | |
| "loss": 0.4733, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 7.198199999999999e-05, | |
| "loss": 0.4732, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "eval_loss": 0.4510314166545868, | |
| "eval_runtime": 1.3224, | |
| "eval_samples_per_second": 139.898, | |
| "eval_steps_per_second": 9.074, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 7.4982e-05, | |
| "loss": 0.4748, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 7.7982e-05, | |
| "loss": 0.4751, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "eval_loss": 0.44608551263809204, | |
| "eval_runtime": 1.3056, | |
| "eval_samples_per_second": 141.703, | |
| "eval_steps_per_second": 9.192, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 8.098199999999999e-05, | |
| "loss": 0.4755, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 8.3982e-05, | |
| "loss": 0.4765, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "eval_loss": 0.4448258578777313, | |
| "eval_runtime": 1.3312, | |
| "eval_samples_per_second": 138.973, | |
| "eval_steps_per_second": 9.014, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 8.698199999999999e-05, | |
| "loss": 0.4771, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 8.9982e-05, | |
| "loss": 0.477, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "eval_loss": 0.4497504234313965, | |
| "eval_runtime": 1.4193, | |
| "eval_samples_per_second": 130.344, | |
| "eval_steps_per_second": 8.455, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 9.298199999999998e-05, | |
| "loss": 0.4776, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 9.598199999999999e-05, | |
| "loss": 0.4779, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "eval_loss": 0.4446822702884674, | |
| "eval_runtime": 1.2963, | |
| "eval_samples_per_second": 142.717, | |
| "eval_steps_per_second": 9.257, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 9.8982e-05, | |
| "loss": 0.4796, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 0.00010197599999999999, | |
| "loss": 0.4795, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "eval_loss": 0.44301700592041016, | |
| "eval_runtime": 1.2604, | |
| "eval_samples_per_second": 146.78, | |
| "eval_steps_per_second": 9.521, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 0.00010496999999999999, | |
| "loss": 0.4804, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 0.00010796999999999998, | |
| "loss": 0.481, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "eval_loss": 0.4499399662017822, | |
| "eval_runtime": 1.2921, | |
| "eval_samples_per_second": 143.181, | |
| "eval_steps_per_second": 9.287, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 0.00011096999999999999, | |
| "loss": 0.4814, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 0.00011397, | |
| "loss": 0.4821, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "eval_loss": 0.4550692141056061, | |
| "eval_runtime": 1.2086, | |
| "eval_samples_per_second": 153.074, | |
| "eval_steps_per_second": 9.929, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 0.00011697, | |
| "loss": 0.483, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 0.00011996999999999998, | |
| "loss": 0.4829, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "eval_loss": 0.4518587291240692, | |
| "eval_runtime": 1.2357, | |
| "eval_samples_per_second": 149.708, | |
| "eval_steps_per_second": 9.711, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 0.00012297, | |
| "loss": 0.4838, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 0.00012597, | |
| "loss": 0.4838, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "eval_loss": 0.45201268792152405, | |
| "eval_runtime": 1.2706, | |
| "eval_samples_per_second": 145.603, | |
| "eval_steps_per_second": 9.444, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 0.00012896999999999998, | |
| "loss": 0.4846, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 0.00013197, | |
| "loss": 0.4856, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "eval_loss": 0.46331045031547546, | |
| "eval_runtime": 1.4645, | |
| "eval_samples_per_second": 126.326, | |
| "eval_steps_per_second": 8.194, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 0.000134958, | |
| "loss": 0.4848, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 0.00013795799999999998, | |
| "loss": 0.4857, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "eval_loss": 0.45755112171173096, | |
| "eval_runtime": 1.2529, | |
| "eval_samples_per_second": 147.652, | |
| "eval_steps_per_second": 9.577, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 0.00014095799999999997, | |
| "loss": 0.4867, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 0.000143958, | |
| "loss": 0.4869, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "eval_loss": 0.44849660992622375, | |
| "eval_runtime": 1.3684, | |
| "eval_samples_per_second": 135.198, | |
| "eval_steps_per_second": 8.77, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 0.00014695799999999998, | |
| "loss": 0.4874, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 0.000149958, | |
| "loss": 0.4882, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "eval_loss": 0.4590979516506195, | |
| "eval_runtime": 1.3063, | |
| "eval_samples_per_second": 141.622, | |
| "eval_steps_per_second": 9.186, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 0.0001499996278877012, | |
| "loss": 0.4888, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 0.00014999849034570668, | |
| "loss": 0.4883, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "eval_loss": 0.4644538164138794, | |
| "eval_runtime": 1.393, | |
| "eval_samples_per_second": 132.808, | |
| "eval_steps_per_second": 8.615, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 0.00014999658731143647, | |
| "loss": 0.4892, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 0.00014999392490663588, | |
| "loss": 0.4889, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "eval_loss": 0.456952303647995, | |
| "eval_runtime": 1.2777, | |
| "eval_samples_per_second": 144.79, | |
| "eval_steps_per_second": 9.392, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 0.00014999052298598836, | |
| "loss": 0.4912, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "learning_rate": 0.0001499863312870767, | |
| "loss": 0.4884, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "eval_loss": 0.4571981132030487, | |
| "eval_runtime": 1.4323, | |
| "eval_samples_per_second": 129.165, | |
| "eval_steps_per_second": 8.378, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "learning_rate": 0.0001499813742288589, | |
| "loss": 0.4887, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 0.00014997565186554453, | |
| "loss": 0.4897, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "eval_loss": 0.4552990198135376, | |
| "eval_runtime": 1.4111, | |
| "eval_samples_per_second": 131.102, | |
| "eval_steps_per_second": 8.504, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 0.00014996916425971245, | |
| "loss": 0.4882, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 0.0001499619114823101, | |
| "loss": 0.4883, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "eval_loss": 0.453418105840683, | |
| "eval_runtime": 1.3895, | |
| "eval_samples_per_second": 133.14, | |
| "eval_steps_per_second": 8.636, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "learning_rate": 0.00014995389361265266, | |
| "loss": 0.4889, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 0.00014994511073842227, | |
| "loss": 0.4881, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "eval_loss": 0.45868200063705444, | |
| "eval_runtime": 1.3438, | |
| "eval_samples_per_second": 137.672, | |
| "eval_steps_per_second": 8.93, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "learning_rate": 0.00014993556295566702, | |
| "loss": 0.4887, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 0.0001499252503688, | |
| "loss": 0.4889, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "eval_loss": 0.4631924331188202, | |
| "eval_runtime": 1.339, | |
| "eval_samples_per_second": 138.166, | |
| "eval_steps_per_second": 8.962, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "learning_rate": 0.00014991417309059794, | |
| "loss": 0.4885, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 0.0001499023312422002, | |
| "loss": 0.4886, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "eval_loss": 0.45870065689086914, | |
| "eval_runtime": 1.3071, | |
| "eval_samples_per_second": 141.531, | |
| "eval_steps_per_second": 9.18, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "learning_rate": 0.00014988972495310734, | |
| "loss": 0.4888, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "learning_rate": 0.0001498763543611797, | |
| "loss": 0.4883, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "eval_loss": 0.46206343173980713, | |
| "eval_runtime": 1.3419, | |
| "eval_samples_per_second": 137.861, | |
| "eval_steps_per_second": 8.942, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "learning_rate": 0.00014986221961263597, | |
| "loss": 0.4884, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "learning_rate": 0.00014984732086205146, | |
| "loss": 0.4876, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "eval_loss": 0.452243447303772, | |
| "eval_runtime": 1.311, | |
| "eval_samples_per_second": 141.113, | |
| "eval_steps_per_second": 9.153, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 4.93, | |
| "learning_rate": 0.00014983165827235656, | |
| "loss": 0.4879, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.00014981523201483478, | |
| "loss": 0.4878, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.45599275827407837, | |
| "eval_runtime": 1.3198, | |
| "eval_samples_per_second": 140.175, | |
| "eval_steps_per_second": 9.092, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 5.06, | |
| "learning_rate": 0.0001497980422691211, | |
| "loss": 0.4879, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 5.13, | |
| "learning_rate": 0.00014978008922319978, | |
| "loss": 0.4883, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 5.13, | |
| "eval_loss": 0.45790329575538635, | |
| "eval_runtime": 1.2841, | |
| "eval_samples_per_second": 144.071, | |
| "eval_steps_per_second": 9.345, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 5.2, | |
| "learning_rate": 0.00014976137307340248, | |
| "loss": 0.4875, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "learning_rate": 0.0001497419337437372, | |
| "loss": 0.4882, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "eval_loss": 0.4554036259651184, | |
| "eval_runtime": 1.4061, | |
| "eval_samples_per_second": 131.565, | |
| "eval_steps_per_second": 8.534, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 5.34, | |
| "learning_rate": 0.00014972169353371555, | |
| "loss": 0.4882, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 5.41, | |
| "learning_rate": 0.0001497006908584238, | |
| "loss": 0.4883, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 5.41, | |
| "eval_loss": 0.4587613046169281, | |
| "eval_runtime": 1.383, | |
| "eval_samples_per_second": 133.763, | |
| "eval_steps_per_second": 8.677, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 5.48, | |
| "learning_rate": 0.00014967892594754389, | |
| "loss": 0.4877, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 5.55, | |
| "learning_rate": 0.00014965639903909335, | |
| "loss": 0.4872, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 5.55, | |
| "eval_loss": 0.4561161398887634, | |
| "eval_runtime": 1.2745, | |
| "eval_samples_per_second": 145.151, | |
| "eval_steps_per_second": 9.415, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 5.62, | |
| "learning_rate": 0.00014963329971066358, | |
| "loss": 0.4911, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 5.69, | |
| "learning_rate": 0.00014960925564539397, | |
| "loss": 0.4868, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 5.69, | |
| "eval_loss": 0.46137019991874695, | |
| "eval_runtime": 1.4076, | |
| "eval_samples_per_second": 131.433, | |
| "eval_steps_per_second": 8.525, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 5.76, | |
| "learning_rate": 0.000149584450344457, | |
| "loss": 0.4873, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 5.83, | |
| "learning_rate": 0.00014955888407911953, | |
| "loss": 0.4875, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 5.83, | |
| "eval_loss": 0.4583793580532074, | |
| "eval_runtime": 1.1996, | |
| "eval_samples_per_second": 154.218, | |
| "eval_steps_per_second": 10.003, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 5.9, | |
| "learning_rate": 0.00014953255712897006, | |
| "loss": 0.4872, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 5.97, | |
| "learning_rate": 0.00014950546978191592, | |
| "loss": 0.4868, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 5.97, | |
| "eval_loss": 0.46193328499794006, | |
| "eval_runtime": 1.2487, | |
| "eval_samples_per_second": 148.152, | |
| "eval_steps_per_second": 9.61, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "learning_rate": 0.00014947762233418003, | |
| "loss": 0.4882, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 6.11, | |
| "learning_rate": 0.00014944901509029757, | |
| "loss": 0.4874, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 6.11, | |
| "eval_loss": 0.4519434869289398, | |
| "eval_runtime": 1.2829, | |
| "eval_samples_per_second": 144.21, | |
| "eval_steps_per_second": 9.354, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 6.17, | |
| "learning_rate": 0.0001494196483631128, | |
| "loss": 0.4874, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 6.24, | |
| "learning_rate": 0.00014938952247377555, | |
| "loss": 0.4874, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 6.24, | |
| "eval_loss": 0.4625035524368286, | |
| "eval_runtime": 1.3409, | |
| "eval_samples_per_second": 137.972, | |
| "eval_steps_per_second": 8.95, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 6.31, | |
| "learning_rate": 0.00014935863775173772, | |
| "loss": 0.487, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 6.38, | |
| "learning_rate": 0.00014932699453474967, | |
| "loss": 0.487, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 6.38, | |
| "eval_loss": 0.45792409777641296, | |
| "eval_runtime": 1.3874, | |
| "eval_samples_per_second": 133.339, | |
| "eval_steps_per_second": 8.649, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 6.45, | |
| "learning_rate": 0.00014929459316885652, | |
| "loss": 0.4872, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 6.52, | |
| "learning_rate": 0.0001492614340083945, | |
| "loss": 0.4872, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 6.52, | |
| "eval_loss": 0.4534100592136383, | |
| "eval_runtime": 1.3917, | |
| "eval_samples_per_second": 132.927, | |
| "eval_steps_per_second": 8.622, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 6.59, | |
| "learning_rate": 0.00014922751741598678, | |
| "loss": 0.4868, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 6.66, | |
| "learning_rate": 0.00014919284376253988, | |
| "loss": 0.4872, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 6.66, | |
| "eval_loss": 0.45163026452064514, | |
| "eval_runtime": 1.3427, | |
| "eval_samples_per_second": 137.777, | |
| "eval_steps_per_second": 8.937, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 6.73, | |
| "learning_rate": 0.00014915741342723924, | |
| "loss": 0.4864, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 6.8, | |
| "learning_rate": 0.00014912122679754534, | |
| "loss": 0.4865, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 6.8, | |
| "eval_loss": 0.4634714126586914, | |
| "eval_runtime": 1.339, | |
| "eval_samples_per_second": 138.163, | |
| "eval_steps_per_second": 8.962, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 6.87, | |
| "learning_rate": 0.0001490842842691894, | |
| "loss": 0.4866, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 6.94, | |
| "learning_rate": 0.00014904658624616897, | |
| "loss": 0.4865, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 6.94, | |
| "eval_loss": 0.4610464572906494, | |
| "eval_runtime": 1.3562, | |
| "eval_samples_per_second": 136.406, | |
| "eval_steps_per_second": 8.848, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 0.00014900821080024855, | |
| "loss": 0.4869, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 7.08, | |
| "learning_rate": 0.00014896900454183386, | |
| "loss": 0.4863, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 7.08, | |
| "eval_loss": 0.45153000950813293, | |
| "eval_runtime": 1.3758, | |
| "eval_samples_per_second": 134.464, | |
| "eval_steps_per_second": 8.722, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 7.15, | |
| "learning_rate": 0.00014892904404943528, | |
| "loss": 0.4864, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 7.22, | |
| "learning_rate": 0.00014888832976005437, | |
| "loss": 0.4861, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 7.22, | |
| "eval_loss": 0.45839324593544006, | |
| "eval_runtime": 1.3527, | |
| "eval_samples_per_second": 136.761, | |
| "eval_steps_per_second": 8.871, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 7.28, | |
| "learning_rate": 0.00014884694580576338, | |
| "loss": 0.4857, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 7.35, | |
| "learning_rate": 0.00014880472677172968, | |
| "loss": 0.4866, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 7.35, | |
| "eval_loss": 0.4540667235851288, | |
| "eval_runtime": 1.4425, | |
| "eval_samples_per_second": 128.253, | |
| "eval_steps_per_second": 8.319, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 7.42, | |
| "learning_rate": 0.00014876175530022752, | |
| "loss": 0.4862, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 7.49, | |
| "learning_rate": 0.000148718031861186, | |
| "loss": 0.4862, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 7.49, | |
| "eval_loss": 0.45079880952835083, | |
| "eval_runtime": 1.426, | |
| "eval_samples_per_second": 129.729, | |
| "eval_steps_per_second": 8.415, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 7.56, | |
| "learning_rate": 0.00014867400540032418, | |
| "loss": 0.4945, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 7.63, | |
| "learning_rate": 0.00014862878697647535, | |
| "loss": 0.4863, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 7.63, | |
| "eval_loss": 0.45646485686302185, | |
| "eval_runtime": 1.2918, | |
| "eval_samples_per_second": 143.21, | |
| "eval_steps_per_second": 9.289, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 7.7, | |
| "learning_rate": 0.00014858281803920744, | |
| "loss": 0.4853, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 7.77, | |
| "learning_rate": 0.0001485360990912294, | |
| "loss": 0.486, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 7.77, | |
| "eval_loss": 0.4665206968784332, | |
| "eval_runtime": 1.3746, | |
| "eval_samples_per_second": 134.585, | |
| "eval_steps_per_second": 8.73, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 7.84, | |
| "learning_rate": 0.00014848863064345212, | |
| "loss": 0.486, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 7.91, | |
| "learning_rate": 0.000148440413214983, | |
| "loss": 0.486, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 7.91, | |
| "eval_loss": 0.45648473501205444, | |
| "eval_runtime": 1.418, | |
| "eval_samples_per_second": 130.464, | |
| "eval_steps_per_second": 8.463, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 7.98, | |
| "learning_rate": 0.00014839144733312009, | |
| "loss": 0.4852, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 8.05, | |
| "learning_rate": 0.0001483417335333464, | |
| "loss": 0.4861, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 8.05, | |
| "eval_loss": 0.4579944908618927, | |
| "eval_runtime": 1.4339, | |
| "eval_samples_per_second": 129.019, | |
| "eval_steps_per_second": 8.369, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 8.12, | |
| "learning_rate": 0.0001482912723593241, | |
| "loss": 0.4852, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 8.19, | |
| "learning_rate": 0.00014824006436288853, | |
| "loss": 0.4852, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 8.19, | |
| "eval_loss": 0.45960545539855957, | |
| "eval_runtime": 1.4194, | |
| "eval_samples_per_second": 130.337, | |
| "eval_steps_per_second": 8.454, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 8.26, | |
| "learning_rate": 0.00014818811010404212, | |
| "loss": 0.4849, | |
| "step": 59500 | |
| }, | |
| { | |
| "epoch": 8.33, | |
| "learning_rate": 0.00014813541015094828, | |
| "loss": 0.4846, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 8.33, | |
| "eval_loss": 0.45274996757507324, | |
| "eval_runtime": 1.438, | |
| "eval_samples_per_second": 128.654, | |
| "eval_steps_per_second": 8.345, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 8.39, | |
| "learning_rate": 0.0001480819650799253, | |
| "loss": 0.4854, | |
| "step": 60500 | |
| }, | |
| { | |
| "epoch": 8.46, | |
| "learning_rate": 0.0001480277754754399, | |
| "loss": 0.4848, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 8.46, | |
| "eval_loss": 0.4504894018173218, | |
| "eval_runtime": 1.4132, | |
| "eval_samples_per_second": 130.905, | |
| "eval_steps_per_second": 8.491, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 8.53, | |
| "learning_rate": 0.00014797284193010093, | |
| "loss": 0.4849, | |
| "step": 61500 | |
| }, | |
| { | |
| "epoch": 8.6, | |
| "learning_rate": 0.00014791716504465282, | |
| "loss": 0.4849, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 8.6, | |
| "eval_loss": 0.4406717121601105, | |
| "eval_runtime": 1.3298, | |
| "eval_samples_per_second": 139.116, | |
| "eval_steps_per_second": 9.024, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 8.67, | |
| "learning_rate": 0.00014786074542796906, | |
| "loss": 0.4847, | |
| "step": 62500 | |
| }, | |
| { | |
| "epoch": 8.74, | |
| "learning_rate": 0.00014780358369704557, | |
| "loss": 0.4851, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 8.74, | |
| "eval_loss": 0.4578949809074402, | |
| "eval_runtime": 1.2912, | |
| "eval_samples_per_second": 143.275, | |
| "eval_steps_per_second": 9.294, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 8.81, | |
| "learning_rate": 0.00014774568047699386, | |
| "loss": 0.4844, | |
| "step": 63500 | |
| }, | |
| { | |
| "epoch": 8.88, | |
| "learning_rate": 0.00014768703640103426, | |
| "loss": 0.4848, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 8.88, | |
| "eval_loss": 0.4559178650379181, | |
| "eval_runtime": 1.4061, | |
| "eval_samples_per_second": 131.569, | |
| "eval_steps_per_second": 8.534, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 8.95, | |
| "learning_rate": 0.000147627652110489, | |
| "loss": 0.4848, | |
| "step": 64500 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "learning_rate": 0.00014756752825477516, | |
| "loss": 0.4851, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "eval_loss": 0.45050284266471863, | |
| "eval_runtime": 1.4888, | |
| "eval_samples_per_second": 124.265, | |
| "eval_steps_per_second": 8.06, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 9.09, | |
| "learning_rate": 0.00014750666549139763, | |
| "loss": 0.4852, | |
| "step": 65500 | |
| }, | |
| { | |
| "epoch": 9.16, | |
| "learning_rate": 0.0001474454362920812, | |
| "loss": 0.4846, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 9.16, | |
| "eval_loss": 0.4615005850791931, | |
| "eval_runtime": 1.3552, | |
| "eval_samples_per_second": 136.507, | |
| "eval_steps_per_second": 8.854, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 9.23, | |
| "learning_rate": 0.00014738310214159147, | |
| "loss": 0.4851, | |
| "step": 66500 | |
| }, | |
| { | |
| "epoch": 9.3, | |
| "learning_rate": 0.00014732003110029247, | |
| "loss": 0.4842, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 9.3, | |
| "eval_loss": 0.4617568850517273, | |
| "eval_runtime": 1.4135, | |
| "eval_samples_per_second": 130.884, | |
| "eval_steps_per_second": 8.49, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 9.37, | |
| "learning_rate": 0.00014725622385791898, | |
| "loss": 0.484, | |
| "step": 67500 | |
| }, | |
| { | |
| "epoch": 9.44, | |
| "learning_rate": 0.00014719168111225673, | |
| "loss": 0.484, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 9.44, | |
| "eval_loss": 0.4558795690536499, | |
| "eval_runtime": 1.3419, | |
| "eval_samples_per_second": 137.865, | |
| "eval_steps_per_second": 8.943, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 9.5, | |
| "learning_rate": 0.00014712640356913495, | |
| "loss": 0.484, | |
| "step": 68500 | |
| }, | |
| { | |
| "epoch": 9.57, | |
| "learning_rate": 0.00014706039194241832, | |
| "loss": 0.4841, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 9.57, | |
| "eval_loss": 0.46133604645729065, | |
| "eval_runtime": 1.3387, | |
| "eval_samples_per_second": 138.192, | |
| "eval_steps_per_second": 8.964, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 9.64, | |
| "learning_rate": 0.0001469936469539994, | |
| "loss": 0.4837, | |
| "step": 69500 | |
| }, | |
| { | |
| "epoch": 9.71, | |
| "learning_rate": 0.00014692616933379077, | |
| "loss": 0.484, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 9.71, | |
| "eval_loss": 0.4527389109134674, | |
| "eval_runtime": 1.3393, | |
| "eval_samples_per_second": 138.131, | |
| "eval_steps_per_second": 8.96, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 9.78, | |
| "learning_rate": 0.0001468579598197168, | |
| "loss": 0.484, | |
| "step": 70500 | |
| }, | |
| { | |
| "epoch": 9.85, | |
| "learning_rate": 0.00014678901915770584, | |
| "loss": 0.4842, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 9.85, | |
| "eval_loss": 0.4482715427875519, | |
| "eval_runtime": 1.2999, | |
| "eval_samples_per_second": 142.321, | |
| "eval_steps_per_second": 9.232, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 9.92, | |
| "learning_rate": 0.00014671934810168194, | |
| "loss": 0.4843, | |
| "step": 71500 | |
| }, | |
| { | |
| "epoch": 9.99, | |
| "learning_rate": 0.00014664894741355652, | |
| "loss": 0.4842, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 9.99, | |
| "eval_loss": 0.45848214626312256, | |
| "eval_runtime": 1.4072, | |
| "eval_samples_per_second": 131.462, | |
| "eval_steps_per_second": 8.527, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 10.06, | |
| "learning_rate": 0.00014657781786322035, | |
| "loss": 0.4836, | |
| "step": 72500 | |
| }, | |
| { | |
| "epoch": 10.13, | |
| "learning_rate": 0.00014650596022853471, | |
| "loss": 0.4837, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 10.13, | |
| "eval_loss": 0.45845624804496765, | |
| "eval_runtime": 1.3792, | |
| "eval_samples_per_second": 134.135, | |
| "eval_steps_per_second": 8.701, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 10.2, | |
| "learning_rate": 0.00014643337529532323, | |
| "loss": 0.4838, | |
| "step": 73500 | |
| }, | |
| { | |
| "epoch": 10.27, | |
| "learning_rate": 0.00014636021120475917, | |
| "loss": 0.4833, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 10.27, | |
| "eval_loss": 0.4540862739086151, | |
| "eval_runtime": 1.2824, | |
| "eval_samples_per_second": 144.264, | |
| "eval_steps_per_second": 9.358, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 10.34, | |
| "learning_rate": 0.00014628617551437316, | |
| "loss": 0.4836, | |
| "step": 74500 | |
| }, | |
| { | |
| "epoch": 10.41, | |
| "learning_rate": 0.0001462114149289917, | |
| "loss": 0.4836, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 10.41, | |
| "eval_loss": 0.45281586050987244, | |
| "eval_runtime": 1.381, | |
| "eval_samples_per_second": 133.963, | |
| "eval_steps_per_second": 8.69, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 10.48, | |
| "learning_rate": 0.00014613593026618457, | |
| "loss": 0.4834, | |
| "step": 75500 | |
| }, | |
| { | |
| "epoch": 10.55, | |
| "learning_rate": 0.00014605972235143998, | |
| "loss": 0.4832, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 10.55, | |
| "eval_loss": 0.44752052426338196, | |
| "eval_runtime": 1.2887, | |
| "eval_samples_per_second": 143.559, | |
| "eval_steps_per_second": 9.312, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 10.61, | |
| "learning_rate": 0.00014598356489470423, | |
| "loss": 0.4841, | |
| "step": 76500 | |
| }, | |
| { | |
| "epoch": 10.68, | |
| "learning_rate": 0.00014590592019575967, | |
| "loss": 0.4836, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 10.68, | |
| "eval_loss": 0.4524598717689514, | |
| "eval_runtime": 1.395, | |
| "eval_samples_per_second": 132.618, | |
| "eval_steps_per_second": 8.602, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 10.75, | |
| "learning_rate": 0.00014582755476023087, | |
| "loss": 0.4838, | |
| "step": 77500 | |
| }, | |
| { | |
| "epoch": 10.82, | |
| "learning_rate": 0.00014574846944510973, | |
| "loss": 0.4826, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 10.82, | |
| "eval_loss": 0.4561995565891266, | |
| "eval_runtime": 1.2744, | |
| "eval_samples_per_second": 145.166, | |
| "eval_steps_per_second": 9.416, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 10.89, | |
| "learning_rate": 0.00014566866511526059, | |
| "loss": 0.483, | |
| "step": 78500 | |
| }, | |
| { | |
| "epoch": 10.96, | |
| "learning_rate": 0.00014558814264341083, | |
| "loss": 0.4824, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 10.96, | |
| "eval_loss": 0.4501703679561615, | |
| "eval_runtime": 1.361, | |
| "eval_samples_per_second": 135.932, | |
| "eval_steps_per_second": 8.817, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 11.03, | |
| "learning_rate": 0.0001455069029101412, | |
| "loss": 0.4832, | |
| "step": 79500 | |
| }, | |
| { | |
| "epoch": 11.1, | |
| "learning_rate": 0.00014542494680387652, | |
| "loss": 0.4828, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 11.1, | |
| "eval_loss": 0.4528810381889343, | |
| "eval_runtime": 1.3979, | |
| "eval_samples_per_second": 132.344, | |
| "eval_steps_per_second": 8.585, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 11.17, | |
| "learning_rate": 0.0001453422752208756, | |
| "loss": 0.4829, | |
| "step": 80500 | |
| }, | |
| { | |
| "epoch": 11.24, | |
| "learning_rate": 0.00014525888906522161, | |
| "loss": 0.4829, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 11.24, | |
| "eval_loss": 0.452385812997818, | |
| "eval_runtime": 1.3808, | |
| "eval_samples_per_second": 133.981, | |
| "eval_steps_per_second": 8.691, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 11.31, | |
| "learning_rate": 0.00014517478924881222, | |
| "loss": 0.4826, | |
| "step": 81500 | |
| }, | |
| { | |
| "epoch": 11.38, | |
| "learning_rate": 0.00014508997669134948, | |
| "loss": 0.4823, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 11.38, | |
| "eval_loss": 0.4506407380104065, | |
| "eval_runtime": 1.3541, | |
| "eval_samples_per_second": 136.62, | |
| "eval_steps_per_second": 8.862, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 11.45, | |
| "learning_rate": 0.00014500445232033005, | |
| "loss": 0.4827, | |
| "step": 82500 | |
| }, | |
| { | |
| "epoch": 11.52, | |
| "learning_rate": 0.0001449183902503642, | |
| "loss": 0.4827, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 11.52, | |
| "eval_loss": 0.4510784149169922, | |
| "eval_runtime": 1.3772, | |
| "eval_samples_per_second": 134.329, | |
| "eval_steps_per_second": 8.713, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 11.59, | |
| "learning_rate": 0.00014483144648477184, | |
| "loss": 0.4826, | |
| "step": 83500 | |
| }, | |
| { | |
| "epoch": 11.66, | |
| "learning_rate": 0.00014474379373286762, | |
| "loss": 0.4823, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 11.66, | |
| "eval_loss": 0.45063039660453796, | |
| "eval_runtime": 1.308, | |
| "eval_samples_per_second": 141.432, | |
| "eval_steps_per_second": 9.174, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 11.72, | |
| "learning_rate": 0.00014465543295320805, | |
| "loss": 0.482, | |
| "step": 84500 | |
| }, | |
| { | |
| "epoch": 11.79, | |
| "learning_rate": 0.00014456636511209239, | |
| "loss": 0.4827, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 11.79, | |
| "eval_loss": 0.45612767338752747, | |
| "eval_runtime": 1.4022, | |
| "eval_samples_per_second": 131.931, | |
| "eval_steps_per_second": 8.558, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 11.86, | |
| "learning_rate": 0.0001444765911835523, | |
| "loss": 0.4819, | |
| "step": 85500 | |
| }, | |
| { | |
| "epoch": 11.93, | |
| "learning_rate": 0.0001443861121493411, | |
| "loss": 0.4832, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 11.93, | |
| "eval_loss": 0.4471343159675598, | |
| "eval_runtime": 1.4636, | |
| "eval_samples_per_second": 126.398, | |
| "eval_steps_per_second": 8.199, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 0.000144294928998923, | |
| "loss": 0.4828, | |
| "step": 86500 | |
| }, | |
| { | |
| "epoch": 12.07, | |
| "learning_rate": 0.00014420304272946233, | |
| "loss": 0.482, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 12.07, | |
| "eval_loss": 0.447856605052948, | |
| "eval_runtime": 1.3062, | |
| "eval_samples_per_second": 141.638, | |
| "eval_steps_per_second": 9.187, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 12.14, | |
| "learning_rate": 0.0001441104543458126, | |
| "loss": 0.4819, | |
| "step": 87500 | |
| }, | |
| { | |
| "epoch": 12.21, | |
| "learning_rate": 0.0001440173521384988, | |
| "loss": 0.4819, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 12.21, | |
| "eval_loss": 0.4560653567314148, | |
| "eval_runtime": 1.2789, | |
| "eval_samples_per_second": 144.65, | |
| "eval_steps_per_second": 9.383, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 12.28, | |
| "learning_rate": 0.00014392336397087298, | |
| "loss": 0.482, | |
| "step": 88500 | |
| }, | |
| { | |
| "epoch": 12.35, | |
| "learning_rate": 0.00014382867674758018, | |
| "loss": 0.4816, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 12.35, | |
| "eval_loss": 0.45898643136024475, | |
| "eval_runtime": 1.4452, | |
| "eval_samples_per_second": 128.01, | |
| "eval_steps_per_second": 8.303, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 12.42, | |
| "learning_rate": 0.00014373367443415487, | |
| "loss": 0.4822, | |
| "step": 89500 | |
| }, | |
| { | |
| "epoch": 12.49, | |
| "learning_rate": 0.0001436375949994348, | |
| "loss": 0.4818, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 12.49, | |
| "eval_loss": 0.4468829035758972, | |
| "eval_runtime": 1.4183, | |
| "eval_samples_per_second": 130.434, | |
| "eval_steps_per_second": 8.461, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 12.56, | |
| "learning_rate": 0.00014354081963417143, | |
| "loss": 0.4817, | |
| "step": 90500 | |
| }, | |
| { | |
| "epoch": 12.63, | |
| "learning_rate": 0.0001434433493966847, | |
| "loss": 0.4815, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 12.63, | |
| "eval_loss": 0.46334829926490784, | |
| "eval_runtime": 1.3078, | |
| "eval_samples_per_second": 141.454, | |
| "eval_steps_per_second": 9.175, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 12.7, | |
| "learning_rate": 0.00014334518535289345, | |
| "loss": 0.4817, | |
| "step": 91500 | |
| }, | |
| { | |
| "epoch": 12.77, | |
| "learning_rate": 0.00014324632857630403, | |
| "loss": 0.4822, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 12.77, | |
| "eval_loss": 0.4566173553466797, | |
| "eval_runtime": 1.4054, | |
| "eval_samples_per_second": 131.633, | |
| "eval_steps_per_second": 8.538, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 12.83, | |
| "learning_rate": 0.0001431467801479982, | |
| "loss": 0.4817, | |
| "step": 92500 | |
| }, | |
| { | |
| "epoch": 12.9, | |
| "learning_rate": 0.0001430465411566217, | |
| "loss": 0.4816, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 12.9, | |
| "eval_loss": 0.4547722339630127, | |
| "eval_runtime": 1.4224, | |
| "eval_samples_per_second": 130.065, | |
| "eval_steps_per_second": 8.437, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 12.97, | |
| "learning_rate": 0.00014294561269837208, | |
| "loss": 0.4819, | |
| "step": 93500 | |
| }, | |
| { | |
| "epoch": 13.04, | |
| "learning_rate": 0.00014284399587698678, | |
| "loss": 0.4824, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 13.04, | |
| "eval_loss": 0.45478177070617676, | |
| "eval_runtime": 1.3566, | |
| "eval_samples_per_second": 136.367, | |
| "eval_steps_per_second": 8.845, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 13.11, | |
| "learning_rate": 0.00014274251296038978, | |
| "loss": 0.4857, | |
| "step": 94500 | |
| }, | |
| { | |
| "epoch": 13.18, | |
| "learning_rate": 0.0001426395282386502, | |
| "loss": 0.4812, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 13.18, | |
| "eval_loss": 0.4533080756664276, | |
| "eval_runtime": 1.4018, | |
| "eval_samples_per_second": 131.972, | |
| "eval_steps_per_second": 8.56, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 13.25, | |
| "learning_rate": 0.00014253585850106554, | |
| "loss": 0.4808, | |
| "step": 95500 | |
| }, | |
| { | |
| "epoch": 13.32, | |
| "learning_rate": 0.00014243150488135145, | |
| "loss": 0.4809, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 13.32, | |
| "eval_loss": 0.45463913679122925, | |
| "eval_runtime": 1.2723, | |
| "eval_samples_per_second": 145.405, | |
| "eval_steps_per_second": 9.432, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 13.39, | |
| "learning_rate": 0.0001423264685207024, | |
| "loss": 0.4816, | |
| "step": 96500 | |
| }, | |
| { | |
| "epoch": 13.46, | |
| "learning_rate": 0.00014222075056777916, | |
| "loss": 0.481, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 13.46, | |
| "eval_loss": 0.4589781165122986, | |
| "eval_runtime": 1.4685, | |
| "eval_samples_per_second": 125.98, | |
| "eval_steps_per_second": 8.172, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 13.53, | |
| "learning_rate": 0.00014211435217869638, | |
| "loss": 0.4812, | |
| "step": 97500 | |
| }, | |
| { | |
| "epoch": 13.6, | |
| "learning_rate": 0.00014200727451700978, | |
| "loss": 0.4807, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 13.6, | |
| "eval_loss": 0.44650688767433167, | |
| "eval_runtime": 1.2669, | |
| "eval_samples_per_second": 146.022, | |
| "eval_steps_per_second": 9.472, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 13.67, | |
| "learning_rate": 0.00014189951875370348, | |
| "loss": 0.4811, | |
| "step": 98500 | |
| }, | |
| { | |
| "epoch": 13.74, | |
| "learning_rate": 0.00014179108606717728, | |
| "loss": 0.4808, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 13.74, | |
| "eval_loss": 0.45313671231269836, | |
| "eval_runtime": 1.434, | |
| "eval_samples_per_second": 129.013, | |
| "eval_steps_per_second": 8.368, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 13.81, | |
| "learning_rate": 0.00014168197764323368, | |
| "loss": 0.4809, | |
| "step": 99500 | |
| }, | |
| { | |
| "epoch": 13.88, | |
| "learning_rate": 0.00014157219467506488, | |
| "loss": 0.4806, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 13.88, | |
| "eval_loss": 0.4459179937839508, | |
| "eval_runtime": 1.3942, | |
| "eval_samples_per_second": 132.692, | |
| "eval_steps_per_second": 8.607, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 13.94, | |
| "learning_rate": 0.0001414617383632398, | |
| "loss": 0.4806, | |
| "step": 100500 | |
| }, | |
| { | |
| "epoch": 14.01, | |
| "learning_rate": 0.0001413506099156911, | |
| "loss": 0.4809, | |
| "step": 101000 | |
| }, | |
| { | |
| "epoch": 14.01, | |
| "eval_loss": 0.4517055153846741, | |
| "eval_runtime": 1.3095, | |
| "eval_samples_per_second": 141.281, | |
| "eval_steps_per_second": 9.164, | |
| "step": 101000 | |
| }, | |
| { | |
| "epoch": 14.08, | |
| "learning_rate": 0.00014123881054770157, | |
| "loss": 0.4806, | |
| "step": 101500 | |
| }, | |
| { | |
| "epoch": 14.15, | |
| "learning_rate": 0.0001411263414818912, | |
| "loss": 0.4801, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 14.15, | |
| "eval_loss": 0.45189717411994934, | |
| "eval_runtime": 1.2719, | |
| "eval_samples_per_second": 145.454, | |
| "eval_steps_per_second": 9.435, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 14.22, | |
| "learning_rate": 0.0001410132039482037, | |
| "loss": 0.4805, | |
| "step": 102500 | |
| }, | |
| { | |
| "epoch": 14.29, | |
| "learning_rate": 0.000140899399183893, | |
| "loss": 0.4801, | |
| "step": 103000 | |
| }, | |
| { | |
| "epoch": 14.29, | |
| "eval_loss": 0.4547403156757355, | |
| "eval_runtime": 1.3022, | |
| "eval_samples_per_second": 142.067, | |
| "eval_steps_per_second": 9.215, | |
| "step": 103000 | |
| }, | |
| { | |
| "epoch": 14.36, | |
| "learning_rate": 0.00014078492843350979, | |
| "loss": 0.48, | |
| "step": 103500 | |
| }, | |
| { | |
| "epoch": 14.43, | |
| "learning_rate": 0.00014066979294888782, | |
| "loss": 0.4805, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 14.43, | |
| "eval_loss": 0.4516749978065491, | |
| "eval_runtime": 1.2682, | |
| "eval_samples_per_second": 145.873, | |
| "eval_steps_per_second": 9.462, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 14.5, | |
| "learning_rate": 0.00014055399398913034, | |
| "loss": 0.4806, | |
| "step": 104500 | |
| }, | |
| { | |
| "epoch": 14.57, | |
| "learning_rate": 0.00014043753282059617, | |
| "loss": 0.4799, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 14.57, | |
| "eval_loss": 0.4491257071495056, | |
| "eval_runtime": 1.2323, | |
| "eval_samples_per_second": 150.131, | |
| "eval_steps_per_second": 9.738, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 14.64, | |
| "learning_rate": 0.00014032041071688605, | |
| "loss": 0.4804, | |
| "step": 105500 | |
| }, | |
| { | |
| "epoch": 14.71, | |
| "learning_rate": 0.0001402026289588285, | |
| "loss": 0.4805, | |
| "step": 106000 | |
| }, | |
| { | |
| "epoch": 14.71, | |
| "eval_loss": 0.45593592524528503, | |
| "eval_runtime": 1.2562, | |
| "eval_samples_per_second": 147.265, | |
| "eval_steps_per_second": 9.552, | |
| "step": 106000 | |
| }, | |
| { | |
| "epoch": 14.78, | |
| "learning_rate": 0.00014008466390471485, | |
| "loss": 0.4805, | |
| "step": 106500 | |
| }, | |
| { | |
| "epoch": 14.85, | |
| "learning_rate": 0.0001399655693349842, | |
| "loss": 0.48, | |
| "step": 107000 | |
| }, | |
| { | |
| "epoch": 14.85, | |
| "eval_loss": 0.4550573527812958, | |
| "eval_runtime": 1.3288, | |
| "eval_samples_per_second": 139.229, | |
| "eval_steps_per_second": 9.031, | |
| "step": 107000 | |
| }, | |
| { | |
| "epoch": 14.92, | |
| "learning_rate": 0.00013984581899139457, | |
| "loss": 0.4799, | |
| "step": 107500 | |
| }, | |
| { | |
| "epoch": 14.99, | |
| "learning_rate": 0.00013972565564541377, | |
| "loss": 0.4796, | |
| "step": 108000 | |
| }, | |
| { | |
| "epoch": 14.99, | |
| "eval_loss": 0.4537319242954254, | |
| "eval_runtime": 1.2437, | |
| "eval_samples_per_second": 148.751, | |
| "eval_steps_per_second": 9.649, | |
| "step": 108000 | |
| }, | |
| { | |
| "epoch": 15.05, | |
| "learning_rate": 0.00013960459899495145, | |
| "loss": 0.4803, | |
| "step": 108500 | |
| }, | |
| { | |
| "epoch": 15.12, | |
| "learning_rate": 0.00013948289051814402, | |
| "loss": 0.4801, | |
| "step": 109000 | |
| }, | |
| { | |
| "epoch": 15.12, | |
| "eval_loss": 0.4508979320526123, | |
| "eval_runtime": 1.3574, | |
| "eval_samples_per_second": 136.289, | |
| "eval_steps_per_second": 8.84, | |
| "step": 109000 | |
| }, | |
| { | |
| "epoch": 15.19, | |
| "learning_rate": 0.00013936053154597593, | |
| "loss": 0.4797, | |
| "step": 109500 | |
| }, | |
| { | |
| "epoch": 15.26, | |
| "learning_rate": 0.0001392375234165452, | |
| "loss": 0.4797, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 15.26, | |
| "eval_loss": 0.44824209809303284, | |
| "eval_runtime": 1.3552, | |
| "eval_samples_per_second": 136.513, | |
| "eval_steps_per_second": 8.855, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 15.33, | |
| "learning_rate": 0.0001391138674750491, | |
| "loss": 0.4798, | |
| "step": 110500 | |
| }, | |
| { | |
| "epoch": 15.4, | |
| "learning_rate": 0.00013898956507376917, | |
| "loss": 0.4798, | |
| "step": 111000 | |
| }, | |
| { | |
| "epoch": 15.4, | |
| "eval_loss": 0.446604460477829, | |
| "eval_runtime": 1.2361, | |
| "eval_samples_per_second": 149.667, | |
| "eval_steps_per_second": 9.708, | |
| "step": 111000 | |
| }, | |
| { | |
| "epoch": 15.47, | |
| "learning_rate": 0.00013886461757205655, | |
| "loss": 0.48, | |
| "step": 111500 | |
| }, | |
| { | |
| "epoch": 15.54, | |
| "learning_rate": 0.0001387390263363171, | |
| "loss": 0.4789, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 15.54, | |
| "eval_loss": 0.4444972574710846, | |
| "eval_runtime": 1.2832, | |
| "eval_samples_per_second": 144.17, | |
| "eval_steps_per_second": 9.352, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 15.61, | |
| "learning_rate": 0.00013861279273999646, | |
| "loss": 0.4798, | |
| "step": 112500 | |
| }, | |
| { | |
| "epoch": 15.68, | |
| "learning_rate": 0.00013848668131967977, | |
| "loss": 0.4808, | |
| "step": 113000 | |
| }, | |
| { | |
| "epoch": 15.68, | |
| "eval_loss": 0.4493043124675751, | |
| "eval_runtime": 1.4157, | |
| "eval_samples_per_second": 130.682, | |
| "eval_steps_per_second": 8.477, | |
| "step": 113000 | |
| }, | |
| { | |
| "epoch": 15.75, | |
| "learning_rate": 0.00013835942664208942, | |
| "loss": 0.4799, | |
| "step": 113500 | |
| }, | |
| { | |
| "epoch": 15.82, | |
| "learning_rate": 0.00013823127937490458, | |
| "loss": 0.4789, | |
| "step": 114000 | |
| }, | |
| { | |
| "epoch": 15.82, | |
| "eval_loss": 0.447512686252594, | |
| "eval_runtime": 1.3478, | |
| "eval_samples_per_second": 137.263, | |
| "eval_steps_per_second": 8.904, | |
| "step": 114000 | |
| }, | |
| { | |
| "epoch": 15.89, | |
| "learning_rate": 0.00013810249529977794, | |
| "loss": 0.4791, | |
| "step": 114500 | |
| }, | |
| { | |
| "epoch": 15.96, | |
| "learning_rate": 0.00013797307582507154, | |
| "loss": 0.4792, | |
| "step": 115000 | |
| }, | |
| { | |
| "epoch": 15.96, | |
| "eval_loss": 0.4542599320411682, | |
| "eval_runtime": 1.3264, | |
| "eval_samples_per_second": 139.478, | |
| "eval_steps_per_second": 9.047, | |
| "step": 115000 | |
| }, | |
| { | |
| "epoch": 16.03, | |
| "learning_rate": 0.00013784302236609602, | |
| "loss": 0.4792, | |
| "step": 115500 | |
| }, | |
| { | |
| "epoch": 16.1, | |
| "learning_rate": 0.00013771233634509523, | |
| "loss": 0.4787, | |
| "step": 116000 | |
| }, | |
| { | |
| "epoch": 16.1, | |
| "eval_loss": 0.44714024662971497, | |
| "eval_runtime": 1.3014, | |
| "eval_samples_per_second": 142.155, | |
| "eval_steps_per_second": 9.221, | |
| "step": 116000 | |
| }, | |
| { | |
| "epoch": 16.16, | |
| "learning_rate": 0.00013758101919123046, | |
| "loss": 0.4789, | |
| "step": 116500 | |
| }, | |
| { | |
| "epoch": 16.23, | |
| "learning_rate": 0.00013744907234056512, | |
| "loss": 0.4796, | |
| "step": 117000 | |
| }, | |
| { | |
| "epoch": 16.23, | |
| "eval_loss": 0.456470787525177, | |
| "eval_runtime": 1.4121, | |
| "eval_samples_per_second": 131.013, | |
| "eval_steps_per_second": 8.498, | |
| "step": 117000 | |
| }, | |
| { | |
| "epoch": 16.3, | |
| "learning_rate": 0.00013731649723604881, | |
| "loss": 0.4792, | |
| "step": 117500 | |
| }, | |
| { | |
| "epoch": 16.37, | |
| "learning_rate": 0.00013718329532750163, | |
| "loss": 0.4787, | |
| "step": 118000 | |
| }, | |
| { | |
| "epoch": 16.37, | |
| "eval_loss": 0.45149141550064087, | |
| "eval_runtime": 1.422, | |
| "eval_samples_per_second": 130.101, | |
| "eval_steps_per_second": 8.439, | |
| "step": 118000 | |
| }, | |
| { | |
| "epoch": 16.44, | |
| "learning_rate": 0.00013704946807159836, | |
| "loss": 0.479, | |
| "step": 118500 | |
| }, | |
| { | |
| "epoch": 16.51, | |
| "learning_rate": 0.00013691501693185236, | |
| "loss": 0.4788, | |
| "step": 119000 | |
| }, | |
| { | |
| "epoch": 16.51, | |
| "eval_loss": 0.4449474513530731, | |
| "eval_runtime": 1.3546, | |
| "eval_samples_per_second": 136.571, | |
| "eval_steps_per_second": 8.859, | |
| "step": 119000 | |
| }, | |
| { | |
| "epoch": 16.58, | |
| "learning_rate": 0.0001367799433785998, | |
| "loss": 0.4792, | |
| "step": 119500 | |
| }, | |
| { | |
| "epoch": 16.65, | |
| "learning_rate": 0.0001366442488889834, | |
| "loss": 0.4783, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 16.65, | |
| "eval_loss": 0.4454094171524048, | |
| "eval_runtime": 1.3113, | |
| "eval_samples_per_second": 141.083, | |
| "eval_steps_per_second": 9.151, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 16.72, | |
| "learning_rate": 0.00013650793494693634, | |
| "loss": 0.4787, | |
| "step": 120500 | |
| }, | |
| { | |
| "epoch": 16.79, | |
| "learning_rate": 0.0001363710030431661, | |
| "loss": 0.4787, | |
| "step": 121000 | |
| }, | |
| { | |
| "epoch": 16.79, | |
| "eval_loss": 0.44856345653533936, | |
| "eval_runtime": 1.3509, | |
| "eval_samples_per_second": 136.945, | |
| "eval_steps_per_second": 8.883, | |
| "step": 121000 | |
| }, | |
| { | |
| "epoch": 16.86, | |
| "learning_rate": 0.00013623345467513802, | |
| "loss": 0.4784, | |
| "step": 121500 | |
| }, | |
| { | |
| "epoch": 16.93, | |
| "learning_rate": 0.00013609529134705898, | |
| "loss": 0.4789, | |
| "step": 122000 | |
| }, | |
| { | |
| "epoch": 16.93, | |
| "eval_loss": 0.4480277895927429, | |
| "eval_runtime": 1.4149, | |
| "eval_samples_per_second": 130.754, | |
| "eval_steps_per_second": 8.481, | |
| "step": 122000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "learning_rate": 0.00013595679273463004, | |
| "loss": 0.4786, | |
| "step": 122500 | |
| }, | |
| { | |
| "epoch": 17.07, | |
| "learning_rate": 0.0001358174052482977, | |
| "loss": 0.4782, | |
| "step": 123000 | |
| }, | |
| { | |
| "epoch": 17.07, | |
| "eval_loss": 0.4529421329498291, | |
| "eval_runtime": 1.3006, | |
| "eval_samples_per_second": 142.246, | |
| "eval_steps_per_second": 9.227, | |
| "step": 123000 | |
| }, | |
| { | |
| "epoch": 17.14, | |
| "learning_rate": 0.0001356774073517643, | |
| "loss": 0.4779, | |
| "step": 123500 | |
| }, | |
| { | |
| "epoch": 17.21, | |
| "learning_rate": 0.00013553680057602438, | |
| "loss": 0.4782, | |
| "step": 124000 | |
| }, | |
| { | |
| "epoch": 17.21, | |
| "eval_loss": 0.448131263256073, | |
| "eval_runtime": 1.4454, | |
| "eval_samples_per_second": 127.994, | |
| "eval_steps_per_second": 8.302, | |
| "step": 124000 | |
| }, | |
| { | |
| "epoch": 17.27, | |
| "learning_rate": 0.00013539558645873117, | |
| "loss": 0.4784, | |
| "step": 124500 | |
| }, | |
| { | |
| "epoch": 17.34, | |
| "learning_rate": 0.00013525405078756463, | |
| "loss": 0.4777, | |
| "step": 125000 | |
| }, | |
| { | |
| "epoch": 17.34, | |
| "eval_loss": 0.452815443277359, | |
| "eval_runtime": 1.3521, | |
| "eval_samples_per_second": 136.827, | |
| "eval_steps_per_second": 8.875, | |
| "step": 125000 | |
| }, | |
| { | |
| "epoch": 17.41, | |
| "learning_rate": 0.00013511162783361505, | |
| "loss": 0.4785, | |
| "step": 125500 | |
| }, | |
| { | |
| "epoch": 17.48, | |
| "learning_rate": 0.00013496860218773315, | |
| "loss": 0.4779, | |
| "step": 126000 | |
| }, | |
| { | |
| "epoch": 17.48, | |
| "eval_loss": 0.4513993561267853, | |
| "eval_runtime": 1.4627, | |
| "eval_samples_per_second": 126.479, | |
| "eval_steps_per_second": 8.204, | |
| "step": 126000 | |
| }, | |
| { | |
| "epoch": 17.55, | |
| "learning_rate": 0.00013482497541402445, | |
| "loss": 0.4781, | |
| "step": 126500 | |
| }, | |
| { | |
| "epoch": 17.62, | |
| "learning_rate": 0.00013468074908316836, | |
| "loss": 0.4781, | |
| "step": 127000 | |
| }, | |
| { | |
| "epoch": 17.62, | |
| "eval_loss": 0.45199939608573914, | |
| "eval_runtime": 1.3306, | |
| "eval_samples_per_second": 139.031, | |
| "eval_steps_per_second": 9.018, | |
| "step": 127000 | |
| }, | |
| { | |
| "epoch": 17.69, | |
| "learning_rate": 0.0001345359247724009, | |
| "loss": 0.4783, | |
| "step": 127500 | |
| }, | |
| { | |
| "epoch": 17.76, | |
| "learning_rate": 0.0001343905040654976, | |
| "loss": 0.4776, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 17.76, | |
| "eval_loss": 0.44953423738479614, | |
| "eval_runtime": 1.2748, | |
| "eval_samples_per_second": 145.125, | |
| "eval_steps_per_second": 9.413, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 17.83, | |
| "learning_rate": 0.00013424448855275597, | |
| "loss": 0.4782, | |
| "step": 128500 | |
| }, | |
| { | |
| "epoch": 17.9, | |
| "learning_rate": 0.00013409817363937984, | |
| "loss": 0.4777, | |
| "step": 129000 | |
| }, | |
| { | |
| "epoch": 17.9, | |
| "eval_loss": 0.4501388669013977, | |
| "eval_runtime": 1.3709, | |
| "eval_samples_per_second": 134.949, | |
| "eval_steps_per_second": 8.753, | |
| "step": 129000 | |
| }, | |
| { | |
| "epoch": 17.97, | |
| "learning_rate": 0.00013395156446640005, | |
| "loss": 0.478, | |
| "step": 129500 | |
| }, | |
| { | |
| "epoch": 18.04, | |
| "learning_rate": 0.00013380377767805118, | |
| "loss": 0.4783, | |
| "step": 130000 | |
| }, | |
| { | |
| "epoch": 18.04, | |
| "eval_loss": 0.4528443217277527, | |
| "eval_runtime": 1.4085, | |
| "eval_samples_per_second": 131.344, | |
| "eval_steps_per_second": 8.52, | |
| "step": 130000 | |
| }, | |
| { | |
| "epoch": 18.11, | |
| "learning_rate": 0.00013365540250020975, | |
| "loss": 0.4781, | |
| "step": 130500 | |
| }, | |
| { | |
| "epoch": 18.18, | |
| "learning_rate": 0.00013350644055548294, | |
| "loss": 0.4771, | |
| "step": 131000 | |
| }, | |
| { | |
| "epoch": 18.18, | |
| "eval_loss": 0.44982901215553284, | |
| "eval_runtime": 1.2299, | |
| "eval_samples_per_second": 150.422, | |
| "eval_steps_per_second": 9.757, | |
| "step": 131000 | |
| }, | |
| { | |
| "epoch": 18.25, | |
| "learning_rate": 0.0001333568934728947, | |
| "loss": 0.4772, | |
| "step": 131500 | |
| }, | |
| { | |
| "epoch": 18.32, | |
| "learning_rate": 0.00013320676288786797, | |
| "loss": 0.4775, | |
| "step": 132000 | |
| }, | |
| { | |
| "epoch": 18.32, | |
| "eval_loss": 0.4524603486061096, | |
| "eval_runtime": 1.3159, | |
| "eval_samples_per_second": 140.59, | |
| "eval_steps_per_second": 9.119, | |
| "step": 132000 | |
| }, | |
| { | |
| "epoch": 18.38, | |
| "learning_rate": 0.00013305605044220678, | |
| "loss": 0.4771, | |
| "step": 132500 | |
| }, | |
| { | |
| "epoch": 18.45, | |
| "learning_rate": 0.00013290475778407828, | |
| "loss": 0.4772, | |
| "step": 133000 | |
| }, | |
| { | |
| "epoch": 18.45, | |
| "eval_loss": 0.4482344388961792, | |
| "eval_runtime": 1.3869, | |
| "eval_samples_per_second": 133.391, | |
| "eval_steps_per_second": 8.652, | |
| "step": 133000 | |
| }, | |
| { | |
| "epoch": 18.52, | |
| "learning_rate": 0.00013275288656799475, | |
| "loss": 0.4779, | |
| "step": 133500 | |
| }, | |
| { | |
| "epoch": 18.59, | |
| "learning_rate": 0.00013260104939421987, | |
| "loss": 0.4775, | |
| "step": 134000 | |
| }, | |
| { | |
| "epoch": 18.59, | |
| "eval_loss": 0.4531766176223755, | |
| "eval_runtime": 1.3099, | |
| "eval_samples_per_second": 141.231, | |
| "eval_steps_per_second": 9.161, | |
| "step": 134000 | |
| }, | |
| { | |
| "epoch": 18.66, | |
| "learning_rate": 0.00013244802834864357, | |
| "loss": 0.4767, | |
| "step": 134500 | |
| }, | |
| { | |
| "epoch": 18.73, | |
| "learning_rate": 0.00013229443373983214, | |
| "loss": 0.4769, | |
| "step": 135000 | |
| }, | |
| { | |
| "epoch": 18.73, | |
| "eval_loss": 0.4537143111228943, | |
| "eval_runtime": 1.2689, | |
| "eval_samples_per_second": 145.794, | |
| "eval_steps_per_second": 9.457, | |
| "step": 135000 | |
| }, | |
| { | |
| "epoch": 18.8, | |
| "learning_rate": 0.00013214026724747165, | |
| "loss": 0.4775, | |
| "step": 135500 | |
| }, | |
| { | |
| "epoch": 18.87, | |
| "learning_rate": 0.00013198553055750217, | |
| "loss": 0.4776, | |
| "step": 136000 | |
| }, | |
| { | |
| "epoch": 18.87, | |
| "eval_loss": 0.45088058710098267, | |
| "eval_runtime": 1.3285, | |
| "eval_samples_per_second": 139.259, | |
| "eval_steps_per_second": 9.033, | |
| "step": 136000 | |
| }, | |
| { | |
| "epoch": 18.94, | |
| "learning_rate": 0.00013183022536209928, | |
| "loss": 0.4772, | |
| "step": 136500 | |
| }, | |
| { | |
| "epoch": 19.01, | |
| "learning_rate": 0.0001316743533596558, | |
| "loss": 0.4775, | |
| "step": 137000 | |
| }, | |
| { | |
| "epoch": 19.01, | |
| "eval_loss": 0.44637706875801086, | |
| "eval_runtime": 1.4739, | |
| "eval_samples_per_second": 125.521, | |
| "eval_steps_per_second": 8.142, | |
| "step": 137000 | |
| }, | |
| { | |
| "epoch": 19.08, | |
| "learning_rate": 0.0001315182296918089, | |
| "loss": 0.4767, | |
| "step": 137500 | |
| }, | |
| { | |
| "epoch": 19.15, | |
| "learning_rate": 0.00013136123032030968, | |
| "loss": 0.4769, | |
| "step": 138000 | |
| }, | |
| { | |
| "epoch": 19.15, | |
| "eval_loss": 0.4463551342487335, | |
| "eval_runtime": 1.2873, | |
| "eval_samples_per_second": 143.713, | |
| "eval_steps_per_second": 9.322, | |
| "step": 138000 | |
| }, | |
| { | |
| "epoch": 19.22, | |
| "learning_rate": 0.0001312036692706245, | |
| "loss": 0.4766, | |
| "step": 138500 | |
| }, | |
| { | |
| "epoch": 19.29, | |
| "learning_rate": 0.0001310455482658157, | |
| "loss": 0.4772, | |
| "step": 139000 | |
| }, | |
| { | |
| "epoch": 19.29, | |
| "eval_loss": 0.44989240169525146, | |
| "eval_runtime": 1.3958, | |
| "eval_samples_per_second": 132.539, | |
| "eval_steps_per_second": 8.597, | |
| "step": 139000 | |
| }, | |
| { | |
| "epoch": 19.36, | |
| "learning_rate": 0.00013088686903506928, | |
| "loss": 0.4766, | |
| "step": 139500 | |
| }, | |
| { | |
| "epoch": 19.43, | |
| "learning_rate": 0.0001307276333136759, | |
| "loss": 0.4766, | |
| "step": 140000 | |
| }, | |
| { | |
| "epoch": 19.43, | |
| "eval_loss": 0.4428194761276245, | |
| "eval_runtime": 1.3007, | |
| "eval_samples_per_second": 142.227, | |
| "eval_steps_per_second": 9.226, | |
| "step": 140000 | |
| }, | |
| { | |
| "epoch": 19.49, | |
| "learning_rate": 0.00013056880323663773, | |
| "loss": 0.4783, | |
| "step": 140500 | |
| }, | |
| { | |
| "epoch": 19.56, | |
| "learning_rate": 0.00013040846307693418, | |
| "loss": 0.4764, | |
| "step": 141000 | |
| }, | |
| { | |
| "epoch": 19.56, | |
| "eval_loss": 0.45361649990081787, | |
| "eval_runtime": 1.2902, | |
| "eval_samples_per_second": 143.387, | |
| "eval_steps_per_second": 9.301, | |
| "step": 141000 | |
| }, | |
| { | |
| "epoch": 19.63, | |
| "learning_rate": 0.00013024757165835455, | |
| "loss": 0.4762, | |
| "step": 141500 | |
| }, | |
| { | |
| "epoch": 19.7, | |
| "learning_rate": 0.00013008613074038167, | |
| "loss": 0.477, | |
| "step": 142000 | |
| }, | |
| { | |
| "epoch": 19.7, | |
| "eval_loss": 0.44440191984176636, | |
| "eval_runtime": 1.4302, | |
| "eval_samples_per_second": 129.355, | |
| "eval_steps_per_second": 8.391, | |
| "step": 142000 | |
| }, | |
| { | |
| "epoch": 19.77, | |
| "learning_rate": 0.00012992414208850748, | |
| "loss": 0.4762, | |
| "step": 142500 | |
| }, | |
| { | |
| "epoch": 19.84, | |
| "learning_rate": 0.000129761607474214, | |
| "loss": 0.4764, | |
| "step": 143000 | |
| }, | |
| { | |
| "epoch": 19.84, | |
| "eval_loss": 0.4482267498970032, | |
| "eval_runtime": 1.3355, | |
| "eval_samples_per_second": 138.528, | |
| "eval_steps_per_second": 8.986, | |
| "step": 143000 | |
| }, | |
| { | |
| "epoch": 19.91, | |
| "learning_rate": 0.00012959852867495364, | |
| "loss": 0.4765, | |
| "step": 143500 | |
| }, | |
| { | |
| "epoch": 19.98, | |
| "learning_rate": 0.00012943490747413015, | |
| "loss": 0.4764, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 19.98, | |
| "eval_loss": 0.4509750008583069, | |
| "eval_runtime": 1.3011, | |
| "eval_samples_per_second": 142.182, | |
| "eval_steps_per_second": 9.223, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 20.05, | |
| "learning_rate": 0.00012927074566107863, | |
| "loss": 0.4764, | |
| "step": 144500 | |
| }, | |
| { | |
| "epoch": 20.12, | |
| "learning_rate": 0.00012910604503104647, | |
| "loss": 0.4763, | |
| "step": 145000 | |
| }, | |
| { | |
| "epoch": 20.12, | |
| "eval_loss": 0.45185399055480957, | |
| "eval_runtime": 1.4864, | |
| "eval_samples_per_second": 124.464, | |
| "eval_steps_per_second": 8.073, | |
| "step": 145000 | |
| }, | |
| { | |
| "epoch": 20.19, | |
| "learning_rate": 0.00012894080738517333, | |
| "loss": 0.4757, | |
| "step": 145500 | |
| }, | |
| { | |
| "epoch": 20.26, | |
| "learning_rate": 0.00012877503453047163, | |
| "loss": 0.4761, | |
| "step": 146000 | |
| }, | |
| { | |
| "epoch": 20.26, | |
| "eval_loss": 0.44523686170578003, | |
| "eval_runtime": 1.2461, | |
| "eval_samples_per_second": 148.467, | |
| "eval_steps_per_second": 9.63, | |
| "step": 146000 | |
| }, | |
| { | |
| "epoch": 20.33, | |
| "learning_rate": 0.00012860872827980677, | |
| "loss": 0.4757, | |
| "step": 146500 | |
| }, | |
| { | |
| "epoch": 20.4, | |
| "learning_rate": 0.00012844189045187722, | |
| "loss": 0.4761, | |
| "step": 147000 | |
| }, | |
| { | |
| "epoch": 20.4, | |
| "eval_loss": 0.44761815667152405, | |
| "eval_runtime": 1.3189, | |
| "eval_samples_per_second": 140.265, | |
| "eval_steps_per_second": 9.098, | |
| "step": 147000 | |
| }, | |
| { | |
| "epoch": 20.47, | |
| "learning_rate": 0.0001282745228711948, | |
| "loss": 0.4756, | |
| "step": 147500 | |
| }, | |
| { | |
| "epoch": 20.54, | |
| "learning_rate": 0.0001281066273680645, | |
| "loss": 0.4756, | |
| "step": 148000 | |
| }, | |
| { | |
| "epoch": 20.54, | |
| "eval_loss": 0.449351966381073, | |
| "eval_runtime": 1.3771, | |
| "eval_samples_per_second": 134.344, | |
| "eval_steps_per_second": 8.714, | |
| "step": 148000 | |
| }, | |
| { | |
| "epoch": 20.6, | |
| "learning_rate": 0.00012793820577856467, | |
| "loss": 0.4763, | |
| "step": 148500 | |
| }, | |
| { | |
| "epoch": 20.67, | |
| "learning_rate": 0.00012776925994452683, | |
| "loss": 0.4757, | |
| "step": 149000 | |
| }, | |
| { | |
| "epoch": 20.67, | |
| "eval_loss": 0.45438215136528015, | |
| "eval_runtime": 1.2596, | |
| "eval_samples_per_second": 146.871, | |
| "eval_steps_per_second": 9.527, | |
| "step": 149000 | |
| }, | |
| { | |
| "epoch": 20.74, | |
| "learning_rate": 0.00012759979171351554, | |
| "loss": 0.4759, | |
| "step": 149500 | |
| }, | |
| { | |
| "epoch": 20.81, | |
| "learning_rate": 0.0001274301434346256, | |
| "loss": 0.4762, | |
| "step": 150000 | |
| }, | |
| { | |
| "epoch": 20.81, | |
| "eval_loss": 0.44118747115135193, | |
| "eval_runtime": 1.2816, | |
| "eval_samples_per_second": 144.353, | |
| "eval_steps_per_second": 9.363, | |
| "step": 150000 | |
| }, | |
| { | |
| "epoch": 20.88, | |
| "learning_rate": 0.00012725963701070271, | |
| "loss": 0.4756, | |
| "step": 150500 | |
| }, | |
| { | |
| "epoch": 20.95, | |
| "learning_rate": 0.00012708861376296116, | |
| "loss": 0.4757, | |
| "step": 151000 | |
| }, | |
| { | |
| "epoch": 20.95, | |
| "eval_loss": 0.44587138295173645, | |
| "eval_runtime": 1.2831, | |
| "eval_samples_per_second": 144.186, | |
| "eval_steps_per_second": 9.353, | |
| "step": 151000 | |
| }, | |
| { | |
| "epoch": 21.02, | |
| "learning_rate": 0.00012691707556168372, | |
| "loss": 0.4758, | |
| "step": 151500 | |
| }, | |
| { | |
| "epoch": 21.09, | |
| "learning_rate": 0.00012674502428278476, | |
| "loss": 0.4749, | |
| "step": 152000 | |
| }, | |
| { | |
| "epoch": 21.09, | |
| "eval_loss": 0.45321565866470337, | |
| "eval_runtime": 1.3999, | |
| "eval_samples_per_second": 132.157, | |
| "eval_steps_per_second": 8.572, | |
| "step": 152000 | |
| }, | |
| { | |
| "epoch": 21.16, | |
| "learning_rate": 0.00012657246180778942, | |
| "loss": 0.4752, | |
| "step": 152500 | |
| }, | |
| { | |
| "epoch": 21.23, | |
| "learning_rate": 0.00012639939002381332, | |
| "loss": 0.4752, | |
| "step": 153000 | |
| }, | |
| { | |
| "epoch": 21.23, | |
| "eval_loss": 0.4477311074733734, | |
| "eval_runtime": 1.4069, | |
| "eval_samples_per_second": 131.493, | |
| "eval_steps_per_second": 8.529, | |
| "step": 153000 | |
| }, | |
| { | |
| "epoch": 21.3, | |
| "learning_rate": 0.0001262258108235418, | |
| "loss": 0.4747, | |
| "step": 153500 | |
| }, | |
| { | |
| "epoch": 21.37, | |
| "learning_rate": 0.00012605207477788834, | |
| "loss": 0.4749, | |
| "step": 154000 | |
| }, | |
| { | |
| "epoch": 21.37, | |
| "eval_loss": 0.43964967131614685, | |
| "eval_runtime": 1.4856, | |
| "eval_samples_per_second": 124.531, | |
| "eval_steps_per_second": 8.078, | |
| "step": 154000 | |
| }, | |
| { | |
| "epoch": 21.44, | |
| "learning_rate": 0.00012587748745058206, | |
| "loss": 0.4755, | |
| "step": 154500 | |
| }, | |
| { | |
| "epoch": 21.51, | |
| "learning_rate": 0.00012570274909192927, | |
| "loss": 0.4764, | |
| "step": 155000 | |
| }, | |
| { | |
| "epoch": 21.51, | |
| "eval_loss": 0.4465893805027008, | |
| "eval_runtime": 1.3187, | |
| "eval_samples_per_second": 140.292, | |
| "eval_steps_per_second": 9.1, | |
| "step": 155000 | |
| }, | |
| { | |
| "epoch": 21.58, | |
| "learning_rate": 0.00012552716125933724, | |
| "loss": 0.4754, | |
| "step": 155500 | |
| }, | |
| { | |
| "epoch": 21.65, | |
| "learning_rate": 0.0001253510755490038, | |
| "loss": 0.4753, | |
| "step": 156000 | |
| }, | |
| { | |
| "epoch": 21.65, | |
| "eval_loss": 0.4523191750049591, | |
| "eval_runtime": 1.3412, | |
| "eval_samples_per_second": 137.933, | |
| "eval_steps_per_second": 8.947, | |
| "step": 156000 | |
| }, | |
| { | |
| "epoch": 21.71, | |
| "learning_rate": 0.00012517484754357648, | |
| "loss": 0.4756, | |
| "step": 156500 | |
| }, | |
| { | |
| "epoch": 21.78, | |
| "learning_rate": 0.00012499777284623038, | |
| "loss": 0.4755, | |
| "step": 157000 | |
| }, | |
| { | |
| "epoch": 21.78, | |
| "eval_loss": 0.4581702947616577, | |
| "eval_runtime": 1.2823, | |
| "eval_samples_per_second": 144.268, | |
| "eval_steps_per_second": 9.358, | |
| "step": 157000 | |
| }, | |
| { | |
| "epoch": 21.85, | |
| "learning_rate": 0.00012482056168383577, | |
| "loss": 0.4757, | |
| "step": 157500 | |
| }, | |
| { | |
| "epoch": 21.92, | |
| "learning_rate": 0.00012464250572981418, | |
| "loss": 0.4749, | |
| "step": 158000 | |
| }, | |
| { | |
| "epoch": 21.92, | |
| "eval_loss": 0.45388588309288025, | |
| "eval_runtime": 1.433, | |
| "eval_samples_per_second": 129.098, | |
| "eval_steps_per_second": 8.374, | |
| "step": 158000 | |
| }, | |
| { | |
| "epoch": 21.99, | |
| "learning_rate": 0.00012446396157250224, | |
| "loss": 0.4748, | |
| "step": 158500 | |
| }, | |
| { | |
| "epoch": 22.06, | |
| "learning_rate": 0.00012428493116443032, | |
| "loss": 0.475, | |
| "step": 159000 | |
| }, | |
| { | |
| "epoch": 22.06, | |
| "eval_loss": 0.45385169982910156, | |
| "eval_runtime": 1.3333, | |
| "eval_samples_per_second": 138.754, | |
| "eval_steps_per_second": 9.0, | |
| "step": 159000 | |
| }, | |
| { | |
| "epoch": 22.13, | |
| "learning_rate": 0.00012410541646344625, | |
| "loss": 0.4751, | |
| "step": 159500 | |
| }, | |
| { | |
| "epoch": 22.2, | |
| "learning_rate": 0.00012392541943269405, | |
| "loss": 0.4747, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 22.2, | |
| "eval_loss": 0.4518774151802063, | |
| "eval_runtime": 1.3056, | |
| "eval_samples_per_second": 141.696, | |
| "eval_steps_per_second": 9.191, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 22.27, | |
| "learning_rate": 0.0001237449420405924, | |
| "loss": 0.4746, | |
| "step": 160500 | |
| }, | |
| { | |
| "epoch": 22.34, | |
| "learning_rate": 0.00012356398626081318, | |
| "loss": 0.4745, | |
| "step": 161000 | |
| }, | |
| { | |
| "epoch": 22.34, | |
| "eval_loss": 0.43704134225845337, | |
| "eval_runtime": 1.2831, | |
| "eval_samples_per_second": 144.177, | |
| "eval_steps_per_second": 9.352, | |
| "step": 161000 | |
| }, | |
| { | |
| "epoch": 22.41, | |
| "learning_rate": 0.00012338255407225979, | |
| "loss": 0.4744, | |
| "step": 161500 | |
| }, | |
| { | |
| "epoch": 22.48, | |
| "learning_rate": 0.00012320064745904554, | |
| "loss": 0.4748, | |
| "step": 162000 | |
| }, | |
| { | |
| "epoch": 22.48, | |
| "eval_loss": 0.4449314773082733, | |
| "eval_runtime": 1.3741, | |
| "eval_samples_per_second": 134.638, | |
| "eval_steps_per_second": 8.733, | |
| "step": 162000 | |
| }, | |
| { | |
| "epoch": 22.55, | |
| "learning_rate": 0.00012301826841047204, | |
| "loss": 0.474, | |
| "step": 162500 | |
| }, | |
| { | |
| "epoch": 22.62, | |
| "learning_rate": 0.00012283541892100733, | |
| "loss": 0.4743, | |
| "step": 163000 | |
| }, | |
| { | |
| "epoch": 22.62, | |
| "eval_loss": 0.44838273525238037, | |
| "eval_runtime": 1.3185, | |
| "eval_samples_per_second": 140.311, | |
| "eval_steps_per_second": 9.101, | |
| "step": 163000 | |
| }, | |
| { | |
| "epoch": 22.69, | |
| "learning_rate": 0.00012265210099026412, | |
| "loss": 0.4747, | |
| "step": 163500 | |
| }, | |
| { | |
| "epoch": 22.76, | |
| "learning_rate": 0.000122468316622978, | |
| "loss": 0.4745, | |
| "step": 164000 | |
| }, | |
| { | |
| "epoch": 22.76, | |
| "eval_loss": 0.44712451100349426, | |
| "eval_runtime": 1.4597, | |
| "eval_samples_per_second": 126.737, | |
| "eval_steps_per_second": 8.221, | |
| "step": 164000 | |
| }, | |
| { | |
| "epoch": 22.82, | |
| "learning_rate": 0.00012228406782898528, | |
| "loss": 0.4741, | |
| "step": 164500 | |
| }, | |
| { | |
| "epoch": 22.89, | |
| "learning_rate": 0.00012209935662320132, | |
| "loss": 0.4739, | |
| "step": 165000 | |
| }, | |
| { | |
| "epoch": 22.89, | |
| "eval_loss": 0.44801923632621765, | |
| "eval_runtime": 1.3259, | |
| "eval_samples_per_second": 139.524, | |
| "eval_steps_per_second": 9.05, | |
| "step": 165000 | |
| }, | |
| { | |
| "epoch": 22.96, | |
| "learning_rate": 0.00012191418502559822, | |
| "loss": 0.4743, | |
| "step": 165500 | |
| }, | |
| { | |
| "epoch": 23.03, | |
| "learning_rate": 0.00012172892677721339, | |
| "loss": 0.4746, | |
| "step": 166000 | |
| }, | |
| { | |
| "epoch": 23.03, | |
| "eval_loss": 0.4518602192401886, | |
| "eval_runtime": 1.3853, | |
| "eval_samples_per_second": 133.543, | |
| "eval_steps_per_second": 8.662, | |
| "step": 166000 | |
| }, | |
| { | |
| "epoch": 23.1, | |
| "learning_rate": 0.00012154433187517636, | |
| "loss": 0.4749, | |
| "step": 166500 | |
| }, | |
| { | |
| "epoch": 23.17, | |
| "learning_rate": 0.00012135779580511397, | |
| "loss": 0.4739, | |
| "step": 167000 | |
| }, | |
| { | |
| "epoch": 23.17, | |
| "eval_loss": 0.4477546811103821, | |
| "eval_runtime": 1.215, | |
| "eval_samples_per_second": 152.268, | |
| "eval_steps_per_second": 9.877, | |
| "step": 167000 | |
| }, | |
| { | |
| "epoch": 23.24, | |
| "learning_rate": 0.00012117080745282275, | |
| "loss": 0.4741, | |
| "step": 167500 | |
| }, | |
| { | |
| "epoch": 23.31, | |
| "learning_rate": 0.00012098336886317734, | |
| "loss": 0.4739, | |
| "step": 168000 | |
| }, | |
| { | |
| "epoch": 23.31, | |
| "eval_loss": 0.44968467950820923, | |
| "eval_runtime": 1.4145, | |
| "eval_samples_per_second": 130.789, | |
| "eval_steps_per_second": 8.484, | |
| "step": 168000 | |
| }, | |
| { | |
| "epoch": 23.38, | |
| "learning_rate": 0.0001207954820859762, | |
| "loss": 0.4734, | |
| "step": 168500 | |
| }, | |
| { | |
| "epoch": 23.45, | |
| "learning_rate": 0.00012060714917591897, | |
| "loss": 0.4738, | |
| "step": 169000 | |
| }, | |
| { | |
| "epoch": 23.45, | |
| "eval_loss": 0.4461642801761627, | |
| "eval_runtime": 1.3919, | |
| "eval_samples_per_second": 132.914, | |
| "eval_steps_per_second": 8.621, | |
| "step": 169000 | |
| }, | |
| { | |
| "epoch": 23.52, | |
| "learning_rate": 0.0001204183721925842, | |
| "loss": 0.4736, | |
| "step": 169500 | |
| }, | |
| { | |
| "epoch": 23.59, | |
| "learning_rate": 0.00012022915320040672, | |
| "loss": 0.474, | |
| "step": 170000 | |
| }, | |
| { | |
| "epoch": 23.59, | |
| "eval_loss": 0.4429852366447449, | |
| "eval_runtime": 1.4452, | |
| "eval_samples_per_second": 128.013, | |
| "eval_steps_per_second": 8.304, | |
| "step": 170000 | |
| }, | |
| { | |
| "epoch": 23.66, | |
| "learning_rate": 0.00012003949426865512, | |
| "loss": 0.4734, | |
| "step": 170500 | |
| }, | |
| { | |
| "epoch": 23.73, | |
| "learning_rate": 0.00011984939747140908, | |
| "loss": 0.4737, | |
| "step": 171000 | |
| }, | |
| { | |
| "epoch": 23.73, | |
| "eval_loss": 0.4483201205730438, | |
| "eval_runtime": 1.3789, | |
| "eval_samples_per_second": 134.168, | |
| "eval_steps_per_second": 8.703, | |
| "step": 171000 | |
| }, | |
| { | |
| "epoch": 23.8, | |
| "learning_rate": 0.00011965886488753674, | |
| "loss": 0.4735, | |
| "step": 171500 | |
| }, | |
| { | |
| "epoch": 23.87, | |
| "learning_rate": 0.00011946789860067191, | |
| "loss": 0.4737, | |
| "step": 172000 | |
| }, | |
| { | |
| "epoch": 23.87, | |
| "eval_loss": 0.45078667998313904, | |
| "eval_runtime": 1.407, | |
| "eval_samples_per_second": 131.488, | |
| "eval_steps_per_second": 8.529, | |
| "step": 172000 | |
| }, | |
| { | |
| "epoch": 23.93, | |
| "learning_rate": 0.0001192765006991913, | |
| "loss": 0.4733, | |
| "step": 172500 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 0.00011908467327619169, | |
| "loss": 0.474, | |
| "step": 173000 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_loss": 0.4439038932323456, | |
| "eval_runtime": 1.5717, | |
| "eval_samples_per_second": 117.704, | |
| "eval_steps_per_second": 7.635, | |
| "step": 173000 | |
| }, | |
| { | |
| "epoch": 24.07, | |
| "learning_rate": 0.00011889241842946705, | |
| "loss": 0.4734, | |
| "step": 173500 | |
| }, | |
| { | |
| "epoch": 24.14, | |
| "learning_rate": 0.00011869973826148558, | |
| "loss": 0.4729, | |
| "step": 174000 | |
| }, | |
| { | |
| "epoch": 24.14, | |
| "eval_loss": 0.44258496165275574, | |
| "eval_runtime": 1.4275, | |
| "eval_samples_per_second": 129.602, | |
| "eval_steps_per_second": 8.407, | |
| "step": 174000 | |
| }, | |
| { | |
| "epoch": 24.21, | |
| "learning_rate": 0.00011850663487936671, | |
| "loss": 0.4736, | |
| "step": 174500 | |
| }, | |
| { | |
| "epoch": 24.28, | |
| "learning_rate": 0.00011831311039485813, | |
| "loss": 0.4735, | |
| "step": 175000 | |
| }, | |
| { | |
| "epoch": 24.28, | |
| "eval_loss": 0.4433186650276184, | |
| "eval_runtime": 1.3374, | |
| "eval_samples_per_second": 138.324, | |
| "eval_steps_per_second": 8.972, | |
| "step": 175000 | |
| }, | |
| { | |
| "epoch": 24.35, | |
| "learning_rate": 0.00011811916692431257, | |
| "loss": 0.473, | |
| "step": 175500 | |
| }, | |
| { | |
| "epoch": 24.42, | |
| "learning_rate": 0.00011792480658866476, | |
| "loss": 0.4722, | |
| "step": 176000 | |
| }, | |
| { | |
| "epoch": 24.42, | |
| "eval_loss": 0.4482550621032715, | |
| "eval_runtime": 1.3965, | |
| "eval_samples_per_second": 132.478, | |
| "eval_steps_per_second": 8.593, | |
| "step": 176000 | |
| }, | |
| { | |
| "epoch": 24.49, | |
| "learning_rate": 0.0001177300315134082, | |
| "loss": 0.4731, | |
| "step": 176500 | |
| }, | |
| { | |
| "epoch": 24.56, | |
| "learning_rate": 0.00011753523461430789, | |
| "loss": 0.4728, | |
| "step": 177000 | |
| }, | |
| { | |
| "epoch": 24.56, | |
| "eval_loss": 0.44964930415153503, | |
| "eval_runtime": 1.2933, | |
| "eval_samples_per_second": 143.042, | |
| "eval_steps_per_second": 9.278, | |
| "step": 177000 | |
| }, | |
| { | |
| "epoch": 24.63, | |
| "learning_rate": 0.00011734002887616938, | |
| "loss": 0.4729, | |
| "step": 177500 | |
| }, | |
| { | |
| "epoch": 24.7, | |
| "learning_rate": 0.00011714402400936337, | |
| "loss": 0.4727, | |
| "step": 178000 | |
| }, | |
| { | |
| "epoch": 24.7, | |
| "eval_loss": 0.4473492503166199, | |
| "eval_runtime": 1.3972, | |
| "eval_samples_per_second": 132.412, | |
| "eval_steps_per_second": 8.589, | |
| "step": 178000 | |
| }, | |
| { | |
| "epoch": 24.77, | |
| "learning_rate": 0.00011694761294146178, | |
| "loss": 0.4729, | |
| "step": 178500 | |
| }, | |
| { | |
| "epoch": 24.84, | |
| "learning_rate": 0.00011675079782038459, | |
| "loss": 0.4729, | |
| "step": 179000 | |
| }, | |
| { | |
| "epoch": 24.84, | |
| "eval_loss": 0.440412700176239, | |
| "eval_runtime": 1.3521, | |
| "eval_samples_per_second": 136.82, | |
| "eval_steps_per_second": 8.875, | |
| "step": 179000 | |
| }, | |
| { | |
| "epoch": 24.91, | |
| "learning_rate": 0.00011655358079847044, | |
| "loss": 0.4734, | |
| "step": 179500 | |
| }, | |
| { | |
| "epoch": 24.98, | |
| "learning_rate": 0.00011635635966349406, | |
| "loss": 0.4722, | |
| "step": 180000 | |
| }, | |
| { | |
| "epoch": 24.98, | |
| "eval_loss": 0.4425950348377228, | |
| "eval_runtime": 1.4026, | |
| "eval_samples_per_second": 131.901, | |
| "eval_steps_per_second": 8.556, | |
| "step": 180000 | |
| }, | |
| { | |
| "epoch": 25.05, | |
| "learning_rate": 0.00011615834610748511, | |
| "loss": 0.4728, | |
| "step": 180500 | |
| }, | |
| { | |
| "epoch": 25.11, | |
| "learning_rate": 0.00011595993712959619, | |
| "loss": 0.4724, | |
| "step": 181000 | |
| }, | |
| { | |
| "epoch": 25.11, | |
| "eval_loss": 0.4478763937950134, | |
| "eval_runtime": 1.2447, | |
| "eval_samples_per_second": 148.632, | |
| "eval_steps_per_second": 9.641, | |
| "step": 181000 | |
| }, | |
| { | |
| "epoch": 25.18, | |
| "learning_rate": 0.00011576193088899439, | |
| "loss": 0.4728, | |
| "step": 181500 | |
| }, | |
| { | |
| "epoch": 25.25, | |
| "learning_rate": 0.00011556313791328178, | |
| "loss": 0.4739, | |
| "step": 182000 | |
| }, | |
| { | |
| "epoch": 25.25, | |
| "eval_loss": 0.44296661019325256, | |
| "eval_runtime": 1.3308, | |
| "eval_samples_per_second": 139.009, | |
| "eval_steps_per_second": 9.017, | |
| "step": 182000 | |
| }, | |
| { | |
| "epoch": 25.32, | |
| "learning_rate": 0.00011536355803243809, | |
| "loss": 0.4723, | |
| "step": 182500 | |
| }, | |
| { | |
| "epoch": 25.39, | |
| "learning_rate": 0.00011516359142138949, | |
| "loss": 0.4723, | |
| "step": 183000 | |
| }, | |
| { | |
| "epoch": 25.39, | |
| "eval_loss": 0.44180306792259216, | |
| "eval_runtime": 1.3053, | |
| "eval_samples_per_second": 141.73, | |
| "eval_steps_per_second": 9.193, | |
| "step": 183000 | |
| }, | |
| { | |
| "epoch": 25.46, | |
| "learning_rate": 0.00011496324026693882, | |
| "loss": 0.472, | |
| "step": 183500 | |
| }, | |
| { | |
| "epoch": 25.53, | |
| "learning_rate": 0.0001147625067600942, | |
| "loss": 0.4724, | |
| "step": 184000 | |
| }, | |
| { | |
| "epoch": 25.53, | |
| "eval_loss": 0.4371403157711029, | |
| "eval_runtime": 1.3813, | |
| "eval_samples_per_second": 133.927, | |
| "eval_steps_per_second": 8.687, | |
| "step": 184000 | |
| }, | |
| { | |
| "epoch": 25.6, | |
| "learning_rate": 0.00011456139309604507, | |
| "loss": 0.4719, | |
| "step": 184500 | |
| }, | |
| { | |
| "epoch": 25.67, | |
| "learning_rate": 0.00011435990147413828, | |
| "loss": 0.472, | |
| "step": 185000 | |
| }, | |
| { | |
| "epoch": 25.67, | |
| "eval_loss": 0.4456477761268616, | |
| "eval_runtime": 1.3621, | |
| "eval_samples_per_second": 135.819, | |
| "eval_steps_per_second": 8.81, | |
| "step": 185000 | |
| }, | |
| { | |
| "epoch": 25.74, | |
| "learning_rate": 0.00011415803409785392, | |
| "loss": 0.472, | |
| "step": 185500 | |
| }, | |
| { | |
| "epoch": 25.81, | |
| "learning_rate": 0.00011395579317478123, | |
| "loss": 0.4726, | |
| "step": 186000 | |
| }, | |
| { | |
| "epoch": 25.81, | |
| "eval_loss": 0.4419301748275757, | |
| "eval_runtime": 1.3745, | |
| "eval_samples_per_second": 134.595, | |
| "eval_steps_per_second": 8.73, | |
| "step": 186000 | |
| }, | |
| { | |
| "epoch": 25.88, | |
| "learning_rate": 0.00011375318091659465, | |
| "loss": 0.4725, | |
| "step": 186500 | |
| }, | |
| { | |
| "epoch": 25.95, | |
| "learning_rate": 0.00011355019953902926, | |
| "loss": 0.4721, | |
| "step": 187000 | |
| }, | |
| { | |
| "epoch": 25.95, | |
| "eval_loss": 0.44172403216362, | |
| "eval_runtime": 1.2569, | |
| "eval_samples_per_second": 147.182, | |
| "eval_steps_per_second": 9.547, | |
| "step": 187000 | |
| }, | |
| { | |
| "epoch": 26.02, | |
| "learning_rate": 0.00011334685126185694, | |
| "loss": 0.4723, | |
| "step": 187500 | |
| }, | |
| { | |
| "epoch": 26.09, | |
| "learning_rate": 0.00011314313830886184, | |
| "loss": 0.4722, | |
| "step": 188000 | |
| }, | |
| { | |
| "epoch": 26.09, | |
| "eval_loss": 0.44749096035957336, | |
| "eval_runtime": 1.3409, | |
| "eval_samples_per_second": 137.963, | |
| "eval_steps_per_second": 8.949, | |
| "step": 188000 | |
| }, | |
| { | |
| "epoch": 26.16, | |
| "learning_rate": 0.0001129390629078162, | |
| "loss": 0.4714, | |
| "step": 188500 | |
| }, | |
| { | |
| "epoch": 26.22, | |
| "learning_rate": 0.00011273462729045592, | |
| "loss": 0.4715, | |
| "step": 189000 | |
| }, | |
| { | |
| "epoch": 26.22, | |
| "eval_loss": 0.43891334533691406, | |
| "eval_runtime": 1.3386, | |
| "eval_samples_per_second": 138.204, | |
| "eval_steps_per_second": 8.965, | |
| "step": 189000 | |
| }, | |
| { | |
| "epoch": 26.29, | |
| "learning_rate": 0.00011252983369245613, | |
| "loss": 0.4716, | |
| "step": 189500 | |
| }, | |
| { | |
| "epoch": 26.36, | |
| "learning_rate": 0.00011232468435340683, | |
| "loss": 0.4717, | |
| "step": 190000 | |
| }, | |
| { | |
| "epoch": 26.36, | |
| "eval_loss": 0.4450508654117584, | |
| "eval_runtime": 1.2763, | |
| "eval_samples_per_second": 144.955, | |
| "eval_steps_per_second": 9.402, | |
| "step": 190000 | |
| }, | |
| { | |
| "epoch": 26.43, | |
| "learning_rate": 0.00011211959287375901, | |
| "loss": 0.4713, | |
| "step": 190500 | |
| }, | |
| { | |
| "epoch": 26.5, | |
| "learning_rate": 0.00011191373948717242, | |
| "loss": 0.4716, | |
| "step": 191000 | |
| }, | |
| { | |
| "epoch": 26.5, | |
| "eval_loss": 0.4439684748649597, | |
| "eval_runtime": 1.3629, | |
| "eval_samples_per_second": 135.738, | |
| "eval_steps_per_second": 8.805, | |
| "step": 191000 | |
| }, | |
| { | |
| "epoch": 26.57, | |
| "learning_rate": 0.00011170753709704381, | |
| "loss": 0.471, | |
| "step": 191500 | |
| }, | |
| { | |
| "epoch": 26.64, | |
| "learning_rate": 0.00011150098795836949, | |
| "loss": 0.4714, | |
| "step": 192000 | |
| }, | |
| { | |
| "epoch": 26.64, | |
| "eval_loss": 0.43994638323783875, | |
| "eval_runtime": 1.2645, | |
| "eval_samples_per_second": 146.299, | |
| "eval_steps_per_second": 9.49, | |
| "step": 192000 | |
| }, | |
| { | |
| "epoch": 26.71, | |
| "learning_rate": 0.00011129409432993779, | |
| "loss": 0.4713, | |
| "step": 192500 | |
| }, | |
| { | |
| "epoch": 26.78, | |
| "learning_rate": 0.00011108685847430426, | |
| "loss": 0.4712, | |
| "step": 193000 | |
| }, | |
| { | |
| "epoch": 26.78, | |
| "eval_loss": 0.43981364369392395, | |
| "eval_runtime": 1.378, | |
| "eval_samples_per_second": 134.256, | |
| "eval_steps_per_second": 8.709, | |
| "step": 193000 | |
| }, | |
| { | |
| "epoch": 26.85, | |
| "learning_rate": 0.00011087969814717285, | |
| "loss": 0.472, | |
| "step": 193500 | |
| }, | |
| { | |
| "epoch": 26.92, | |
| "learning_rate": 0.0001106717853128616, | |
| "loss": 0.4709, | |
| "step": 194000 | |
| }, | |
| { | |
| "epoch": 26.92, | |
| "eval_loss": 0.4423602223396301, | |
| "eval_runtime": 1.4176, | |
| "eval_samples_per_second": 130.501, | |
| "eval_steps_per_second": 8.465, | |
| "step": 194000 | |
| }, | |
| { | |
| "epoch": 26.99, | |
| "learning_rate": 0.00011046353705682016, | |
| "loss": 0.4714, | |
| "step": 194500 | |
| }, | |
| { | |
| "epoch": 27.06, | |
| "learning_rate": 0.00011025495565641824, | |
| "loss": 0.4714, | |
| "step": 195000 | |
| }, | |
| { | |
| "epoch": 27.06, | |
| "eval_loss": 0.45326730608940125, | |
| "eval_runtime": 1.3206, | |
| "eval_samples_per_second": 140.087, | |
| "eval_steps_per_second": 9.087, | |
| "step": 195000 | |
| }, | |
| { | |
| "epoch": 27.13, | |
| "learning_rate": 0.00011004604339266847, | |
| "loss": 0.4713, | |
| "step": 195500 | |
| }, | |
| { | |
| "epoch": 27.2, | |
| "learning_rate": 0.00010983722135828816, | |
| "loss": 0.4706, | |
| "step": 196000 | |
| }, | |
| { | |
| "epoch": 27.2, | |
| "eval_loss": 0.43939587473869324, | |
| "eval_runtime": 1.3732, | |
| "eval_samples_per_second": 134.718, | |
| "eval_steps_per_second": 8.738, | |
| "step": 196000 | |
| }, | |
| { | |
| "epoch": 27.27, | |
| "learning_rate": 0.00010962765487562423, | |
| "loss": 0.471, | |
| "step": 196500 | |
| }, | |
| { | |
| "epoch": 27.33, | |
| "learning_rate": 0.00010941776438967333, | |
| "loss": 0.471, | |
| "step": 197000 | |
| }, | |
| { | |
| "epoch": 27.33, | |
| "eval_loss": 0.44356608390808105, | |
| "eval_runtime": 1.2936, | |
| "eval_samples_per_second": 143.016, | |
| "eval_steps_per_second": 9.277, | |
| "step": 197000 | |
| }, | |
| { | |
| "epoch": 27.4, | |
| "learning_rate": 0.00010920755219576423, | |
| "loss": 0.4709, | |
| "step": 197500 | |
| }, | |
| { | |
| "epoch": 27.47, | |
| "learning_rate": 0.0001089970205927438, | |
| "loss": 0.4707, | |
| "step": 198000 | |
| }, | |
| { | |
| "epoch": 27.47, | |
| "eval_loss": 0.442117840051651, | |
| "eval_runtime": 1.2666, | |
| "eval_samples_per_second": 146.059, | |
| "eval_steps_per_second": 9.474, | |
| "step": 198000 | |
| }, | |
| { | |
| "epoch": 27.54, | |
| "learning_rate": 0.00010878659389531198, | |
| "loss": 0.4707, | |
| "step": 198500 | |
| }, | |
| { | |
| "epoch": 27.61, | |
| "learning_rate": 0.0001085766989233304, | |
| "loss": 0.471, | |
| "step": 199000 | |
| }, | |
| { | |
| "epoch": 27.61, | |
| "eval_loss": 0.44586172699928284, | |
| "eval_runtime": 1.2641, | |
| "eval_samples_per_second": 146.347, | |
| "eval_steps_per_second": 9.493, | |
| "step": 199000 | |
| }, | |
| { | |
| "epoch": 27.68, | |
| "learning_rate": 0.00010836522541162288, | |
| "loss": 0.471, | |
| "step": 199500 | |
| }, | |
| { | |
| "epoch": 27.75, | |
| "learning_rate": 0.00010815344170235474, | |
| "loss": 0.4707, | |
| "step": 200000 | |
| }, | |
| { | |
| "epoch": 27.75, | |
| "eval_loss": 0.4438597857952118, | |
| "eval_runtime": 1.3122, | |
| "eval_samples_per_second": 140.987, | |
| "eval_steps_per_second": 9.145, | |
| "step": 200000 | |
| }, | |
| { | |
| "epoch": 27.82, | |
| "learning_rate": 0.00010794135011155871, | |
| "loss": 0.4713, | |
| "step": 200500 | |
| }, | |
| { | |
| "epoch": 27.89, | |
| "learning_rate": 0.00010772895295863448, | |
| "loss": 0.471, | |
| "step": 201000 | |
| }, | |
| { | |
| "epoch": 27.89, | |
| "eval_loss": 0.446729838848114, | |
| "eval_runtime": 1.2963, | |
| "eval_samples_per_second": 142.711, | |
| "eval_steps_per_second": 9.257, | |
| "step": 201000 | |
| }, | |
| { | |
| "epoch": 27.96, | |
| "learning_rate": 0.00010751625256632328, | |
| "loss": 0.4709, | |
| "step": 201500 | |
| }, | |
| { | |
| "epoch": 28.03, | |
| "learning_rate": 0.00010730325126068249, | |
| "loss": 0.471, | |
| "step": 202000 | |
| }, | |
| { | |
| "epoch": 28.03, | |
| "eval_loss": 0.4438862204551697, | |
| "eval_runtime": 1.3617, | |
| "eval_samples_per_second": 135.862, | |
| "eval_steps_per_second": 8.813, | |
| "step": 202000 | |
| }, | |
| { | |
| "epoch": 28.1, | |
| "learning_rate": 0.00010708995137106029, | |
| "loss": 0.4704, | |
| "step": 202500 | |
| }, | |
| { | |
| "epoch": 28.17, | |
| "learning_rate": 0.00010687635523007008, | |
| "loss": 0.4704, | |
| "step": 203000 | |
| }, | |
| { | |
| "epoch": 28.17, | |
| "eval_loss": 0.44452282786369324, | |
| "eval_runtime": 1.2694, | |
| "eval_samples_per_second": 145.738, | |
| "eval_steps_per_second": 9.453, | |
| "step": 203000 | |
| }, | |
| { | |
| "epoch": 28.24, | |
| "learning_rate": 0.00010666246517356506, | |
| "loss": 0.4701, | |
| "step": 203500 | |
| }, | |
| { | |
| "epoch": 28.31, | |
| "learning_rate": 0.00010644828354061256, | |
| "loss": 0.4705, | |
| "step": 204000 | |
| }, | |
| { | |
| "epoch": 28.31, | |
| "eval_loss": 0.44292566180229187, | |
| "eval_runtime": 1.3369, | |
| "eval_samples_per_second": 138.378, | |
| "eval_steps_per_second": 8.976, | |
| "step": 204000 | |
| }, | |
| { | |
| "epoch": 28.38, | |
| "learning_rate": 0.0001062338126734687, | |
| "loss": 0.4702, | |
| "step": 204500 | |
| }, | |
| { | |
| "epoch": 28.44, | |
| "learning_rate": 0.00010601905491755247, | |
| "loss": 0.4706, | |
| "step": 205000 | |
| }, | |
| { | |
| "epoch": 28.44, | |
| "eval_loss": 0.4382130801677704, | |
| "eval_runtime": 1.3584, | |
| "eval_samples_per_second": 136.194, | |
| "eval_steps_per_second": 8.834, | |
| "step": 205000 | |
| }, | |
| { | |
| "epoch": 28.51, | |
| "learning_rate": 0.00010580401262142026, | |
| "loss": 0.4703, | |
| "step": 205500 | |
| }, | |
| { | |
| "epoch": 28.58, | |
| "learning_rate": 0.00010558868813674022, | |
| "loss": 0.4703, | |
| "step": 206000 | |
| }, | |
| { | |
| "epoch": 28.58, | |
| "eval_loss": 0.44251275062561035, | |
| "eval_runtime": 1.3909, | |
| "eval_samples_per_second": 133.01, | |
| "eval_steps_per_second": 8.628, | |
| "step": 206000 | |
| }, | |
| { | |
| "epoch": 28.65, | |
| "learning_rate": 0.00010537308381826636, | |
| "loss": 0.4695, | |
| "step": 206500 | |
| }, | |
| { | |
| "epoch": 28.72, | |
| "learning_rate": 0.00010515763406275424, | |
| "loss": 0.4695, | |
| "step": 207000 | |
| }, | |
| { | |
| "epoch": 28.72, | |
| "eval_loss": 0.441448837518692, | |
| "eval_runtime": 1.299, | |
| "eval_samples_per_second": 142.42, | |
| "eval_steps_per_second": 9.238, | |
| "step": 207000 | |
| }, | |
| { | |
| "epoch": 28.79, | |
| "learning_rate": 0.00010494147770104224, | |
| "loss": 0.4697, | |
| "step": 207500 | |
| }, | |
| { | |
| "epoch": 28.86, | |
| "learning_rate": 0.00010472504858332604, | |
| "loss": 0.4696, | |
| "step": 208000 | |
| }, | |
| { | |
| "epoch": 28.86, | |
| "eval_loss": 0.4405233561992645, | |
| "eval_runtime": 1.3279, | |
| "eval_samples_per_second": 139.321, | |
| "eval_steps_per_second": 9.037, | |
| "step": 208000 | |
| }, | |
| { | |
| "epoch": 28.93, | |
| "learning_rate": 0.00010450834907643986, | |
| "loss": 0.4697, | |
| "step": 208500 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "learning_rate": 0.00010429138155017476, | |
| "loss": 0.4696, | |
| "step": 209000 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_loss": 0.4460256099700928, | |
| "eval_runtime": 1.1542, | |
| "eval_samples_per_second": 160.282, | |
| "eval_steps_per_second": 10.397, | |
| "step": 209000 | |
| }, | |
| { | |
| "epoch": 29.07, | |
| "learning_rate": 0.00010407414837725286, | |
| "loss": 0.4701, | |
| "step": 209500 | |
| }, | |
| { | |
| "epoch": 29.14, | |
| "learning_rate": 0.00010385665193330129, | |
| "loss": 0.4701, | |
| "step": 210000 | |
| }, | |
| { | |
| "epoch": 29.14, | |
| "eval_loss": 0.4460484981536865, | |
| "eval_runtime": 1.3974, | |
| "eval_samples_per_second": 132.39, | |
| "eval_steps_per_second": 8.587, | |
| "step": 210000 | |
| }, | |
| { | |
| "epoch": 29.21, | |
| "learning_rate": 0.00010363889459682637, | |
| "loss": 0.4694, | |
| "step": 210500 | |
| }, | |
| { | |
| "epoch": 29.28, | |
| "learning_rate": 0.00010342087874918744, | |
| "loss": 0.4696, | |
| "step": 211000 | |
| }, | |
| { | |
| "epoch": 29.28, | |
| "eval_loss": 0.4396804869174957, | |
| "eval_runtime": 1.3526, | |
| "eval_samples_per_second": 136.773, | |
| "eval_steps_per_second": 8.872, | |
| "step": 211000 | |
| }, | |
| { | |
| "epoch": 29.35, | |
| "learning_rate": 0.00010320260677457086, | |
| "loss": 0.4689, | |
| "step": 211500 | |
| }, | |
| { | |
| "epoch": 29.42, | |
| "learning_rate": 0.00010298451836303776, | |
| "loss": 0.4693, | |
| "step": 212000 | |
| }, | |
| { | |
| "epoch": 29.42, | |
| "eval_loss": 0.4438728988170624, | |
| "eval_runtime": 1.3437, | |
| "eval_samples_per_second": 137.675, | |
| "eval_steps_per_second": 8.93, | |
| "step": 212000 | |
| }, | |
| { | |
| "epoch": 29.49, | |
| "learning_rate": 0.00010276574179851642, | |
| "loss": 0.4695, | |
| "step": 212500 | |
| }, | |
| { | |
| "epoch": 29.55, | |
| "learning_rate": 0.00010254671627149016, | |
| "loss": 0.4694, | |
| "step": 213000 | |
| }, | |
| { | |
| "epoch": 29.55, | |
| "eval_loss": 0.4494737684726715, | |
| "eval_runtime": 1.3148, | |
| "eval_samples_per_second": 140.708, | |
| "eval_steps_per_second": 9.127, | |
| "step": 213000 | |
| }, | |
| { | |
| "epoch": 29.62, | |
| "learning_rate": 0.00010232744417718707, | |
| "loss": 0.4692, | |
| "step": 213500 | |
| }, | |
| { | |
| "epoch": 29.69, | |
| "learning_rate": 0.00010210792791353163, | |
| "loss": 0.469, | |
| "step": 214000 | |
| }, | |
| { | |
| "epoch": 29.69, | |
| "eval_loss": 0.44658780097961426, | |
| "eval_runtime": 1.3457, | |
| "eval_samples_per_second": 137.477, | |
| "eval_steps_per_second": 8.917, | |
| "step": 214000 | |
| }, | |
| { | |
| "epoch": 29.76, | |
| "learning_rate": 0.00010188816988111854, | |
| "loss": 0.4693, | |
| "step": 214500 | |
| }, | |
| { | |
| "epoch": 29.83, | |
| "learning_rate": 0.0001016681724831864, | |
| "loss": 0.4691, | |
| "step": 215000 | |
| }, | |
| { | |
| "epoch": 29.83, | |
| "eval_loss": 0.43355101346969604, | |
| "eval_runtime": 1.4163, | |
| "eval_samples_per_second": 130.619, | |
| "eval_steps_per_second": 8.473, | |
| "step": 215000 | |
| }, | |
| { | |
| "epoch": 29.9, | |
| "learning_rate": 0.00010144793812559155, | |
| "loss": 0.4691, | |
| "step": 215500 | |
| }, | |
| { | |
| "epoch": 29.97, | |
| "learning_rate": 0.00010122791038707925, | |
| "loss": 0.4694, | |
| "step": 216000 | |
| }, | |
| { | |
| "epoch": 29.97, | |
| "eval_loss": 0.4376647174358368, | |
| "eval_runtime": 1.269, | |
| "eval_samples_per_second": 145.78, | |
| "eval_steps_per_second": 9.456, | |
| "step": 216000 | |
| }, | |
| { | |
| "epoch": 30.04, | |
| "learning_rate": 0.00010100765143119065, | |
| "loss": 0.4696, | |
| "step": 216500 | |
| }, | |
| { | |
| "epoch": 30.11, | |
| "learning_rate": 0.00010078804782907829, | |
| "loss": 0.4698, | |
| "step": 217000 | |
| }, | |
| { | |
| "epoch": 30.11, | |
| "eval_loss": 0.43560221791267395, | |
| "eval_runtime": 1.4174, | |
| "eval_samples_per_second": 130.525, | |
| "eval_steps_per_second": 8.467, | |
| "step": 217000 | |
| }, | |
| { | |
| "epoch": 30.18, | |
| "learning_rate": 0.00010056689200396548, | |
| "loss": 0.4685, | |
| "step": 217500 | |
| }, | |
| { | |
| "epoch": 30.25, | |
| "learning_rate": 0.00010034551126261683, | |
| "loss": 0.4689, | |
| "step": 218000 | |
| }, | |
| { | |
| "epoch": 30.25, | |
| "eval_loss": 0.43806299567222595, | |
| "eval_runtime": 1.3648, | |
| "eval_samples_per_second": 135.548, | |
| "eval_steps_per_second": 8.792, | |
| "step": 218000 | |
| }, | |
| { | |
| "epoch": 30.32, | |
| "learning_rate": 0.00010012390802601666, | |
| "loss": 0.4685, | |
| "step": 218500 | |
| }, | |
| { | |
| "epoch": 30.39, | |
| "learning_rate": 9.990208471758243e-05, | |
| "loss": 0.4685, | |
| "step": 219000 | |
| }, | |
| { | |
| "epoch": 30.39, | |
| "eval_loss": 0.44310352206230164, | |
| "eval_runtime": 1.2698, | |
| "eval_samples_per_second": 145.698, | |
| "eval_steps_per_second": 9.451, | |
| "step": 219000 | |
| }, | |
| { | |
| "epoch": 30.46, | |
| "learning_rate": 9.968004376313833e-05, | |
| "loss": 0.469, | |
| "step": 219500 | |
| }, | |
| { | |
| "epoch": 30.53, | |
| "learning_rate": 9.945778759088867e-05, | |
| "loss": 0.4688, | |
| "step": 220000 | |
| }, | |
| { | |
| "epoch": 30.53, | |
| "eval_loss": 0.4411117434501648, | |
| "eval_runtime": 1.4619, | |
| "eval_samples_per_second": 126.55, | |
| "eval_steps_per_second": 8.209, | |
| "step": 220000 | |
| }, | |
| { | |
| "epoch": 30.6, | |
| "learning_rate": 9.923531863139129e-05, | |
| "loss": 0.4687, | |
| "step": 220500 | |
| }, | |
| { | |
| "epoch": 30.66, | |
| "learning_rate": 9.901263931753117e-05, | |
| "loss": 0.4687, | |
| "step": 221000 | |
| }, | |
| { | |
| "epoch": 30.66, | |
| "eval_loss": 0.444545179605484, | |
| "eval_runtime": 1.4274, | |
| "eval_samples_per_second": 129.604, | |
| "eval_steps_per_second": 8.407, | |
| "step": 221000 | |
| }, | |
| { | |
| "epoch": 30.73, | |
| "learning_rate": 9.878975208449357e-05, | |
| "loss": 0.4686, | |
| "step": 221500 | |
| }, | |
| { | |
| "epoch": 30.8, | |
| "learning_rate": 9.856665936973753e-05, | |
| "loss": 0.4685, | |
| "step": 222000 | |
| }, | |
| { | |
| "epoch": 30.8, | |
| "eval_loss": 0.44319838285446167, | |
| "eval_runtime": 1.625, | |
| "eval_samples_per_second": 113.845, | |
| "eval_steps_per_second": 7.385, | |
| "step": 222000 | |
| }, | |
| { | |
| "epoch": 30.87, | |
| "learning_rate": 9.834336361296929e-05, | |
| "loss": 0.4682, | |
| "step": 222500 | |
| }, | |
| { | |
| "epoch": 30.94, | |
| "learning_rate": 9.811986725611542e-05, | |
| "loss": 0.4687, | |
| "step": 223000 | |
| }, | |
| { | |
| "epoch": 30.94, | |
| "eval_loss": 0.43832239508628845, | |
| "eval_runtime": 1.4789, | |
| "eval_samples_per_second": 125.09, | |
| "eval_steps_per_second": 8.114, | |
| "step": 223000 | |
| }, | |
| { | |
| "epoch": 31.01, | |
| "learning_rate": 9.789617274329632e-05, | |
| "loss": 0.4685, | |
| "step": 223500 | |
| }, | |
| { | |
| "epoch": 31.08, | |
| "learning_rate": 9.76722825207993e-05, | |
| "loss": 0.4681, | |
| "step": 224000 | |
| }, | |
| { | |
| "epoch": 31.08, | |
| "eval_loss": 0.4371243119239807, | |
| "eval_runtime": 1.2937, | |
| "eval_samples_per_second": 142.997, | |
| "eval_steps_per_second": 9.275, | |
| "step": 224000 | |
| }, | |
| { | |
| "epoch": 31.15, | |
| "learning_rate": 9.7448199037052e-05, | |
| "loss": 0.468, | |
| "step": 224500 | |
| }, | |
| { | |
| "epoch": 31.22, | |
| "learning_rate": 9.722392474259546e-05, | |
| "loss": 0.4683, | |
| "step": 225000 | |
| }, | |
| { | |
| "epoch": 31.22, | |
| "eval_loss": 0.4383920133113861, | |
| "eval_runtime": 1.3579, | |
| "eval_samples_per_second": 136.242, | |
| "eval_steps_per_second": 8.837, | |
| "step": 225000 | |
| }, | |
| { | |
| "epoch": 31.29, | |
| "learning_rate": 9.699946209005747e-05, | |
| "loss": 0.4681, | |
| "step": 225500 | |
| }, | |
| { | |
| "epoch": 31.36, | |
| "learning_rate": 9.677481353412562e-05, | |
| "loss": 0.4678, | |
| "step": 226000 | |
| }, | |
| { | |
| "epoch": 31.36, | |
| "eval_loss": 0.4395655393600464, | |
| "eval_runtime": 1.4128, | |
| "eval_samples_per_second": 130.944, | |
| "eval_steps_per_second": 8.494, | |
| "step": 226000 | |
| }, | |
| { | |
| "epoch": 31.43, | |
| "learning_rate": 9.65504313769716e-05, | |
| "loss": 0.4681, | |
| "step": 226500 | |
| }, | |
| { | |
| "epoch": 31.5, | |
| "learning_rate": 9.632541874594076e-05, | |
| "loss": 0.4682, | |
| "step": 227000 | |
| }, | |
| { | |
| "epoch": 31.5, | |
| "eval_loss": 0.4387070834636688, | |
| "eval_runtime": 1.3852, | |
| "eval_samples_per_second": 133.557, | |
| "eval_steps_per_second": 8.663, | |
| "step": 227000 | |
| }, | |
| { | |
| "epoch": 31.57, | |
| "learning_rate": 9.610022758274608e-05, | |
| "loss": 0.4678, | |
| "step": 227500 | |
| }, | |
| { | |
| "epoch": 31.64, | |
| "learning_rate": 9.587486035004206e-05, | |
| "loss": 0.4671, | |
| "step": 228000 | |
| }, | |
| { | |
| "epoch": 31.64, | |
| "eval_loss": 0.43819934129714966, | |
| "eval_runtime": 1.4407, | |
| "eval_samples_per_second": 128.406, | |
| "eval_steps_per_second": 8.329, | |
| "step": 228000 | |
| }, | |
| { | |
| "epoch": 31.71, | |
| "learning_rate": 9.564931951240863e-05, | |
| "loss": 0.4677, | |
| "step": 228500 | |
| }, | |
| { | |
| "epoch": 31.77, | |
| "learning_rate": 9.542405912943224e-05, | |
| "loss": 0.4676, | |
| "step": 229000 | |
| }, | |
| { | |
| "epoch": 31.77, | |
| "eval_loss": 0.44104936718940735, | |
| "eval_runtime": 1.2764, | |
| "eval_samples_per_second": 144.942, | |
| "eval_steps_per_second": 9.402, | |
| "step": 229000 | |
| }, | |
| { | |
| "epoch": 31.84, | |
| "learning_rate": 9.519817881812249e-05, | |
| "loss": 0.4679, | |
| "step": 229500 | |
| }, | |
| { | |
| "epoch": 31.91, | |
| "learning_rate": 9.497213230196413e-05, | |
| "loss": 0.4681, | |
| "step": 230000 | |
| }, | |
| { | |
| "epoch": 31.91, | |
| "eval_loss": 0.4391230046749115, | |
| "eval_runtime": 1.302, | |
| "eval_samples_per_second": 142.084, | |
| "eval_steps_per_second": 9.216, | |
| "step": 230000 | |
| }, | |
| { | |
| "epoch": 31.98, | |
| "learning_rate": 9.474592205296567e-05, | |
| "loss": 0.4674, | |
| "step": 230500 | |
| }, | |
| { | |
| "epoch": 32.05, | |
| "learning_rate": 9.451955054492613e-05, | |
| "loss": 0.4676, | |
| "step": 231000 | |
| }, | |
| { | |
| "epoch": 32.05, | |
| "eval_loss": 0.4428912103176117, | |
| "eval_runtime": 1.3006, | |
| "eval_samples_per_second": 142.245, | |
| "eval_steps_per_second": 9.227, | |
| "step": 231000 | |
| }, | |
| { | |
| "epoch": 32.12, | |
| "learning_rate": 9.429347347081072e-05, | |
| "loss": 0.468, | |
| "step": 231500 | |
| }, | |
| { | |
| "epoch": 32.19, | |
| "learning_rate": 9.406678718325199e-05, | |
| "loss": 0.4673, | |
| "step": 232000 | |
| }, | |
| { | |
| "epoch": 32.19, | |
| "eval_loss": 0.43948763608932495, | |
| "eval_runtime": 1.3886, | |
| "eval_samples_per_second": 133.23, | |
| "eval_steps_per_second": 8.642, | |
| "step": 232000 | |
| }, | |
| { | |
| "epoch": 32.26, | |
| "learning_rate": 9.383994706356235e-05, | |
| "loss": 0.4671, | |
| "step": 232500 | |
| }, | |
| { | |
| "epoch": 32.33, | |
| "learning_rate": 9.361295559242895e-05, | |
| "loss": 0.4669, | |
| "step": 233000 | |
| }, | |
| { | |
| "epoch": 32.33, | |
| "eval_loss": 0.4389004409313202, | |
| "eval_runtime": 1.4112, | |
| "eval_samples_per_second": 131.092, | |
| "eval_steps_per_second": 8.503, | |
| "step": 233000 | |
| }, | |
| { | |
| "epoch": 32.4, | |
| "learning_rate": 9.338581525219419e-05, | |
| "loss": 0.4674, | |
| "step": 233500 | |
| }, | |
| { | |
| "epoch": 32.47, | |
| "learning_rate": 9.315852852682843e-05, | |
| "loss": 0.4675, | |
| "step": 234000 | |
| }, | |
| { | |
| "epoch": 32.47, | |
| "eval_loss": 0.445227712392807, | |
| "eval_runtime": 1.2657, | |
| "eval_samples_per_second": 146.167, | |
| "eval_steps_per_second": 9.481, | |
| "step": 234000 | |
| }, | |
| { | |
| "epoch": 32.54, | |
| "learning_rate": 9.293109790190286e-05, | |
| "loss": 0.467, | |
| "step": 234500 | |
| }, | |
| { | |
| "epoch": 32.61, | |
| "learning_rate": 9.270352586456241e-05, | |
| "loss": 0.4667, | |
| "step": 235000 | |
| }, | |
| { | |
| "epoch": 32.61, | |
| "eval_loss": 0.4395338296890259, | |
| "eval_runtime": 1.3986, | |
| "eval_samples_per_second": 132.275, | |
| "eval_steps_per_second": 8.58, | |
| "step": 235000 | |
| }, | |
| { | |
| "epoch": 32.68, | |
| "learning_rate": 9.247627046241149e-05, | |
| "loss": 0.4667, | |
| "step": 235500 | |
| }, | |
| { | |
| "epoch": 32.75, | |
| "learning_rate": 9.224842333821526e-05, | |
| "loss": 0.4667, | |
| "step": 236000 | |
| }, | |
| { | |
| "epoch": 32.75, | |
| "eval_loss": 0.44597160816192627, | |
| "eval_runtime": 1.3803, | |
| "eval_samples_per_second": 134.024, | |
| "eval_steps_per_second": 8.693, | |
| "step": 236000 | |
| }, | |
| { | |
| "epoch": 32.82, | |
| "learning_rate": 9.202044226722378e-05, | |
| "loss": 0.467, | |
| "step": 236500 | |
| }, | |
| { | |
| "epoch": 32.88, | |
| "learning_rate": 9.179232974260151e-05, | |
| "loss": 0.4672, | |
| "step": 237000 | |
| }, | |
| { | |
| "epoch": 32.88, | |
| "eval_loss": 0.4403511583805084, | |
| "eval_runtime": 1.285, | |
| "eval_samples_per_second": 143.964, | |
| "eval_steps_per_second": 9.338, | |
| "step": 237000 | |
| }, | |
| { | |
| "epoch": 32.95, | |
| "learning_rate": 9.156454486896012e-05, | |
| "loss": 0.4672, | |
| "step": 237500 | |
| }, | |
| { | |
| "epoch": 33.02, | |
| "learning_rate": 9.133617717272672e-05, | |
| "loss": 0.4667, | |
| "step": 238000 | |
| }, | |
| { | |
| "epoch": 33.02, | |
| "eval_loss": 0.43722978234291077, | |
| "eval_runtime": 1.3529, | |
| "eval_samples_per_second": 136.739, | |
| "eval_steps_per_second": 8.87, | |
| "step": 238000 | |
| }, | |
| { | |
| "epoch": 33.09, | |
| "learning_rate": 9.110768550587597e-05, | |
| "loss": 0.4663, | |
| "step": 238500 | |
| }, | |
| { | |
| "epoch": 33.16, | |
| "learning_rate": 9.087907236715611e-05, | |
| "loss": 0.4663, | |
| "step": 239000 | |
| }, | |
| { | |
| "epoch": 33.16, | |
| "eval_loss": 0.43622609972953796, | |
| "eval_runtime": 1.5302, | |
| "eval_samples_per_second": 120.902, | |
| "eval_steps_per_second": 7.842, | |
| "step": 239000 | |
| }, | |
| { | |
| "epoch": 33.23, | |
| "learning_rate": 9.065034025664387e-05, | |
| "loss": 0.4665, | |
| "step": 239500 | |
| }, | |
| { | |
| "epoch": 33.3, | |
| "learning_rate": 9.042194948745301e-05, | |
| "loss": 0.4669, | |
| "step": 240000 | |
| }, | |
| { | |
| "epoch": 33.3, | |
| "eval_loss": 0.4427553713321686, | |
| "eval_runtime": 1.9547, | |
| "eval_samples_per_second": 94.644, | |
| "eval_steps_per_second": 6.139, | |
| "step": 240000 | |
| }, | |
| { | |
| "epoch": 33.37, | |
| "learning_rate": 9.019298716419978e-05, | |
| "loss": 0.4669, | |
| "step": 240500 | |
| }, | |
| { | |
| "epoch": 33.44, | |
| "learning_rate": 8.996391337207199e-05, | |
| "loss": 0.4662, | |
| "step": 241000 | |
| }, | |
| { | |
| "epoch": 33.44, | |
| "eval_loss": 0.43700045347213745, | |
| "eval_runtime": 1.4983, | |
| "eval_samples_per_second": 123.472, | |
| "eval_steps_per_second": 8.009, | |
| "step": 241000 | |
| }, | |
| { | |
| "epoch": 33.51, | |
| "learning_rate": 8.973473061618393e-05, | |
| "loss": 0.467, | |
| "step": 241500 | |
| }, | |
| { | |
| "epoch": 33.58, | |
| "learning_rate": 8.950635876843523e-05, | |
| "loss": 0.4662, | |
| "step": 242000 | |
| }, | |
| { | |
| "epoch": 33.58, | |
| "eval_loss": 0.43820101022720337, | |
| "eval_runtime": 1.8161, | |
| "eval_samples_per_second": 101.864, | |
| "eval_steps_per_second": 6.607, | |
| "step": 242000 | |
| }, | |
| { | |
| "epoch": 33.65, | |
| "learning_rate": 8.927696601591206e-05, | |
| "loss": 0.4661, | |
| "step": 242500 | |
| }, | |
| { | |
| "epoch": 33.72, | |
| "learning_rate": 8.904747181197483e-05, | |
| "loss": 0.466, | |
| "step": 243000 | |
| }, | |
| { | |
| "epoch": 33.72, | |
| "eval_loss": 0.439488023519516, | |
| "eval_runtime": 1.9649, | |
| "eval_samples_per_second": 94.152, | |
| "eval_steps_per_second": 6.107, | |
| "step": 243000 | |
| }, | |
| { | |
| "epoch": 33.79, | |
| "learning_rate": 8.881787866633541e-05, | |
| "loss": 0.4663, | |
| "step": 243500 | |
| }, | |
| { | |
| "epoch": 33.86, | |
| "learning_rate": 8.858818908978764e-05, | |
| "loss": 0.4661, | |
| "step": 244000 | |
| }, | |
| { | |
| "epoch": 33.86, | |
| "eval_loss": 0.4417674243450165, | |
| "eval_runtime": 1.9528, | |
| "eval_samples_per_second": 94.735, | |
| "eval_steps_per_second": 6.145, | |
| "step": 244000 | |
| }, | |
| { | |
| "epoch": 33.93, | |
| "learning_rate": 8.835840559417993e-05, | |
| "loss": 0.4658, | |
| "step": 244500 | |
| }, | |
| { | |
| "epoch": 33.99, | |
| "learning_rate": 8.812853069238779e-05, | |
| "loss": 0.4663, | |
| "step": 245000 | |
| }, | |
| { | |
| "epoch": 33.99, | |
| "eval_loss": 0.4406869411468506, | |
| "eval_runtime": 1.9749, | |
| "eval_samples_per_second": 93.675, | |
| "eval_steps_per_second": 6.076, | |
| "step": 245000 | |
| }, | |
| { | |
| "epoch": 34.06, | |
| "learning_rate": 8.78985668982863e-05, | |
| "loss": 0.4664, | |
| "step": 245500 | |
| }, | |
| { | |
| "epoch": 34.13, | |
| "learning_rate": 8.766851672672264e-05, | |
| "loss": 0.4661, | |
| "step": 246000 | |
| }, | |
| { | |
| "epoch": 34.13, | |
| "eval_loss": 0.4346267282962799, | |
| "eval_runtime": 1.3563, | |
| "eval_samples_per_second": 136.397, | |
| "eval_steps_per_second": 8.847, | |
| "step": 246000 | |
| }, | |
| { | |
| "epoch": 34.2, | |
| "learning_rate": 8.743838269348869e-05, | |
| "loss": 0.4657, | |
| "step": 246500 | |
| }, | |
| { | |
| "epoch": 34.27, | |
| "learning_rate": 8.720816731529334e-05, | |
| "loss": 0.4652, | |
| "step": 247000 | |
| }, | |
| { | |
| "epoch": 34.27, | |
| "eval_loss": 0.4391646981239319, | |
| "eval_runtime": 1.4449, | |
| "eval_samples_per_second": 128.041, | |
| "eval_steps_per_second": 8.305, | |
| "step": 247000 | |
| }, | |
| { | |
| "epoch": 34.34, | |
| "learning_rate": 8.697787310973507e-05, | |
| "loss": 0.4651, | |
| "step": 247500 | |
| }, | |
| { | |
| "epoch": 34.41, | |
| "learning_rate": 8.674750259527444e-05, | |
| "loss": 0.4662, | |
| "step": 248000 | |
| }, | |
| { | |
| "epoch": 34.41, | |
| "eval_loss": 0.4395732879638672, | |
| "eval_runtime": 1.2788, | |
| "eval_samples_per_second": 144.666, | |
| "eval_steps_per_second": 9.384, | |
| "step": 248000 | |
| }, | |
| { | |
| "epoch": 34.48, | |
| "learning_rate": 8.651798021207188e-05, | |
| "loss": 0.4663, | |
| "step": 248500 | |
| }, | |
| { | |
| "epoch": 34.55, | |
| "learning_rate": 8.628746491855551e-05, | |
| "loss": 0.4655, | |
| "step": 249000 | |
| }, | |
| { | |
| "epoch": 34.55, | |
| "eval_loss": 0.4426644742488861, | |
| "eval_runtime": 1.3113, | |
| "eval_samples_per_second": 141.076, | |
| "eval_steps_per_second": 9.151, | |
| "step": 249000 | |
| }, | |
| { | |
| "epoch": 34.62, | |
| "learning_rate": 8.60568808663301e-05, | |
| "loss": 0.4651, | |
| "step": 249500 | |
| }, | |
| { | |
| "epoch": 34.69, | |
| "learning_rate": 8.582623057702597e-05, | |
| "loss": 0.4657, | |
| "step": 250000 | |
| }, | |
| { | |
| "epoch": 34.69, | |
| "eval_loss": 0.44838571548461914, | |
| "eval_runtime": 1.312, | |
| "eval_samples_per_second": 141.003, | |
| "eval_steps_per_second": 9.146, | |
| "step": 250000 | |
| }, | |
| { | |
| "epoch": 34.76, | |
| "learning_rate": 8.559551657299767e-05, | |
| "loss": 0.4662, | |
| "step": 250500 | |
| }, | |
| { | |
| "epoch": 34.83, | |
| "learning_rate": 8.536520298707998e-05, | |
| "loss": 0.4654, | |
| "step": 251000 | |
| }, | |
| { | |
| "epoch": 34.83, | |
| "eval_loss": 0.42675724625587463, | |
| "eval_runtime": 1.3077, | |
| "eval_samples_per_second": 141.473, | |
| "eval_steps_per_second": 9.177, | |
| "step": 251000 | |
| }, | |
| { | |
| "epoch": 34.9, | |
| "learning_rate": 8.513436923824351e-05, | |
| "loss": 0.4649, | |
| "step": 251500 | |
| }, | |
| { | |
| "epoch": 34.97, | |
| "learning_rate": 8.490347934076768e-05, | |
| "loss": 0.4655, | |
| "step": 252000 | |
| }, | |
| { | |
| "epoch": 34.97, | |
| "eval_loss": 0.4383569657802582, | |
| "eval_runtime": 1.5065, | |
| "eval_samples_per_second": 122.799, | |
| "eval_steps_per_second": 7.965, | |
| "step": 252000 | |
| }, | |
| { | |
| "epoch": 35.04, | |
| "learning_rate": 8.467253581962737e-05, | |
| "loss": 0.4657, | |
| "step": 252500 | |
| }, | |
| { | |
| "epoch": 35.1, | |
| "learning_rate": 8.444154120038393e-05, | |
| "loss": 0.4649, | |
| "step": 253000 | |
| }, | |
| { | |
| "epoch": 35.1, | |
| "eval_loss": 0.43828797340393066, | |
| "eval_runtime": 1.4173, | |
| "eval_samples_per_second": 130.53, | |
| "eval_steps_per_second": 8.467, | |
| "step": 253000 | |
| }, | |
| { | |
| "epoch": 35.17, | |
| "learning_rate": 8.421049800915756e-05, | |
| "loss": 0.4653, | |
| "step": 253500 | |
| }, | |
| { | |
| "epoch": 35.24, | |
| "learning_rate": 8.397940877259951e-05, | |
| "loss": 0.465, | |
| "step": 254000 | |
| }, | |
| { | |
| "epoch": 35.24, | |
| "eval_loss": 0.4367583394050598, | |
| "eval_runtime": 1.4298, | |
| "eval_samples_per_second": 129.389, | |
| "eval_steps_per_second": 8.393, | |
| "step": 254000 | |
| }, | |
| { | |
| "epoch": 35.31, | |
| "learning_rate": 8.374827601786469e-05, | |
| "loss": 0.4646, | |
| "step": 254500 | |
| }, | |
| { | |
| "epoch": 35.38, | |
| "learning_rate": 8.351802704586772e-05, | |
| "loss": 0.4648, | |
| "step": 255000 | |
| }, | |
| { | |
| "epoch": 35.38, | |
| "eval_loss": 0.4326806664466858, | |
| "eval_runtime": 1.2828, | |
| "eval_samples_per_second": 144.22, | |
| "eval_steps_per_second": 9.355, | |
| "step": 255000 | |
| }, | |
| { | |
| "epoch": 35.45, | |
| "learning_rate": 8.328681498693332e-05, | |
| "loss": 0.4648, | |
| "step": 255500 | |
| }, | |
| { | |
| "epoch": 35.52, | |
| "learning_rate": 8.305556698391678e-05, | |
| "loss": 0.4647, | |
| "step": 256000 | |
| }, | |
| { | |
| "epoch": 35.52, | |
| "eval_loss": 0.44159042835235596, | |
| "eval_runtime": 1.4429, | |
| "eval_samples_per_second": 128.215, | |
| "eval_steps_per_second": 8.317, | |
| "step": 256000 | |
| }, | |
| { | |
| "epoch": 35.59, | |
| "learning_rate": 8.282428556570928e-05, | |
| "loss": 0.4643, | |
| "step": 256500 | |
| }, | |
| { | |
| "epoch": 35.66, | |
| "learning_rate": 8.25929732615673e-05, | |
| "loss": 0.4652, | |
| "step": 257000 | |
| }, | |
| { | |
| "epoch": 35.66, | |
| "eval_loss": 0.438982754945755, | |
| "eval_runtime": 1.333, | |
| "eval_samples_per_second": 138.783, | |
| "eval_steps_per_second": 9.002, | |
| "step": 257000 | |
| }, | |
| { | |
| "epoch": 35.73, | |
| "learning_rate": 8.236163260108516e-05, | |
| "loss": 0.4645, | |
| "step": 257500 | |
| }, | |
| { | |
| "epoch": 35.8, | |
| "learning_rate": 8.21302661141673e-05, | |
| "loss": 0.4646, | |
| "step": 258000 | |
| }, | |
| { | |
| "epoch": 35.8, | |
| "eval_loss": 0.4449821710586548, | |
| "eval_runtime": 1.5341, | |
| "eval_samples_per_second": 120.588, | |
| "eval_steps_per_second": 7.822, | |
| "step": 258000 | |
| }, | |
| { | |
| "epoch": 35.87, | |
| "learning_rate": 8.189887633100046e-05, | |
| "loss": 0.465, | |
| "step": 258500 | |
| }, | |
| { | |
| "epoch": 35.94, | |
| "learning_rate": 8.166746578202634e-05, | |
| "loss": 0.4651, | |
| "step": 259000 | |
| }, | |
| { | |
| "epoch": 35.94, | |
| "eval_loss": 0.4354371428489685, | |
| "eval_runtime": 1.3878, | |
| "eval_samples_per_second": 133.304, | |
| "eval_steps_per_second": 8.647, | |
| "step": 259000 | |
| }, | |
| { | |
| "epoch": 36.01, | |
| "learning_rate": 8.14364998719983e-05, | |
| "loss": 0.4652, | |
| "step": 259500 | |
| }, | |
| { | |
| "epoch": 36.08, | |
| "learning_rate": 8.120505541249758e-05, | |
| "loss": 0.4643, | |
| "step": 260000 | |
| }, | |
| { | |
| "epoch": 36.08, | |
| "eval_loss": 0.4472554922103882, | |
| "eval_runtime": 1.3524, | |
| "eval_samples_per_second": 136.792, | |
| "eval_steps_per_second": 8.873, | |
| "step": 260000 | |
| }, | |
| { | |
| "epoch": 36.15, | |
| "learning_rate": 8.097359777470398e-05, | |
| "loss": 0.4641, | |
| "step": 260500 | |
| }, | |
| { | |
| "epoch": 36.21, | |
| "learning_rate": 8.074259243531422e-05, | |
| "loss": 0.464, | |
| "step": 261000 | |
| }, | |
| { | |
| "epoch": 36.21, | |
| "eval_loss": 0.4422769844532013, | |
| "eval_runtime": 1.3389, | |
| "eval_samples_per_second": 138.17, | |
| "eval_steps_per_second": 8.962, | |
| "step": 261000 | |
| }, | |
| { | |
| "epoch": 36.28, | |
| "learning_rate": 8.051111604830743e-05, | |
| "loss": 0.4645, | |
| "step": 261500 | |
| }, | |
| { | |
| "epoch": 36.35, | |
| "learning_rate": 8.027963407181743e-05, | |
| "loss": 0.4638, | |
| "step": 262000 | |
| }, | |
| { | |
| "epoch": 36.35, | |
| "eval_loss": 0.4338819682598114, | |
| "eval_runtime": 1.6313, | |
| "eval_samples_per_second": 113.407, | |
| "eval_steps_per_second": 7.356, | |
| "step": 262000 | |
| }, | |
| { | |
| "epoch": 36.42, | |
| "learning_rate": 8.00486120087324e-05, | |
| "loss": 0.4648, | |
| "step": 262500 | |
| }, | |
| { | |
| "epoch": 36.49, | |
| "learning_rate": 7.98171264461855e-05, | |
| "loss": 0.464, | |
| "step": 263000 | |
| }, | |
| { | |
| "epoch": 36.49, | |
| "eval_loss": 0.44382044672966003, | |
| "eval_runtime": 1.7404, | |
| "eval_samples_per_second": 106.298, | |
| "eval_steps_per_second": 6.895, | |
| "step": 263000 | |
| }, | |
| { | |
| "epoch": 36.56, | |
| "learning_rate": 7.958564288351447e-05, | |
| "loss": 0.4637, | |
| "step": 263500 | |
| }, | |
| { | |
| "epoch": 36.63, | |
| "learning_rate": 7.935416385218652e-05, | |
| "loss": 0.464, | |
| "step": 264000 | |
| }, | |
| { | |
| "epoch": 36.63, | |
| "eval_loss": 0.43979740142822266, | |
| "eval_runtime": 1.747, | |
| "eval_samples_per_second": 105.895, | |
| "eval_steps_per_second": 6.869, | |
| "step": 264000 | |
| }, | |
| { | |
| "epoch": 36.7, | |
| "learning_rate": 7.912269188361918e-05, | |
| "loss": 0.4642, | |
| "step": 264500 | |
| }, | |
| { | |
| "epoch": 36.77, | |
| "learning_rate": 7.889122950915287e-05, | |
| "loss": 0.4637, | |
| "step": 265000 | |
| }, | |
| { | |
| "epoch": 36.77, | |
| "eval_loss": 0.43520936369895935, | |
| "eval_runtime": 1.77, | |
| "eval_samples_per_second": 104.517, | |
| "eval_steps_per_second": 6.779, | |
| "step": 265000 | |
| }, | |
| { | |
| "epoch": 36.84, | |
| "learning_rate": 7.865977926002297e-05, | |
| "loss": 0.4641, | |
| "step": 265500 | |
| }, | |
| { | |
| "epoch": 36.91, | |
| "learning_rate": 7.842834366733236e-05, | |
| "loss": 0.4641, | |
| "step": 266000 | |
| }, | |
| { | |
| "epoch": 36.91, | |
| "eval_loss": 0.4351678490638733, | |
| "eval_runtime": 1.7687, | |
| "eval_samples_per_second": 104.598, | |
| "eval_steps_per_second": 6.785, | |
| "step": 266000 | |
| }, | |
| { | |
| "epoch": 36.98, | |
| "learning_rate": 7.819738807999911e-05, | |
| "loss": 0.4633, | |
| "step": 266500 | |
| }, | |
| { | |
| "epoch": 37.05, | |
| "learning_rate": 7.796598935086499e-05, | |
| "loss": 0.4651, | |
| "step": 267000 | |
| }, | |
| { | |
| "epoch": 37.05, | |
| "eval_loss": 0.43237701058387756, | |
| "eval_runtime": 1.2775, | |
| "eval_samples_per_second": 144.818, | |
| "eval_steps_per_second": 9.394, | |
| "step": 267000 | |
| }, | |
| { | |
| "epoch": 37.12, | |
| "learning_rate": 7.773461286534548e-05, | |
| "loss": 0.4634, | |
| "step": 267500 | |
| }, | |
| { | |
| "epoch": 37.19, | |
| "learning_rate": 7.750326115373669e-05, | |
| "loss": 0.4637, | |
| "step": 268000 | |
| }, | |
| { | |
| "epoch": 37.19, | |
| "eval_loss": 0.43414822220802307, | |
| "eval_runtime": 1.2962, | |
| "eval_samples_per_second": 142.727, | |
| "eval_steps_per_second": 9.258, | |
| "step": 268000 | |
| }, | |
| { | |
| "epoch": 37.26, | |
| "learning_rate": 7.727193674606392e-05, | |
| "loss": 0.4631, | |
| "step": 268500 | |
| }, | |
| { | |
| "epoch": 37.32, | |
| "learning_rate": 7.704064217205385e-05, | |
| "loss": 0.4633, | |
| "step": 269000 | |
| }, | |
| { | |
| "epoch": 37.32, | |
| "eval_loss": 0.4331218898296356, | |
| "eval_runtime": 1.268, | |
| "eval_samples_per_second": 145.901, | |
| "eval_steps_per_second": 9.464, | |
| "step": 269000 | |
| }, | |
| { | |
| "epoch": 37.39, | |
| "learning_rate": 7.680937996110681e-05, | |
| "loss": 0.4628, | |
| "step": 269500 | |
| }, | |
| { | |
| "epoch": 37.46, | |
| "learning_rate": 7.657815264226939e-05, | |
| "loss": 0.4639, | |
| "step": 270000 | |
| }, | |
| { | |
| "epoch": 37.46, | |
| "eval_loss": 0.4391315281391144, | |
| "eval_runtime": 1.4376, | |
| "eval_samples_per_second": 128.688, | |
| "eval_steps_per_second": 8.347, | |
| "step": 270000 | |
| }, | |
| { | |
| "epoch": 37.53, | |
| "learning_rate": 7.634742508497605e-05, | |
| "loss": 0.4626, | |
| "step": 270500 | |
| }, | |
| { | |
| "epoch": 37.6, | |
| "learning_rate": 7.611627505352226e-05, | |
| "loss": 0.463, | |
| "step": 271000 | |
| }, | |
| { | |
| "epoch": 37.6, | |
| "eval_loss": 0.43801698088645935, | |
| "eval_runtime": 1.5521, | |
| "eval_samples_per_second": 119.193, | |
| "eval_steps_per_second": 7.731, | |
| "step": 271000 | |
| }, | |
| { | |
| "epoch": 37.67, | |
| "learning_rate": 7.588516749386228e-05, | |
| "loss": 0.4633, | |
| "step": 271500 | |
| }, | |
| { | |
| "epoch": 37.74, | |
| "learning_rate": 7.56541049333513e-05, | |
| "loss": 0.4635, | |
| "step": 272000 | |
| }, | |
| { | |
| "epoch": 37.74, | |
| "eval_loss": 0.43551453948020935, | |
| "eval_runtime": 1.5399, | |
| "eval_samples_per_second": 120.139, | |
| "eval_steps_per_second": 7.793, | |
| "step": 272000 | |
| }, | |
| { | |
| "epoch": 37.81, | |
| "learning_rate": 7.542308989885254e-05, | |
| "loss": 0.4628, | |
| "step": 272500 | |
| }, | |
| { | |
| "epoch": 37.88, | |
| "learning_rate": 7.51921249167093e-05, | |
| "loss": 0.4631, | |
| "step": 273000 | |
| }, | |
| { | |
| "epoch": 37.88, | |
| "eval_loss": 0.4397287368774414, | |
| "eval_runtime": 1.6946, | |
| "eval_samples_per_second": 109.168, | |
| "eval_steps_per_second": 7.081, | |
| "step": 273000 | |
| }, | |
| { | |
| "epoch": 37.95, | |
| "learning_rate": 7.496121251271771e-05, | |
| "loss": 0.4629, | |
| "step": 273500 | |
| }, | |
| { | |
| "epoch": 38.02, | |
| "learning_rate": 7.473035521209879e-05, | |
| "loss": 0.464, | |
| "step": 274000 | |
| }, | |
| { | |
| "epoch": 38.02, | |
| "eval_loss": 0.4335973262786865, | |
| "eval_runtime": 1.395, | |
| "eval_samples_per_second": 132.617, | |
| "eval_steps_per_second": 8.602, | |
| "step": 274000 | |
| }, | |
| { | |
| "epoch": 38.09, | |
| "learning_rate": 7.45000170796258e-05, | |
| "loss": 0.463, | |
| "step": 274500 | |
| }, | |
| { | |
| "epoch": 38.16, | |
| "learning_rate": 7.426927743615492e-05, | |
| "loss": 0.4629, | |
| "step": 275000 | |
| }, | |
| { | |
| "epoch": 38.16, | |
| "eval_loss": 0.4339427947998047, | |
| "eval_runtime": 1.2162, | |
| "eval_samples_per_second": 152.116, | |
| "eval_steps_per_second": 9.867, | |
| "step": 275000 | |
| }, | |
| { | |
| "epoch": 38.23, | |
| "learning_rate": 7.403860046294785e-05, | |
| "loss": 0.4628, | |
| "step": 275500 | |
| }, | |
| { | |
| "epoch": 38.3, | |
| "learning_rate": 7.380798868265099e-05, | |
| "loss": 0.4634, | |
| "step": 276000 | |
| }, | |
| { | |
| "epoch": 38.3, | |
| "eval_loss": 0.43547430634498596, | |
| "eval_runtime": 1.4273, | |
| "eval_samples_per_second": 129.617, | |
| "eval_steps_per_second": 8.408, | |
| "step": 276000 | |
| }, | |
| { | |
| "epoch": 38.37, | |
| "learning_rate": 7.357790563607352e-05, | |
| "loss": 0.4628, | |
| "step": 276500 | |
| }, | |
| { | |
| "epoch": 38.43, | |
| "learning_rate": 7.334743166366936e-05, | |
| "loss": 0.4632, | |
| "step": 277000 | |
| }, | |
| { | |
| "epoch": 38.43, | |
| "eval_loss": 0.43882909417152405, | |
| "eval_runtime": 1.4222, | |
| "eval_samples_per_second": 130.082, | |
| "eval_steps_per_second": 8.438, | |
| "step": 277000 | |
| }, | |
| { | |
| "epoch": 38.5, | |
| "learning_rate": 7.311703044268671e-05, | |
| "loss": 0.4622, | |
| "step": 277500 | |
| }, | |
| { | |
| "epoch": 38.57, | |
| "learning_rate": 7.28871650678614e-05, | |
| "loss": 0.4628, | |
| "step": 278000 | |
| }, | |
| { | |
| "epoch": 38.57, | |
| "eval_loss": 0.43408775329589844, | |
| "eval_runtime": 1.2936, | |
| "eval_samples_per_second": 143.016, | |
| "eval_steps_per_second": 9.277, | |
| "step": 278000 | |
| }, | |
| { | |
| "epoch": 38.64, | |
| "learning_rate": 7.265691674969816e-05, | |
| "loss": 0.4627, | |
| "step": 278500 | |
| }, | |
| { | |
| "epoch": 38.71, | |
| "learning_rate": 7.242674873431688e-05, | |
| "loss": 0.4621, | |
| "step": 279000 | |
| }, | |
| { | |
| "epoch": 38.71, | |
| "eval_loss": 0.433734267950058, | |
| "eval_runtime": 1.3622, | |
| "eval_samples_per_second": 135.812, | |
| "eval_steps_per_second": 8.809, | |
| "step": 279000 | |
| }, | |
| { | |
| "epoch": 38.78, | |
| "learning_rate": 7.21966635387981e-05, | |
| "loss": 0.4624, | |
| "step": 279500 | |
| }, | |
| { | |
| "epoch": 38.85, | |
| "learning_rate": 7.196712359219827e-05, | |
| "loss": 0.4626, | |
| "step": 280000 | |
| }, | |
| { | |
| "epoch": 38.85, | |
| "eval_loss": 0.43395352363586426, | |
| "eval_runtime": 1.294, | |
| "eval_samples_per_second": 142.964, | |
| "eval_steps_per_second": 9.273, | |
| "step": 280000 | |
| }, | |
| { | |
| "epoch": 38.92, | |
| "learning_rate": 7.173721140578366e-05, | |
| "loss": 0.4619, | |
| "step": 280500 | |
| }, | |
| { | |
| "epoch": 38.99, | |
| "learning_rate": 7.150738957990125e-05, | |
| "loss": 0.462, | |
| "step": 281000 | |
| }, | |
| { | |
| "epoch": 38.99, | |
| "eval_loss": 0.4305775463581085, | |
| "eval_runtime": 1.3687, | |
| "eval_samples_per_second": 135.162, | |
| "eval_steps_per_second": 8.767, | |
| "step": 281000 | |
| }, | |
| { | |
| "epoch": 39.06, | |
| "learning_rate": 7.127766062784582e-05, | |
| "loss": 0.4622, | |
| "step": 281500 | |
| }, | |
| { | |
| "epoch": 39.13, | |
| "learning_rate": 7.104940457387272e-05, | |
| "loss": 0.8286, | |
| "step": 282000 | |
| }, | |
| { | |
| "epoch": 39.13, | |
| "eval_loss": 0.45042213797569275, | |
| "eval_runtime": 1.3879, | |
| "eval_samples_per_second": 133.294, | |
| "eval_steps_per_second": 8.646, | |
| "step": 282000 | |
| }, | |
| { | |
| "epoch": 39.2, | |
| "learning_rate": 7.081986831039455e-05, | |
| "loss": 0.4675, | |
| "step": 282500 | |
| }, | |
| { | |
| "epoch": 39.27, | |
| "learning_rate": 7.059043243936574e-05, | |
| "loss": 0.4624, | |
| "step": 283000 | |
| }, | |
| { | |
| "epoch": 39.27, | |
| "eval_loss": 0.43986353278160095, | |
| "eval_runtime": 1.3047, | |
| "eval_samples_per_second": 141.79, | |
| "eval_steps_per_second": 9.197, | |
| "step": 283000 | |
| }, | |
| { | |
| "epoch": 39.34, | |
| "learning_rate": 7.036109946986026e-05, | |
| "loss": 0.4622, | |
| "step": 283500 | |
| }, | |
| { | |
| "epoch": 39.41, | |
| "learning_rate": 7.013187190982666e-05, | |
| "loss": 0.4621, | |
| "step": 284000 | |
| }, | |
| { | |
| "epoch": 39.41, | |
| "eval_loss": 0.4350989758968353, | |
| "eval_runtime": 1.3405, | |
| "eval_samples_per_second": 138.009, | |
| "eval_steps_per_second": 8.952, | |
| "step": 284000 | |
| }, | |
| { | |
| "epoch": 39.48, | |
| "learning_rate": 6.990275226606087e-05, | |
| "loss": 0.4625, | |
| "step": 284500 | |
| }, | |
| { | |
| "epoch": 39.54, | |
| "learning_rate": 6.967374304417855e-05, | |
| "loss": 0.4622, | |
| "step": 285000 | |
| }, | |
| { | |
| "epoch": 39.54, | |
| "eval_loss": 0.43041324615478516, | |
| "eval_runtime": 1.3052, | |
| "eval_samples_per_second": 141.744, | |
| "eval_steps_per_second": 9.194, | |
| "step": 285000 | |
| }, | |
| { | |
| "epoch": 39.61, | |
| "learning_rate": 6.944484674858791e-05, | |
| "loss": 0.4618, | |
| "step": 285500 | |
| }, | |
| { | |
| "epoch": 39.68, | |
| "learning_rate": 6.92160658824621e-05, | |
| "loss": 0.4619, | |
| "step": 286000 | |
| }, | |
| { | |
| "epoch": 39.68, | |
| "eval_loss": 0.4329047203063965, | |
| "eval_runtime": 1.3268, | |
| "eval_samples_per_second": 139.431, | |
| "eval_steps_per_second": 9.044, | |
| "step": 286000 | |
| }, | |
| { | |
| "epoch": 39.75, | |
| "learning_rate": 6.898740294771208e-05, | |
| "loss": 0.4609, | |
| "step": 286500 | |
| }, | |
| { | |
| "epoch": 39.82, | |
| "learning_rate": 6.875886044495907e-05, | |
| "loss": 0.4618, | |
| "step": 287000 | |
| }, | |
| { | |
| "epoch": 39.82, | |
| "eval_loss": 0.42083120346069336, | |
| "eval_runtime": 1.2649, | |
| "eval_samples_per_second": 146.251, | |
| "eval_steps_per_second": 9.487, | |
| "step": 287000 | |
| }, | |
| { | |
| "epoch": 39.89, | |
| "learning_rate": 6.853044087350723e-05, | |
| "loss": 0.4621, | |
| "step": 287500 | |
| }, | |
| { | |
| "epoch": 39.96, | |
| "learning_rate": 6.830214673131643e-05, | |
| "loss": 0.462, | |
| "step": 288000 | |
| }, | |
| { | |
| "epoch": 39.96, | |
| "eval_loss": 0.44138768315315247, | |
| "eval_runtime": 1.284, | |
| "eval_samples_per_second": 144.078, | |
| "eval_steps_per_second": 9.346, | |
| "step": 288000 | |
| }, | |
| { | |
| "epoch": 40.03, | |
| "learning_rate": 6.807398051497478e-05, | |
| "loss": 0.4619, | |
| "step": 288500 | |
| }, | |
| { | |
| "epoch": 40.1, | |
| "learning_rate": 6.784594471967154e-05, | |
| "loss": 0.4615, | |
| "step": 289000 | |
| }, | |
| { | |
| "epoch": 40.1, | |
| "eval_loss": 0.4353402256965637, | |
| "eval_runtime": 1.4649, | |
| "eval_samples_per_second": 126.285, | |
| "eval_steps_per_second": 8.191, | |
| "step": 289000 | |
| }, | |
| { | |
| "epoch": 40.17, | |
| "learning_rate": 6.761804183916954e-05, | |
| "loss": 0.4616, | |
| "step": 289500 | |
| }, | |
| { | |
| "epoch": 40.24, | |
| "learning_rate": 6.739027436577824e-05, | |
| "loss": 0.4614, | |
| "step": 290000 | |
| }, | |
| { | |
| "epoch": 40.24, | |
| "eval_loss": 0.4397503137588501, | |
| "eval_runtime": 1.241, | |
| "eval_samples_per_second": 149.068, | |
| "eval_steps_per_second": 9.669, | |
| "step": 290000 | |
| }, | |
| { | |
| "epoch": 40.31, | |
| "learning_rate": 6.716264479032627e-05, | |
| "loss": 0.4607, | |
| "step": 290500 | |
| }, | |
| { | |
| "epoch": 40.38, | |
| "learning_rate": 6.693515560213409e-05, | |
| "loss": 0.4611, | |
| "step": 291000 | |
| }, | |
| { | |
| "epoch": 40.38, | |
| "eval_loss": 0.4370949864387512, | |
| "eval_runtime": 1.355, | |
| "eval_samples_per_second": 136.534, | |
| "eval_steps_per_second": 8.856, | |
| "step": 291000 | |
| }, | |
| { | |
| "epoch": 40.45, | |
| "learning_rate": 6.670780928898711e-05, | |
| "loss": 0.4615, | |
| "step": 291500 | |
| }, | |
| { | |
| "epoch": 40.52, | |
| "learning_rate": 6.648106259228962e-05, | |
| "loss": 0.4608, | |
| "step": 292000 | |
| }, | |
| { | |
| "epoch": 40.52, | |
| "eval_loss": 0.4326191544532776, | |
| "eval_runtime": 1.3203, | |
| "eval_samples_per_second": 140.118, | |
| "eval_steps_per_second": 9.089, | |
| "step": 292000 | |
| }, | |
| { | |
| "epoch": 40.59, | |
| "learning_rate": 6.625400918814145e-05, | |
| "loss": 0.4604, | |
| "step": 292500 | |
| }, | |
| { | |
| "epoch": 40.65, | |
| "learning_rate": 6.602710610794654e-05, | |
| "loss": 0.4611, | |
| "step": 293000 | |
| }, | |
| { | |
| "epoch": 40.65, | |
| "eval_loss": 0.4331806004047394, | |
| "eval_runtime": 1.3174, | |
| "eval_samples_per_second": 140.426, | |
| "eval_steps_per_second": 9.109, | |
| "step": 293000 | |
| }, | |
| { | |
| "epoch": 40.72, | |
| "learning_rate": 6.580035583308054e-05, | |
| "loss": 0.4613, | |
| "step": 293500 | |
| }, | |
| { | |
| "epoch": 40.79, | |
| "learning_rate": 6.557376084324819e-05, | |
| "loss": 0.4614, | |
| "step": 294000 | |
| }, | |
| { | |
| "epoch": 40.79, | |
| "eval_loss": 0.4342820346355438, | |
| "eval_runtime": 1.384, | |
| "eval_samples_per_second": 133.668, | |
| "eval_steps_per_second": 8.67, | |
| "step": 294000 | |
| }, | |
| { | |
| "epoch": 40.86, | |
| "learning_rate": 6.534732361645596e-05, | |
| "loss": 0.4603, | |
| "step": 294500 | |
| }, | |
| { | |
| "epoch": 40.93, | |
| "learning_rate": 6.512149902139615e-05, | |
| "loss": 0.4609, | |
| "step": 295000 | |
| }, | |
| { | |
| "epoch": 40.93, | |
| "eval_loss": 0.43060681223869324, | |
| "eval_runtime": 1.4594, | |
| "eval_samples_per_second": 126.766, | |
| "eval_steps_per_second": 8.223, | |
| "step": 295000 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "learning_rate": 6.489538441987944e-05, | |
| "loss": 0.4618, | |
| "step": 295500 | |
| }, | |
| { | |
| "epoch": 41.07, | |
| "learning_rate": 6.466943500001871e-05, | |
| "loss": 0.4608, | |
| "step": 296000 | |
| }, | |
| { | |
| "epoch": 41.07, | |
| "eval_loss": 0.43232059478759766, | |
| "eval_runtime": 1.4238, | |
| "eval_samples_per_second": 129.937, | |
| "eval_steps_per_second": 8.428, | |
| "step": 296000 | |
| }, | |
| { | |
| "epoch": 41.14, | |
| "learning_rate": 6.444365323276068e-05, | |
| "loss": 0.4605, | |
| "step": 296500 | |
| }, | |
| { | |
| "epoch": 41.21, | |
| "learning_rate": 6.421804158721853e-05, | |
| "loss": 0.4608, | |
| "step": 297000 | |
| }, | |
| { | |
| "epoch": 41.21, | |
| "eval_loss": 0.43206915259361267, | |
| "eval_runtime": 1.493, | |
| "eval_samples_per_second": 123.915, | |
| "eval_steps_per_second": 8.038, | |
| "step": 297000 | |
| }, | |
| { | |
| "epoch": 41.28, | |
| "learning_rate": 6.399260253064511e-05, | |
| "loss": 0.4608, | |
| "step": 297500 | |
| }, | |
| { | |
| "epoch": 41.35, | |
| "learning_rate": 6.376733852840578e-05, | |
| "loss": 0.4601, | |
| "step": 298000 | |
| }, | |
| { | |
| "epoch": 41.35, | |
| "eval_loss": 0.43304702639579773, | |
| "eval_runtime": 1.3148, | |
| "eval_samples_per_second": 140.708, | |
| "eval_steps_per_second": 9.127, | |
| "step": 298000 | |
| }, | |
| { | |
| "epoch": 41.42, | |
| "learning_rate": 6.35422520439516e-05, | |
| "loss": 0.4599, | |
| "step": 298500 | |
| }, | |
| { | |
| "epoch": 41.49, | |
| "learning_rate": 6.331779517054821e-05, | |
| "loss": 0.4606, | |
| "step": 299000 | |
| }, | |
| { | |
| "epoch": 41.49, | |
| "eval_loss": 0.43612292408943176, | |
| "eval_runtime": 1.4452, | |
| "eval_samples_per_second": 128.012, | |
| "eval_steps_per_second": 8.304, | |
| "step": 299000 | |
| }, | |
| { | |
| "epoch": 41.56, | |
| "learning_rate": 6.309396926796281e-05, | |
| "loss": 0.4599, | |
| "step": 299500 | |
| }, | |
| { | |
| "epoch": 41.63, | |
| "learning_rate": 6.286942898131997e-05, | |
| "loss": 0.4606, | |
| "step": 300000 | |
| }, | |
| { | |
| "epoch": 41.63, | |
| "eval_loss": 0.4367000162601471, | |
| "eval_runtime": 1.3451, | |
| "eval_samples_per_second": 137.539, | |
| "eval_steps_per_second": 8.921, | |
| "step": 300000 | |
| }, | |
| { | |
| "epoch": 41.7, | |
| "learning_rate": 6.264507603185725e-05, | |
| "loss": 0.4597, | |
| "step": 300500 | |
| }, | |
| { | |
| "epoch": 41.76, | |
| "learning_rate": 6.242091287306253e-05, | |
| "loss": 0.46, | |
| "step": 301000 | |
| }, | |
| { | |
| "epoch": 41.76, | |
| "eval_loss": 0.43270692229270935, | |
| "eval_runtime": 1.2785, | |
| "eval_samples_per_second": 144.699, | |
| "eval_steps_per_second": 9.386, | |
| "step": 301000 | |
| }, | |
| { | |
| "epoch": 41.83, | |
| "learning_rate": 6.219694195634821e-05, | |
| "loss": 0.4603, | |
| "step": 301500 | |
| }, | |
| { | |
| "epoch": 41.9, | |
| "learning_rate": 6.197316573102436e-05, | |
| "loss": 0.4596, | |
| "step": 302000 | |
| }, | |
| { | |
| "epoch": 41.9, | |
| "eval_loss": 0.43059635162353516, | |
| "eval_runtime": 1.4989, | |
| "eval_samples_per_second": 123.424, | |
| "eval_steps_per_second": 8.006, | |
| "step": 302000 | |
| }, | |
| { | |
| "epoch": 41.97, | |
| "learning_rate": 6.174958664427192e-05, | |
| "loss": 0.4603, | |
| "step": 302500 | |
| }, | |
| { | |
| "epoch": 42.04, | |
| "learning_rate": 6.152620714111597e-05, | |
| "loss": 0.46, | |
| "step": 303000 | |
| }, | |
| { | |
| "epoch": 42.04, | |
| "eval_loss": 0.43519648909568787, | |
| "eval_runtime": 1.3175, | |
| "eval_samples_per_second": 140.413, | |
| "eval_steps_per_second": 9.108, | |
| "step": 303000 | |
| }, | |
| { | |
| "epoch": 42.11, | |
| "learning_rate": 6.130302966439894e-05, | |
| "loss": 0.4598, | |
| "step": 303500 | |
| }, | |
| { | |
| "epoch": 42.18, | |
| "learning_rate": 6.1080056654754e-05, | |
| "loss": 0.46, | |
| "step": 304000 | |
| }, | |
| { | |
| "epoch": 42.18, | |
| "eval_loss": 0.4337790012359619, | |
| "eval_runtime": 1.2831, | |
| "eval_samples_per_second": 144.178, | |
| "eval_steps_per_second": 9.352, | |
| "step": 304000 | |
| }, | |
| { | |
| "epoch": 42.25, | |
| "learning_rate": 6.085729055057823e-05, | |
| "loss": 0.4601, | |
| "step": 304500 | |
| }, | |
| { | |
| "epoch": 42.32, | |
| "learning_rate": 6.063473378800607e-05, | |
| "loss": 0.4597, | |
| "step": 305000 | |
| }, | |
| { | |
| "epoch": 42.32, | |
| "eval_loss": 0.43329939246177673, | |
| "eval_runtime": 1.2575, | |
| "eval_samples_per_second": 147.119, | |
| "eval_steps_per_second": 9.543, | |
| "step": 305000 | |
| }, | |
| { | |
| "epoch": 42.39, | |
| "learning_rate": 6.041283327788843e-05, | |
| "loss": 0.4593, | |
| "step": 305500 | |
| }, | |
| { | |
| "epoch": 42.46, | |
| "learning_rate": 6.019203421060304e-05, | |
| "loss": 0.4596, | |
| "step": 306000 | |
| }, | |
| { | |
| "epoch": 42.46, | |
| "eval_loss": 0.4334431290626526, | |
| "eval_runtime": 1.3268, | |
| "eval_samples_per_second": 139.43, | |
| "eval_steps_per_second": 9.044, | |
| "step": 306000 | |
| }, | |
| { | |
| "epoch": 42.53, | |
| "learning_rate": 5.997011832389982e-05, | |
| "loss": 0.46, | |
| "step": 306500 | |
| }, | |
| { | |
| "epoch": 42.6, | |
| "learning_rate": 5.974842148077354e-05, | |
| "loss": 0.4591, | |
| "step": 307000 | |
| }, | |
| { | |
| "epoch": 42.6, | |
| "eval_loss": 0.4334283769130707, | |
| "eval_runtime": 1.4267, | |
| "eval_samples_per_second": 129.67, | |
| "eval_steps_per_second": 8.411, | |
| "step": 307000 | |
| }, | |
| { | |
| "epoch": 42.67, | |
| "learning_rate": 5.952694610566536e-05, | |
| "loss": 0.4596, | |
| "step": 307500 | |
| }, | |
| { | |
| "epoch": 42.74, | |
| "learning_rate": 5.930569462059449e-05, | |
| "loss": 0.4597, | |
| "step": 308000 | |
| }, | |
| { | |
| "epoch": 42.74, | |
| "eval_loss": 0.4318722188472748, | |
| "eval_runtime": 1.2649, | |
| "eval_samples_per_second": 146.253, | |
| "eval_steps_per_second": 9.487, | |
| "step": 308000 | |
| }, | |
| { | |
| "epoch": 42.81, | |
| "learning_rate": 5.9084669445131754e-05, | |
| "loss": 0.4597, | |
| "step": 308500 | |
| }, | |
| { | |
| "epoch": 42.87, | |
| "learning_rate": 5.886387299637301e-05, | |
| "loss": 0.4586, | |
| "step": 309000 | |
| }, | |
| { | |
| "epoch": 42.87, | |
| "eval_loss": 0.4267691969871521, | |
| "eval_runtime": 1.3287, | |
| "eval_samples_per_second": 139.236, | |
| "eval_steps_per_second": 9.031, | |
| "step": 309000 | |
| }, | |
| { | |
| "epoch": 42.94, | |
| "learning_rate": 5.8643307688912876e-05, | |
| "loss": 0.4596, | |
| "step": 309500 | |
| }, | |
| { | |
| "epoch": 43.01, | |
| "learning_rate": 5.8422975934818206e-05, | |
| "loss": 0.4593, | |
| "step": 310000 | |
| }, | |
| { | |
| "epoch": 43.01, | |
| "eval_loss": 0.4366314113140106, | |
| "eval_runtime": 1.3736, | |
| "eval_samples_per_second": 134.683, | |
| "eval_steps_per_second": 8.736, | |
| "step": 310000 | |
| }, | |
| { | |
| "epoch": 43.08, | |
| "learning_rate": 5.820288014360176e-05, | |
| "loss": 0.4592, | |
| "step": 310500 | |
| }, | |
| { | |
| "epoch": 43.15, | |
| "learning_rate": 5.798302272219588e-05, | |
| "loss": 0.4591, | |
| "step": 311000 | |
| }, | |
| { | |
| "epoch": 43.15, | |
| "eval_loss": 0.428290456533432, | |
| "eval_runtime": 1.2599, | |
| "eval_samples_per_second": 146.841, | |
| "eval_steps_per_second": 9.525, | |
| "step": 311000 | |
| }, | |
| { | |
| "epoch": 43.22, | |
| "learning_rate": 5.776340607492607e-05, | |
| "loss": 0.4584, | |
| "step": 311500 | |
| }, | |
| { | |
| "epoch": 43.29, | |
| "learning_rate": 5.754403260348481e-05, | |
| "loss": 0.4587, | |
| "step": 312000 | |
| }, | |
| { | |
| "epoch": 43.29, | |
| "eval_loss": 0.4289395809173584, | |
| "eval_runtime": 1.3295, | |
| "eval_samples_per_second": 139.154, | |
| "eval_steps_per_second": 9.026, | |
| "step": 312000 | |
| }, | |
| { | |
| "epoch": 43.36, | |
| "learning_rate": 5.732490470690522e-05, | |
| "loss": 0.4588, | |
| "step": 312500 | |
| }, | |
| { | |
| "epoch": 43.43, | |
| "learning_rate": 5.7106024781534895e-05, | |
| "loss": 0.4594, | |
| "step": 313000 | |
| }, | |
| { | |
| "epoch": 43.43, | |
| "eval_loss": 0.43324732780456543, | |
| "eval_runtime": 1.3614, | |
| "eval_samples_per_second": 135.891, | |
| "eval_steps_per_second": 8.815, | |
| "step": 313000 | |
| }, | |
| { | |
| "epoch": 43.5, | |
| "learning_rate": 5.6887395221009625e-05, | |
| "loss": 0.4585, | |
| "step": 313500 | |
| }, | |
| { | |
| "epoch": 43.57, | |
| "learning_rate": 5.666901841622724e-05, | |
| "loss": 0.459, | |
| "step": 314000 | |
| }, | |
| { | |
| "epoch": 43.57, | |
| "eval_loss": 0.4326333999633789, | |
| "eval_runtime": 1.4268, | |
| "eval_samples_per_second": 129.664, | |
| "eval_steps_per_second": 8.411, | |
| "step": 314000 | |
| }, | |
| { | |
| "epoch": 43.64, | |
| "learning_rate": 5.6451332742423816e-05, | |
| "loss": 0.459, | |
| "step": 314500 | |
| }, | |
| { | |
| "epoch": 43.71, | |
| "learning_rate": 5.62334680933011e-05, | |
| "loss": 0.4586, | |
| "step": 315000 | |
| }, | |
| { | |
| "epoch": 43.71, | |
| "eval_loss": 0.4356025755405426, | |
| "eval_runtime": 1.3678, | |
| "eval_samples_per_second": 135.255, | |
| "eval_steps_per_second": 8.773, | |
| "step": 315000 | |
| }, | |
| { | |
| "epoch": 43.78, | |
| "learning_rate": 5.601586335116362e-05, | |
| "loss": 0.4586, | |
| "step": 315500 | |
| }, | |
| { | |
| "epoch": 43.85, | |
| "learning_rate": 5.5798520895701915e-05, | |
| "loss": 0.4581, | |
| "step": 316000 | |
| }, | |
| { | |
| "epoch": 43.85, | |
| "eval_loss": 0.427127480506897, | |
| "eval_runtime": 1.294, | |
| "eval_samples_per_second": 142.967, | |
| "eval_steps_per_second": 9.274, | |
| "step": 316000 | |
| }, | |
| { | |
| "epoch": 43.92, | |
| "learning_rate": 5.5581876993609666e-05, | |
| "loss": 0.4587, | |
| "step": 316500 | |
| }, | |
| { | |
| "epoch": 43.98, | |
| "learning_rate": 5.5365499057136866e-05, | |
| "loss": 0.4584, | |
| "step": 317000 | |
| }, | |
| { | |
| "epoch": 43.98, | |
| "eval_loss": 0.43246105313301086, | |
| "eval_runtime": 1.3243, | |
| "eval_samples_per_second": 139.696, | |
| "eval_steps_per_second": 9.061, | |
| "step": 317000 | |
| }, | |
| { | |
| "epoch": 44.05, | |
| "learning_rate": 5.514895662868006e-05, | |
| "loss": 0.4589, | |
| "step": 317500 | |
| }, | |
| { | |
| "epoch": 44.12, | |
| "learning_rate": 5.493268596725206e-05, | |
| "loss": 0.4586, | |
| "step": 318000 | |
| }, | |
| { | |
| "epoch": 44.12, | |
| "eval_loss": 0.43503591418266296, | |
| "eval_runtime": 1.4646, | |
| "eval_samples_per_second": 126.317, | |
| "eval_steps_per_second": 8.194, | |
| "step": 318000 | |
| }, | |
| { | |
| "epoch": 44.19, | |
| "learning_rate": 5.471668943795419e-05, | |
| "loss": 0.4584, | |
| "step": 318500 | |
| }, | |
| { | |
| "epoch": 44.26, | |
| "learning_rate": 5.4500969402889874e-05, | |
| "loss": 0.4584, | |
| "step": 319000 | |
| }, | |
| { | |
| "epoch": 44.26, | |
| "eval_loss": 0.427314430475235, | |
| "eval_runtime": 1.4555, | |
| "eval_samples_per_second": 127.101, | |
| "eval_steps_per_second": 8.244, | |
| "step": 319000 | |
| }, | |
| { | |
| "epoch": 44.33, | |
| "learning_rate": 5.428552822113888e-05, | |
| "loss": 0.4582, | |
| "step": 319500 | |
| }, | |
| { | |
| "epoch": 44.4, | |
| "learning_rate": 5.4070368248731424e-05, | |
| "loss": 0.4576, | |
| "step": 320000 | |
| }, | |
| { | |
| "epoch": 44.4, | |
| "eval_loss": 0.4284280240535736, | |
| "eval_runtime": 1.3511, | |
| "eval_samples_per_second": 136.923, | |
| "eval_steps_per_second": 8.882, | |
| "step": 320000 | |
| }, | |
| { | |
| "epoch": 44.47, | |
| "learning_rate": 5.385549183862251e-05, | |
| "loss": 0.4582, | |
| "step": 320500 | |
| }, | |
| { | |
| "epoch": 44.54, | |
| "learning_rate": 5.36413302347614e-05, | |
| "loss": 0.458, | |
| "step": 321000 | |
| }, | |
| { | |
| "epoch": 44.54, | |
| "eval_loss": 0.43313825130462646, | |
| "eval_runtime": 1.3515, | |
| "eval_samples_per_second": 136.88, | |
| "eval_steps_per_second": 8.879, | |
| "step": 321000 | |
| }, | |
| { | |
| "epoch": 44.61, | |
| "learning_rate": 5.342702741682713e-05, | |
| "loss": 0.4573, | |
| "step": 321500 | |
| }, | |
| { | |
| "epoch": 44.68, | |
| "learning_rate": 5.3213015196663704e-05, | |
| "loss": 0.4581, | |
| "step": 322000 | |
| }, | |
| { | |
| "epoch": 44.68, | |
| "eval_loss": 0.4263160824775696, | |
| "eval_runtime": 1.282, | |
| "eval_samples_per_second": 144.307, | |
| "eval_steps_per_second": 9.36, | |
| "step": 322000 | |
| }, | |
| { | |
| "epoch": 44.75, | |
| "learning_rate": 5.2999295914674395e-05, | |
| "loss": 0.4579, | |
| "step": 322500 | |
| }, | |
| { | |
| "epoch": 44.82, | |
| "learning_rate": 5.278629845983565e-05, | |
| "loss": 0.4579, | |
| "step": 323000 | |
| }, | |
| { | |
| "epoch": 44.82, | |
| "eval_loss": 0.4283221960067749, | |
| "eval_runtime": 1.2519, | |
| "eval_samples_per_second": 147.773, | |
| "eval_steps_per_second": 9.585, | |
| "step": 323000 | |
| }, | |
| { | |
| "epoch": 44.89, | |
| "learning_rate": 5.257317146501924e-05, | |
| "loss": 0.4578, | |
| "step": 323500 | |
| }, | |
| { | |
| "epoch": 44.96, | |
| "learning_rate": 5.236034440560551e-05, | |
| "loss": 0.4583, | |
| "step": 324000 | |
| }, | |
| { | |
| "epoch": 44.96, | |
| "eval_loss": 0.43619590997695923, | |
| "eval_runtime": 1.2753, | |
| "eval_samples_per_second": 145.067, | |
| "eval_steps_per_second": 9.41, | |
| "step": 324000 | |
| }, | |
| { | |
| "epoch": 45.03, | |
| "learning_rate": 5.21478196090371e-05, | |
| "loss": 0.4582, | |
| "step": 324500 | |
| }, | |
| { | |
| "epoch": 45.1, | |
| "learning_rate": 5.1936023534349374e-05, | |
| "loss": 0.4571, | |
| "step": 325000 | |
| }, | |
| { | |
| "epoch": 45.1, | |
| "eval_loss": 0.4329734742641449, | |
| "eval_runtime": 1.2904, | |
| "eval_samples_per_second": 143.362, | |
| "eval_steps_per_second": 9.299, | |
| "step": 325000 | |
| }, | |
| { | |
| "epoch": 45.16, | |
| "learning_rate": 5.1724109616422535e-05, | |
| "loss": 0.4576, | |
| "step": 325500 | |
| }, | |
| { | |
| "epoch": 45.23, | |
| "learning_rate": 5.151250491910275e-05, | |
| "loss": 0.4566, | |
| "step": 326000 | |
| }, | |
| { | |
| "epoch": 45.23, | |
| "eval_loss": 0.42997583746910095, | |
| "eval_runtime": 1.2531, | |
| "eval_samples_per_second": 147.64, | |
| "eval_steps_per_second": 9.577, | |
| "step": 326000 | |
| }, | |
| { | |
| "epoch": 45.3, | |
| "learning_rate": 5.130121175646505e-05, | |
| "loss": 0.4573, | |
| "step": 326500 | |
| }, | |
| { | |
| "epoch": 45.37, | |
| "learning_rate": 5.109065408306044e-05, | |
| "loss": 0.4572, | |
| "step": 327000 | |
| }, | |
| { | |
| "epoch": 45.37, | |
| "eval_loss": 0.4257906675338745, | |
| "eval_runtime": 1.3322, | |
| "eval_samples_per_second": 138.863, | |
| "eval_steps_per_second": 9.007, | |
| "step": 327000 | |
| }, | |
| { | |
| "epoch": 45.44, | |
| "learning_rate": 5.0879990283753815e-05, | |
| "loss": 0.4576, | |
| "step": 327500 | |
| }, | |
| { | |
| "epoch": 45.51, | |
| "learning_rate": 5.066964493620802e-05, | |
| "loss": 0.4574, | |
| "step": 328000 | |
| }, | |
| { | |
| "epoch": 45.51, | |
| "eval_loss": 0.42002588510513306, | |
| "eval_runtime": 1.3087, | |
| "eval_samples_per_second": 141.356, | |
| "eval_steps_per_second": 9.169, | |
| "step": 328000 | |
| }, | |
| { | |
| "epoch": 45.58, | |
| "learning_rate": 5.046004006827927e-05, | |
| "loss": 0.4573, | |
| "step": 328500 | |
| }, | |
| { | |
| "epoch": 45.65, | |
| "learning_rate": 5.025033787326889e-05, | |
| "loss": 0.4573, | |
| "step": 329000 | |
| }, | |
| { | |
| "epoch": 45.65, | |
| "eval_loss": 0.4298509359359741, | |
| "eval_runtime": 1.2432, | |
| "eval_samples_per_second": 148.814, | |
| "eval_steps_per_second": 9.653, | |
| "step": 329000 | |
| }, | |
| { | |
| "epoch": 45.72, | |
| "learning_rate": 5.004096101579722e-05, | |
| "loss": 0.4571, | |
| "step": 329500 | |
| }, | |
| { | |
| "epoch": 45.79, | |
| "learning_rate": 4.983191178557604e-05, | |
| "loss": 0.4578, | |
| "step": 330000 | |
| }, | |
| { | |
| "epoch": 45.79, | |
| "eval_loss": 0.43188604712486267, | |
| "eval_runtime": 1.2251, | |
| "eval_samples_per_second": 151.012, | |
| "eval_steps_per_second": 9.795, | |
| "step": 330000 | |
| }, | |
| { | |
| "epoch": 45.86, | |
| "learning_rate": 4.962319246873419e-05, | |
| "loss": 0.4576, | |
| "step": 330500 | |
| }, | |
| { | |
| "epoch": 45.93, | |
| "learning_rate": 4.9414805347792704e-05, | |
| "loss": 0.4576, | |
| "step": 331000 | |
| }, | |
| { | |
| "epoch": 45.93, | |
| "eval_loss": 0.4352248013019562, | |
| "eval_runtime": 1.3596, | |
| "eval_samples_per_second": 136.073, | |
| "eval_steps_per_second": 8.826, | |
| "step": 331000 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "learning_rate": 4.920675270163976e-05, | |
| "loss": 0.4573, | |
| "step": 331500 | |
| }, | |
| { | |
| "epoch": 46.07, | |
| "learning_rate": 4.899903680550578e-05, | |
| "loss": 0.4574, | |
| "step": 332000 | |
| }, | |
| { | |
| "epoch": 46.07, | |
| "eval_loss": 0.4277680218219757, | |
| "eval_runtime": 1.304, | |
| "eval_samples_per_second": 141.867, | |
| "eval_steps_per_second": 9.202, | |
| "step": 332000 | |
| }, | |
| { | |
| "epoch": 46.14, | |
| "learning_rate": 4.8791659930938476e-05, | |
| "loss": 0.4567, | |
| "step": 332500 | |
| }, | |
| { | |
| "epoch": 46.21, | |
| "learning_rate": 4.858503807483613e-05, | |
| "loss": 0.4572, | |
| "step": 333000 | |
| }, | |
| { | |
| "epoch": 46.21, | |
| "eval_loss": 0.4325651526451111, | |
| "eval_runtime": 1.4573, | |
| "eval_samples_per_second": 126.944, | |
| "eval_steps_per_second": 8.234, | |
| "step": 333000 | |
| }, | |
| { | |
| "epoch": 46.27, | |
| "learning_rate": 4.837875839490377e-05, | |
| "loss": 0.4566, | |
| "step": 333500 | |
| }, | |
| { | |
| "epoch": 46.34, | |
| "learning_rate": 4.817241078937126e-05, | |
| "loss": 0.4568, | |
| "step": 334000 | |
| }, | |
| { | |
| "epoch": 46.34, | |
| "eval_loss": 0.42952632904052734, | |
| "eval_runtime": 1.348, | |
| "eval_samples_per_second": 137.239, | |
| "eval_steps_per_second": 8.902, | |
| "step": 334000 | |
| }, | |
| { | |
| "epoch": 46.41, | |
| "learning_rate": 4.7966411245255116e-05, | |
| "loss": 0.4567, | |
| "step": 334500 | |
| }, | |
| { | |
| "epoch": 46.48, | |
| "learning_rate": 4.776199486161653e-05, | |
| "loss": 0.4569, | |
| "step": 335000 | |
| }, | |
| { | |
| "epoch": 46.48, | |
| "eval_loss": 0.43004167079925537, | |
| "eval_runtime": 1.4336, | |
| "eval_samples_per_second": 129.047, | |
| "eval_steps_per_second": 8.371, | |
| "step": 335000 | |
| }, | |
| { | |
| "epoch": 46.55, | |
| "learning_rate": 4.755669607275862e-05, | |
| "loss": 0.4568, | |
| "step": 335500 | |
| }, | |
| { | |
| "epoch": 46.62, | |
| "learning_rate": 4.735175207867456e-05, | |
| "loss": 0.4566, | |
| "step": 336000 | |
| }, | |
| { | |
| "epoch": 46.62, | |
| "eval_loss": 0.4332566261291504, | |
| "eval_runtime": 1.3133, | |
| "eval_samples_per_second": 140.869, | |
| "eval_steps_per_second": 9.137, | |
| "step": 336000 | |
| }, | |
| { | |
| "epoch": 46.69, | |
| "learning_rate": 4.7147165120599086e-05, | |
| "loss": 0.4559, | |
| "step": 336500 | |
| }, | |
| { | |
| "epoch": 46.76, | |
| "learning_rate": 4.694293743586235e-05, | |
| "loss": 0.4567, | |
| "step": 337000 | |
| }, | |
| { | |
| "epoch": 46.76, | |
| "eval_loss": 0.4261642396450043, | |
| "eval_runtime": 1.2437, | |
| "eval_samples_per_second": 148.753, | |
| "eval_steps_per_second": 9.649, | |
| "step": 337000 | |
| }, | |
| { | |
| "epoch": 46.83, | |
| "learning_rate": 4.673907125786556e-05, | |
| "loss": 0.4567, | |
| "step": 337500 | |
| }, | |
| { | |
| "epoch": 46.9, | |
| "learning_rate": 4.653597545645173e-05, | |
| "loss": 0.4564, | |
| "step": 338000 | |
| }, | |
| { | |
| "epoch": 46.9, | |
| "eval_loss": 0.43535733222961426, | |
| "eval_runtime": 1.3354, | |
| "eval_samples_per_second": 138.536, | |
| "eval_steps_per_second": 8.986, | |
| "step": 338000 | |
| }, | |
| { | |
| "epoch": 46.97, | |
| "learning_rate": 4.633324414988516e-05, | |
| "loss": 0.4601, | |
| "step": 338500 | |
| }, | |
| { | |
| "epoch": 47.04, | |
| "learning_rate": 4.6130474375707824e-05, | |
| "loss": 0.4574, | |
| "step": 339000 | |
| }, | |
| { | |
| "epoch": 47.04, | |
| "eval_loss": 0.43565723299980164, | |
| "eval_runtime": 1.4317, | |
| "eval_samples_per_second": 129.219, | |
| "eval_steps_per_second": 8.382, | |
| "step": 339000 | |
| }, | |
| { | |
| "epoch": 47.11, | |
| "learning_rate": 4.592807499323636e-05, | |
| "loss": 0.4565, | |
| "step": 339500 | |
| }, | |
| { | |
| "epoch": 47.18, | |
| "learning_rate": 4.572604821587795e-05, | |
| "loss": 0.4564, | |
| "step": 340000 | |
| }, | |
| { | |
| "epoch": 47.18, | |
| "eval_loss": 0.4307515025138855, | |
| "eval_runtime": 1.4736, | |
| "eval_samples_per_second": 125.541, | |
| "eval_steps_per_second": 8.143, | |
| "step": 340000 | |
| }, | |
| { | |
| "epoch": 47.25, | |
| "learning_rate": 4.552439625296505e-05, | |
| "loss": 0.4561, | |
| "step": 340500 | |
| }, | |
| { | |
| "epoch": 47.32, | |
| "learning_rate": 4.5323121309731276e-05, | |
| "loss": 0.4554, | |
| "step": 341000 | |
| }, | |
| { | |
| "epoch": 47.32, | |
| "eval_loss": 0.4350062906742096, | |
| "eval_runtime": 1.2761, | |
| "eval_samples_per_second": 144.972, | |
| "eval_steps_per_second": 9.404, | |
| "step": 341000 | |
| }, | |
| { | |
| "epoch": 47.38, | |
| "learning_rate": 4.512222558728712e-05, | |
| "loss": 0.4561, | |
| "step": 341500 | |
| }, | |
| { | |
| "epoch": 47.45, | |
| "learning_rate": 4.4921711282596053e-05, | |
| "loss": 0.456, | |
| "step": 342000 | |
| }, | |
| { | |
| "epoch": 47.45, | |
| "eval_loss": 0.4400256276130676, | |
| "eval_runtime": 1.4304, | |
| "eval_samples_per_second": 129.339, | |
| "eval_steps_per_second": 8.39, | |
| "step": 342000 | |
| }, | |
| { | |
| "epoch": 47.52, | |
| "learning_rate": 4.472158058845034e-05, | |
| "loss": 0.4563, | |
| "step": 342500 | |
| }, | |
| { | |
| "epoch": 47.59, | |
| "learning_rate": 4.45218356934472e-05, | |
| "loss": 0.456, | |
| "step": 343000 | |
| }, | |
| { | |
| "epoch": 47.59, | |
| "eval_loss": 0.4236604571342468, | |
| "eval_runtime": 1.4771, | |
| "eval_samples_per_second": 125.249, | |
| "eval_steps_per_second": 8.124, | |
| "step": 343000 | |
| }, | |
| { | |
| "epoch": 47.66, | |
| "learning_rate": 4.432247878196481e-05, | |
| "loss": 0.4557, | |
| "step": 343500 | |
| }, | |
| { | |
| "epoch": 47.73, | |
| "learning_rate": 4.412351203413846e-05, | |
| "loss": 0.4559, | |
| "step": 344000 | |
| }, | |
| { | |
| "epoch": 47.73, | |
| "eval_loss": 0.42355087399482727, | |
| "eval_runtime": 1.3018, | |
| "eval_samples_per_second": 142.115, | |
| "eval_steps_per_second": 9.218, | |
| "step": 344000 | |
| }, | |
| { | |
| "epoch": 47.8, | |
| "learning_rate": 4.3924937625836546e-05, | |
| "loss": 0.456, | |
| "step": 344500 | |
| }, | |
| { | |
| "epoch": 47.87, | |
| "learning_rate": 4.3726757728637025e-05, | |
| "loss": 0.4559, | |
| "step": 345000 | |
| }, | |
| { | |
| "epoch": 47.87, | |
| "eval_loss": 0.43047869205474854, | |
| "eval_runtime": 1.2595, | |
| "eval_samples_per_second": 146.879, | |
| "eval_steps_per_second": 9.527, | |
| "step": 345000 | |
| }, | |
| { | |
| "epoch": 47.94, | |
| "learning_rate": 4.3528974509803495e-05, | |
| "loss": 0.4558, | |
| "step": 345500 | |
| }, | |
| { | |
| "epoch": 48.01, | |
| "learning_rate": 4.333159013226154e-05, | |
| "loss": 0.4559, | |
| "step": 346000 | |
| }, | |
| { | |
| "epoch": 48.01, | |
| "eval_loss": 0.42453786730766296, | |
| "eval_runtime": 1.4787, | |
| "eval_samples_per_second": 125.106, | |
| "eval_steps_per_second": 8.115, | |
| "step": 346000 | |
| }, | |
| { | |
| "epoch": 48.08, | |
| "learning_rate": 4.3135000319700124e-05, | |
| "loss": 0.4559, | |
| "step": 346500 | |
| }, | |
| { | |
| "epoch": 48.15, | |
| "learning_rate": 4.293841928759285e-05, | |
| "loss": 0.4549, | |
| "step": 347000 | |
| }, | |
| { | |
| "epoch": 48.15, | |
| "eval_loss": 0.41822031140327454, | |
| "eval_runtime": 1.385, | |
| "eval_samples_per_second": 133.578, | |
| "eval_steps_per_second": 8.664, | |
| "step": 347000 | |
| }, | |
| { | |
| "epoch": 48.22, | |
| "learning_rate": 4.2742243554994435e-05, | |
| "loss": 0.4553, | |
| "step": 347500 | |
| }, | |
| { | |
| "epoch": 48.29, | |
| "learning_rate": 4.254647526725133e-05, | |
| "loss": 0.4556, | |
| "step": 348000 | |
| }, | |
| { | |
| "epoch": 48.29, | |
| "eval_loss": 0.432986855506897, | |
| "eval_runtime": 1.3432, | |
| "eval_samples_per_second": 137.734, | |
| "eval_steps_per_second": 8.934, | |
| "step": 348000 | |
| }, | |
| { | |
| "epoch": 48.36, | |
| "learning_rate": 4.235111656525411e-05, | |
| "loss": 0.4554, | |
| "step": 348500 | |
| }, | |
| { | |
| "epoch": 48.43, | |
| "learning_rate": 4.215616958541425e-05, | |
| "loss": 0.4551, | |
| "step": 349000 | |
| }, | |
| { | |
| "epoch": 48.43, | |
| "eval_loss": 0.4397284984588623, | |
| "eval_runtime": 1.4485, | |
| "eval_samples_per_second": 127.714, | |
| "eval_steps_per_second": 8.284, | |
| "step": 349000 | |
| }, | |
| { | |
| "epoch": 48.49, | |
| "learning_rate": 4.1961636459640674e-05, | |
| "loss": 0.4549, | |
| "step": 349500 | |
| }, | |
| { | |
| "epoch": 48.56, | |
| "learning_rate": 4.1767519315316486e-05, | |
| "loss": 0.455, | |
| "step": 350000 | |
| }, | |
| { | |
| "epoch": 48.56, | |
| "eval_loss": 0.42523685097694397, | |
| "eval_runtime": 1.2279, | |
| "eval_samples_per_second": 150.663, | |
| "eval_steps_per_second": 9.773, | |
| "step": 350000 | |
| }, | |
| { | |
| "epoch": 48.63, | |
| "learning_rate": 4.157382027527568e-05, | |
| "loss": 0.455, | |
| "step": 350500 | |
| }, | |
| { | |
| "epoch": 48.7, | |
| "learning_rate": 4.1380541457779925e-05, | |
| "loss": 0.4548, | |
| "step": 351000 | |
| }, | |
| { | |
| "epoch": 48.7, | |
| "eval_loss": 0.4245500862598419, | |
| "eval_runtime": 1.3864, | |
| "eval_samples_per_second": 133.437, | |
| "eval_steps_per_second": 8.655, | |
| "step": 351000 | |
| }, | |
| { | |
| "epoch": 48.77, | |
| "learning_rate": 4.118807026656386e-05, | |
| "loss": 0.4549, | |
| "step": 351500 | |
| }, | |
| { | |
| "epoch": 48.84, | |
| "learning_rate": 4.099563737954589e-05, | |
| "loss": 0.4551, | |
| "step": 352000 | |
| }, | |
| { | |
| "epoch": 48.84, | |
| "eval_loss": 0.4291282594203949, | |
| "eval_runtime": 1.4115, | |
| "eval_samples_per_second": 131.064, | |
| "eval_steps_per_second": 8.501, | |
| "step": 352000 | |
| }, | |
| { | |
| "epoch": 48.91, | |
| "learning_rate": 4.0803631037988514e-05, | |
| "loss": 0.4548, | |
| "step": 352500 | |
| }, | |
| { | |
| "epoch": 48.98, | |
| "learning_rate": 4.0612053341642264e-05, | |
| "loss": 0.4554, | |
| "step": 353000 | |
| }, | |
| { | |
| "epoch": 48.98, | |
| "eval_loss": 0.42864859104156494, | |
| "eval_runtime": 1.2975, | |
| "eval_samples_per_second": 142.581, | |
| "eval_steps_per_second": 9.248, | |
| "step": 353000 | |
| }, | |
| { | |
| "epoch": 49.05, | |
| "learning_rate": 4.042090638557016e-05, | |
| "loss": 0.4556, | |
| "step": 353500 | |
| }, | |
| { | |
| "epoch": 49.12, | |
| "learning_rate": 4.02301922601247e-05, | |
| "loss": 0.4547, | |
| "step": 354000 | |
| }, | |
| { | |
| "epoch": 49.12, | |
| "eval_loss": 0.4335607588291168, | |
| "eval_runtime": 1.4371, | |
| "eval_samples_per_second": 128.729, | |
| "eval_steps_per_second": 8.35, | |
| "step": 354000 | |
| }, | |
| { | |
| "epoch": 49.19, | |
| "learning_rate": 4.003991305092499e-05, | |
| "loss": 0.4544, | |
| "step": 354500 | |
| }, | |
| { | |
| "epoch": 49.26, | |
| "learning_rate": 3.9850070838834005e-05, | |
| "loss": 0.4548, | |
| "step": 355000 | |
| }, | |
| { | |
| "epoch": 49.26, | |
| "eval_loss": 0.43242689967155457, | |
| "eval_runtime": 1.2661, | |
| "eval_samples_per_second": 146.119, | |
| "eval_steps_per_second": 9.478, | |
| "step": 355000 | |
| }, | |
| { | |
| "epoch": 49.33, | |
| "learning_rate": 3.9662181177343955e-05, | |
| "loss": 0.455, | |
| "step": 355500 | |
| }, | |
| { | |
| "epoch": 49.4, | |
| "learning_rate": 3.947321564555882e-05, | |
| "loss": 0.4545, | |
| "step": 356000 | |
| }, | |
| { | |
| "epoch": 49.4, | |
| "eval_loss": 0.42357033491134644, | |
| "eval_runtime": 1.2998, | |
| "eval_samples_per_second": 142.325, | |
| "eval_steps_per_second": 9.232, | |
| "step": 356000 | |
| }, | |
| { | |
| "epoch": 49.47, | |
| "learning_rate": 3.928469330819442e-05, | |
| "loss": 0.4543, | |
| "step": 356500 | |
| }, | |
| { | |
| "epoch": 49.54, | |
| "learning_rate": 3.9096991935330003e-05, | |
| "loss": 0.4547, | |
| "step": 357000 | |
| }, | |
| { | |
| "epoch": 49.54, | |
| "eval_loss": 0.4344870150089264, | |
| "eval_runtime": 1.4216, | |
| "eval_samples_per_second": 130.138, | |
| "eval_steps_per_second": 8.441, | |
| "step": 357000 | |
| }, | |
| { | |
| "epoch": 49.6, | |
| "learning_rate": 3.8909361270212906e-05, | |
| "loss": 0.4548, | |
| "step": 357500 | |
| }, | |
| { | |
| "epoch": 49.67, | |
| "learning_rate": 3.872217996573768e-05, | |
| "loss": 0.4542, | |
| "step": 358000 | |
| }, | |
| { | |
| "epoch": 49.67, | |
| "eval_loss": 0.4328906536102295, | |
| "eval_runtime": 1.3917, | |
| "eval_samples_per_second": 132.927, | |
| "eval_steps_per_second": 8.622, | |
| "step": 358000 | |
| }, | |
| { | |
| "epoch": 49.74, | |
| "learning_rate": 3.853545006888908e-05, | |
| "loss": 0.4547, | |
| "step": 358500 | |
| }, | |
| { | |
| "epoch": 49.81, | |
| "learning_rate": 3.834917362171529e-05, | |
| "loss": 0.4545, | |
| "step": 359000 | |
| }, | |
| { | |
| "epoch": 49.81, | |
| "eval_loss": 0.4240635633468628, | |
| "eval_runtime": 1.384, | |
| "eval_samples_per_second": 133.67, | |
| "eval_steps_per_second": 8.67, | |
| "step": 359000 | |
| }, | |
| { | |
| "epoch": 49.88, | |
| "learning_rate": 3.816335266130577e-05, | |
| "loss": 0.4544, | |
| "step": 359500 | |
| }, | |
| { | |
| "epoch": 49.95, | |
| "learning_rate": 3.7977989219768646e-05, | |
| "loss": 0.4541, | |
| "step": 360000 | |
| }, | |
| { | |
| "epoch": 49.95, | |
| "eval_loss": 0.41770491003990173, | |
| "eval_runtime": 1.2864, | |
| "eval_samples_per_second": 143.813, | |
| "eval_steps_per_second": 9.328, | |
| "step": 360000 | |
| }, | |
| { | |
| "epoch": 50.02, | |
| "learning_rate": 3.779308532420894e-05, | |
| "loss": 0.4549, | |
| "step": 360500 | |
| }, | |
| { | |
| "epoch": 50.09, | |
| "learning_rate": 3.760864299670598e-05, | |
| "loss": 0.454, | |
| "step": 361000 | |
| }, | |
| { | |
| "epoch": 50.09, | |
| "eval_loss": 0.42438188195228577, | |
| "eval_runtime": 1.5248, | |
| "eval_samples_per_second": 121.326, | |
| "eval_steps_per_second": 7.87, | |
| "step": 361000 | |
| }, | |
| { | |
| "epoch": 50.16, | |
| "learning_rate": 3.742466425429149e-05, | |
| "loss": 0.4544, | |
| "step": 361500 | |
| }, | |
| { | |
| "epoch": 50.23, | |
| "learning_rate": 3.724115110892756e-05, | |
| "loss": 0.4538, | |
| "step": 362000 | |
| }, | |
| { | |
| "epoch": 50.23, | |
| "eval_loss": 0.4190036952495575, | |
| "eval_runtime": 1.4148, | |
| "eval_samples_per_second": 130.758, | |
| "eval_steps_per_second": 8.482, | |
| "step": 362000 | |
| }, | |
| { | |
| "epoch": 50.3, | |
| "learning_rate": 3.7058105567484526e-05, | |
| "loss": 0.4541, | |
| "step": 362500 | |
| }, | |
| { | |
| "epoch": 50.37, | |
| "learning_rate": 3.6875529631719126e-05, | |
| "loss": 0.4535, | |
| "step": 363000 | |
| }, | |
| { | |
| "epoch": 50.37, | |
| "eval_loss": 0.43312662839889526, | |
| "eval_runtime": 1.4875, | |
| "eval_samples_per_second": 124.369, | |
| "eval_steps_per_second": 8.067, | |
| "step": 363000 | |
| }, | |
| { | |
| "epoch": 50.44, | |
| "learning_rate": 3.66934252982525e-05, | |
| "loss": 0.454, | |
| "step": 363500 | |
| }, | |
| { | |
| "epoch": 50.51, | |
| "learning_rate": 3.6512157346060225e-05, | |
| "loss": 0.4545, | |
| "step": 364000 | |
| }, | |
| { | |
| "epoch": 50.51, | |
| "eval_loss": 0.4252246022224426, | |
| "eval_runtime": 1.4584, | |
| "eval_samples_per_second": 126.855, | |
| "eval_steps_per_second": 8.228, | |
| "step": 364000 | |
| }, | |
| { | |
| "epoch": 50.58, | |
| "learning_rate": 3.63313630695476e-05, | |
| "loss": 0.4541, | |
| "step": 364500 | |
| }, | |
| { | |
| "epoch": 50.65, | |
| "learning_rate": 3.615068355683803e-05, | |
| "loss": 0.454, | |
| "step": 365000 | |
| }, | |
| { | |
| "epoch": 50.65, | |
| "eval_loss": 0.43154436349868774, | |
| "eval_runtime": 1.6686, | |
| "eval_samples_per_second": 110.872, | |
| "eval_steps_per_second": 7.192, | |
| "step": 365000 | |
| }, | |
| { | |
| "epoch": 50.71, | |
| "learning_rate": 3.597048357322779e-05, | |
| "loss": 0.4538, | |
| "step": 365500 | |
| }, | |
| { | |
| "epoch": 50.78, | |
| "learning_rate": 3.579076508935504e-05, | |
| "loss": 0.4536, | |
| "step": 366000 | |
| }, | |
| { | |
| "epoch": 50.78, | |
| "eval_loss": 0.4300937056541443, | |
| "eval_runtime": 1.6992, | |
| "eval_samples_per_second": 108.874, | |
| "eval_steps_per_second": 7.062, | |
| "step": 366000 | |
| }, | |
| { | |
| "epoch": 50.85, | |
| "learning_rate": 3.5611530070592334e-05, | |
| "loss": 0.4536, | |
| "step": 366500 | |
| }, | |
| { | |
| "epoch": 50.92, | |
| "learning_rate": 3.543278047702514e-05, | |
| "loss": 0.4534, | |
| "step": 367000 | |
| }, | |
| { | |
| "epoch": 50.92, | |
| "eval_loss": 0.43572941422462463, | |
| "eval_runtime": 1.6472, | |
| "eval_samples_per_second": 112.315, | |
| "eval_steps_per_second": 7.285, | |
| "step": 367000 | |
| }, | |
| { | |
| "epoch": 50.99, | |
| "learning_rate": 3.525451826343032e-05, | |
| "loss": 0.4536, | |
| "step": 367500 | |
| }, | |
| { | |
| "epoch": 51.06, | |
| "learning_rate": 3.507710043537942e-05, | |
| "loss": 0.4537, | |
| "step": 368000 | |
| }, | |
| { | |
| "epoch": 51.06, | |
| "eval_loss": 0.43337032198905945, | |
| "eval_runtime": 1.2953, | |
| "eval_samples_per_second": 142.824, | |
| "eval_steps_per_second": 9.264, | |
| "step": 368000 | |
| }, | |
| { | |
| "epoch": 51.13, | |
| "learning_rate": 3.4899817840235556e-05, | |
| "loss": 0.4532, | |
| "step": 368500 | |
| }, | |
| { | |
| "epoch": 51.2, | |
| "learning_rate": 3.4723028453458075e-05, | |
| "loss": 0.4535, | |
| "step": 369000 | |
| }, | |
| { | |
| "epoch": 51.2, | |
| "eval_loss": 0.4200479984283447, | |
| "eval_runtime": 1.3971, | |
| "eval_samples_per_second": 132.414, | |
| "eval_steps_per_second": 8.589, | |
| "step": 369000 | |
| }, | |
| { | |
| "epoch": 51.27, | |
| "learning_rate": 3.4546734208387424e-05, | |
| "loss": 0.453, | |
| "step": 369500 | |
| }, | |
| { | |
| "epoch": 51.34, | |
| "learning_rate": 3.43709370329492e-05, | |
| "loss": 0.4538, | |
| "step": 370000 | |
| }, | |
| { | |
| "epoch": 51.34, | |
| "eval_loss": 0.42738237977027893, | |
| "eval_runtime": 1.2968, | |
| "eval_samples_per_second": 142.663, | |
| "eval_steps_per_second": 9.254, | |
| "step": 370000 | |
| }, | |
| { | |
| "epoch": 51.41, | |
| "learning_rate": 3.41956388496332e-05, | |
| "loss": 0.4536, | |
| "step": 370500 | |
| }, | |
| { | |
| "epoch": 51.48, | |
| "learning_rate": 3.40208415754722e-05, | |
| "loss": 0.4536, | |
| "step": 371000 | |
| }, | |
| { | |
| "epoch": 51.48, | |
| "eval_loss": 0.41781699657440186, | |
| "eval_runtime": 1.2907, | |
| "eval_samples_per_second": 143.329, | |
| "eval_steps_per_second": 9.297, | |
| "step": 371000 | |
| }, | |
| { | |
| "epoch": 51.55, | |
| "learning_rate": 3.3846547122021226e-05, | |
| "loss": 0.4531, | |
| "step": 371500 | |
| }, | |
| { | |
| "epoch": 51.62, | |
| "learning_rate": 3.367275739533648e-05, | |
| "loss": 0.4534, | |
| "step": 372000 | |
| }, | |
| { | |
| "epoch": 51.62, | |
| "eval_loss": 0.4181431233882904, | |
| "eval_runtime": 1.3515, | |
| "eval_samples_per_second": 136.885, | |
| "eval_steps_per_second": 8.879, | |
| "step": 372000 | |
| }, | |
| { | |
| "epoch": 51.69, | |
| "learning_rate": 3.349947429595459e-05, | |
| "loss": 0.4526, | |
| "step": 372500 | |
| }, | |
| { | |
| "epoch": 51.76, | |
| "learning_rate": 3.3326699718871764e-05, | |
| "loss": 0.4533, | |
| "step": 373000 | |
| }, | |
| { | |
| "epoch": 51.76, | |
| "eval_loss": 0.4211100935935974, | |
| "eval_runtime": 1.3352, | |
| "eval_samples_per_second": 138.561, | |
| "eval_steps_per_second": 8.988, | |
| "step": 373000 | |
| }, | |
| { | |
| "epoch": 51.82, | |
| "learning_rate": 3.315443555352308e-05, | |
| "loss": 0.4525, | |
| "step": 373500 | |
| }, | |
| { | |
| "epoch": 51.89, | |
| "learning_rate": 3.298268368376187e-05, | |
| "loss": 0.4535, | |
| "step": 374000 | |
| }, | |
| { | |
| "epoch": 51.89, | |
| "eval_loss": 0.4289679527282715, | |
| "eval_runtime": 1.3822, | |
| "eval_samples_per_second": 133.849, | |
| "eval_steps_per_second": 8.682, | |
| "step": 374000 | |
| }, | |
| { | |
| "epoch": 51.96, | |
| "learning_rate": 3.281144598783902e-05, | |
| "loss": 0.4529, | |
| "step": 374500 | |
| }, | |
| { | |
| "epoch": 52.03, | |
| "learning_rate": 3.2641747125725525e-05, | |
| "loss": 0.4535, | |
| "step": 375000 | |
| }, | |
| { | |
| "epoch": 52.03, | |
| "eval_loss": 0.4201316237449646, | |
| "eval_runtime": 1.2705, | |
| "eval_samples_per_second": 145.613, | |
| "eval_steps_per_second": 9.445, | |
| "step": 375000 | |
| }, | |
| { | |
| "epoch": 52.1, | |
| "learning_rate": 3.247154027668326e-05, | |
| "loss": 0.4523, | |
| "step": 375500 | |
| }, | |
| { | |
| "epoch": 52.17, | |
| "learning_rate": 3.2301853191261837e-05, | |
| "loss": 0.4526, | |
| "step": 376000 | |
| }, | |
| { | |
| "epoch": 52.17, | |
| "eval_loss": 0.4263089597225189, | |
| "eval_runtime": 1.255, | |
| "eval_samples_per_second": 147.413, | |
| "eval_steps_per_second": 9.562, | |
| "step": 376000 | |
| }, | |
| { | |
| "epoch": 52.24, | |
| "learning_rate": 3.21333633454771e-05, | |
| "loss": 0.4526, | |
| "step": 376500 | |
| }, | |
| { | |
| "epoch": 52.31, | |
| "learning_rate": 3.196471925105066e-05, | |
| "loss": 0.4526, | |
| "step": 377000 | |
| }, | |
| { | |
| "epoch": 52.31, | |
| "eval_loss": 0.4236815273761749, | |
| "eval_runtime": 1.3806, | |
| "eval_samples_per_second": 133.999, | |
| "eval_steps_per_second": 8.692, | |
| "step": 377000 | |
| }, | |
| { | |
| "epoch": 52.38, | |
| "learning_rate": 3.1796600462758575e-05, | |
| "loss": 0.4532, | |
| "step": 377500 | |
| }, | |
| { | |
| "epoch": 52.45, | |
| "learning_rate": 3.1629008819120935e-05, | |
| "loss": 0.4524, | |
| "step": 378000 | |
| }, | |
| { | |
| "epoch": 52.45, | |
| "eval_loss": 0.4254463016986847, | |
| "eval_runtime": 1.2654, | |
| "eval_samples_per_second": 146.204, | |
| "eval_steps_per_second": 9.483, | |
| "step": 378000 | |
| }, | |
| { | |
| "epoch": 52.52, | |
| "learning_rate": 3.146194615289314e-05, | |
| "loss": 0.4523, | |
| "step": 378500 | |
| }, | |
| { | |
| "epoch": 52.59, | |
| "learning_rate": 3.129541429104573e-05, | |
| "loss": 0.4529, | |
| "step": 379000 | |
| }, | |
| { | |
| "epoch": 52.59, | |
| "eval_loss": 0.42601755261421204, | |
| "eval_runtime": 1.4268, | |
| "eval_samples_per_second": 129.661, | |
| "eval_steps_per_second": 8.41, | |
| "step": 379000 | |
| }, | |
| { | |
| "epoch": 52.66, | |
| "learning_rate": 3.1129415054744466e-05, | |
| "loss": 0.4525, | |
| "step": 379500 | |
| }, | |
| { | |
| "epoch": 52.73, | |
| "learning_rate": 3.0963950259330426e-05, | |
| "loss": 0.4531, | |
| "step": 380000 | |
| }, | |
| { | |
| "epoch": 52.73, | |
| "eval_loss": 0.4202404022216797, | |
| "eval_runtime": 1.4812, | |
| "eval_samples_per_second": 124.898, | |
| "eval_steps_per_second": 8.101, | |
| "step": 380000 | |
| }, | |
| { | |
| "epoch": 52.8, | |
| "learning_rate": 3.0799021714300064e-05, | |
| "loss": 0.4528, | |
| "step": 380500 | |
| }, | |
| { | |
| "epoch": 52.87, | |
| "learning_rate": 3.063463122328553e-05, | |
| "loss": 0.4523, | |
| "step": 381000 | |
| }, | |
| { | |
| "epoch": 52.87, | |
| "eval_loss": 0.42233461141586304, | |
| "eval_runtime": 1.6606, | |
| "eval_samples_per_second": 111.404, | |
| "eval_steps_per_second": 7.226, | |
| "step": 381000 | |
| }, | |
| { | |
| "epoch": 52.93, | |
| "learning_rate": 3.0470780584034914e-05, | |
| "loss": 0.4525, | |
| "step": 381500 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "learning_rate": 3.0307471588392577e-05, | |
| "loss": 0.4523, | |
| "step": 382000 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_loss": 0.4270618259906769, | |
| "eval_runtime": 1.4098, | |
| "eval_samples_per_second": 131.228, | |
| "eval_steps_per_second": 8.512, | |
| "step": 382000 | |
| }, | |
| { | |
| "epoch": 53.07, | |
| "learning_rate": 3.0144706022279473e-05, | |
| "loss": 0.4523, | |
| "step": 382500 | |
| }, | |
| { | |
| "epoch": 53.14, | |
| "learning_rate": 2.9982485665673786e-05, | |
| "loss": 0.4522, | |
| "step": 383000 | |
| }, | |
| { | |
| "epoch": 53.14, | |
| "eval_loss": 0.4285798668861389, | |
| "eval_runtime": 1.3032, | |
| "eval_samples_per_second": 141.954, | |
| "eval_steps_per_second": 9.208, | |
| "step": 383000 | |
| }, | |
| { | |
| "epoch": 53.21, | |
| "learning_rate": 2.9820812292591337e-05, | |
| "loss": 0.4524, | |
| "step": 383500 | |
| }, | |
| { | |
| "epoch": 53.28, | |
| "learning_rate": 2.965968767106625e-05, | |
| "loss": 0.4524, | |
| "step": 384000 | |
| }, | |
| { | |
| "epoch": 53.28, | |
| "eval_loss": 0.4256191849708557, | |
| "eval_runtime": 1.223, | |
| "eval_samples_per_second": 151.266, | |
| "eval_steps_per_second": 9.812, | |
| "step": 384000 | |
| }, | |
| { | |
| "epoch": 53.35, | |
| "learning_rate": 2.9499113563131592e-05, | |
| "loss": 0.4522, | |
| "step": 384500 | |
| }, | |
| { | |
| "epoch": 53.42, | |
| "learning_rate": 2.9339091724800015e-05, | |
| "loss": 0.4515, | |
| "step": 385000 | |
| }, | |
| { | |
| "epoch": 53.42, | |
| "eval_loss": 0.42210718989372253, | |
| "eval_runtime": 1.2868, | |
| "eval_samples_per_second": 143.764, | |
| "eval_steps_per_second": 9.325, | |
| "step": 385000 | |
| }, | |
| { | |
| "epoch": 53.49, | |
| "learning_rate": 2.9179623906044737e-05, | |
| "loss": 0.4518, | |
| "step": 385500 | |
| }, | |
| { | |
| "epoch": 53.56, | |
| "learning_rate": 2.9020711850780284e-05, | |
| "loss": 0.4513, | |
| "step": 386000 | |
| }, | |
| { | |
| "epoch": 53.56, | |
| "eval_loss": 0.425523579120636, | |
| "eval_runtime": 1.4209, | |
| "eval_samples_per_second": 130.197, | |
| "eval_steps_per_second": 8.445, | |
| "step": 386000 | |
| }, | |
| { | |
| "epoch": 53.63, | |
| "learning_rate": 2.8862357296843427e-05, | |
| "loss": 0.452, | |
| "step": 386500 | |
| }, | |
| { | |
| "epoch": 53.7, | |
| "learning_rate": 2.8704561975974218e-05, | |
| "loss": 0.452, | |
| "step": 387000 | |
| }, | |
| { | |
| "epoch": 53.7, | |
| "eval_loss": 0.427028089761734, | |
| "eval_runtime": 1.5058, | |
| "eval_samples_per_second": 122.86, | |
| "eval_steps_per_second": 7.969, | |
| "step": 387000 | |
| }, | |
| { | |
| "epoch": 53.77, | |
| "learning_rate": 2.854732761379696e-05, | |
| "loss": 0.4514, | |
| "step": 387500 | |
| }, | |
| { | |
| "epoch": 53.84, | |
| "learning_rate": 2.839065592980148e-05, | |
| "loss": 0.4519, | |
| "step": 388000 | |
| }, | |
| { | |
| "epoch": 53.84, | |
| "eval_loss": 0.42220446467399597, | |
| "eval_runtime": 1.6802, | |
| "eval_samples_per_second": 110.105, | |
| "eval_steps_per_second": 7.142, | |
| "step": 388000 | |
| }, | |
| { | |
| "epoch": 53.91, | |
| "learning_rate": 2.82348602875107e-05, | |
| "loss": 0.4517, | |
| "step": 388500 | |
| }, | |
| { | |
| "epoch": 53.98, | |
| "learning_rate": 2.8079317959818956e-05, | |
| "loss": 0.4518, | |
| "step": 389000 | |
| }, | |
| { | |
| "epoch": 53.98, | |
| "eval_loss": 0.4233224391937256, | |
| "eval_runtime": 1.5975, | |
| "eval_samples_per_second": 115.803, | |
| "eval_steps_per_second": 7.512, | |
| "step": 389000 | |
| }, | |
| { | |
| "epoch": 54.04, | |
| "learning_rate": 2.7924343428387574e-05, | |
| "loss": 0.4518, | |
| "step": 389500 | |
| }, | |
| { | |
| "epoch": 54.11, | |
| "learning_rate": 2.7769938387993203e-05, | |
| "loss": 0.4513, | |
| "step": 390000 | |
| }, | |
| { | |
| "epoch": 54.11, | |
| "eval_loss": 0.42325669527053833, | |
| "eval_runtime": 1.4287, | |
| "eval_samples_per_second": 129.488, | |
| "eval_steps_per_second": 8.399, | |
| "step": 390000 | |
| }, | |
| { | |
| "epoch": 54.18, | |
| "learning_rate": 2.761641162374983e-05, | |
| "loss": 0.4512, | |
| "step": 390500 | |
| }, | |
| { | |
| "epoch": 54.25, | |
| "learning_rate": 2.7463149477430953e-05, | |
| "loss": 0.4517, | |
| "step": 391000 | |
| }, | |
| { | |
| "epoch": 54.25, | |
| "eval_loss": 0.4239380657672882, | |
| "eval_runtime": 1.4388, | |
| "eval_samples_per_second": 128.582, | |
| "eval_steps_per_second": 8.34, | |
| "step": 391000 | |
| }, | |
| { | |
| "epoch": 54.32, | |
| "learning_rate": 2.731046186569221e-05, | |
| "loss": 0.4516, | |
| "step": 391500 | |
| }, | |
| { | |
| "epoch": 54.39, | |
| "learning_rate": 2.71586541049571e-05, | |
| "loss": 0.4518, | |
| "step": 392000 | |
| }, | |
| { | |
| "epoch": 54.39, | |
| "eval_loss": 0.42732805013656616, | |
| "eval_runtime": 1.358, | |
| "eval_samples_per_second": 136.233, | |
| "eval_steps_per_second": 8.837, | |
| "step": 392000 | |
| }, | |
| { | |
| "epoch": 54.46, | |
| "learning_rate": 2.700711940798765e-05, | |
| "loss": 0.4515, | |
| "step": 392500 | |
| }, | |
| { | |
| "epoch": 54.53, | |
| "learning_rate": 2.6856164232670142e-05, | |
| "loss": 0.4508, | |
| "step": 393000 | |
| }, | |
| { | |
| "epoch": 54.53, | |
| "eval_loss": 0.42004072666168213, | |
| "eval_runtime": 1.2491, | |
| "eval_samples_per_second": 148.104, | |
| "eval_steps_per_second": 9.607, | |
| "step": 393000 | |
| }, | |
| { | |
| "epoch": 54.6, | |
| "learning_rate": 2.67057902298262e-05, | |
| "loss": 0.4513, | |
| "step": 393500 | |
| }, | |
| { | |
| "epoch": 54.67, | |
| "learning_rate": 2.6555999043921808e-05, | |
| "loss": 0.4511, | |
| "step": 394000 | |
| }, | |
| { | |
| "epoch": 54.67, | |
| "eval_loss": 0.4236282408237457, | |
| "eval_runtime": 1.2986, | |
| "eval_samples_per_second": 142.456, | |
| "eval_steps_per_second": 9.24, | |
| "step": 394000 | |
| }, | |
| { | |
| "epoch": 54.74, | |
| "learning_rate": 2.6406792313049402e-05, | |
| "loss": 0.4513, | |
| "step": 394500 | |
| }, | |
| { | |
| "epoch": 54.81, | |
| "learning_rate": 2.625817166890986e-05, | |
| "loss": 0.4508, | |
| "step": 395000 | |
| }, | |
| { | |
| "epoch": 54.81, | |
| "eval_loss": 0.41928112506866455, | |
| "eval_runtime": 1.2191, | |
| "eval_samples_per_second": 151.752, | |
| "eval_steps_per_second": 9.843, | |
| "step": 395000 | |
| }, | |
| { | |
| "epoch": 54.88, | |
| "learning_rate": 2.6110138736794743e-05, | |
| "loss": 0.4518, | |
| "step": 395500 | |
| }, | |
| { | |
| "epoch": 54.95, | |
| "learning_rate": 2.5962989433545918e-05, | |
| "loss": 0.4507, | |
| "step": 396000 | |
| }, | |
| { | |
| "epoch": 54.95, | |
| "eval_loss": 0.4292617440223694, | |
| "eval_runtime": 1.3922, | |
| "eval_samples_per_second": 132.879, | |
| "eval_steps_per_second": 8.619, | |
| "step": 396000 | |
| }, | |
| { | |
| "epoch": 55.02, | |
| "learning_rate": 2.581613559213658e-05, | |
| "loss": 0.4517, | |
| "step": 396500 | |
| }, | |
| { | |
| "epoch": 55.09, | |
| "learning_rate": 2.56698742967874e-05, | |
| "loss": 0.4508, | |
| "step": 397000 | |
| }, | |
| { | |
| "epoch": 55.09, | |
| "eval_loss": 0.4187283515930176, | |
| "eval_runtime": 1.3865, | |
| "eval_samples_per_second": 133.432, | |
| "eval_steps_per_second": 8.655, | |
| "step": 397000 | |
| }, | |
| { | |
| "epoch": 55.15, | |
| "learning_rate": 2.5524207146988447e-05, | |
| "loss": 0.4504, | |
| "step": 397500 | |
| }, | |
| { | |
| "epoch": 55.22, | |
| "learning_rate": 2.537913573573237e-05, | |
| "loss": 0.4504, | |
| "step": 398000 | |
| }, | |
| { | |
| "epoch": 55.22, | |
| "eval_loss": 0.4283367991447449, | |
| "eval_runtime": 1.2871, | |
| "eval_samples_per_second": 143.738, | |
| "eval_steps_per_second": 9.324, | |
| "step": 398000 | |
| }, | |
| { | |
| "epoch": 55.29, | |
| "learning_rate": 2.52349500004877e-05, | |
| "loss": 0.4513, | |
| "step": 398500 | |
| }, | |
| { | |
| "epoch": 55.36, | |
| "learning_rate": 2.509107361983578e-05, | |
| "loss": 0.4512, | |
| "step": 399000 | |
| }, | |
| { | |
| "epoch": 55.36, | |
| "eval_loss": 0.4239468276500702, | |
| "eval_runtime": 1.3492, | |
| "eval_samples_per_second": 137.123, | |
| "eval_steps_per_second": 8.894, | |
| "step": 399000 | |
| }, | |
| { | |
| "epoch": 55.43, | |
| "learning_rate": 2.4947797714405616e-05, | |
| "loss": 0.4508, | |
| "step": 399500 | |
| }, | |
| { | |
| "epoch": 55.5, | |
| "learning_rate": 2.480512385103948e-05, | |
| "loss": 0.4504, | |
| "step": 400000 | |
| }, | |
| { | |
| "epoch": 55.5, | |
| "eval_loss": 0.4269140362739563, | |
| "eval_runtime": 1.4306, | |
| "eval_samples_per_second": 129.315, | |
| "eval_steps_per_second": 8.388, | |
| "step": 400000 | |
| }, | |
| { | |
| "epoch": 55.57, | |
| "learning_rate": 2.4663337127089114e-05, | |
| "loss": 0.4511, | |
| "step": 400500 | |
| }, | |
| { | |
| "epoch": 55.64, | |
| "learning_rate": 2.4521870810167605e-05, | |
| "loss": 0.4506, | |
| "step": 401000 | |
| }, | |
| { | |
| "epoch": 55.64, | |
| "eval_loss": 0.42908209562301636, | |
| "eval_runtime": 1.3786, | |
| "eval_samples_per_second": 134.192, | |
| "eval_steps_per_second": 8.704, | |
| "step": 401000 | |
| }, | |
| { | |
| "epoch": 55.71, | |
| "learning_rate": 2.4381011193178528e-05, | |
| "loss": 0.4501, | |
| "step": 401500 | |
| }, | |
| { | |
| "epoch": 55.78, | |
| "learning_rate": 2.424075981654012e-05, | |
| "loss": 0.4504, | |
| "step": 402000 | |
| }, | |
| { | |
| "epoch": 55.78, | |
| "eval_loss": 0.42375433444976807, | |
| "eval_runtime": 1.4548, | |
| "eval_samples_per_second": 127.164, | |
| "eval_steps_per_second": 8.248, | |
| "step": 402000 | |
| }, | |
| { | |
| "epoch": 55.85, | |
| "learning_rate": 2.4101396887653254e-05, | |
| "loss": 0.4504, | |
| "step": 402500 | |
| }, | |
| { | |
| "epoch": 55.92, | |
| "learning_rate": 2.3962365362225434e-05, | |
| "loss": 0.4503, | |
| "step": 403000 | |
| }, | |
| { | |
| "epoch": 55.92, | |
| "eval_loss": 0.42001548409461975, | |
| "eval_runtime": 1.3313, | |
| "eval_samples_per_second": 138.963, | |
| "eval_steps_per_second": 9.014, | |
| "step": 403000 | |
| }, | |
| { | |
| "epoch": 55.99, | |
| "learning_rate": 2.3823946655392004e-05, | |
| "loss": 0.4513, | |
| "step": 403500 | |
| }, | |
| { | |
| "epoch": 56.06, | |
| "learning_rate": 2.3686142280877743e-05, | |
| "loss": 0.4506, | |
| "step": 404000 | |
| }, | |
| { | |
| "epoch": 56.06, | |
| "eval_loss": 0.4185764193534851, | |
| "eval_runtime": 1.4515, | |
| "eval_samples_per_second": 127.452, | |
| "eval_steps_per_second": 8.267, | |
| "step": 404000 | |
| }, | |
| { | |
| "epoch": 56.13, | |
| "learning_rate": 2.3549227507153627e-05, | |
| "loss": 0.4498, | |
| "step": 404500 | |
| }, | |
| { | |
| "epoch": 56.2, | |
| "learning_rate": 2.3412927603158495e-05, | |
| "loss": 0.4507, | |
| "step": 405000 | |
| }, | |
| { | |
| "epoch": 56.2, | |
| "eval_loss": 0.4259674847126007, | |
| "eval_runtime": 1.4534, | |
| "eval_samples_per_second": 127.292, | |
| "eval_steps_per_second": 8.257, | |
| "step": 405000 | |
| }, | |
| { | |
| "epoch": 56.26, | |
| "learning_rate": 2.3276972762387238e-05, | |
| "loss": 0.4507, | |
| "step": 405500 | |
| }, | |
| { | |
| "epoch": 56.33, | |
| "learning_rate": 2.3141638235554014e-05, | |
| "loss": 0.4504, | |
| "step": 406000 | |
| }, | |
| { | |
| "epoch": 56.33, | |
| "eval_loss": 0.4188092350959778, | |
| "eval_runtime": 1.3766, | |
| "eval_samples_per_second": 134.394, | |
| "eval_steps_per_second": 8.717, | |
| "step": 406000 | |
| }, | |
| { | |
| "epoch": 56.4, | |
| "learning_rate": 2.3006925502655538e-05, | |
| "loss": 0.4499, | |
| "step": 406500 | |
| }, | |
| { | |
| "epoch": 56.47, | |
| "learning_rate": 2.287283603688867e-05, | |
| "loss": 0.4503, | |
| "step": 407000 | |
| }, | |
| { | |
| "epoch": 56.47, | |
| "eval_loss": 0.42306798696517944, | |
| "eval_runtime": 1.4461, | |
| "eval_samples_per_second": 127.93, | |
| "eval_steps_per_second": 8.298, | |
| "step": 407000 | |
| }, | |
| { | |
| "epoch": 56.54, | |
| "learning_rate": 2.273937130463433e-05, | |
| "loss": 0.4502, | |
| "step": 407500 | |
| }, | |
| { | |
| "epoch": 56.61, | |
| "learning_rate": 2.260653276544143e-05, | |
| "loss": 0.4498, | |
| "step": 408000 | |
| }, | |
| { | |
| "epoch": 56.61, | |
| "eval_loss": 0.4147878587245941, | |
| "eval_runtime": 1.3663, | |
| "eval_samples_per_second": 135.406, | |
| "eval_steps_per_second": 8.783, | |
| "step": 408000 | |
| }, | |
| { | |
| "epoch": 56.68, | |
| "learning_rate": 2.2474321872010953e-05, | |
| "loss": 0.4508, | |
| "step": 408500 | |
| }, | |
| { | |
| "epoch": 56.75, | |
| "learning_rate": 2.234274007018007e-05, | |
| "loss": 0.4499, | |
| "step": 409000 | |
| }, | |
| { | |
| "epoch": 56.75, | |
| "eval_loss": 0.4182484447956085, | |
| "eval_runtime": 1.4788, | |
| "eval_samples_per_second": 125.098, | |
| "eval_steps_per_second": 8.114, | |
| "step": 409000 | |
| }, | |
| { | |
| "epoch": 56.82, | |
| "learning_rate": 2.2212050071226316e-05, | |
| "loss": 0.4494, | |
| "step": 409500 | |
| }, | |
| { | |
| "epoch": 56.89, | |
| "learning_rate": 2.2081729497221867e-05, | |
| "loss": 0.4498, | |
| "step": 410000 | |
| }, | |
| { | |
| "epoch": 56.89, | |
| "eval_loss": 0.42287564277648926, | |
| "eval_runtime": 1.4156, | |
| "eval_samples_per_second": 130.687, | |
| "eval_steps_per_second": 8.477, | |
| "step": 410000 | |
| }, | |
| { | |
| "epoch": 56.96, | |
| "learning_rate": 2.1952301049460503e-05, | |
| "loss": 0.4499, | |
| "step": 410500 | |
| }, | |
| { | |
| "epoch": 57.03, | |
| "learning_rate": 2.1823247392531053e-05, | |
| "loss": 0.4501, | |
| "step": 411000 | |
| }, | |
| { | |
| "epoch": 57.03, | |
| "eval_loss": 0.42520666122436523, | |
| "eval_runtime": 1.4416, | |
| "eval_samples_per_second": 128.331, | |
| "eval_steps_per_second": 8.324, | |
| "step": 411000 | |
| }, | |
| { | |
| "epoch": 57.1, | |
| "learning_rate": 2.1694829947247343e-05, | |
| "loss": 0.4496, | |
| "step": 411500 | |
| }, | |
| { | |
| "epoch": 57.17, | |
| "learning_rate": 2.156705011796204e-05, | |
| "loss": 0.4497, | |
| "step": 412000 | |
| }, | |
| { | |
| "epoch": 57.17, | |
| "eval_loss": 0.4220258593559265, | |
| "eval_runtime": 1.3143, | |
| "eval_samples_per_second": 140.763, | |
| "eval_steps_per_second": 9.131, | |
| "step": 412000 | |
| }, | |
| { | |
| "epoch": 57.24, | |
| "learning_rate": 2.1439909302054865e-05, | |
| "loss": 0.4495, | |
| "step": 412500 | |
| }, | |
| { | |
| "epoch": 57.31, | |
| "learning_rate": 2.13134088899174e-05, | |
| "loss": 0.45, | |
| "step": 413000 | |
| }, | |
| { | |
| "epoch": 57.31, | |
| "eval_loss": 0.4181089699268341, | |
| "eval_runtime": 1.3009, | |
| "eval_samples_per_second": 142.205, | |
| "eval_steps_per_second": 9.224, | |
| "step": 413000 | |
| }, | |
| { | |
| "epoch": 57.37, | |
| "learning_rate": 2.1187801340768273e-05, | |
| "loss": 0.4495, | |
| "step": 413500 | |
| }, | |
| { | |
| "epoch": 57.44, | |
| "learning_rate": 2.106258459162047e-05, | |
| "loss": 0.4497, | |
| "step": 414000 | |
| }, | |
| { | |
| "epoch": 57.44, | |
| "eval_loss": 0.42704877257347107, | |
| "eval_runtime": 1.5278, | |
| "eval_samples_per_second": 121.087, | |
| "eval_steps_per_second": 7.854, | |
| "step": 414000 | |
| }, | |
| { | |
| "epoch": 57.51, | |
| "learning_rate": 2.0938012372604977e-05, | |
| "loss": 0.4494, | |
| "step": 414500 | |
| }, | |
| { | |
| "epoch": 57.58, | |
| "learning_rate": 2.081408604602362e-05, | |
| "loss": 0.4497, | |
| "step": 415000 | |
| }, | |
| { | |
| "epoch": 57.58, | |
| "eval_loss": 0.4207887351512909, | |
| "eval_runtime": 1.466, | |
| "eval_samples_per_second": 126.195, | |
| "eval_steps_per_second": 8.186, | |
| "step": 415000 | |
| }, | |
| { | |
| "epoch": 57.65, | |
| "learning_rate": 2.0691052878422197e-05, | |
| "loss": 0.4498, | |
| "step": 415500 | |
| }, | |
| { | |
| "epoch": 57.72, | |
| "learning_rate": 2.0568421096813818e-05, | |
| "loss": 0.4499, | |
| "step": 416000 | |
| }, | |
| { | |
| "epoch": 57.72, | |
| "eval_loss": 0.42236852645874023, | |
| "eval_runtime": 1.4433, | |
| "eval_samples_per_second": 128.175, | |
| "eval_steps_per_second": 8.314, | |
| "step": 416000 | |
| }, | |
| { | |
| "epoch": 57.79, | |
| "learning_rate": 2.0446439249430564e-05, | |
| "loss": 0.4494, | |
| "step": 416500 | |
| }, | |
| { | |
| "epoch": 57.86, | |
| "learning_rate": 2.0325108670246337e-05, | |
| "loss": 0.4496, | |
| "step": 417000 | |
| }, | |
| { | |
| "epoch": 57.86, | |
| "eval_loss": 0.42070433497428894, | |
| "eval_runtime": 1.4057, | |
| "eval_samples_per_second": 131.609, | |
| "eval_steps_per_second": 8.537, | |
| "step": 417000 | |
| }, | |
| { | |
| "epoch": 57.93, | |
| "learning_rate": 2.0204430686112928e-05, | |
| "loss": 0.4492, | |
| "step": 417500 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "learning_rate": 2.0084406616745435e-05, | |
| "loss": 0.4494, | |
| "step": 418000 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_loss": 0.4267515540122986, | |
| "eval_runtime": 1.3575, | |
| "eval_samples_per_second": 136.277, | |
| "eval_steps_per_second": 8.84, | |
| "step": 418000 | |
| }, | |
| { | |
| "epoch": 58.07, | |
| "learning_rate": 1.9965275857606217e-05, | |
| "loss": 0.45, | |
| "step": 418500 | |
| }, | |
| { | |
| "epoch": 58.14, | |
| "learning_rate": 1.984656223393361e-05, | |
| "loss": 0.4499, | |
| "step": 419000 | |
| }, | |
| { | |
| "epoch": 58.14, | |
| "eval_loss": 0.4240288734436035, | |
| "eval_runtime": 1.564, | |
| "eval_samples_per_second": 118.29, | |
| "eval_steps_per_second": 7.673, | |
| "step": 419000 | |
| }, | |
| { | |
| "epoch": 58.21, | |
| "learning_rate": 1.9728506438618975e-05, | |
| "loss": 0.4499, | |
| "step": 419500 | |
| }, | |
| { | |
| "epoch": 58.28, | |
| "learning_rate": 1.9611109762701606e-05, | |
| "loss": 0.4495, | |
| "step": 420000 | |
| }, | |
| { | |
| "epoch": 58.28, | |
| "eval_loss": 0.4293997287750244, | |
| "eval_runtime": 1.3004, | |
| "eval_samples_per_second": 142.261, | |
| "eval_steps_per_second": 9.228, | |
| "step": 420000 | |
| }, | |
| { | |
| "epoch": 58.35, | |
| "learning_rate": 1.94943734900127e-05, | |
| "loss": 0.4492, | |
| "step": 420500 | |
| }, | |
| { | |
| "epoch": 58.42, | |
| "learning_rate": 1.937853038514574e-05, | |
| "loss": 0.4487, | |
| "step": 421000 | |
| }, | |
| { | |
| "epoch": 58.42, | |
| "eval_loss": 0.4207267463207245, | |
| "eval_runtime": 1.3489, | |
| "eval_samples_per_second": 137.154, | |
| "eval_steps_per_second": 8.896, | |
| "step": 421000 | |
| }, | |
| { | |
| "epoch": 58.48, | |
| "learning_rate": 1.9263117414344867e-05, | |
| "loss": 0.4484, | |
| "step": 421500 | |
| }, | |
| { | |
| "epoch": 58.55, | |
| "learning_rate": 1.9148368652361025e-05, | |
| "loss": 0.4495, | |
| "step": 422000 | |
| }, | |
| { | |
| "epoch": 58.55, | |
| "eval_loss": 0.4246247708797455, | |
| "eval_runtime": 1.4028, | |
| "eval_samples_per_second": 131.881, | |
| "eval_steps_per_second": 8.554, | |
| "step": 422000 | |
| }, | |
| { | |
| "epoch": 58.62, | |
| "learning_rate": 1.903428535406832e-05, | |
| "loss": 0.4493, | |
| "step": 422500 | |
| }, | |
| { | |
| "epoch": 58.69, | |
| "learning_rate": 1.8920868767063384e-05, | |
| "loss": 0.4491, | |
| "step": 423000 | |
| }, | |
| { | |
| "epoch": 58.69, | |
| "eval_loss": 0.42133408784866333, | |
| "eval_runtime": 1.3492, | |
| "eval_samples_per_second": 137.118, | |
| "eval_steps_per_second": 8.894, | |
| "step": 423000 | |
| }, | |
| { | |
| "epoch": 58.76, | |
| "learning_rate": 1.880812013165191e-05, | |
| "loss": 0.4486, | |
| "step": 423500 | |
| }, | |
| { | |
| "epoch": 58.83, | |
| "learning_rate": 1.8696040680834842e-05, | |
| "loss": 0.4492, | |
| "step": 424000 | |
| }, | |
| { | |
| "epoch": 58.83, | |
| "eval_loss": 0.4240739643573761, | |
| "eval_runtime": 1.3437, | |
| "eval_samples_per_second": 137.682, | |
| "eval_steps_per_second": 8.931, | |
| "step": 424000 | |
| }, | |
| { | |
| "epoch": 58.9, | |
| "learning_rate": 1.8584631640295125e-05, | |
| "loss": 0.4486, | |
| "step": 424500 | |
| }, | |
| { | |
| "epoch": 58.97, | |
| "learning_rate": 1.84741150321165e-05, | |
| "loss": 0.4486, | |
| "step": 425000 | |
| }, | |
| { | |
| "epoch": 58.97, | |
| "eval_loss": 0.4246968924999237, | |
| "eval_runtime": 1.4975, | |
| "eval_samples_per_second": 123.537, | |
| "eval_steps_per_second": 8.013, | |
| "step": 425000 | |
| }, | |
| { | |
| "epoch": 59.04, | |
| "learning_rate": 1.8364049112957962e-05, | |
| "loss": 0.4489, | |
| "step": 425500 | |
| }, | |
| { | |
| "epoch": 59.11, | |
| "learning_rate": 1.8254657234683382e-05, | |
| "loss": 0.4485, | |
| "step": 426000 | |
| }, | |
| { | |
| "epoch": 59.11, | |
| "eval_loss": 0.4162987768650055, | |
| "eval_runtime": 1.4233, | |
| "eval_samples_per_second": 129.976, | |
| "eval_steps_per_second": 8.431, | |
| "step": 426000 | |
| }, | |
| { | |
| "epoch": 59.18, | |
| "learning_rate": 1.8145940593584787e-05, | |
| "loss": 0.4488, | |
| "step": 426500 | |
| }, | |
| { | |
| "epoch": 59.25, | |
| "learning_rate": 1.8037900378569963e-05, | |
| "loss": 0.4489, | |
| "step": 427000 | |
| }, | |
| { | |
| "epoch": 59.25, | |
| "eval_loss": 0.4239360988140106, | |
| "eval_runtime": 1.3783, | |
| "eval_samples_per_second": 134.225, | |
| "eval_steps_per_second": 8.706, | |
| "step": 427000 | |
| }, | |
| { | |
| "epoch": 59.32, | |
| "learning_rate": 1.7930537771149402e-05, | |
| "loss": 0.4489, | |
| "step": 427500 | |
| }, | |
| { | |
| "epoch": 59.39, | |
| "learning_rate": 1.7824066634873994e-05, | |
| "loss": 0.4483, | |
| "step": 428000 | |
| }, | |
| { | |
| "epoch": 59.39, | |
| "eval_loss": 0.4239516854286194, | |
| "eval_runtime": 1.2618, | |
| "eval_samples_per_second": 146.616, | |
| "eval_steps_per_second": 9.51, | |
| "step": 428000 | |
| }, | |
| { | |
| "epoch": 59.46, | |
| "learning_rate": 1.7718061396463565e-05, | |
| "loss": 0.4486, | |
| "step": 428500 | |
| }, | |
| { | |
| "epoch": 59.53, | |
| "learning_rate": 1.761294723111157e-05, | |
| "loss": 0.4491, | |
| "step": 429000 | |
| }, | |
| { | |
| "epoch": 59.53, | |
| "eval_loss": 0.42144644260406494, | |
| "eval_runtime": 1.3607, | |
| "eval_samples_per_second": 135.957, | |
| "eval_steps_per_second": 8.819, | |
| "step": 429000 | |
| }, | |
| { | |
| "epoch": 59.59, | |
| "learning_rate": 1.750830398945445e-05, | |
| "loss": 0.448, | |
| "step": 429500 | |
| }, | |
| { | |
| "epoch": 59.66, | |
| "learning_rate": 1.7404344146972867e-05, | |
| "loss": 0.4485, | |
| "step": 430000 | |
| }, | |
| { | |
| "epoch": 59.66, | |
| "eval_loss": 0.4285011887550354, | |
| "eval_runtime": 1.3489, | |
| "eval_samples_per_second": 137.154, | |
| "eval_steps_per_second": 8.896, | |
| "step": 430000 | |
| }, | |
| { | |
| "epoch": 59.73, | |
| "learning_rate": 1.730106884055495e-05, | |
| "loss": 0.449, | |
| "step": 430500 | |
| }, | |
| { | |
| "epoch": 59.8, | |
| "learning_rate": 1.7198479199602952e-05, | |
| "loss": 0.449, | |
| "step": 431000 | |
| }, | |
| { | |
| "epoch": 59.8, | |
| "eval_loss": 0.42652076482772827, | |
| "eval_runtime": 1.388, | |
| "eval_samples_per_second": 133.284, | |
| "eval_steps_per_second": 8.645, | |
| "step": 431000 | |
| }, | |
| { | |
| "epoch": 59.87, | |
| "learning_rate": 1.7096576346020748e-05, | |
| "loss": 0.4488, | |
| "step": 431500 | |
| }, | |
| { | |
| "epoch": 59.94, | |
| "learning_rate": 1.699536139420159e-05, | |
| "loss": 0.4484, | |
| "step": 432000 | |
| }, | |
| { | |
| "epoch": 59.94, | |
| "eval_loss": 0.41880765557289124, | |
| "eval_runtime": 1.4677, | |
| "eval_samples_per_second": 126.046, | |
| "eval_steps_per_second": 8.176, | |
| "step": 432000 | |
| }, | |
| { | |
| "epoch": 60.01, | |
| "learning_rate": 1.6895035814539804e-05, | |
| "loss": 0.449, | |
| "step": 432500 | |
| }, | |
| { | |
| "epoch": 60.08, | |
| "learning_rate": 1.6795198598015313e-05, | |
| "loss": 0.4484, | |
| "step": 433000 | |
| }, | |
| { | |
| "epoch": 60.08, | |
| "eval_loss": 0.4175633490085602, | |
| "eval_runtime": 1.3456, | |
| "eval_samples_per_second": 137.481, | |
| "eval_steps_per_second": 8.918, | |
| "step": 433000 | |
| }, | |
| { | |
| "epoch": 60.15, | |
| "learning_rate": 1.6696052579072644e-05, | |
| "loss": 0.4473, | |
| "step": 433500 | |
| }, | |
| { | |
| "epoch": 60.22, | |
| "learning_rate": 1.6597598841956794e-05, | |
| "loss": 0.4488, | |
| "step": 434000 | |
| }, | |
| { | |
| "epoch": 60.22, | |
| "eval_loss": 0.4199577867984772, | |
| "eval_runtime": 1.3012, | |
| "eval_samples_per_second": 142.172, | |
| "eval_steps_per_second": 9.222, | |
| "step": 434000 | |
| }, | |
| { | |
| "epoch": 60.29, | |
| "learning_rate": 1.6500033291415622e-05, | |
| "loss": 0.448, | |
| "step": 434500 | |
| }, | |
| { | |
| "epoch": 60.36, | |
| "learning_rate": 1.640296595047672e-05, | |
| "loss": 0.448, | |
| "step": 435000 | |
| }, | |
| { | |
| "epoch": 60.36, | |
| "eval_loss": 0.4116031229496002, | |
| "eval_runtime": 1.4238, | |
| "eval_samples_per_second": 129.935, | |
| "eval_steps_per_second": 8.428, | |
| "step": 435000 | |
| }, | |
| { | |
| "epoch": 60.43, | |
| "learning_rate": 1.6306594096513022e-05, | |
| "loss": 0.4484, | |
| "step": 435500 | |
| }, | |
| { | |
| "epoch": 60.5, | |
| "learning_rate": 1.621091878343171e-05, | |
| "loss": 0.4477, | |
| "step": 436000 | |
| }, | |
| { | |
| "epoch": 60.5, | |
| "eval_loss": 0.42147019505500793, | |
| "eval_runtime": 1.2453, | |
| "eval_samples_per_second": 148.563, | |
| "eval_steps_per_second": 9.636, | |
| "step": 436000 | |
| }, | |
| { | |
| "epoch": 60.57, | |
| "learning_rate": 1.6115941057522653e-05, | |
| "loss": 0.4485, | |
| "step": 436500 | |
| }, | |
| { | |
| "epoch": 60.64, | |
| "learning_rate": 1.6021661957447076e-05, | |
| "loss": 0.4484, | |
| "step": 437000 | |
| }, | |
| { | |
| "epoch": 60.64, | |
| "eval_loss": 0.4203680157661438, | |
| "eval_runtime": 1.4005, | |
| "eval_samples_per_second": 132.091, | |
| "eval_steps_per_second": 8.568, | |
| "step": 437000 | |
| }, | |
| { | |
| "epoch": 60.7, | |
| "learning_rate": 1.5928082514226098e-05, | |
| "loss": 0.4487, | |
| "step": 437500 | |
| }, | |
| { | |
| "epoch": 60.77, | |
| "learning_rate": 1.5835388808800246e-05, | |
| "loss": 0.448, | |
| "step": 438000 | |
| }, | |
| { | |
| "epoch": 60.77, | |
| "eval_loss": 0.40932518243789673, | |
| "eval_runtime": 1.3707, | |
| "eval_samples_per_second": 134.964, | |
| "eval_steps_per_second": 8.754, | |
| "step": 438000 | |
| }, | |
| { | |
| "epoch": 60.84, | |
| "learning_rate": 1.5743210337334882e-05, | |
| "loss": 0.448, | |
| "step": 438500 | |
| }, | |
| { | |
| "epoch": 60.91, | |
| "learning_rate": 1.5651734567826426e-05, | |
| "loss": 0.4479, | |
| "step": 439000 | |
| }, | |
| { | |
| "epoch": 60.91, | |
| "eval_loss": 0.41809263825416565, | |
| "eval_runtime": 1.2925, | |
| "eval_samples_per_second": 143.136, | |
| "eval_steps_per_second": 9.285, | |
| "step": 439000 | |
| }, | |
| { | |
| "epoch": 60.98, | |
| "learning_rate": 1.556096250063923e-05, | |
| "loss": 0.448, | |
| "step": 439500 | |
| }, | |
| { | |
| "epoch": 61.05, | |
| "learning_rate": 1.547089512844209e-05, | |
| "loss": 0.4481, | |
| "step": 440000 | |
| }, | |
| { | |
| "epoch": 61.05, | |
| "eval_loss": 0.4232490360736847, | |
| "eval_runtime": 1.3629, | |
| "eval_samples_per_second": 135.739, | |
| "eval_steps_per_second": 8.805, | |
| "step": 440000 | |
| }, | |
| { | |
| "epoch": 61.12, | |
| "learning_rate": 1.538153343619732e-05, | |
| "loss": 0.4478, | |
| "step": 440500 | |
| }, | |
| { | |
| "epoch": 61.19, | |
| "learning_rate": 1.5293055005330644e-05, | |
| "loss": 0.4477, | |
| "step": 441000 | |
| }, | |
| { | |
| "epoch": 61.19, | |
| "eval_loss": 0.4201977252960205, | |
| "eval_runtime": 1.4241, | |
| "eval_samples_per_second": 129.905, | |
| "eval_steps_per_second": 8.426, | |
| "step": 441000 | |
| }, | |
| { | |
| "epoch": 61.26, | |
| "learning_rate": 1.5205106180782385e-05, | |
| "loss": 0.4482, | |
| "step": 441500 | |
| }, | |
| { | |
| "epoch": 61.33, | |
| "learning_rate": 1.511786594281187e-05, | |
| "loss": 0.4478, | |
| "step": 442000 | |
| }, | |
| { | |
| "epoch": 61.33, | |
| "eval_loss": 0.41671010851860046, | |
| "eval_runtime": 1.351, | |
| "eval_samples_per_second": 136.94, | |
| "eval_steps_per_second": 8.883, | |
| "step": 442000 | |
| }, | |
| { | |
| "epoch": 61.4, | |
| "learning_rate": 1.5031335245464367e-05, | |
| "loss": 0.4485, | |
| "step": 442500 | |
| }, | |
| { | |
| "epoch": 61.47, | |
| "learning_rate": 1.4945856899331104e-05, | |
| "loss": 0.4481, | |
| "step": 443000 | |
| }, | |
| { | |
| "epoch": 61.47, | |
| "eval_loss": 0.4173124432563782, | |
| "eval_runtime": 1.4874, | |
| "eval_samples_per_second": 124.381, | |
| "eval_steps_per_second": 8.068, | |
| "step": 443000 | |
| }, | |
| { | |
| "epoch": 61.54, | |
| "learning_rate": 1.48610842948986e-05, | |
| "loss": 0.4483, | |
| "step": 443500 | |
| }, | |
| { | |
| "epoch": 61.61, | |
| "learning_rate": 1.477685025624781e-05, | |
| "loss": 0.4483, | |
| "step": 444000 | |
| }, | |
| { | |
| "epoch": 61.61, | |
| "eval_loss": 0.41581404209136963, | |
| "eval_runtime": 1.6578, | |
| "eval_samples_per_second": 111.595, | |
| "eval_steps_per_second": 7.239, | |
| "step": 444000 | |
| }, | |
| { | |
| "epoch": 61.68, | |
| "learning_rate": 1.4693159969167797e-05, | |
| "loss": 0.4483, | |
| "step": 444500 | |
| }, | |
| { | |
| "epoch": 61.75, | |
| "learning_rate": 1.4610183867227295e-05, | |
| "loss": 0.4473, | |
| "step": 445000 | |
| }, | |
| { | |
| "epoch": 61.75, | |
| "eval_loss": 0.41741910576820374, | |
| "eval_runtime": 1.7118, | |
| "eval_samples_per_second": 108.076, | |
| "eval_steps_per_second": 7.01, | |
| "step": 445000 | |
| }, | |
| { | |
| "epoch": 61.81, | |
| "learning_rate": 1.4527922857839624e-05, | |
| "loss": 0.4478, | |
| "step": 445500 | |
| }, | |
| { | |
| "epoch": 61.88, | |
| "learning_rate": 1.4446377840598036e-05, | |
| "loss": 0.4474, | |
| "step": 446000 | |
| }, | |
| { | |
| "epoch": 61.88, | |
| "eval_loss": 0.4265962243080139, | |
| "eval_runtime": 1.6624, | |
| "eval_samples_per_second": 111.288, | |
| "eval_steps_per_second": 7.219, | |
| "step": 446000 | |
| }, | |
| { | |
| "epoch": 61.95, | |
| "learning_rate": 1.4365549707265762e-05, | |
| "loss": 0.4477, | |
| "step": 446500 | |
| }, | |
| { | |
| "epoch": 62.02, | |
| "learning_rate": 1.4285439341766323e-05, | |
| "loss": 0.4477, | |
| "step": 447000 | |
| }, | |
| { | |
| "epoch": 62.02, | |
| "eval_loss": 0.424228310585022, | |
| "eval_runtime": 1.5115, | |
| "eval_samples_per_second": 122.398, | |
| "eval_steps_per_second": 7.939, | |
| "step": 447000 | |
| }, | |
| { | |
| "epoch": 62.09, | |
| "learning_rate": 1.420604762017384e-05, | |
| "loss": 0.4476, | |
| "step": 447500 | |
| }, | |
| { | |
| "epoch": 62.16, | |
| "learning_rate": 1.4127375410703455e-05, | |
| "loss": 0.4476, | |
| "step": 448000 | |
| }, | |
| { | |
| "epoch": 62.16, | |
| "eval_loss": 0.42402705550193787, | |
| "eval_runtime": 1.3286, | |
| "eval_samples_per_second": 139.247, | |
| "eval_steps_per_second": 9.032, | |
| "step": 448000 | |
| }, | |
| { | |
| "epoch": 62.23, | |
| "learning_rate": 1.4049423573701852e-05, | |
| "loss": 0.4475, | |
| "step": 448500 | |
| }, | |
| { | |
| "epoch": 62.3, | |
| "learning_rate": 1.3972192961637821e-05, | |
| "loss": 0.4478, | |
| "step": 449000 | |
| }, | |
| { | |
| "epoch": 62.3, | |
| "eval_loss": 0.42862966656684875, | |
| "eval_runtime": 1.3196, | |
| "eval_samples_per_second": 140.197, | |
| "eval_steps_per_second": 9.094, | |
| "step": 449000 | |
| }, | |
| { | |
| "epoch": 62.37, | |
| "learning_rate": 1.3895684419092996e-05, | |
| "loss": 0.4475, | |
| "step": 449500 | |
| }, | |
| { | |
| "epoch": 62.44, | |
| "learning_rate": 1.3819898782752499e-05, | |
| "loss": 0.4474, | |
| "step": 450000 | |
| }, | |
| { | |
| "epoch": 62.44, | |
| "eval_loss": 0.4294210374355316, | |
| "eval_runtime": 2.0421, | |
| "eval_samples_per_second": 90.595, | |
| "eval_steps_per_second": 5.876, | |
| "step": 450000 | |
| }, | |
| { | |
| "epoch": 62.51, | |
| "learning_rate": 1.3744836881395923e-05, | |
| "loss": 0.4479, | |
| "step": 450500 | |
| }, | |
| { | |
| "epoch": 62.58, | |
| "learning_rate": 1.3670647486930825e-05, | |
| "loss": 0.4482, | |
| "step": 451000 | |
| }, | |
| { | |
| "epoch": 62.58, | |
| "eval_loss": 0.41438260674476624, | |
| "eval_runtime": 1.3839, | |
| "eval_samples_per_second": 133.675, | |
| "eval_steps_per_second": 8.671, | |
| "step": 451000 | |
| }, | |
| { | |
| "epoch": 62.65, | |
| "learning_rate": 1.3597034058669625e-05, | |
| "loss": 0.4476, | |
| "step": 451500 | |
| }, | |
| { | |
| "epoch": 62.72, | |
| "learning_rate": 1.3524146802605277e-05, | |
| "loss": 0.4471, | |
| "step": 452000 | |
| }, | |
| { | |
| "epoch": 62.72, | |
| "eval_loss": 0.4316233992576599, | |
| "eval_runtime": 1.385, | |
| "eval_samples_per_second": 133.575, | |
| "eval_steps_per_second": 8.664, | |
| "step": 452000 | |
| }, | |
| { | |
| "epoch": 62.79, | |
| "learning_rate": 1.3451986515821102e-05, | |
| "loss": 0.4468, | |
| "step": 452500 | |
| }, | |
| { | |
| "epoch": 62.86, | |
| "learning_rate": 1.3380553987450471e-05, | |
| "loss": 0.448, | |
| "step": 453000 | |
| }, | |
| { | |
| "epoch": 62.86, | |
| "eval_loss": 0.4228358864784241, | |
| "eval_runtime": 1.383, | |
| "eval_samples_per_second": 133.771, | |
| "eval_steps_per_second": 8.677, | |
| "step": 453000 | |
| }, | |
| { | |
| "epoch": 62.92, | |
| "learning_rate": 1.3309849998668048e-05, | |
| "loss": 0.4476, | |
| "step": 453500 | |
| }, | |
| { | |
| "epoch": 62.99, | |
| "learning_rate": 1.3239875322681331e-05, | |
| "loss": 0.4474, | |
| "step": 454000 | |
| }, | |
| { | |
| "epoch": 62.99, | |
| "eval_loss": 0.42418819665908813, | |
| "eval_runtime": 1.4256, | |
| "eval_samples_per_second": 129.767, | |
| "eval_steps_per_second": 8.417, | |
| "step": 454000 | |
| }, | |
| { | |
| "epoch": 63.06, | |
| "learning_rate": 1.3170630724722182e-05, | |
| "loss": 0.4477, | |
| "step": 454500 | |
| }, | |
| { | |
| "epoch": 63.13, | |
| "learning_rate": 1.3102116962038392e-05, | |
| "loss": 0.447, | |
| "step": 455000 | |
| }, | |
| { | |
| "epoch": 63.13, | |
| "eval_loss": 0.4230823516845703, | |
| "eval_runtime": 1.4363, | |
| "eval_samples_per_second": 128.803, | |
| "eval_steps_per_second": 8.355, | |
| "step": 455000 | |
| }, | |
| { | |
| "epoch": 63.2, | |
| "learning_rate": 1.3034469617626461e-05, | |
| "loss": 0.4473, | |
| "step": 455500 | |
| }, | |
| { | |
| "epoch": 63.27, | |
| "learning_rate": 1.2967418299873526e-05, | |
| "loss": 0.4475, | |
| "step": 456000 | |
| }, | |
| { | |
| "epoch": 63.27, | |
| "eval_loss": 0.4234711825847626, | |
| "eval_runtime": 1.3311, | |
| "eval_samples_per_second": 138.983, | |
| "eval_steps_per_second": 9.015, | |
| "step": 456000 | |
| }, | |
| { | |
| "epoch": 63.34, | |
| "learning_rate": 1.29011000396945e-05, | |
| "loss": 0.4475, | |
| "step": 456500 | |
| }, | |
| { | |
| "epoch": 63.41, | |
| "learning_rate": 1.2835515562335245e-05, | |
| "loss": 0.4475, | |
| "step": 457000 | |
| }, | |
| { | |
| "epoch": 63.41, | |
| "eval_loss": 0.42788252234458923, | |
| "eval_runtime": 1.3825, | |
| "eval_samples_per_second": 133.816, | |
| "eval_steps_per_second": 8.68, | |
| "step": 457000 | |
| }, | |
| { | |
| "epoch": 63.48, | |
| "learning_rate": 1.277079455146798e-05, | |
| "loss": 0.4477, | |
| "step": 457500 | |
| }, | |
| { | |
| "epoch": 63.55, | |
| "learning_rate": 1.2706678312259012e-05, | |
| "loss": 0.4476, | |
| "step": 458000 | |
| }, | |
| { | |
| "epoch": 63.55, | |
| "eval_loss": 0.42295461893081665, | |
| "eval_runtime": 1.4126, | |
| "eval_samples_per_second": 130.962, | |
| "eval_steps_per_second": 8.495, | |
| "step": 458000 | |
| }, | |
| { | |
| "epoch": 63.62, | |
| "learning_rate": 1.2643297982034681e-05, | |
| "loss": 0.4469, | |
| "step": 458500 | |
| }, | |
| { | |
| "epoch": 63.69, | |
| "learning_rate": 1.2580654253912125e-05, | |
| "loss": 0.4464, | |
| "step": 459000 | |
| }, | |
| { | |
| "epoch": 63.69, | |
| "eval_loss": 0.4144819974899292, | |
| "eval_runtime": 1.3008, | |
| "eval_samples_per_second": 142.217, | |
| "eval_steps_per_second": 9.225, | |
| "step": 459000 | |
| }, | |
| { | |
| "epoch": 63.76, | |
| "learning_rate": 1.251874781295312e-05, | |
| "loss": 0.4468, | |
| "step": 459500 | |
| }, | |
| { | |
| "epoch": 63.83, | |
| "learning_rate": 1.2457579336156563e-05, | |
| "loss": 0.4467, | |
| "step": 460000 | |
| }, | |
| { | |
| "epoch": 63.83, | |
| "eval_loss": 0.42297813296318054, | |
| "eval_runtime": 1.5334, | |
| "eval_samples_per_second": 120.645, | |
| "eval_steps_per_second": 7.826, | |
| "step": 460000 | |
| }, | |
| { | |
| "epoch": 63.9, | |
| "learning_rate": 1.2397149492451143e-05, | |
| "loss": 0.4472, | |
| "step": 460500 | |
| }, | |
| { | |
| "epoch": 63.97, | |
| "learning_rate": 1.2337458942687934e-05, | |
| "loss": 0.4465, | |
| "step": 461000 | |
| }, | |
| { | |
| "epoch": 63.97, | |
| "eval_loss": 0.42076122760772705, | |
| "eval_runtime": 1.481, | |
| "eval_samples_per_second": 124.918, | |
| "eval_steps_per_second": 8.103, | |
| "step": 461000 | |
| }, | |
| { | |
| "epoch": 64.03, | |
| "learning_rate": 1.2278508339633242e-05, | |
| "loss": 0.4481, | |
| "step": 461500 | |
| }, | |
| { | |
| "epoch": 64.1, | |
| "learning_rate": 1.2220298327961394e-05, | |
| "loss": 0.4466, | |
| "step": 462000 | |
| }, | |
| { | |
| "epoch": 64.1, | |
| "eval_loss": 0.42430469393730164, | |
| "eval_runtime": 1.3654, | |
| "eval_samples_per_second": 135.494, | |
| "eval_steps_per_second": 8.789, | |
| "step": 462000 | |
| }, | |
| { | |
| "epoch": 64.17, | |
| "learning_rate": 1.216282954424777e-05, | |
| "loss": 0.4469, | |
| "step": 462500 | |
| }, | |
| { | |
| "epoch": 64.24, | |
| "learning_rate": 1.2106102616961766e-05, | |
| "loss": 0.447, | |
| "step": 463000 | |
| }, | |
| { | |
| "epoch": 64.24, | |
| "eval_loss": 0.42202654480934143, | |
| "eval_runtime": 1.4124, | |
| "eval_samples_per_second": 130.982, | |
| "eval_steps_per_second": 8.496, | |
| "step": 463000 | |
| }, | |
| { | |
| "epoch": 64.31, | |
| "learning_rate": 1.2050118166459983e-05, | |
| "loss": 0.4469, | |
| "step": 463500 | |
| }, | |
| { | |
| "epoch": 64.38, | |
| "learning_rate": 1.199498654569664e-05, | |
| "loss": 0.4473, | |
| "step": 464000 | |
| }, | |
| { | |
| "epoch": 64.38, | |
| "eval_loss": 0.4253380000591278, | |
| "eval_runtime": 1.5206, | |
| "eval_samples_per_second": 121.661, | |
| "eval_steps_per_second": 7.891, | |
| "step": 464000 | |
| }, | |
| { | |
| "epoch": 64.45, | |
| "learning_rate": 1.1940487389364166e-05, | |
| "loss": 0.4468, | |
| "step": 464500 | |
| }, | |
| { | |
| "epoch": 64.52, | |
| "learning_rate": 1.1886732520957502e-05, | |
| "loss": 0.4471, | |
| "step": 465000 | |
| }, | |
| { | |
| "epoch": 64.52, | |
| "eval_loss": 0.41941824555397034, | |
| "eval_runtime": 1.3857, | |
| "eval_samples_per_second": 133.507, | |
| "eval_steps_per_second": 8.66, | |
| "step": 465000 | |
| }, | |
| { | |
| "epoch": 64.59, | |
| "learning_rate": 1.1833722528331292e-05, | |
| "loss": 0.4471, | |
| "step": 465500 | |
| }, | |
| { | |
| "epoch": 64.66, | |
| "learning_rate": 1.1781665563635293e-05, | |
| "loss": 0.447, | |
| "step": 466000 | |
| }, | |
| { | |
| "epoch": 64.66, | |
| "eval_loss": 0.4262169599533081, | |
| "eval_runtime": 1.4244, | |
| "eval_samples_per_second": 129.876, | |
| "eval_steps_per_second": 8.424, | |
| "step": 466000 | |
| }, | |
| { | |
| "epoch": 64.73, | |
| "learning_rate": 1.1730144068308223e-05, | |
| "loss": 0.4466, | |
| "step": 466500 | |
| }, | |
| { | |
| "epoch": 64.8, | |
| "learning_rate": 1.167936916118783e-05, | |
| "loss": 0.447, | |
| "step": 467000 | |
| }, | |
| { | |
| "epoch": 64.8, | |
| "eval_loss": 0.4245114028453827, | |
| "eval_runtime": 1.37, | |
| "eval_samples_per_second": 135.041, | |
| "eval_steps_per_second": 8.759, | |
| "step": 467000 | |
| }, | |
| { | |
| "epoch": 64.87, | |
| "learning_rate": 1.1629341397540343e-05, | |
| "loss": 0.4466, | |
| "step": 467500 | |
| }, | |
| { | |
| "epoch": 64.94, | |
| "learning_rate": 1.1580061324461396e-05, | |
| "loss": 0.4468, | |
| "step": 468000 | |
| }, | |
| { | |
| "epoch": 64.94, | |
| "eval_loss": 0.41434457898139954, | |
| "eval_runtime": 1.7979, | |
| "eval_samples_per_second": 102.898, | |
| "eval_steps_per_second": 6.674, | |
| "step": 468000 | |
| }, | |
| { | |
| "epoch": 65.01, | |
| "learning_rate": 1.1531529480869956e-05, | |
| "loss": 0.4471, | |
| "step": 468500 | |
| }, | |
| { | |
| "epoch": 65.08, | |
| "learning_rate": 1.1483746397502495e-05, | |
| "loss": 0.4463, | |
| "step": 469000 | |
| }, | |
| { | |
| "epoch": 65.08, | |
| "eval_loss": 0.4186690151691437, | |
| "eval_runtime": 1.3076, | |
| "eval_samples_per_second": 141.477, | |
| "eval_steps_per_second": 9.177, | |
| "step": 469000 | |
| }, | |
| { | |
| "epoch": 65.14, | |
| "learning_rate": 1.1436712596907158e-05, | |
| "loss": 0.4465, | |
| "step": 469500 | |
| }, | |
| { | |
| "epoch": 65.21, | |
| "learning_rate": 1.1390428593438056e-05, | |
| "loss": 0.4465, | |
| "step": 470000 | |
| }, | |
| { | |
| "epoch": 65.21, | |
| "eval_loss": 0.41854894161224365, | |
| "eval_runtime": 1.6737, | |
| "eval_samples_per_second": 110.532, | |
| "eval_steps_per_second": 7.17, | |
| "step": 470000 | |
| }, | |
| { | |
| "epoch": 65.28, | |
| "learning_rate": 1.1344894893249622e-05, | |
| "loss": 0.447, | |
| "step": 470500 | |
| }, | |
| { | |
| "epoch": 65.35, | |
| "learning_rate": 1.130020081046253e-05, | |
| "loss": 0.4465, | |
| "step": 471000 | |
| }, | |
| { | |
| "epoch": 65.35, | |
| "eval_loss": 0.4243544340133667, | |
| "eval_runtime": 1.8118, | |
| "eval_samples_per_second": 102.111, | |
| "eval_steps_per_second": 6.623, | |
| "step": 471000 | |
| }, | |
| { | |
| "epoch": 65.42, | |
| "learning_rate": 1.1256255015520584e-05, | |
| "loss": 0.4465, | |
| "step": 471500 | |
| }, | |
| { | |
| "epoch": 65.49, | |
| "learning_rate": 1.1212972171983502e-05, | |
| "loss": 0.4467, | |
| "step": 472000 | |
| }, | |
| { | |
| "epoch": 65.49, | |
| "eval_loss": 0.4200620949268341, | |
| "eval_runtime": 1.7012, | |
| "eval_samples_per_second": 108.746, | |
| "eval_steps_per_second": 7.054, | |
| "step": 472000 | |
| }, | |
| { | |
| "epoch": 65.56, | |
| "learning_rate": 1.1170441572362081e-05, | |
| "loss": 0.4466, | |
| "step": 472500 | |
| }, | |
| { | |
| "epoch": 65.63, | |
| "learning_rate": 1.1128663681764173e-05, | |
| "loss": 0.4465, | |
| "step": 473000 | |
| }, | |
| { | |
| "epoch": 65.63, | |
| "eval_loss": 0.41595694422721863, | |
| "eval_runtime": 1.6375, | |
| "eval_samples_per_second": 112.976, | |
| "eval_steps_per_second": 7.328, | |
| "step": 473000 | |
| }, | |
| { | |
| "epoch": 65.7, | |
| "learning_rate": 1.1087638957066064e-05, | |
| "loss": 0.4471, | |
| "step": 473500 | |
| }, | |
| { | |
| "epoch": 65.77, | |
| "learning_rate": 1.104736784690758e-05, | |
| "loss": 0.4467, | |
| "step": 474000 | |
| }, | |
| { | |
| "epoch": 65.77, | |
| "eval_loss": 0.4272841215133667, | |
| "eval_runtime": 1.8167, | |
| "eval_samples_per_second": 101.832, | |
| "eval_steps_per_second": 6.605, | |
| "step": 474000 | |
| }, | |
| { | |
| "epoch": 65.84, | |
| "learning_rate": 1.1007929072962149e-05, | |
| "loss": 0.4465, | |
| "step": 474500 | |
| }, | |
| { | |
| "epoch": 65.91, | |
| "learning_rate": 1.0969164995431939e-05, | |
| "loss": 0.4465, | |
| "step": 475000 | |
| }, | |
| { | |
| "epoch": 65.91, | |
| "eval_loss": 0.4183247685432434, | |
| "eval_runtime": 1.9109, | |
| "eval_samples_per_second": 96.811, | |
| "eval_steps_per_second": 6.28, | |
| "step": 475000 | |
| }, | |
| { | |
| "epoch": 65.98, | |
| "learning_rate": 1.0931155828053629e-05, | |
| "loss": 0.4468, | |
| "step": 475500 | |
| }, | |
| { | |
| "epoch": 66.05, | |
| "learning_rate": 1.0893901986489377e-05, | |
| "loss": 0.4467, | |
| "step": 476000 | |
| }, | |
| { | |
| "epoch": 66.05, | |
| "eval_loss": 0.4227275848388672, | |
| "eval_runtime": 1.3989, | |
| "eval_samples_per_second": 132.248, | |
| "eval_steps_per_second": 8.578, | |
| "step": 476000 | |
| }, | |
| { | |
| "epoch": 66.12, | |
| "learning_rate": 1.0857403878141225e-05, | |
| "loss": 0.4458, | |
| "step": 476500 | |
| }, | |
| { | |
| "epoch": 66.19, | |
| "learning_rate": 1.082166190214664e-05, | |
| "loss": 0.4469, | |
| "step": 477000 | |
| }, | |
| { | |
| "epoch": 66.19, | |
| "eval_loss": 0.41657933592796326, | |
| "eval_runtime": 1.3422, | |
| "eval_samples_per_second": 137.83, | |
| "eval_steps_per_second": 8.94, | |
| "step": 477000 | |
| }, | |
| { | |
| "epoch": 66.26, | |
| "learning_rate": 1.078667644937414e-05, | |
| "loss": 0.4469, | |
| "step": 477500 | |
| }, | |
| { | |
| "epoch": 66.32, | |
| "learning_rate": 1.0752447902419035e-05, | |
| "loss": 0.4467, | |
| "step": 478000 | |
| }, | |
| { | |
| "epoch": 66.32, | |
| "eval_loss": 0.4198838472366333, | |
| "eval_runtime": 1.2904, | |
| "eval_samples_per_second": 143.372, | |
| "eval_steps_per_second": 9.3, | |
| "step": 478000 | |
| }, | |
| { | |
| "epoch": 66.39, | |
| "learning_rate": 1.071904282212263e-05, | |
| "loss": 0.4465, | |
| "step": 478500 | |
| }, | |
| { | |
| "epoch": 66.46, | |
| "learning_rate": 1.0686327685822393e-05, | |
| "loss": 0.4464, | |
| "step": 479000 | |
| }, | |
| { | |
| "epoch": 66.46, | |
| "eval_loss": 0.41814476251602173, | |
| "eval_runtime": 1.2937, | |
| "eval_samples_per_second": 142.996, | |
| "eval_steps_per_second": 9.275, | |
| "step": 479000 | |
| }, | |
| { | |
| "epoch": 66.53, | |
| "learning_rate": 1.0654370552737557e-05, | |
| "loss": 0.446, | |
| "step": 479500 | |
| }, | |
| { | |
| "epoch": 66.6, | |
| "learning_rate": 1.0623171772346204e-05, | |
| "loss": 0.4463, | |
| "step": 480000 | |
| }, | |
| { | |
| "epoch": 66.6, | |
| "eval_loss": 0.4216901659965515, | |
| "eval_runtime": 1.2778, | |
| "eval_samples_per_second": 144.775, | |
| "eval_steps_per_second": 9.391, | |
| "step": 480000 | |
| }, | |
| { | |
| "epoch": 66.67, | |
| "learning_rate": 1.0592791808607091e-05, | |
| "loss": 0.4466, | |
| "step": 480500 | |
| }, | |
| { | |
| "epoch": 66.74, | |
| "learning_rate": 1.0563109230480105e-05, | |
| "loss": 0.4464, | |
| "step": 481000 | |
| }, | |
| { | |
| "epoch": 66.74, | |
| "eval_loss": 0.4157991111278534, | |
| "eval_runtime": 1.2484, | |
| "eval_samples_per_second": 148.187, | |
| "eval_steps_per_second": 9.612, | |
| "step": 481000 | |
| }, | |
| { | |
| "epoch": 66.81, | |
| "learning_rate": 1.0534186003065792e-05, | |
| "loss": 0.4469, | |
| "step": 481500 | |
| }, | |
| { | |
| "epoch": 66.88, | |
| "learning_rate": 1.050602244266395e-05, | |
| "loss": 0.4468, | |
| "step": 482000 | |
| }, | |
| { | |
| "epoch": 66.88, | |
| "eval_loss": 0.4190557599067688, | |
| "eval_runtime": 1.405, | |
| "eval_samples_per_second": 131.674, | |
| "eval_steps_per_second": 8.541, | |
| "step": 482000 | |
| }, | |
| { | |
| "epoch": 66.95, | |
| "learning_rate": 1.0478618857266753e-05, | |
| "loss": 0.4457, | |
| "step": 482500 | |
| }, | |
| { | |
| "epoch": 67.02, | |
| "learning_rate": 1.0451975546555428e-05, | |
| "loss": 0.447, | |
| "step": 483000 | |
| }, | |
| { | |
| "epoch": 67.02, | |
| "eval_loss": 0.4247581362724304, | |
| "eval_runtime": 1.4501, | |
| "eval_samples_per_second": 127.577, | |
| "eval_steps_per_second": 8.275, | |
| "step": 483000 | |
| }, | |
| { | |
| "epoch": 67.09, | |
| "learning_rate": 1.0426092801896943e-05, | |
| "loss": 0.4458, | |
| "step": 483500 | |
| }, | |
| { | |
| "epoch": 67.16, | |
| "learning_rate": 1.0400970906340845e-05, | |
| "loss": 0.4465, | |
| "step": 484000 | |
| }, | |
| { | |
| "epoch": 67.16, | |
| "eval_loss": 0.42342451214790344, | |
| "eval_runtime": 1.4065, | |
| "eval_samples_per_second": 131.531, | |
| "eval_steps_per_second": 8.532, | |
| "step": 484000 | |
| }, | |
| { | |
| "epoch": 67.23, | |
| "learning_rate": 1.0376658096379588e-05, | |
| "loss": 0.4459, | |
| "step": 484500 | |
| }, | |
| { | |
| "epoch": 67.3, | |
| "learning_rate": 1.0353057191851014e-05, | |
| "loss": 0.4463, | |
| "step": 485000 | |
| }, | |
| { | |
| "epoch": 67.3, | |
| "eval_loss": 0.4237620234489441, | |
| "eval_runtime": 1.4335, | |
| "eval_samples_per_second": 129.058, | |
| "eval_steps_per_second": 8.371, | |
| "step": 485000 | |
| }, | |
| { | |
| "epoch": 67.37, | |
| "learning_rate": 1.033021793513056e-05, | |
| "loss": 0.4463, | |
| "step": 485500 | |
| }, | |
| { | |
| "epoch": 67.43, | |
| "learning_rate": 1.030814057598469e-05, | |
| "loss": 0.446, | |
| "step": 486000 | |
| }, | |
| { | |
| "epoch": 67.43, | |
| "eval_loss": 0.41616541147232056, | |
| "eval_runtime": 1.3014, | |
| "eval_samples_per_second": 142.159, | |
| "eval_steps_per_second": 9.221, | |
| "step": 486000 | |
| }, | |
| { | |
| "epoch": 67.5, | |
| "learning_rate": 1.0286867225517075e-05, | |
| "loss": 0.4464, | |
| "step": 486500 | |
| }, | |
| { | |
| "epoch": 67.57, | |
| "learning_rate": 1.0266312852517802e-05, | |
| "loss": 0.4462, | |
| "step": 487000 | |
| }, | |
| { | |
| "epoch": 67.57, | |
| "eval_loss": 0.4202038645744324, | |
| "eval_runtime": 1.3496, | |
| "eval_samples_per_second": 137.08, | |
| "eval_steps_per_second": 8.892, | |
| "step": 487000 | |
| }, | |
| { | |
| "epoch": 67.64, | |
| "learning_rate": 1.0246521075948845e-05, | |
| "loss": 0.4466, | |
| "step": 487500 | |
| }, | |
| { | |
| "epoch": 67.71, | |
| "learning_rate": 1.0227492112249914e-05, | |
| "loss": 0.4462, | |
| "step": 488000 | |
| }, | |
| { | |
| "epoch": 67.71, | |
| "eval_loss": 0.41774439811706543, | |
| "eval_runtime": 1.2813, | |
| "eval_samples_per_second": 144.38, | |
| "eval_steps_per_second": 9.365, | |
| "step": 488000 | |
| }, | |
| { | |
| "epoch": 67.78, | |
| "learning_rate": 1.020922616951869e-05, | |
| "loss": 0.4458, | |
| "step": 488500 | |
| }, | |
| { | |
| "epoch": 67.85, | |
| "learning_rate": 1.019172344750861e-05, | |
| "loss": 0.4455, | |
| "step": 489000 | |
| }, | |
| { | |
| "epoch": 67.85, | |
| "eval_loss": 0.4227893650531769, | |
| "eval_runtime": 1.4104, | |
| "eval_samples_per_second": 131.172, | |
| "eval_steps_per_second": 8.508, | |
| "step": 489000 | |
| }, | |
| { | |
| "epoch": 67.92, | |
| "learning_rate": 1.017498413762663e-05, | |
| "loss": 0.4461, | |
| "step": 489500 | |
| }, | |
| { | |
| "epoch": 67.99, | |
| "learning_rate": 1.0159039612175048e-05, | |
| "loss": 0.4463, | |
| "step": 490000 | |
| }, | |
| { | |
| "epoch": 67.99, | |
| "eval_loss": 0.41463714838027954, | |
| "eval_runtime": 1.3969, | |
| "eval_samples_per_second": 132.434, | |
| "eval_steps_per_second": 8.59, | |
| "step": 490000 | |
| }, | |
| { | |
| "epoch": 68.06, | |
| "learning_rate": 1.0143826139665367e-05, | |
| "loss": 0.4464, | |
| "step": 490500 | |
| }, | |
| { | |
| "epoch": 68.13, | |
| "learning_rate": 1.0129376603081064e-05, | |
| "loss": 0.4454, | |
| "step": 491000 | |
| }, | |
| { | |
| "epoch": 68.13, | |
| "eval_loss": 0.4189724624156952, | |
| "eval_runtime": 1.4324, | |
| "eval_samples_per_second": 129.152, | |
| "eval_steps_per_second": 8.377, | |
| "step": 491000 | |
| }, | |
| { | |
| "epoch": 68.2, | |
| "learning_rate": 1.0115691160439967e-05, | |
| "loss": 0.4468, | |
| "step": 491500 | |
| }, | |
| { | |
| "epoch": 68.27, | |
| "learning_rate": 1.010276996140389e-05, | |
| "loss": 0.446, | |
| "step": 492000 | |
| }, | |
| { | |
| "epoch": 68.27, | |
| "eval_loss": 0.42191821336746216, | |
| "eval_runtime": 1.3157, | |
| "eval_samples_per_second": 140.609, | |
| "eval_steps_per_second": 9.121, | |
| "step": 492000 | |
| }, | |
| { | |
| "epoch": 68.34, | |
| "learning_rate": 1.0090613147276983e-05, | |
| "loss": 0.447, | |
| "step": 492500 | |
| }, | |
| { | |
| "epoch": 68.41, | |
| "learning_rate": 1.0079220851004224e-05, | |
| "loss": 0.4461, | |
| "step": 493000 | |
| }, | |
| { | |
| "epoch": 68.41, | |
| "eval_loss": 0.4250451922416687, | |
| "eval_runtime": 1.5611, | |
| "eval_samples_per_second": 118.504, | |
| "eval_steps_per_second": 7.687, | |
| "step": 493000 | |
| }, | |
| { | |
| "epoch": 68.48, | |
| "learning_rate": 1.0068593197169942e-05, | |
| "loss": 0.4466, | |
| "step": 493500 | |
| }, | |
| { | |
| "epoch": 68.54, | |
| "learning_rate": 1.0058749264484569e-05, | |
| "loss": 0.4462, | |
| "step": 494000 | |
| }, | |
| { | |
| "epoch": 68.54, | |
| "eval_loss": 0.4171859323978424, | |
| "eval_runtime": 1.7206, | |
| "eval_samples_per_second": 107.521, | |
| "eval_steps_per_second": 6.974, | |
| "step": 494000 | |
| }, | |
| { | |
| "epoch": 68.61, | |
| "learning_rate": 1.0049649705995797e-05, | |
| "loss": 0.4455, | |
| "step": 494500 | |
| }, | |
| { | |
| "epoch": 68.68, | |
| "learning_rate": 1.0041315113330795e-05, | |
| "loss": 0.4464, | |
| "step": 495000 | |
| }, | |
| { | |
| "epoch": 68.68, | |
| "eval_loss": 0.41223111748695374, | |
| "eval_runtime": 1.6922, | |
| "eval_samples_per_second": 109.323, | |
| "eval_steps_per_second": 7.091, | |
| "step": 495000 | |
| }, | |
| { | |
| "epoch": 68.75, | |
| "learning_rate": 1.003374557763534e-05, | |
| "loss": 0.4462, | |
| "step": 495500 | |
| }, | |
| { | |
| "epoch": 68.82, | |
| "learning_rate": 1.0026941181688666e-05, | |
| "loss": 0.4459, | |
| "step": 496000 | |
| }, | |
| { | |
| "epoch": 68.82, | |
| "eval_loss": 0.41784965991973877, | |
| "eval_runtime": 1.7276, | |
| "eval_samples_per_second": 107.084, | |
| "eval_steps_per_second": 6.946, | |
| "step": 496000 | |
| }, | |
| { | |
| "epoch": 68.89, | |
| "learning_rate": 1.0020913314537103e-05, | |
| "loss": 0.4455, | |
| "step": 496500 | |
| }, | |
| { | |
| "epoch": 68.96, | |
| "learning_rate": 1.001563788233432e-05, | |
| "loss": 0.4459, | |
| "step": 497000 | |
| }, | |
| { | |
| "epoch": 68.96, | |
| "eval_loss": 0.4094962477684021, | |
| "eval_runtime": 1.7269, | |
| "eval_samples_per_second": 107.131, | |
| "eval_steps_per_second": 6.949, | |
| "step": 497000 | |
| }, | |
| { | |
| "epoch": 69.03, | |
| "learning_rate": 1.0011127787903172e-05, | |
| "loss": 0.4458, | |
| "step": 497500 | |
| }, | |
| { | |
| "epoch": 69.1, | |
| "learning_rate": 1.0007383080565327e-05, | |
| "loss": 0.4458, | |
| "step": 498000 | |
| }, | |
| { | |
| "epoch": 69.1, | |
| "eval_loss": 0.41240301728248596, | |
| "eval_runtime": 1.4516, | |
| "eval_samples_per_second": 127.441, | |
| "eval_steps_per_second": 8.266, | |
| "step": 498000 | |
| }, | |
| { | |
| "epoch": 69.17, | |
| "learning_rate": 1.0004403801272306e-05, | |
| "loss": 0.4462, | |
| "step": 498500 | |
| }, | |
| { | |
| "epoch": 69.24, | |
| "learning_rate": 1.000218998260502e-05, | |
| "loss": 0.4458, | |
| "step": 499000 | |
| }, | |
| { | |
| "epoch": 69.24, | |
| "eval_loss": 0.4181687533855438, | |
| "eval_runtime": 1.4502, | |
| "eval_samples_per_second": 127.573, | |
| "eval_steps_per_second": 8.275, | |
| "step": 499000 | |
| }, | |
| { | |
| "epoch": 69.31, | |
| "learning_rate": 1.0000743781475326e-05, | |
| "loss": 0.4461, | |
| "step": 499500 | |
| }, | |
| { | |
| "epoch": 69.38, | |
| "learning_rate": 1.000006002205894e-05, | |
| "loss": 0.4458, | |
| "step": 500000 | |
| }, | |
| { | |
| "epoch": 69.38, | |
| "eval_loss": 0.4177255928516388, | |
| "eval_runtime": 1.3131, | |
| "eval_samples_per_second": 140.889, | |
| "eval_steps_per_second": 9.139, | |
| "step": 500000 | |
| }, | |
| { | |
| "epoch": 69.38, | |
| "step": 500000, | |
| "total_flos": 3.686314695252681e+22, | |
| "train_loss": 0.46582102978515627, | |
| "train_runtime": 361543.3816, | |
| "train_samples_per_second": 354.038, | |
| "train_steps_per_second": 1.383 | |
| } | |
| ], | |
| "max_steps": 500000, | |
| "num_train_epochs": 70, | |
| "total_flos": 3.686314695252681e+22, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |