| { |
| "best_global_step": 342, |
| "best_metric": 0.029218414798378944, |
| "best_model_checkpoint": "saves_multiple/lora/llama-3-8b-instruct/train_cb_42_1760623599/checkpoint-342", |
| "epoch": 20.0, |
| "eval_steps": 57, |
| "global_step": 1140, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.08771929824561403, |
| "grad_norm": 8.494623184204102, |
| "learning_rate": 1.7543859649122807e-06, |
| "loss": 1.0586, |
| "num_input_tokens_seen": 3232, |
| "step": 5, |
| "train_runtime": 3.8237, |
| "train_tokens_per_second": 845.261 |
| }, |
| { |
| "epoch": 0.17543859649122806, |
| "grad_norm": 8.132691383361816, |
| "learning_rate": 3.9473684210526315e-06, |
| "loss": 1.0315, |
| "num_input_tokens_seen": 6432, |
| "step": 10, |
| "train_runtime": 5.1072, |
| "train_tokens_per_second": 1259.399 |
| }, |
| { |
| "epoch": 0.2631578947368421, |
| "grad_norm": 7.127818584442139, |
| "learning_rate": 6.140350877192982e-06, |
| "loss": 0.9965, |
| "num_input_tokens_seen": 9376, |
| "step": 15, |
| "train_runtime": 6.2945, |
| "train_tokens_per_second": 1489.556 |
| }, |
| { |
| "epoch": 0.3508771929824561, |
| "grad_norm": 9.343673706054688, |
| "learning_rate": 8.333333333333334e-06, |
| "loss": 0.9492, |
| "num_input_tokens_seen": 12448, |
| "step": 20, |
| "train_runtime": 7.5451, |
| "train_tokens_per_second": 1649.807 |
| }, |
| { |
| "epoch": 0.43859649122807015, |
| "grad_norm": 10.404763221740723, |
| "learning_rate": 1.0526315789473684e-05, |
| "loss": 0.841, |
| "num_input_tokens_seen": 15456, |
| "step": 25, |
| "train_runtime": 8.7407, |
| "train_tokens_per_second": 1768.28 |
| }, |
| { |
| "epoch": 0.5263157894736842, |
| "grad_norm": 4.930759429931641, |
| "learning_rate": 1.2719298245614037e-05, |
| "loss": 0.4148, |
| "num_input_tokens_seen": 18592, |
| "step": 30, |
| "train_runtime": 9.9987, |
| "train_tokens_per_second": 1859.432 |
| }, |
| { |
| "epoch": 0.6140350877192983, |
| "grad_norm": 8.16590404510498, |
| "learning_rate": 1.4912280701754386e-05, |
| "loss": 0.1678, |
| "num_input_tokens_seen": 23136, |
| "step": 35, |
| "train_runtime": 11.658, |
| "train_tokens_per_second": 1984.565 |
| }, |
| { |
| "epoch": 0.7017543859649122, |
| "grad_norm": 4.578836441040039, |
| "learning_rate": 1.7105263157894737e-05, |
| "loss": 0.085, |
| "num_input_tokens_seen": 26496, |
| "step": 40, |
| "train_runtime": 12.9762, |
| "train_tokens_per_second": 2041.899 |
| }, |
| { |
| "epoch": 0.7894736842105263, |
| "grad_norm": 3.7975993156433105, |
| "learning_rate": 1.929824561403509e-05, |
| "loss": 0.2507, |
| "num_input_tokens_seen": 29728, |
| "step": 45, |
| "train_runtime": 14.261, |
| "train_tokens_per_second": 2084.569 |
| }, |
| { |
| "epoch": 0.8771929824561403, |
| "grad_norm": 0.2967110276222229, |
| "learning_rate": 2.149122807017544e-05, |
| "loss": 0.2552, |
| "num_input_tokens_seen": 33024, |
| "step": 50, |
| "train_runtime": 15.539, |
| "train_tokens_per_second": 2125.236 |
| }, |
| { |
| "epoch": 0.9649122807017544, |
| "grad_norm": 2.793760299682617, |
| "learning_rate": 2.368421052631579e-05, |
| "loss": 0.135, |
| "num_input_tokens_seen": 35904, |
| "step": 55, |
| "train_runtime": 16.7398, |
| "train_tokens_per_second": 2144.824 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.14342579245567322, |
| "eval_runtime": 0.6417, |
| "eval_samples_per_second": 38.957, |
| "eval_steps_per_second": 10.908, |
| "num_input_tokens_seen": 36480, |
| "step": 57 |
| }, |
| { |
| "epoch": 1.0526315789473684, |
| "grad_norm": 6.821105003356934, |
| "learning_rate": 2.5877192982456143e-05, |
| "loss": 0.0674, |
| "num_input_tokens_seen": 38016, |
| "step": 60, |
| "train_runtime": 19.7582, |
| "train_tokens_per_second": 1924.059 |
| }, |
| { |
| "epoch": 1.1403508771929824, |
| "grad_norm": 0.8933197259902954, |
| "learning_rate": 2.8070175438596492e-05, |
| "loss": 0.0944, |
| "num_input_tokens_seen": 40800, |
| "step": 65, |
| "train_runtime": 21.1821, |
| "train_tokens_per_second": 1926.153 |
| }, |
| { |
| "epoch": 1.2280701754385965, |
| "grad_norm": 0.5491461753845215, |
| "learning_rate": 3.0263157894736844e-05, |
| "loss": 0.2026, |
| "num_input_tokens_seen": 43648, |
| "step": 70, |
| "train_runtime": 22.3782, |
| "train_tokens_per_second": 1950.474 |
| }, |
| { |
| "epoch": 1.3157894736842106, |
| "grad_norm": 8.093488693237305, |
| "learning_rate": 3.24561403508772e-05, |
| "loss": 0.2489, |
| "num_input_tokens_seen": 46112, |
| "step": 75, |
| "train_runtime": 23.4429, |
| "train_tokens_per_second": 1966.991 |
| }, |
| { |
| "epoch": 1.4035087719298245, |
| "grad_norm": 3.7320401668548584, |
| "learning_rate": 3.4649122807017546e-05, |
| "loss": 0.0975, |
| "num_input_tokens_seen": 49632, |
| "step": 80, |
| "train_runtime": 24.8017, |
| "train_tokens_per_second": 2001.15 |
| }, |
| { |
| "epoch": 1.4912280701754386, |
| "grad_norm": 0.8583314418792725, |
| "learning_rate": 3.6842105263157895e-05, |
| "loss": 0.0394, |
| "num_input_tokens_seen": 53024, |
| "step": 85, |
| "train_runtime": 26.1295, |
| "train_tokens_per_second": 2029.281 |
| }, |
| { |
| "epoch": 1.5789473684210527, |
| "grad_norm": 0.5694026947021484, |
| "learning_rate": 3.9035087719298244e-05, |
| "loss": 0.1608, |
| "num_input_tokens_seen": 56672, |
| "step": 90, |
| "train_runtime": 27.5262, |
| "train_tokens_per_second": 2058.841 |
| }, |
| { |
| "epoch": 1.6666666666666665, |
| "grad_norm": 11.088506698608398, |
| "learning_rate": 4.12280701754386e-05, |
| "loss": 0.3092, |
| "num_input_tokens_seen": 59296, |
| "step": 95, |
| "train_runtime": 28.623, |
| "train_tokens_per_second": 2071.62 |
| }, |
| { |
| "epoch": 1.7543859649122808, |
| "grad_norm": 8.009852409362793, |
| "learning_rate": 4.342105263157895e-05, |
| "loss": 0.1174, |
| "num_input_tokens_seen": 62528, |
| "step": 100, |
| "train_runtime": 29.9438, |
| "train_tokens_per_second": 2088.18 |
| }, |
| { |
| "epoch": 1.8421052631578947, |
| "grad_norm": 0.12083383649587631, |
| "learning_rate": 4.56140350877193e-05, |
| "loss": 0.01, |
| "num_input_tokens_seen": 65856, |
| "step": 105, |
| "train_runtime": 31.2514, |
| "train_tokens_per_second": 2107.296 |
| }, |
| { |
| "epoch": 1.9298245614035088, |
| "grad_norm": 6.154247760772705, |
| "learning_rate": 4.780701754385965e-05, |
| "loss": 0.2326, |
| "num_input_tokens_seen": 69664, |
| "step": 110, |
| "train_runtime": 32.7155, |
| "train_tokens_per_second": 2129.387 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.10932660102844238, |
| "eval_runtime": 0.6425, |
| "eval_samples_per_second": 38.91, |
| "eval_steps_per_second": 10.895, |
| "num_input_tokens_seen": 72112, |
| "step": 114 |
| }, |
| { |
| "epoch": 2.017543859649123, |
| "grad_norm": 0.55507493019104, |
| "learning_rate": 5e-05, |
| "loss": 0.2628, |
| "num_input_tokens_seen": 72848, |
| "step": 115, |
| "train_runtime": 36.5841, |
| "train_tokens_per_second": 1991.249 |
| }, |
| { |
| "epoch": 2.1052631578947367, |
| "grad_norm": 0.6052560210227966, |
| "learning_rate": 4.999707014206475e-05, |
| "loss": 0.0551, |
| "num_input_tokens_seen": 75888, |
| "step": 120, |
| "train_runtime": 38.0935, |
| "train_tokens_per_second": 1992.152 |
| }, |
| { |
| "epoch": 2.192982456140351, |
| "grad_norm": 0.09418032318353653, |
| "learning_rate": 4.9988281254984414e-05, |
| "loss": 0.069, |
| "num_input_tokens_seen": 78896, |
| "step": 125, |
| "train_runtime": 39.3005, |
| "train_tokens_per_second": 2007.507 |
| }, |
| { |
| "epoch": 2.280701754385965, |
| "grad_norm": 0.056536927819252014, |
| "learning_rate": 4.997363539877422e-05, |
| "loss": 0.0621, |
| "num_input_tokens_seen": 82288, |
| "step": 130, |
| "train_runtime": 40.623, |
| "train_tokens_per_second": 2025.652 |
| }, |
| { |
| "epoch": 2.3684210526315788, |
| "grad_norm": 7.772035598754883, |
| "learning_rate": 4.9953136006256415e-05, |
| "loss": 0.1343, |
| "num_input_tokens_seen": 85936, |
| "step": 135, |
| "train_runtime": 42.0414, |
| "train_tokens_per_second": 2044.078 |
| }, |
| { |
| "epoch": 2.456140350877193, |
| "grad_norm": 0.17343752086162567, |
| "learning_rate": 4.9926787882255636e-05, |
| "loss": 0.3138, |
| "num_input_tokens_seen": 88784, |
| "step": 140, |
| "train_runtime": 43.2019, |
| "train_tokens_per_second": 2055.093 |
| }, |
| { |
| "epoch": 2.543859649122807, |
| "grad_norm": 9.291604042053223, |
| "learning_rate": 4.9894597202472696e-05, |
| "loss": 0.0806, |
| "num_input_tokens_seen": 91696, |
| "step": 145, |
| "train_runtime": 44.3994, |
| "train_tokens_per_second": 2065.251 |
| }, |
| { |
| "epoch": 2.6315789473684212, |
| "grad_norm": 7.780226707458496, |
| "learning_rate": 4.985657151203706e-05, |
| "loss": 0.1802, |
| "num_input_tokens_seen": 95024, |
| "step": 150, |
| "train_runtime": 45.6977, |
| "train_tokens_per_second": 2079.406 |
| }, |
| { |
| "epoch": 2.719298245614035, |
| "grad_norm": 1.6253339052200317, |
| "learning_rate": 4.9812719723738435e-05, |
| "loss": 0.0775, |
| "num_input_tokens_seen": 98512, |
| "step": 155, |
| "train_runtime": 47.0711, |
| "train_tokens_per_second": 2092.833 |
| }, |
| { |
| "epoch": 2.807017543859649, |
| "grad_norm": 0.9703297019004822, |
| "learning_rate": 4.976305211593758e-05, |
| "loss": 0.1003, |
| "num_input_tokens_seen": 101744, |
| "step": 160, |
| "train_runtime": 48.3588, |
| "train_tokens_per_second": 2103.938 |
| }, |
| { |
| "epoch": 2.8947368421052633, |
| "grad_norm": 0.8048807382583618, |
| "learning_rate": 4.970758033015731e-05, |
| "loss": 0.0666, |
| "num_input_tokens_seen": 105264, |
| "step": 165, |
| "train_runtime": 49.7167, |
| "train_tokens_per_second": 2117.274 |
| }, |
| { |
| "epoch": 2.982456140350877, |
| "grad_norm": 0.10845348238945007, |
| "learning_rate": 4.9646317368353743e-05, |
| "loss": 0.0139, |
| "num_input_tokens_seen": 108592, |
| "step": 170, |
| "train_runtime": 51.0449, |
| "train_tokens_per_second": 2127.381 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 0.10847818106412888, |
| "eval_runtime": 0.6424, |
| "eval_samples_per_second": 38.918, |
| "eval_steps_per_second": 10.897, |
| "num_input_tokens_seen": 108712, |
| "step": 171 |
| }, |
| { |
| "epoch": 3.0701754385964914, |
| "grad_norm": 0.323029488325119, |
| "learning_rate": 4.957927758986888e-05, |
| "loss": 0.3918, |
| "num_input_tokens_seen": 111976, |
| "step": 175, |
| "train_runtime": 55.7944, |
| "train_tokens_per_second": 2006.938 |
| }, |
| { |
| "epoch": 3.1578947368421053, |
| "grad_norm": 0.017210999503731728, |
| "learning_rate": 4.9506476708064865e-05, |
| "loss": 0.0303, |
| "num_input_tokens_seen": 114568, |
| "step": 180, |
| "train_runtime": 56.9077, |
| "train_tokens_per_second": 2013.225 |
| }, |
| { |
| "epoch": 3.245614035087719, |
| "grad_norm": 0.07567677646875381, |
| "learning_rate": 4.9427931786641e-05, |
| "loss": 0.1294, |
| "num_input_tokens_seen": 117384, |
| "step": 185, |
| "train_runtime": 58.0701, |
| "train_tokens_per_second": 2021.417 |
| }, |
| { |
| "epoch": 3.3333333333333335, |
| "grad_norm": 4.6189446449279785, |
| "learning_rate": 4.93436612356342e-05, |
| "loss": 0.071, |
| "num_input_tokens_seen": 120968, |
| "step": 190, |
| "train_runtime": 59.4743, |
| "train_tokens_per_second": 2033.955 |
| }, |
| { |
| "epoch": 3.4210526315789473, |
| "grad_norm": 5.940680027008057, |
| "learning_rate": 4.925368480710385e-05, |
| "loss": 0.0725, |
| "num_input_tokens_seen": 124616, |
| "step": 195, |
| "train_runtime": 60.8639, |
| "train_tokens_per_second": 2047.452 |
| }, |
| { |
| "epoch": 3.5087719298245617, |
| "grad_norm": 0.4284672737121582, |
| "learning_rate": 4.915802359050222e-05, |
| "loss": 0.0469, |
| "num_input_tokens_seen": 128104, |
| "step": 200, |
| "train_runtime": 62.2429, |
| "train_tokens_per_second": 2058.132 |
| }, |
| { |
| "epoch": 3.5964912280701755, |
| "grad_norm": 1.3333511352539062, |
| "learning_rate": 4.905670000773126e-05, |
| "loss": 0.0207, |
| "num_input_tokens_seen": 131528, |
| "step": 205, |
| "train_runtime": 63.5701, |
| "train_tokens_per_second": 2069.021 |
| }, |
| { |
| "epoch": 3.6842105263157894, |
| "grad_norm": 8.823066711425781, |
| "learning_rate": 4.894973780788722e-05, |
| "loss": 0.1907, |
| "num_input_tokens_seen": 134600, |
| "step": 210, |
| "train_runtime": 64.8071, |
| "train_tokens_per_second": 2076.934 |
| }, |
| { |
| "epoch": 3.7719298245614032, |
| "grad_norm": 0.4703969359397888, |
| "learning_rate": 4.88371620616941e-05, |
| "loss": 0.0202, |
| "num_input_tokens_seen": 137896, |
| "step": 215, |
| "train_runtime": 66.098, |
| "train_tokens_per_second": 2086.234 |
| }, |
| { |
| "epoch": 3.8596491228070176, |
| "grad_norm": 0.08913834393024445, |
| "learning_rate": 4.871899915562736e-05, |
| "loss": 0.0165, |
| "num_input_tokens_seen": 141064, |
| "step": 220, |
| "train_runtime": 67.3512, |
| "train_tokens_per_second": 2094.455 |
| }, |
| { |
| "epoch": 3.9473684210526314, |
| "grad_norm": 0.11559370905160904, |
| "learning_rate": 4.8595276785729236e-05, |
| "loss": 0.0032, |
| "num_input_tokens_seen": 144104, |
| "step": 225, |
| "train_runtime": 68.5497, |
| "train_tokens_per_second": 2102.183 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 0.09485358744859695, |
| "eval_runtime": 0.6446, |
| "eval_samples_per_second": 38.783, |
| "eval_steps_per_second": 10.859, |
| "num_input_tokens_seen": 145296, |
| "step": 228 |
| }, |
| { |
| "epoch": 4.035087719298246, |
| "grad_norm": 24.598941802978516, |
| "learning_rate": 4.846602395111711e-05, |
| "loss": 0.1017, |
| "num_input_tokens_seen": 146576, |
| "step": 230, |
| "train_runtime": 71.7307, |
| "train_tokens_per_second": 2043.421 |
| }, |
| { |
| "epoch": 4.12280701754386, |
| "grad_norm": 2.7570149898529053, |
| "learning_rate": 4.833127094718643e-05, |
| "loss": 0.0112, |
| "num_input_tokens_seen": 149456, |
| "step": 235, |
| "train_runtime": 73.1951, |
| "train_tokens_per_second": 2041.885 |
| }, |
| { |
| "epoch": 4.2105263157894735, |
| "grad_norm": 0.10396062582731247, |
| "learning_rate": 4.819104935850983e-05, |
| "loss": 0.0426, |
| "num_input_tokens_seen": 152496, |
| "step": 240, |
| "train_runtime": 74.4434, |
| "train_tokens_per_second": 2048.481 |
| }, |
| { |
| "epoch": 4.298245614035087, |
| "grad_norm": 0.04137900471687317, |
| "learning_rate": 4.804539205143405e-05, |
| "loss": 0.0015, |
| "num_input_tokens_seen": 155504, |
| "step": 245, |
| "train_runtime": 75.664, |
| "train_tokens_per_second": 2055.192 |
| }, |
| { |
| "epoch": 4.385964912280702, |
| "grad_norm": 0.19739504158496857, |
| "learning_rate": 4.789433316637644e-05, |
| "loss": 0.0183, |
| "num_input_tokens_seen": 158640, |
| "step": 250, |
| "train_runtime": 76.8983, |
| "train_tokens_per_second": 2062.984 |
| }, |
| { |
| "epoch": 4.473684210526316, |
| "grad_norm": 0.008732669986784458, |
| "learning_rate": 4.7737908109822854e-05, |
| "loss": 0.0021, |
| "num_input_tokens_seen": 161296, |
| "step": 255, |
| "train_runtime": 78.0196, |
| "train_tokens_per_second": 2067.379 |
| }, |
| { |
| "epoch": 4.56140350877193, |
| "grad_norm": 0.0051896702498197556, |
| "learning_rate": 4.757615354602874e-05, |
| "loss": 0.0786, |
| "num_input_tokens_seen": 164656, |
| "step": 260, |
| "train_runtime": 79.3409, |
| "train_tokens_per_second": 2075.298 |
| }, |
| { |
| "epoch": 4.649122807017544, |
| "grad_norm": 0.07156688719987869, |
| "learning_rate": 4.7409107388425504e-05, |
| "loss": 0.076, |
| "num_input_tokens_seen": 168240, |
| "step": 265, |
| "train_runtime": 80.7228, |
| "train_tokens_per_second": 2084.168 |
| }, |
| { |
| "epoch": 4.7368421052631575, |
| "grad_norm": 0.01761333830654621, |
| "learning_rate": 4.723680879073396e-05, |
| "loss": 0.0053, |
| "num_input_tokens_seen": 171568, |
| "step": 270, |
| "train_runtime": 82.0319, |
| "train_tokens_per_second": 2091.479 |
| }, |
| { |
| "epoch": 4.824561403508772, |
| "grad_norm": 0.0254210252314806, |
| "learning_rate": 4.70592981377872e-05, |
| "loss": 0.0006, |
| "num_input_tokens_seen": 174320, |
| "step": 275, |
| "train_runtime": 83.1588, |
| "train_tokens_per_second": 2096.23 |
| }, |
| { |
| "epoch": 4.912280701754386, |
| "grad_norm": 0.006780566181987524, |
| "learning_rate": 4.6876617036064844e-05, |
| "loss": 0.0009, |
| "num_input_tokens_seen": 178448, |
| "step": 280, |
| "train_runtime": 84.7181, |
| "train_tokens_per_second": 2106.373 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 0.006025549024343491, |
| "learning_rate": 4.668880830394093e-05, |
| "loss": 0.0003, |
| "num_input_tokens_seen": 181408, |
| "step": 285, |
| "train_runtime": 86.0378, |
| "train_tokens_per_second": 2108.468 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 0.030761491507291794, |
| "eval_runtime": 0.6439, |
| "eval_samples_per_second": 38.826, |
| "eval_steps_per_second": 10.871, |
| "num_input_tokens_seen": 181408, |
| "step": 285 |
| }, |
| { |
| "epoch": 5.087719298245614, |
| "grad_norm": 0.043372299522161484, |
| "learning_rate": 4.649591596164778e-05, |
| "loss": 0.0002, |
| "num_input_tokens_seen": 184352, |
| "step": 290, |
| "train_runtime": 89.9631, |
| "train_tokens_per_second": 2049.195 |
| }, |
| { |
| "epoch": 5.175438596491228, |
| "grad_norm": 0.007011930923908949, |
| "learning_rate": 4.629798522095818e-05, |
| "loss": 0.0002, |
| "num_input_tokens_seen": 187680, |
| "step": 295, |
| "train_runtime": 91.2651, |
| "train_tokens_per_second": 2056.426 |
| }, |
| { |
| "epoch": 5.2631578947368425, |
| "grad_norm": 0.0068562207743525505, |
| "learning_rate": 4.6095062474588225e-05, |
| "loss": 0.0018, |
| "num_input_tokens_seen": 190880, |
| "step": 300, |
| "train_runtime": 92.5599, |
| "train_tokens_per_second": 2062.232 |
| }, |
| { |
| "epoch": 5.350877192982456, |
| "grad_norm": 0.02268863655626774, |
| "learning_rate": 4.588719528532342e-05, |
| "loss": 0.0002, |
| "num_input_tokens_seen": 194592, |
| "step": 305, |
| "train_runtime": 93.9826, |
| "train_tokens_per_second": 2070.511 |
| }, |
| { |
| "epoch": 5.43859649122807, |
| "grad_norm": 0.009367495775222778, |
| "learning_rate": 4.5674432374870455e-05, |
| "loss": 0.0002, |
| "num_input_tokens_seen": 198720, |
| "step": 310, |
| "train_runtime": 95.535, |
| "train_tokens_per_second": 2080.075 |
| }, |
| { |
| "epoch": 5.526315789473684, |
| "grad_norm": 1.1162317991256714, |
| "learning_rate": 4.545682361243748e-05, |
| "loss": 0.0509, |
| "num_input_tokens_seen": 201856, |
| "step": 315, |
| "train_runtime": 96.8134, |
| "train_tokens_per_second": 2085.002 |
| }, |
| { |
| "epoch": 5.614035087719298, |
| "grad_norm": 0.07315769791603088, |
| "learning_rate": 4.5234420003045236e-05, |
| "loss": 0.0003, |
| "num_input_tokens_seen": 204800, |
| "step": 320, |
| "train_runtime": 98.0044, |
| "train_tokens_per_second": 2089.703 |
| }, |
| { |
| "epoch": 5.701754385964913, |
| "grad_norm": 0.003813532181084156, |
| "learning_rate": 4.5007273675572104e-05, |
| "loss": 0.0014, |
| "num_input_tokens_seen": 208064, |
| "step": 325, |
| "train_runtime": 99.3081, |
| "train_tokens_per_second": 2095.137 |
| }, |
| { |
| "epoch": 5.7894736842105265, |
| "grad_norm": 0.09451882541179657, |
| "learning_rate": 4.4775437870535685e-05, |
| "loss": 0.0361, |
| "num_input_tokens_seen": 211168, |
| "step": 330, |
| "train_runtime": 100.5374, |
| "train_tokens_per_second": 2100.392 |
| }, |
| { |
| "epoch": 5.87719298245614, |
| "grad_norm": 0.00236014393158257, |
| "learning_rate": 4.4538966927613836e-05, |
| "loss": 0.0003, |
| "num_input_tokens_seen": 214144, |
| "step": 335, |
| "train_runtime": 101.7516, |
| "train_tokens_per_second": 2104.576 |
| }, |
| { |
| "epoch": 5.964912280701754, |
| "grad_norm": 0.007808553520590067, |
| "learning_rate": 4.4297916272908024e-05, |
| "loss": 0.0189, |
| "num_input_tokens_seen": 217216, |
| "step": 340, |
| "train_runtime": 102.98, |
| "train_tokens_per_second": 2109.302 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_loss": 0.029218414798378944, |
| "eval_runtime": 0.6447, |
| "eval_samples_per_second": 38.779, |
| "eval_steps_per_second": 10.858, |
| "num_input_tokens_seen": 217760, |
| "step": 342 |
| }, |
| { |
| "epoch": 6.052631578947368, |
| "grad_norm": 0.00644970266148448, |
| "learning_rate": 4.405234240595214e-05, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 219808, |
| "step": 345, |
| "train_runtime": 106.5658, |
| "train_tokens_per_second": 2062.65 |
| }, |
| { |
| "epoch": 6.140350877192983, |
| "grad_norm": 0.005264418199658394, |
| "learning_rate": 4.3802302886469606e-05, |
| "loss": 0.0324, |
| "num_input_tokens_seen": 223232, |
| "step": 350, |
| "train_runtime": 107.9067, |
| "train_tokens_per_second": 2068.75 |
| }, |
| { |
| "epoch": 6.228070175438597, |
| "grad_norm": 0.052017372101545334, |
| "learning_rate": 4.3547856320882044e-05, |
| "loss": 0.0004, |
| "num_input_tokens_seen": 227008, |
| "step": 355, |
| "train_runtime": 109.3404, |
| "train_tokens_per_second": 2076.159 |
| }, |
| { |
| "epoch": 6.315789473684211, |
| "grad_norm": 0.2490016371011734, |
| "learning_rate": 4.328906234857259e-05, |
| "loss": 0.0006, |
| "num_input_tokens_seen": 230016, |
| "step": 360, |
| "train_runtime": 110.5626, |
| "train_tokens_per_second": 2080.415 |
| }, |
| { |
| "epoch": 6.4035087719298245, |
| "grad_norm": 0.03515232726931572, |
| "learning_rate": 4.302598162790712e-05, |
| "loss": 0.0004, |
| "num_input_tokens_seen": 233632, |
| "step": 365, |
| "train_runtime": 111.9753, |
| "train_tokens_per_second": 2086.46 |
| }, |
| { |
| "epoch": 6.491228070175438, |
| "grad_norm": 0.08412598073482513, |
| "learning_rate": 4.27586758220166e-05, |
| "loss": 0.0004, |
| "num_input_tokens_seen": 236960, |
| "step": 370, |
| "train_runtime": 113.2746, |
| "train_tokens_per_second": 2091.908 |
| }, |
| { |
| "epoch": 6.578947368421053, |
| "grad_norm": 0.007359183859080076, |
| "learning_rate": 4.2487207584343955e-05, |
| "loss": 0.0002, |
| "num_input_tokens_seen": 240160, |
| "step": 375, |
| "train_runtime": 114.5591, |
| "train_tokens_per_second": 2096.385 |
| }, |
| { |
| "epoch": 6.666666666666667, |
| "grad_norm": 0.04393015801906586, |
| "learning_rate": 4.2211640543958796e-05, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 243264, |
| "step": 380, |
| "train_runtime": 115.8432, |
| "train_tokens_per_second": 2099.942 |
| }, |
| { |
| "epoch": 6.754385964912281, |
| "grad_norm": 0.002249289769679308, |
| "learning_rate": 4.193203929064353e-05, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 246560, |
| "step": 385, |
| "train_runtime": 117.1373, |
| "train_tokens_per_second": 2104.88 |
| }, |
| { |
| "epoch": 6.842105263157895, |
| "grad_norm": 0.004690971225500107, |
| "learning_rate": 4.164846935975421e-05, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 249408, |
| "step": 390, |
| "train_runtime": 118.2984, |
| "train_tokens_per_second": 2108.296 |
| }, |
| { |
| "epoch": 6.9298245614035086, |
| "grad_norm": 0.01847480610013008, |
| "learning_rate": 4.136099721685983e-05, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 252192, |
| "step": 395, |
| "train_runtime": 119.4488, |
| "train_tokens_per_second": 2111.298 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_loss": 0.06291545182466507, |
| "eval_runtime": 0.6437, |
| "eval_samples_per_second": 38.836, |
| "eval_steps_per_second": 10.874, |
| "num_input_tokens_seen": 254568, |
| "step": 399 |
| }, |
| { |
| "epoch": 7.017543859649122, |
| "grad_norm": 0.004235400352627039, |
| "learning_rate": 4.1069690242163484e-05, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 255432, |
| "step": 400, |
| "train_runtime": 122.772, |
| "train_tokens_per_second": 2080.54 |
| }, |
| { |
| "epoch": 7.105263157894737, |
| "grad_norm": 0.009064249694347382, |
| "learning_rate": 4.0774616714709316e-05, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 258408, |
| "step": 405, |
| "train_runtime": 124.372, |
| "train_tokens_per_second": 2077.702 |
| }, |
| { |
| "epoch": 7.192982456140351, |
| "grad_norm": 0.0008939403924159706, |
| "learning_rate": 4.047584579637857e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 262024, |
| "step": 410, |
| "train_runtime": 125.7496, |
| "train_tokens_per_second": 2083.697 |
| }, |
| { |
| "epoch": 7.280701754385965, |
| "grad_norm": 0.0015289457514882088, |
| "learning_rate": 4.0173447515678916e-05, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 265032, |
| "step": 415, |
| "train_runtime": 126.9735, |
| "train_tokens_per_second": 2087.301 |
| }, |
| { |
| "epoch": 7.368421052631579, |
| "grad_norm": 1.3487358093261719, |
| "learning_rate": 3.986749275133057e-05, |
| "loss": 0.0021, |
| "num_input_tokens_seen": 267656, |
| "step": 420, |
| "train_runtime": 128.0925, |
| "train_tokens_per_second": 2089.552 |
| }, |
| { |
| "epoch": 7.456140350877193, |
| "grad_norm": 0.001081734080798924, |
| "learning_rate": 3.955805321565304e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 271592, |
| "step": 425, |
| "train_runtime": 129.5451, |
| "train_tokens_per_second": 2096.505 |
| }, |
| { |
| "epoch": 7.543859649122807, |
| "grad_norm": 0.0019081695936620235, |
| "learning_rate": 3.9245201437756654e-05, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 275016, |
| "step": 430, |
| "train_runtime": 130.9082, |
| "train_tokens_per_second": 2100.83 |
| }, |
| { |
| "epoch": 7.631578947368421, |
| "grad_norm": 0.01948564313352108, |
| "learning_rate": 3.892901074654255e-05, |
| "loss": 0.0002, |
| "num_input_tokens_seen": 278248, |
| "step": 435, |
| "train_runtime": 132.2161, |
| "train_tokens_per_second": 2104.493 |
| }, |
| { |
| "epoch": 7.719298245614035, |
| "grad_norm": 0.0027705966494977474, |
| "learning_rate": 3.860955525351516e-05, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 281320, |
| "step": 440, |
| "train_runtime": 133.4249, |
| "train_tokens_per_second": 2108.452 |
| }, |
| { |
| "epoch": 7.807017543859649, |
| "grad_norm": 0.0025500233750790358, |
| "learning_rate": 3.82869098354114e-05, |
| "loss": 0.0002, |
| "num_input_tokens_seen": 284360, |
| "step": 445, |
| "train_runtime": 134.646, |
| "train_tokens_per_second": 2111.909 |
| }, |
| { |
| "epoch": 7.894736842105263, |
| "grad_norm": 0.007163232192397118, |
| "learning_rate": 3.796115011665034e-05, |
| "loss": 0.0002, |
| "num_input_tokens_seen": 287944, |
| "step": 450, |
| "train_runtime": 136.0289, |
| "train_tokens_per_second": 2116.786 |
| }, |
| { |
| "epoch": 7.982456140350877, |
| "grad_norm": 0.0030522786546498537, |
| "learning_rate": 3.763235245160775e-05, |
| "loss": 0.0002, |
| "num_input_tokens_seen": 290696, |
| "step": 455, |
| "train_runtime": 137.1508, |
| "train_tokens_per_second": 2119.535 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_loss": 0.04268428683280945, |
| "eval_runtime": 0.6445, |
| "eval_samples_per_second": 38.787, |
| "eval_steps_per_second": 10.86, |
| "num_input_tokens_seen": 291000, |
| "step": 456 |
| }, |
| { |
| "epoch": 8.070175438596491, |
| "grad_norm": 0.0008271585684269667, |
| "learning_rate": 3.7300593906719464e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 293432, |
| "step": 460, |
| "train_runtime": 140.2977, |
| "train_tokens_per_second": 2091.495 |
| }, |
| { |
| "epoch": 8.157894736842104, |
| "grad_norm": 0.002823996590450406, |
| "learning_rate": 3.69659522424179e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 296888, |
| "step": 465, |
| "train_runtime": 141.9407, |
| "train_tokens_per_second": 2091.633 |
| }, |
| { |
| "epoch": 8.24561403508772, |
| "grad_norm": 0.0013278720434755087, |
| "learning_rate": 3.662850589490592e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 300312, |
| "step": 470, |
| "train_runtime": 143.2734, |
| "train_tokens_per_second": 2096.076 |
| }, |
| { |
| "epoch": 8.333333333333334, |
| "grad_norm": 0.009819025173783302, |
| "learning_rate": 3.628833395777224e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 303544, |
| "step": 475, |
| "train_runtime": 144.5549, |
| "train_tokens_per_second": 2099.853 |
| }, |
| { |
| "epoch": 8.421052631578947, |
| "grad_norm": 0.004232250619679689, |
| "learning_rate": 3.59455161634528e-05, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 306872, |
| "step": 480, |
| "train_runtime": 145.874, |
| "train_tokens_per_second": 2103.678 |
| }, |
| { |
| "epoch": 8.508771929824562, |
| "grad_norm": 0.0021570452954620123, |
| "learning_rate": 3.560013286454242e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 309592, |
| "step": 485, |
| "train_runtime": 147.0269, |
| "train_tokens_per_second": 2105.683 |
| }, |
| { |
| "epoch": 8.596491228070175, |
| "grad_norm": 0.0009255345212295651, |
| "learning_rate": 3.5252265014961006e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 312728, |
| "step": 490, |
| "train_runtime": 148.2746, |
| "train_tokens_per_second": 2109.114 |
| }, |
| { |
| "epoch": 8.68421052631579, |
| "grad_norm": 0.002535737119615078, |
| "learning_rate": 3.490199415097892e-05, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 316088, |
| "step": 495, |
| "train_runtime": 149.6068, |
| "train_tokens_per_second": 2112.792 |
| }, |
| { |
| "epoch": 8.771929824561404, |
| "grad_norm": 0.0004993479233235121, |
| "learning_rate": 3.45494023721058e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 319352, |
| "step": 500, |
| "train_runtime": 150.9334, |
| "train_tokens_per_second": 2115.847 |
| }, |
| { |
| "epoch": 8.859649122807017, |
| "grad_norm": 0.006932998076081276, |
| "learning_rate": 3.4194572321847336e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 323256, |
| "step": 505, |
| "train_runtime": 152.4581, |
| "train_tokens_per_second": 2120.294 |
| }, |
| { |
| "epoch": 8.947368421052632, |
| "grad_norm": 0.003917379770427942, |
| "learning_rate": 3.383758716833459e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 326200, |
| "step": 510, |
| "train_runtime": 153.6278, |
| "train_tokens_per_second": 2123.313 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_loss": 0.04754660651087761, |
| "eval_runtime": 0.647, |
| "eval_samples_per_second": 38.64, |
| "eval_steps_per_second": 10.819, |
| "num_input_tokens_seen": 327792, |
| "step": 513 |
| }, |
| { |
| "epoch": 9.035087719298245, |
| "grad_norm": 0.0015364107675850391, |
| "learning_rate": 3.347853058483037e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 329008, |
| "step": 515, |
| "train_runtime": 156.7988, |
| "train_tokens_per_second": 2098.281 |
| }, |
| { |
| "epoch": 9.12280701754386, |
| "grad_norm": 0.000525821465998888, |
| "learning_rate": 3.311748673011709e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 332304, |
| "step": 520, |
| "train_runtime": 158.4335, |
| "train_tokens_per_second": 2097.435 |
| }, |
| { |
| "epoch": 9.210526315789474, |
| "grad_norm": 0.006314833648502827, |
| "learning_rate": 3.275454022877097e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 335792, |
| "step": 525, |
| "train_runtime": 159.7737, |
| "train_tokens_per_second": 2101.672 |
| }, |
| { |
| "epoch": 9.298245614035087, |
| "grad_norm": 0.0005037735099904239, |
| "learning_rate": 3.238977615132697e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 338672, |
| "step": 530, |
| "train_runtime": 160.9477, |
| "train_tokens_per_second": 2104.236 |
| }, |
| { |
| "epoch": 9.385964912280702, |
| "grad_norm": 0.0008415406919084489, |
| "learning_rate": 3.202327999433924e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 341968, |
| "step": 535, |
| "train_runtime": 162.2401, |
| "train_tokens_per_second": 2107.79 |
| }, |
| { |
| "epoch": 9.473684210526315, |
| "grad_norm": 0.002791994484141469, |
| "learning_rate": 3.165513766034167e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 345232, |
| "step": 540, |
| "train_runtime": 163.5711, |
| "train_tokens_per_second": 2110.593 |
| }, |
| { |
| "epoch": 9.56140350877193, |
| "grad_norm": 0.002184842247515917, |
| "learning_rate": 3.128543543771336e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 348656, |
| "step": 545, |
| "train_runtime": 164.9004, |
| "train_tokens_per_second": 2114.343 |
| }, |
| { |
| "epoch": 9.649122807017545, |
| "grad_norm": 0.0018682386726140976, |
| "learning_rate": 3.091425998045356e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 351248, |
| "step": 550, |
| "train_runtime": 166.0028, |
| "train_tokens_per_second": 2115.917 |
| }, |
| { |
| "epoch": 9.736842105263158, |
| "grad_norm": 0.0015412045177072287, |
| "learning_rate": 3.0541698287870965e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 355024, |
| "step": 555, |
| "train_runtime": 167.4708, |
| "train_tokens_per_second": 2119.916 |
| }, |
| { |
| "epoch": 9.824561403508772, |
| "grad_norm": 0.002560933120548725, |
| "learning_rate": 3.01678376841921e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 357776, |
| "step": 560, |
| "train_runtime": 168.6037, |
| "train_tokens_per_second": 2121.993 |
| }, |
| { |
| "epoch": 9.912280701754385, |
| "grad_norm": 0.0010628009913489223, |
| "learning_rate": 2.9792765798093465e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 360784, |
| "step": 565, |
| "train_runtime": 169.8207, |
| "train_tokens_per_second": 2124.5 |
| }, |
| { |
| "epoch": 10.0, |
| "grad_norm": 0.0005139501881785691, |
| "learning_rate": 2.94165705421624e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 363864, |
| "step": 570, |
| "train_runtime": 171.1798, |
| "train_tokens_per_second": 2125.624 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_loss": 0.04690895602107048, |
| "eval_runtime": 0.6437, |
| "eval_samples_per_second": 38.841, |
| "eval_steps_per_second": 10.875, |
| "num_input_tokens_seen": 363864, |
| "step": 570 |
| }, |
| { |
| "epoch": 10.087719298245615, |
| "grad_norm": 0.0008024319540709257, |
| "learning_rate": 2.9039340092291373e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 368120, |
| "step": 575, |
| "train_runtime": 175.4012, |
| "train_tokens_per_second": 2098.731 |
| }, |
| { |
| "epoch": 10.175438596491228, |
| "grad_norm": 0.007118534296751022, |
| "learning_rate": 2.8661162867010543e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 371416, |
| "step": 580, |
| "train_runtime": 176.7029, |
| "train_tokens_per_second": 2101.924 |
| }, |
| { |
| "epoch": 10.263157894736842, |
| "grad_norm": 0.0016102839726954699, |
| "learning_rate": 2.8282127506763456e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 374168, |
| "step": 585, |
| "train_runtime": 177.8312, |
| "train_tokens_per_second": 2104.063 |
| }, |
| { |
| "epoch": 10.350877192982455, |
| "grad_norm": 0.004948667716234922, |
| "learning_rate": 2.7902322853130757e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 377496, |
| "step": 590, |
| "train_runtime": 179.1517, |
| "train_tokens_per_second": 2107.13 |
| }, |
| { |
| "epoch": 10.43859649122807, |
| "grad_norm": 0.007659234572201967, |
| "learning_rate": 2.752183792800671e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 381592, |
| "step": 595, |
| "train_runtime": 180.6897, |
| "train_tokens_per_second": 2111.863 |
| }, |
| { |
| "epoch": 10.526315789473685, |
| "grad_norm": 0.0006496281712315977, |
| "learning_rate": 2.7140761912733474e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 384760, |
| "step": 600, |
| "train_runtime": 181.9668, |
| "train_tokens_per_second": 2114.451 |
| }, |
| { |
| "epoch": 10.614035087719298, |
| "grad_norm": 0.0013017425080761313, |
| "learning_rate": 2.6759184127198046e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 387512, |
| "step": 605, |
| "train_runtime": 183.1195, |
| "train_tokens_per_second": 2116.17 |
| }, |
| { |
| "epoch": 10.701754385964913, |
| "grad_norm": 0.000603329623118043, |
| "learning_rate": 2.6377194008896637e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 390680, |
| "step": 610, |
| "train_runtime": 184.3787, |
| "train_tokens_per_second": 2118.9 |
| }, |
| { |
| "epoch": 10.789473684210526, |
| "grad_norm": 0.000789643032476306, |
| "learning_rate": 2.5994881091971605e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 393944, |
| "step": 615, |
| "train_runtime": 185.6894, |
| "train_tokens_per_second": 2121.521 |
| }, |
| { |
| "epoch": 10.87719298245614, |
| "grad_norm": 0.0011890205787494779, |
| "learning_rate": 2.5612334986225623e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 396632, |
| "step": 620, |
| "train_runtime": 186.8066, |
| "train_tokens_per_second": 2123.223 |
| }, |
| { |
| "epoch": 10.964912280701755, |
| "grad_norm": 0.0020256524439901114, |
| "learning_rate": 2.5229645356118163e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 399288, |
| "step": 625, |
| "train_runtime": 187.9454, |
| "train_tokens_per_second": 2124.49 |
| }, |
| { |
| "epoch": 11.0, |
| "eval_loss": 0.046334002166986465, |
| "eval_runtime": 0.6469, |
| "eval_samples_per_second": 38.646, |
| "eval_steps_per_second": 10.821, |
| "num_input_tokens_seen": 400104, |
| "step": 627 |
| }, |
| { |
| "epoch": 11.052631578947368, |
| "grad_norm": 0.0008229435770772398, |
| "learning_rate": 2.4846901899749185e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 401928, |
| "step": 630, |
| "train_runtime": 191.0983, |
| "train_tokens_per_second": 2103.252 |
| }, |
| { |
| "epoch": 11.140350877192983, |
| "grad_norm": 0.0010029375553131104, |
| "learning_rate": 2.4464194327834926e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 404360, |
| "step": 635, |
| "train_runtime": 192.5562, |
| "train_tokens_per_second": 2099.958 |
| }, |
| { |
| "epoch": 11.228070175438596, |
| "grad_norm": 0.0021509698126465082, |
| "learning_rate": 2.4081612342680694e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 407496, |
| "step": 640, |
| "train_runtime": 193.8434, |
| "train_tokens_per_second": 2102.191 |
| }, |
| { |
| "epoch": 11.31578947368421, |
| "grad_norm": 0.0006697690696455538, |
| "learning_rate": 2.369924561715569e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 410760, |
| "step": 645, |
| "train_runtime": 195.111, |
| "train_tokens_per_second": 2105.263 |
| }, |
| { |
| "epoch": 11.403508771929825, |
| "grad_norm": 0.0008098175167106092, |
| "learning_rate": 2.3317183773674718e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 413832, |
| "step": 650, |
| "train_runtime": 196.3412, |
| "train_tokens_per_second": 2107.718 |
| }, |
| { |
| "epoch": 11.491228070175438, |
| "grad_norm": 0.0004035372694488615, |
| "learning_rate": 2.2935516363191693e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 417320, |
| "step": 655, |
| "train_runtime": 197.6938, |
| "train_tokens_per_second": 2110.941 |
| }, |
| { |
| "epoch": 11.578947368421053, |
| "grad_norm": 0.00039830661262385547, |
| "learning_rate": 2.2554332844209904e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 420232, |
| "step": 660, |
| "train_runtime": 198.9023, |
| "train_tokens_per_second": 2112.756 |
| }, |
| { |
| "epoch": 11.666666666666666, |
| "grad_norm": 0.0005065247532911599, |
| "learning_rate": 2.2173722561813987e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 423528, |
| "step": 665, |
| "train_runtime": 200.1755, |
| "train_tokens_per_second": 2115.783 |
| }, |
| { |
| "epoch": 11.75438596491228, |
| "grad_norm": 0.0006726135616190732, |
| "learning_rate": 2.179377472672842e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 426920, |
| "step": 670, |
| "train_runtime": 201.5145, |
| "train_tokens_per_second": 2118.557 |
| }, |
| { |
| "epoch": 11.842105263157894, |
| "grad_norm": 0.0006947590154595673, |
| "learning_rate": 2.1414578394407597e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 431016, |
| "step": 675, |
| "train_runtime": 203.0651, |
| "train_tokens_per_second": 2122.551 |
| }, |
| { |
| "epoch": 11.929824561403509, |
| "grad_norm": 0.0052534546703100204, |
| "learning_rate": 2.1036222444162147e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 434600, |
| "step": 680, |
| "train_runtime": 204.4684, |
| "train_tokens_per_second": 2125.512 |
| }, |
| { |
| "epoch": 12.0, |
| "eval_loss": 0.053546272218227386, |
| "eval_runtime": 0.6477, |
| "eval_samples_per_second": 38.597, |
| "eval_steps_per_second": 10.807, |
| "num_input_tokens_seen": 436440, |
| "step": 684 |
| }, |
| { |
| "epoch": 12.017543859649123, |
| "grad_norm": 0.0031985475216060877, |
| "learning_rate": 2.0658795558326743e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 437016, |
| "step": 685, |
| "train_runtime": 207.716, |
| "train_tokens_per_second": 2103.911 |
| }, |
| { |
| "epoch": 12.105263157894736, |
| "grad_norm": 0.0005819392972625792, |
| "learning_rate": 2.0282386201473894e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 440280, |
| "step": 690, |
| "train_runtime": 209.2852, |
| "train_tokens_per_second": 2103.732 |
| }, |
| { |
| "epoch": 12.192982456140351, |
| "grad_norm": 0.00071110570570454, |
| "learning_rate": 1.99070825996789e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 443800, |
| "step": 695, |
| "train_runtime": 210.6866, |
| "train_tokens_per_second": 2106.446 |
| }, |
| { |
| "epoch": 12.280701754385966, |
| "grad_norm": 0.00034673104528337717, |
| "learning_rate": 1.9532972719840607e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 446168, |
| "step": 700, |
| "train_runtime": 211.7393, |
| "train_tokens_per_second": 2107.157 |
| }, |
| { |
| "epoch": 12.368421052631579, |
| "grad_norm": 0.0018633338622748852, |
| "learning_rate": 1.9160144249063035e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 449560, |
| "step": 705, |
| "train_runtime": 213.0749, |
| "train_tokens_per_second": 2109.868 |
| }, |
| { |
| "epoch": 12.456140350877194, |
| "grad_norm": 0.0005754131125286222, |
| "learning_rate": 1.8788684574102467e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 452824, |
| "step": 710, |
| "train_runtime": 214.3617, |
| "train_tokens_per_second": 2112.429 |
| }, |
| { |
| "epoch": 12.543859649122806, |
| "grad_norm": 0.00047461054055020213, |
| "learning_rate": 1.8418680760885027e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 456120, |
| "step": 715, |
| "train_runtime": 215.6778, |
| "train_tokens_per_second": 2114.822 |
| }, |
| { |
| "epoch": 12.631578947368421, |
| "grad_norm": 0.001994197955355048, |
| "learning_rate": 1.805021953409934e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 459736, |
| "step": 720, |
| "train_runtime": 217.0701, |
| "train_tokens_per_second": 2117.915 |
| }, |
| { |
| "epoch": 12.719298245614034, |
| "grad_norm": 0.0011361304204910994, |
| "learning_rate": 1.7683387256869353e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 462584, |
| "step": 725, |
| "train_runtime": 218.2301, |
| "train_tokens_per_second": 2119.708 |
| }, |
| { |
| "epoch": 12.807017543859649, |
| "grad_norm": 0.00045960358693264425, |
| "learning_rate": 1.7318269910511736e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 465688, |
| "step": 730, |
| "train_runtime": 219.4842, |
| "train_tokens_per_second": 2121.738 |
| }, |
| { |
| "epoch": 12.894736842105264, |
| "grad_norm": 0.004071191884577274, |
| "learning_rate": 1.6954953074382863e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 468856, |
| "step": 735, |
| "train_runtime": 220.7449, |
| "train_tokens_per_second": 2123.972 |
| }, |
| { |
| "epoch": 12.982456140350877, |
| "grad_norm": 0.0025077101308852434, |
| "learning_rate": 1.659352190581993e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 471768, |
| "step": 740, |
| "train_runtime": 221.91, |
| "train_tokens_per_second": 2125.943 |
| }, |
| { |
| "epoch": 13.0, |
| "eval_loss": 0.049703001976013184, |
| "eval_runtime": 0.6465, |
| "eval_samples_per_second": 38.667, |
| "eval_steps_per_second": 10.827, |
| "num_input_tokens_seen": 471944, |
| "step": 741 |
| }, |
| { |
| "epoch": 13.070175438596491, |
| "grad_norm": 0.0004011514538433403, |
| "learning_rate": 1.6234061120181142e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 474344, |
| "step": 745, |
| "train_runtime": 226.3226, |
| "train_tokens_per_second": 2095.875 |
| }, |
| { |
| "epoch": 13.157894736842104, |
| "grad_norm": 0.002411268185824156, |
| "learning_rate": 1.5876654970989308e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 478120, |
| "step": 750, |
| "train_runtime": 227.7803, |
| "train_tokens_per_second": 2099.04 |
| }, |
| { |
| "epoch": 13.24561403508772, |
| "grad_norm": 0.0006114121642895043, |
| "learning_rate": 1.552138723018382e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 480840, |
| "step": 755, |
| "train_runtime": 228.8881, |
| "train_tokens_per_second": 2100.765 |
| }, |
| { |
| "epoch": 13.333333333333334, |
| "grad_norm": 0.0003881508018821478, |
| "learning_rate": 1.5168341168485423e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 484552, |
| "step": 760, |
| "train_runtime": 230.3267, |
| "train_tokens_per_second": 2103.76 |
| }, |
| { |
| "epoch": 13.421052631578947, |
| "grad_norm": 0.0005596206174232066, |
| "learning_rate": 1.4817599535878565e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 487304, |
| "step": 765, |
| "train_runtime": 231.4977, |
| "train_tokens_per_second": 2105.006 |
| }, |
| { |
| "epoch": 13.508771929824562, |
| "grad_norm": 0.003762410022318363, |
| "learning_rate": 1.4469244542215682e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 490536, |
| "step": 770, |
| "train_runtime": 232.7818, |
| "train_tokens_per_second": 2107.278 |
| }, |
| { |
| "epoch": 13.596491228070175, |
| "grad_norm": 0.0003943524498026818, |
| "learning_rate": 1.4123357837948175e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 493128, |
| "step": 775, |
| "train_runtime": 233.8846, |
| "train_tokens_per_second": 2108.424 |
| }, |
| { |
| "epoch": 13.68421052631579, |
| "grad_norm": 0.0020312978886067867, |
| "learning_rate": 1.3780020494988446e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 496136, |
| "step": 780, |
| "train_runtime": 235.091, |
| "train_tokens_per_second": 2110.4 |
| }, |
| { |
| "epoch": 13.771929824561404, |
| "grad_norm": 0.0006078864680603147, |
| "learning_rate": 1.3439312987707615e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 499432, |
| "step": 785, |
| "train_runtime": 236.421, |
| "train_tokens_per_second": 2112.469 |
| }, |
| { |
| "epoch": 13.859649122807017, |
| "grad_norm": 0.0009284237748943269, |
| "learning_rate": 1.3101315174073162e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 502984, |
| "step": 790, |
| "train_runtime": 237.7822, |
| "train_tokens_per_second": 2115.314 |
| }, |
| { |
| "epoch": 13.947368421052632, |
| "grad_norm": 0.000585039088036865, |
| "learning_rate": 1.2766106276931223e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 506376, |
| "step": 795, |
| "train_runtime": 239.1015, |
| "train_tokens_per_second": 2117.828 |
| }, |
| { |
| "epoch": 14.0, |
| "eval_loss": 0.05849914625287056, |
| "eval_runtime": 0.6443, |
| "eval_samples_per_second": 38.804, |
| "eval_steps_per_second": 10.865, |
| "num_input_tokens_seen": 508424, |
| "step": 798 |
| }, |
| { |
| "epoch": 14.035087719298245, |
| "grad_norm": 0.00040168012492358685, |
| "learning_rate": 1.243376486543755e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 509672, |
| "step": 800, |
| "train_runtime": 242.457, |
| "train_tokens_per_second": 2102.113 |
| }, |
| { |
| "epoch": 14.12280701754386, |
| "grad_norm": 0.0003365933371242136, |
| "learning_rate": 1.2104368836641908e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 513320, |
| "step": 805, |
| "train_runtime": 244.0859, |
| "train_tokens_per_second": 2103.03 |
| }, |
| { |
| "epoch": 14.210526315789474, |
| "grad_norm": 0.00046245771227404475, |
| "learning_rate": 1.1777995397229771e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 516296, |
| "step": 810, |
| "train_runtime": 245.2637, |
| "train_tokens_per_second": 2105.065 |
| }, |
| { |
| "epoch": 14.298245614035087, |
| "grad_norm": 0.0010048067197203636, |
| "learning_rate": 1.1454721045426073e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 520040, |
| "step": 815, |
| "train_runtime": 246.7378, |
| "train_tokens_per_second": 2107.662 |
| }, |
| { |
| "epoch": 14.385964912280702, |
| "grad_norm": 0.0006219562492333353, |
| "learning_rate": 1.113462155306478e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 523272, |
| "step": 820, |
| "train_runtime": 248.0285, |
| "train_tokens_per_second": 2109.725 |
| }, |
| { |
| "epoch": 14.473684210526315, |
| "grad_norm": 0.0015207750257104635, |
| "learning_rate": 1.0817771947828934e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 527112, |
| "step": 825, |
| "train_runtime": 249.5068, |
| "train_tokens_per_second": 2112.616 |
| }, |
| { |
| "epoch": 14.56140350877193, |
| "grad_norm": 0.00064323894912377, |
| "learning_rate": 1.0504246495664932e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 530568, |
| "step": 830, |
| "train_runtime": 250.8496, |
| "train_tokens_per_second": 2115.084 |
| }, |
| { |
| "epoch": 14.649122807017545, |
| "grad_norm": 0.005003608763217926, |
| "learning_rate": 1.0194118683375503e-05, |
| "loss": 0.0, |
| "num_input_tokens_seen": 533192, |
| "step": 835, |
| "train_runtime": 251.9834, |
| "train_tokens_per_second": 2115.981 |
| }, |
| { |
| "epoch": 14.736842105263158, |
| "grad_norm": 0.0005010716267861426, |
| "learning_rate": 9.887461201395176e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 536232, |
| "step": 840, |
| "train_runtime": 253.2111, |
| "train_tokens_per_second": 2117.727 |
| }, |
| { |
| "epoch": 14.824561403508772, |
| "grad_norm": 0.0005740668857470155, |
| "learning_rate": 9.584345926752524e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 539624, |
| "step": 845, |
| "train_runtime": 254.5318, |
| "train_tokens_per_second": 2120.065 |
| }, |
| { |
| "epoch": 14.912280701754385, |
| "grad_norm": 0.0010048388503491879, |
| "learning_rate": 9.284843906222948e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 542664, |
| "step": 850, |
| "train_runtime": 255.7526, |
| "train_tokens_per_second": 2121.832 |
| }, |
| { |
| "epoch": 15.0, |
| "grad_norm": 0.00393655663356185, |
| "learning_rate": 8.98902533967618e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 545352, |
| "step": 855, |
| "train_runtime": 256.9979, |
| "train_tokens_per_second": 2122.01 |
| }, |
| { |
| "epoch": 15.0, |
| "eval_loss": 0.05685203894972801, |
| "eval_runtime": 0.6496, |
| "eval_samples_per_second": 38.486, |
| "eval_steps_per_second": 10.776, |
| "num_input_tokens_seen": 545352, |
| "step": 855 |
| }, |
| { |
| "epoch": 15.087719298245615, |
| "grad_norm": 0.0004725376202259213, |
| "learning_rate": 8.696959563622174e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 548488, |
| "step": 860, |
| "train_runtime": 260.6678, |
| "train_tokens_per_second": 2104.165 |
| }, |
| { |
| "epoch": 15.175438596491228, |
| "grad_norm": 0.003261847887188196, |
| "learning_rate": 8.40871503495947e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 552008, |
| "step": 865, |
| "train_runtime": 262.0583, |
| "train_tokens_per_second": 2106.432 |
| }, |
| { |
| "epoch": 15.263157894736842, |
| "grad_norm": 0.0011708957608789206, |
| "learning_rate": 8.124359314929622e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 555944, |
| "step": 870, |
| "train_runtime": 263.5898, |
| "train_tokens_per_second": 2109.126 |
| }, |
| { |
| "epoch": 15.350877192982455, |
| "grad_norm": 0.0014813272282481194, |
| "learning_rate": 7.843959053281663e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 558888, |
| "step": 875, |
| "train_runtime": 264.8111, |
| "train_tokens_per_second": 2110.516 |
| }, |
| { |
| "epoch": 15.43859649122807, |
| "grad_norm": 0.0027633686549961567, |
| "learning_rate": 7.5675799726501155e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 562536, |
| "step": 880, |
| "train_runtime": 266.2091, |
| "train_tokens_per_second": 2113.136 |
| }, |
| { |
| "epoch": 15.526315789473685, |
| "grad_norm": 0.0005604032194241881, |
| "learning_rate": 7.295286853150391e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 565160, |
| "step": 885, |
| "train_runtime": 267.3271, |
| "train_tokens_per_second": 2114.114 |
| }, |
| { |
| "epoch": 15.614035087719298, |
| "grad_norm": 0.0029854937456548214, |
| "learning_rate": 7.027143517195023e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 568232, |
| "step": 890, |
| "train_runtime": 268.5595, |
| "train_tokens_per_second": 2115.852 |
| }, |
| { |
| "epoch": 15.701754385964913, |
| "grad_norm": 0.0011887118453159928, |
| "learning_rate": 6.763212814534484e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 571048, |
| "step": 895, |
| "train_runtime": 269.7166, |
| "train_tokens_per_second": 2117.215 |
| }, |
| { |
| "epoch": 15.789473684210526, |
| "grad_norm": 0.001011132844723761, |
| "learning_rate": 6.503556607525838e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 574664, |
| "step": 900, |
| "train_runtime": 271.1283, |
| "train_tokens_per_second": 2119.528 |
| }, |
| { |
| "epoch": 15.87719298245614, |
| "grad_norm": 0.000857419625390321, |
| "learning_rate": 6.248235756632984e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 577608, |
| "step": 905, |
| "train_runtime": 272.3251, |
| "train_tokens_per_second": 2121.024 |
| }, |
| { |
| "epoch": 15.964912280701755, |
| "grad_norm": 0.0007091089501045644, |
| "learning_rate": 5.997310106161589e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 580680, |
| "step": 910, |
| "train_runtime": 273.5022, |
| "train_tokens_per_second": 2123.127 |
| }, |
| { |
| "epoch": 16.0, |
| "eval_loss": 0.05738845840096474, |
| "eval_runtime": 0.6505, |
| "eval_samples_per_second": 38.431, |
| "eval_steps_per_second": 10.761, |
| "num_input_tokens_seen": 581368, |
| "step": 912 |
| }, |
| { |
| "epoch": 16.05263157894737, |
| "grad_norm": 0.0010650490876287222, |
| "learning_rate": 5.7508384702323226e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 583544, |
| "step": 915, |
| "train_runtime": 276.9244, |
| "train_tokens_per_second": 2107.232 |
| }, |
| { |
| "epoch": 16.140350877192983, |
| "grad_norm": 0.0006341239786706865, |
| "learning_rate": 5.508878618995439e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 586424, |
| "step": 920, |
| "train_runtime": 278.1967, |
| "train_tokens_per_second": 2107.947 |
| }, |
| { |
| "epoch": 16.228070175438596, |
| "grad_norm": 0.000871942494995892, |
| "learning_rate": 5.271487265090163e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 589976, |
| "step": 925, |
| "train_runtime": 279.6016, |
| "train_tokens_per_second": 2110.059 |
| }, |
| { |
| "epoch": 16.31578947368421, |
| "grad_norm": 0.00048285795492120087, |
| "learning_rate": 5.038720050351842e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 593048, |
| "step": 930, |
| "train_runtime": 280.8565, |
| "train_tokens_per_second": 2111.569 |
| }, |
| { |
| "epoch": 16.403508771929825, |
| "grad_norm": 0.001297388575039804, |
| "learning_rate": 4.810631532770182e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 596472, |
| "step": 935, |
| "train_runtime": 282.1903, |
| "train_tokens_per_second": 2113.723 |
| }, |
| { |
| "epoch": 16.49122807017544, |
| "grad_norm": 0.00048762926599010825, |
| "learning_rate": 4.587275173701428e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 599544, |
| "step": 940, |
| "train_runtime": 283.416, |
| "train_tokens_per_second": 2115.421 |
| }, |
| { |
| "epoch": 16.57894736842105, |
| "grad_norm": 0.002341912128031254, |
| "learning_rate": 4.368703325337667e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 603032, |
| "step": 945, |
| "train_runtime": 284.7716, |
| "train_tokens_per_second": 2117.599 |
| }, |
| { |
| "epoch": 16.666666666666668, |
| "grad_norm": 0.0009274564799852669, |
| "learning_rate": 4.154967218436037e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 605560, |
| "step": 950, |
| "train_runtime": 285.8802, |
| "train_tokens_per_second": 2118.23 |
| }, |
| { |
| "epoch": 16.75438596491228, |
| "grad_norm": 0.00048819792573340237, |
| "learning_rate": 3.94611695031086e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 609176, |
| "step": 955, |
| "train_runtime": 287.3244, |
| "train_tokens_per_second": 2120.168 |
| }, |
| { |
| "epoch": 16.842105263157894, |
| "grad_norm": 0.0005237769219093025, |
| "learning_rate": 3.74220147309135e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 612024, |
| "step": 960, |
| "train_runtime": 288.4884, |
| "train_tokens_per_second": 2121.486 |
| }, |
| { |
| "epoch": 16.92982456140351, |
| "grad_norm": 0.000496424559969455, |
| "learning_rate": 3.543268582247844e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 615064, |
| "step": 965, |
| "train_runtime": 289.7175, |
| "train_tokens_per_second": 2122.978 |
| }, |
| { |
| "epoch": 17.0, |
| "eval_loss": 0.057452987879514694, |
| "eval_runtime": 0.6509, |
| "eval_samples_per_second": 38.408, |
| "eval_steps_per_second": 10.754, |
| "num_input_tokens_seen": 616776, |
| "step": 969 |
| }, |
| { |
| "epoch": 17.017543859649123, |
| "grad_norm": 0.002946019871160388, |
| "learning_rate": 3.3493649053890326e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 617640, |
| "step": 970, |
| "train_runtime": 292.8543, |
| "train_tokens_per_second": 2109.035 |
| }, |
| { |
| "epoch": 17.105263157894736, |
| "grad_norm": 0.0033382540568709373, |
| "learning_rate": 3.1605358913330385e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 620424, |
| "step": 975, |
| "train_runtime": 294.3542, |
| "train_tokens_per_second": 2107.747 |
| }, |
| { |
| "epoch": 17.19298245614035, |
| "grad_norm": 0.0005159943248145282, |
| "learning_rate": 2.9768257994546662e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 623176, |
| "step": 980, |
| "train_runtime": 295.5392, |
| "train_tokens_per_second": 2108.607 |
| }, |
| { |
| "epoch": 17.280701754385966, |
| "grad_norm": 0.00030576359131373465, |
| "learning_rate": 2.7982776893115627e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 626600, |
| "step": 985, |
| "train_runtime": 296.8757, |
| "train_tokens_per_second": 2110.648 |
| }, |
| { |
| "epoch": 17.36842105263158, |
| "grad_norm": 0.0003654029860626906, |
| "learning_rate": 2.624933410551508e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 629992, |
| "step": 990, |
| "train_runtime": 298.1865, |
| "train_tokens_per_second": 2112.745 |
| }, |
| { |
| "epoch": 17.45614035087719, |
| "grad_norm": 0.0005527487373910844, |
| "learning_rate": 2.456833593103361e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 633128, |
| "step": 995, |
| "train_runtime": 299.4453, |
| "train_tokens_per_second": 2114.336 |
| }, |
| { |
| "epoch": 17.54385964912281, |
| "grad_norm": 0.0023809513077139854, |
| "learning_rate": 2.2940176376538445e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 635880, |
| "step": 1000, |
| "train_runtime": 300.5684, |
| "train_tokens_per_second": 2115.592 |
| }, |
| { |
| "epoch": 17.63157894736842, |
| "grad_norm": 0.0007673691725358367, |
| "learning_rate": 2.136523706412477e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 639208, |
| "step": 1005, |
| "train_runtime": 301.8855, |
| "train_tokens_per_second": 2117.385 |
| }, |
| { |
| "epoch": 17.719298245614034, |
| "grad_norm": 0.0003941990726161748, |
| "learning_rate": 1.984388714166799e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 642152, |
| "step": 1010, |
| "train_runtime": 303.0857, |
| "train_tokens_per_second": 2118.715 |
| }, |
| { |
| "epoch": 17.80701754385965, |
| "grad_norm": 0.00032321223989129066, |
| "learning_rate": 1.837648319629956e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 645800, |
| "step": 1015, |
| "train_runtime": 304.5079, |
| "train_tokens_per_second": 2120.799 |
| }, |
| { |
| "epoch": 17.894736842105264, |
| "grad_norm": 0.0014884057454764843, |
| "learning_rate": 1.6963369170826943e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 649736, |
| "step": 1020, |
| "train_runtime": 305.9981, |
| "train_tokens_per_second": 2123.333 |
| }, |
| { |
| "epoch": 17.982456140350877, |
| "grad_norm": 0.0009696213528513908, |
| "learning_rate": 1.5604876283117326e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 653064, |
| "step": 1025, |
| "train_runtime": 307.2888, |
| "train_tokens_per_second": 2125.245 |
| }, |
| { |
| "epoch": 18.0, |
| "eval_loss": 0.05298217758536339, |
| "eval_runtime": 0.6501, |
| "eval_samples_per_second": 38.456, |
| "eval_steps_per_second": 10.768, |
| "num_input_tokens_seen": 653152, |
| "step": 1026 |
| }, |
| { |
| "epoch": 18.07017543859649, |
| "grad_norm": 0.0009916668059304357, |
| "learning_rate": 1.4301322948464147e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 655424, |
| "step": 1030, |
| "train_runtime": 310.8359, |
| "train_tokens_per_second": 2108.585 |
| }, |
| { |
| "epoch": 18.157894736842106, |
| "grad_norm": 0.000655690731946379, |
| "learning_rate": 1.3053014704953987e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 658848, |
| "step": 1035, |
| "train_runtime": 312.1513, |
| "train_tokens_per_second": 2110.669 |
| }, |
| { |
| "epoch": 18.24561403508772, |
| "grad_norm": 0.0011434548068791628, |
| "learning_rate": 1.1860244141851773e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 661888, |
| "step": 1040, |
| "train_runtime": 313.4054, |
| "train_tokens_per_second": 2111.923 |
| }, |
| { |
| "epoch": 18.333333333333332, |
| "grad_norm": 0.002060619182884693, |
| "learning_rate": 1.0723290831021471e-06, |
| "loss": 0.0, |
| "num_input_tokens_seen": 665664, |
| "step": 1045, |
| "train_runtime": 314.8785, |
| "train_tokens_per_second": 2114.035 |
| }, |
| { |
| "epoch": 18.42105263157895, |
| "grad_norm": 0.0003666201955638826, |
| "learning_rate": 9.642421261397472e-07, |
| "loss": 0.0, |
| "num_input_tokens_seen": 668896, |
| "step": 1050, |
| "train_runtime": 316.1697, |
| "train_tokens_per_second": 2115.623 |
| }, |
| { |
| "epoch": 18.50877192982456, |
| "grad_norm": 0.0004000212938990444, |
| "learning_rate": 8.617888776522642e-07, |
| "loss": 0.0, |
| "num_input_tokens_seen": 672352, |
| "step": 1055, |
| "train_runtime": 317.5438, |
| "train_tokens_per_second": 2117.352 |
| }, |
| { |
| "epoch": 18.596491228070175, |
| "grad_norm": 0.0006306173163466156, |
| "learning_rate": 7.649933515167407e-07, |
| "loss": 0.0, |
| "num_input_tokens_seen": 675392, |
| "step": 1060, |
| "train_runtime": 318.7705, |
| "train_tokens_per_second": 2118.74 |
| }, |
| { |
| "epoch": 18.68421052631579, |
| "grad_norm": 0.0009248993592336774, |
| "learning_rate": 6.738782355044049e-07, |
| "loss": 0.0, |
| "num_input_tokens_seen": 678080, |
| "step": 1065, |
| "train_runtime": 319.889, |
| "train_tokens_per_second": 2119.736 |
| }, |
| { |
| "epoch": 18.771929824561404, |
| "grad_norm": 0.0004742000892292708, |
| "learning_rate": 5.88464885962911e-07, |
| "loss": 0.0, |
| "num_input_tokens_seen": 681440, |
| "step": 1070, |
| "train_runtime": 321.212, |
| "train_tokens_per_second": 2121.465 |
| }, |
| { |
| "epoch": 18.859649122807017, |
| "grad_norm": 0.0013239184627309442, |
| "learning_rate": 5.087733228106517e-07, |
| "loss": 0.0, |
| "num_input_tokens_seen": 684608, |
| "step": 1075, |
| "train_runtime": 322.4571, |
| "train_tokens_per_second": 2123.098 |
| }, |
| { |
| "epoch": 18.94736842105263, |
| "grad_norm": 0.00036334068863652647, |
| "learning_rate": 4.3482222484432513e-07, |
| "loss": 0.0, |
| "num_input_tokens_seen": 688480, |
| "step": 1080, |
| "train_runtime": 323.9254, |
| "train_tokens_per_second": 2125.428 |
| }, |
| { |
| "epoch": 19.0, |
| "eval_loss": 0.05078503116965294, |
| "eval_runtime": 0.6559, |
| "eval_samples_per_second": 38.117, |
| "eval_steps_per_second": 10.673, |
| "num_input_tokens_seen": 689856, |
| "step": 1083 |
| }, |
| { |
| "epoch": 19.035087719298247, |
| "grad_norm": 0.001993294572457671, |
| "learning_rate": 3.666289253608235e-07, |
| "loss": 0.0, |
| "num_input_tokens_seen": 691200, |
| "step": 1085, |
| "train_runtime": 327.2107, |
| "train_tokens_per_second": 2112.4 |
| }, |
| { |
| "epoch": 19.12280701754386, |
| "grad_norm": 0.0036186480429023504, |
| "learning_rate": 3.0420940809451624e-07, |
| "loss": 0.0, |
| "num_input_tokens_seen": 694240, |
| "step": 1090, |
| "train_runtime": 328.7182, |
| "train_tokens_per_second": 2111.961 |
| }, |
| { |
| "epoch": 19.210526315789473, |
| "grad_norm": 0.0004895579186268151, |
| "learning_rate": 2.47578303470844e-07, |
| "loss": 0.0, |
| "num_input_tokens_seen": 697472, |
| "step": 1095, |
| "train_runtime": 330.0119, |
| "train_tokens_per_second": 2113.475 |
| }, |
| { |
| "epoch": 19.29824561403509, |
| "grad_norm": 0.000327645568177104, |
| "learning_rate": 1.96748885177106e-07, |
| "loss": 0.0, |
| "num_input_tokens_seen": 699872, |
| "step": 1100, |
| "train_runtime": 331.0607, |
| "train_tokens_per_second": 2114.03 |
| }, |
| { |
| "epoch": 19.385964912280702, |
| "grad_norm": 0.0010647806338965893, |
| "learning_rate": 1.517330670512629e-07, |
| "loss": 0.0, |
| "num_input_tokens_seen": 704736, |
| "step": 1105, |
| "train_runtime": 332.8495, |
| "train_tokens_per_second": 2117.281 |
| }, |
| { |
| "epoch": 19.473684210526315, |
| "grad_norm": 0.0005168251227587461, |
| "learning_rate": 1.125414002894759e-07, |
| "loss": 0.0, |
| "num_input_tokens_seen": 707968, |
| "step": 1110, |
| "train_runtime": 334.1293, |
| "train_tokens_per_second": 2118.844 |
| }, |
| { |
| "epoch": 19.56140350877193, |
| "grad_norm": 0.0008096309611573815, |
| "learning_rate": 7.918307097301014e-08, |
| "loss": 0.0, |
| "num_input_tokens_seen": 711136, |
| "step": 1115, |
| "train_runtime": 335.3917, |
| "train_tokens_per_second": 2120.315 |
| }, |
| { |
| "epoch": 19.649122807017545, |
| "grad_norm": 0.0002859925734810531, |
| "learning_rate": 5.166589791513465e-08, |
| "loss": 0.0, |
| "num_input_tokens_seen": 714432, |
| "step": 1120, |
| "train_runtime": 336.6857, |
| "train_tokens_per_second": 2121.955 |
| }, |
| { |
| "epoch": 19.736842105263158, |
| "grad_norm": 0.0004952243762090802, |
| "learning_rate": 2.999633082847453e-08, |
| "loss": 0.0, |
| "num_input_tokens_seen": 717440, |
| "step": 1125, |
| "train_runtime": 337.9103, |
| "train_tokens_per_second": 2123.167 |
| }, |
| { |
| "epoch": 19.82456140350877, |
| "grad_norm": 0.0011136343237012625, |
| "learning_rate": 1.4179448813278484e-08, |
| "loss": 0.0, |
| "num_input_tokens_seen": 720480, |
| "step": 1130, |
| "train_runtime": 339.1559, |
| "train_tokens_per_second": 2124.333 |
| }, |
| { |
| "epoch": 19.912280701754387, |
| "grad_norm": 0.0005656600114889443, |
| "learning_rate": 4.218959166932268e-09, |
| "loss": 0.0, |
| "num_input_tokens_seen": 723552, |
| "step": 1135, |
| "train_runtime": 340.4299, |
| "train_tokens_per_second": 2125.407 |
| }, |
| { |
| "epoch": 20.0, |
| "grad_norm": 0.0010879135224968195, |
| "learning_rate": 1.1719651499819683e-10, |
| "loss": 0.0, |
| "num_input_tokens_seen": 725992, |
| "step": 1140, |
| "train_runtime": 341.5924, |
| "train_tokens_per_second": 2125.317 |
| }, |
| { |
| "epoch": 20.0, |
| "eval_loss": 0.05127305909991264, |
| "eval_runtime": 0.647, |
| "eval_samples_per_second": 38.642, |
| "eval_steps_per_second": 10.82, |
| "num_input_tokens_seen": 725992, |
| "step": 1140 |
| }, |
| { |
| "epoch": 20.0, |
| "num_input_tokens_seen": 725992, |
| "step": 1140, |
| "total_flos": 3.275503728898867e+16, |
| "train_loss": 0.04678131848158317, |
| "train_runtime": 343.4721, |
| "train_samples_per_second": 13.102, |
| "train_steps_per_second": 3.319 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 1140, |
| "num_input_tokens_seen": 725992, |
| "num_train_epochs": 20, |
| "save_steps": 57, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3.275503728898867e+16, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
