| { | |
| "best_metric": 93.2776, | |
| "best_model_checkpoint": "models/lemmatization-seed-2-philta_finally/checkpoint-164868", | |
| "epoch": 32.99984990243659, | |
| "global_step": 164868, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.979983987189753e-05, | |
| "loss": 2.1491, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.959967974379504e-05, | |
| "loss": 0.6907, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 9.939951961569256e-05, | |
| "loss": 0.5698, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 9.919935948759008e-05, | |
| "loss": 0.5212, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 9.89991993594876e-05, | |
| "loss": 0.4783, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 9.879903923138511e-05, | |
| "loss": 0.468, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 9.859887910328262e-05, | |
| "loss": 0.4402, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 9.839871897518015e-05, | |
| "loss": 0.4079, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 9.819855884707767e-05, | |
| "loss": 0.3856, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.28772488236427307, | |
| "eval_lowercase_match_acc": 88.1229, | |
| "eval_runtime": 4369.0377, | |
| "eval_samples_per_second": 5.066, | |
| "eval_steps_per_second": 2.533, | |
| "step": 4996 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 9.799839871897519e-05, | |
| "loss": 0.3696, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 9.77982385908727e-05, | |
| "loss": 0.3373, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 9.759807846277023e-05, | |
| "loss": 0.3308, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 9.739791833466774e-05, | |
| "loss": 0.3049, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 9.719775820656527e-05, | |
| "loss": 0.3195, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 9.699759807846276e-05, | |
| "loss": 0.2952, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 9.679743795036029e-05, | |
| "loss": 0.2949, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 9.659727782225782e-05, | |
| "loss": 0.2897, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 9.639711769415533e-05, | |
| "loss": 0.2725, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 9.619695756605284e-05, | |
| "loss": 0.2866, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.23798207938671112, | |
| "eval_lowercase_match_acc": 90.1242, | |
| "eval_runtime": 5070.7184, | |
| "eval_samples_per_second": 4.365, | |
| "eval_steps_per_second": 2.183, | |
| "step": 9992 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 9.599679743795037e-05, | |
| "loss": 0.2696, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 9.579663730984788e-05, | |
| "loss": 0.2399, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 9.559647718174541e-05, | |
| "loss": 0.2305, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 9.539631705364291e-05, | |
| "loss": 0.2285, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 9.519615692554043e-05, | |
| "loss": 0.233, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 9.499599679743796e-05, | |
| "loss": 0.2284, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 9.479583666933547e-05, | |
| "loss": 0.2302, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 9.459567654123299e-05, | |
| "loss": 0.2195, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 9.439551641313051e-05, | |
| "loss": 0.2267, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 9.419535628502803e-05, | |
| "loss": 0.2181, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.21965482831001282, | |
| "eval_lowercase_match_acc": 91.1904, | |
| "eval_runtime": 5163.2805, | |
| "eval_samples_per_second": 4.287, | |
| "eval_steps_per_second": 2.144, | |
| "step": 14988 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 9.399519615692555e-05, | |
| "loss": 0.2145, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 9.379503602882305e-05, | |
| "loss": 0.1931, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 9.359487590072058e-05, | |
| "loss": 0.1881, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 9.33947157726181e-05, | |
| "loss": 0.1895, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 9.319455564451562e-05, | |
| "loss": 0.1819, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 9.299439551641313e-05, | |
| "loss": 0.182, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 9.279423538831066e-05, | |
| "loss": 0.1837, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 9.259407526020817e-05, | |
| "loss": 0.1839, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 9.23939151321057e-05, | |
| "loss": 0.1757, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "learning_rate": 9.219375500400321e-05, | |
| "loss": 0.178, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.2106914520263672, | |
| "eval_lowercase_match_acc": 91.7326, | |
| "eval_runtime": 3762.7729, | |
| "eval_samples_per_second": 5.883, | |
| "eval_steps_per_second": 2.941, | |
| "step": 19984 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 9.199359487590072e-05, | |
| "loss": 0.1833, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 9.179343474779825e-05, | |
| "loss": 0.1575, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 9.159327461969576e-05, | |
| "loss": 0.1572, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 9.139311449159327e-05, | |
| "loss": 0.159, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 9.11929543634908e-05, | |
| "loss": 0.1535, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 9.099279423538831e-05, | |
| "loss": 0.1612, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 9.079263410728584e-05, | |
| "loss": 0.1524, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "learning_rate": 9.059247397918335e-05, | |
| "loss": 0.1611, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 9.039231385108086e-05, | |
| "loss": 0.1533, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "learning_rate": 9.019215372297839e-05, | |
| "loss": 0.1537, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.20324945449829102, | |
| "eval_lowercase_match_acc": 92.0352, | |
| "eval_runtime": 3885.1477, | |
| "eval_samples_per_second": 5.697, | |
| "eval_steps_per_second": 2.849, | |
| "step": 24980 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 8.99919935948759e-05, | |
| "loss": 0.1492, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "learning_rate": 8.979183346677342e-05, | |
| "loss": 0.1344, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 5.2, | |
| "learning_rate": 8.959167333867094e-05, | |
| "loss": 0.1317, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 5.3, | |
| "learning_rate": 8.939151321056846e-05, | |
| "loss": 0.1319, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 5.4, | |
| "learning_rate": 8.919135308246598e-05, | |
| "loss": 0.1314, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 5.5, | |
| "learning_rate": 8.89911929543635e-05, | |
| "loss": 0.1361, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "learning_rate": 8.879103282626101e-05, | |
| "loss": 0.1348, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 5.7, | |
| "learning_rate": 8.859087269815853e-05, | |
| "loss": 0.127, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 5.8, | |
| "learning_rate": 8.839071257005605e-05, | |
| "loss": 0.137, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 5.9, | |
| "learning_rate": 8.819055244195357e-05, | |
| "loss": 0.1358, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.2009614259004593, | |
| "eval_lowercase_match_acc": 92.1572, | |
| "eval_runtime": 4606.4788, | |
| "eval_samples_per_second": 4.805, | |
| "eval_steps_per_second": 2.403, | |
| "step": 29976 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 8.799039231385109e-05, | |
| "loss": 0.1308, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 6.1, | |
| "learning_rate": 8.77902321857486e-05, | |
| "loss": 0.113, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 6.2, | |
| "learning_rate": 8.759007205764613e-05, | |
| "loss": 0.1144, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 6.3, | |
| "learning_rate": 8.738991192954364e-05, | |
| "loss": 0.1135, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "learning_rate": 8.718975180144115e-05, | |
| "loss": 0.1161, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 6.51, | |
| "learning_rate": 8.698959167333868e-05, | |
| "loss": 0.1183, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 6.61, | |
| "learning_rate": 8.678943154523619e-05, | |
| "loss": 0.1162, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 6.71, | |
| "learning_rate": 8.658927141713372e-05, | |
| "loss": 0.1124, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 6.81, | |
| "learning_rate": 8.638911128903123e-05, | |
| "loss": 0.1106, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 6.91, | |
| "learning_rate": 8.618895116092874e-05, | |
| "loss": 0.115, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.20892679691314697, | |
| "eval_lowercase_match_acc": 92.609, | |
| "eval_runtime": 4588.1045, | |
| "eval_samples_per_second": 4.824, | |
| "eval_steps_per_second": 2.412, | |
| "step": 34972 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 8.598879103282627e-05, | |
| "loss": 0.1188, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 7.11, | |
| "learning_rate": 8.578863090472378e-05, | |
| "loss": 0.0967, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 7.21, | |
| "learning_rate": 8.55884707766213e-05, | |
| "loss": 0.1048, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 7.31, | |
| "learning_rate": 8.538831064851882e-05, | |
| "loss": 0.0991, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 7.41, | |
| "learning_rate": 8.518815052041633e-05, | |
| "loss": 0.096, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 7.51, | |
| "learning_rate": 8.498799039231386e-05, | |
| "loss": 0.1028, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 7.61, | |
| "learning_rate": 8.478783026421137e-05, | |
| "loss": 0.0968, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 7.71, | |
| "learning_rate": 8.458767013610889e-05, | |
| "loss": 0.0999, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 7.81, | |
| "learning_rate": 8.438751000800641e-05, | |
| "loss": 0.0991, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 7.91, | |
| "learning_rate": 8.418734987990394e-05, | |
| "loss": 0.0994, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.2047615349292755, | |
| "eval_lowercase_match_acc": 92.3921, | |
| "eval_runtime": 4481.5661, | |
| "eval_samples_per_second": 4.939, | |
| "eval_steps_per_second": 2.47, | |
| "step": 39968 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 8.398718975180144e-05, | |
| "loss": 0.1056, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 8.11, | |
| "learning_rate": 8.378702962369896e-05, | |
| "loss": 0.0907, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 8.21, | |
| "learning_rate": 8.358686949559648e-05, | |
| "loss": 0.0879, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 8.31, | |
| "learning_rate": 8.3386709367494e-05, | |
| "loss": 0.0901, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 8.41, | |
| "learning_rate": 8.318654923939152e-05, | |
| "loss": 0.0888, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 8.51, | |
| "learning_rate": 8.298638911128903e-05, | |
| "loss": 0.0911, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 8.61, | |
| "learning_rate": 8.278622898318655e-05, | |
| "loss": 0.0903, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 8.71, | |
| "learning_rate": 8.258606885508408e-05, | |
| "loss": 0.0843, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 8.81, | |
| "learning_rate": 8.238590872698158e-05, | |
| "loss": 0.0918, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 8.91, | |
| "learning_rate": 8.218574859887911e-05, | |
| "loss": 0.0873, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.20837198197841644, | |
| "eval_lowercase_match_acc": 92.8168, | |
| "eval_runtime": 4924.2181, | |
| "eval_samples_per_second": 4.495, | |
| "eval_steps_per_second": 2.248, | |
| "step": 44964 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 8.198558847077662e-05, | |
| "loss": 0.0907, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 9.11, | |
| "learning_rate": 8.178542834267415e-05, | |
| "loss": 0.0723, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 9.21, | |
| "learning_rate": 8.158526821457166e-05, | |
| "loss": 0.0744, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 9.31, | |
| "learning_rate": 8.138510808646917e-05, | |
| "loss": 0.0786, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 9.41, | |
| "learning_rate": 8.11849479583667e-05, | |
| "loss": 0.0851, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 9.51, | |
| "learning_rate": 8.098478783026422e-05, | |
| "loss": 0.0743, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 9.61, | |
| "learning_rate": 8.078462770216172e-05, | |
| "loss": 0.0826, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 9.71, | |
| "learning_rate": 8.058446757405925e-05, | |
| "loss": 0.0852, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 9.81, | |
| "learning_rate": 8.038430744595678e-05, | |
| "loss": 0.0789, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 9.91, | |
| "learning_rate": 8.018414731785429e-05, | |
| "loss": 0.0777, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.20926587283611298, | |
| "eval_lowercase_match_acc": 92.8078, | |
| "eval_runtime": 5857.6443, | |
| "eval_samples_per_second": 3.779, | |
| "eval_steps_per_second": 1.889, | |
| "step": 49960 | |
| }, | |
| { | |
| "epoch": 10.01, | |
| "learning_rate": 7.99839871897518e-05, | |
| "loss": 0.0772, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 10.11, | |
| "learning_rate": 7.978382706164931e-05, | |
| "loss": 0.0687, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 10.21, | |
| "learning_rate": 7.958366693354684e-05, | |
| "loss": 0.0712, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 10.31, | |
| "learning_rate": 7.938350680544437e-05, | |
| "loss": 0.071, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 10.41, | |
| "learning_rate": 7.918334667734188e-05, | |
| "loss": 0.0706, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 10.51, | |
| "learning_rate": 7.89831865492394e-05, | |
| "loss": 0.0713, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 10.61, | |
| "learning_rate": 7.878302642113692e-05, | |
| "loss": 0.0649, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 10.71, | |
| "learning_rate": 7.858286629303443e-05, | |
| "loss": 0.0747, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 10.81, | |
| "learning_rate": 7.838270616493195e-05, | |
| "loss": 0.0692, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 10.91, | |
| "learning_rate": 7.818254603682946e-05, | |
| "loss": 0.0729, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 0.2255134880542755, | |
| "eval_lowercase_match_acc": 92.8529, | |
| "eval_runtime": 4053.7342, | |
| "eval_samples_per_second": 5.46, | |
| "eval_steps_per_second": 2.73, | |
| "step": 54956 | |
| }, | |
| { | |
| "epoch": 11.01, | |
| "learning_rate": 7.798238590872698e-05, | |
| "loss": 0.0666, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 11.11, | |
| "learning_rate": 7.778222578062451e-05, | |
| "loss": 0.0544, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 11.21, | |
| "learning_rate": 7.758206565252202e-05, | |
| "loss": 0.0667, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 11.31, | |
| "learning_rate": 7.738190552441954e-05, | |
| "loss": 0.0623, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 11.41, | |
| "learning_rate": 7.718174539631706e-05, | |
| "loss": 0.06, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 11.51, | |
| "learning_rate": 7.698158526821458e-05, | |
| "loss": 0.068, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 11.61, | |
| "learning_rate": 7.67814251401121e-05, | |
| "loss": 0.0607, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 11.71, | |
| "learning_rate": 7.65812650120096e-05, | |
| "loss": 0.0614, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 11.81, | |
| "learning_rate": 7.638110488390713e-05, | |
| "loss": 0.066, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 11.91, | |
| "learning_rate": 7.618094475580465e-05, | |
| "loss": 0.0641, | |
| "step": 59500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 0.2248515486717224, | |
| "eval_lowercase_match_acc": 92.9388, | |
| "eval_runtime": 5148.8388, | |
| "eval_samples_per_second": 4.299, | |
| "eval_steps_per_second": 2.15, | |
| "step": 59952 | |
| }, | |
| { | |
| "epoch": 12.01, | |
| "learning_rate": 7.598078462770217e-05, | |
| "loss": 0.0662, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 12.11, | |
| "learning_rate": 7.578062449959968e-05, | |
| "loss": 0.0574, | |
| "step": 60500 | |
| }, | |
| { | |
| "epoch": 12.21, | |
| "learning_rate": 7.55804643714972e-05, | |
| "loss": 0.0529, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 12.31, | |
| "learning_rate": 7.538030424339472e-05, | |
| "loss": 0.0578, | |
| "step": 61500 | |
| }, | |
| { | |
| "epoch": 12.41, | |
| "learning_rate": 7.518014411529225e-05, | |
| "loss": 0.0538, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 12.51, | |
| "learning_rate": 7.497998398718974e-05, | |
| "loss": 0.055, | |
| "step": 62500 | |
| }, | |
| { | |
| "epoch": 12.61, | |
| "learning_rate": 7.477982385908727e-05, | |
| "loss": 0.057, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 12.71, | |
| "learning_rate": 7.45796637309848e-05, | |
| "loss": 0.056, | |
| "step": 63500 | |
| }, | |
| { | |
| "epoch": 12.81, | |
| "learning_rate": 7.437950360288231e-05, | |
| "loss": 0.0564, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 12.91, | |
| "learning_rate": 7.417934347477982e-05, | |
| "loss": 0.0617, | |
| "step": 64500 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 0.23913247883319855, | |
| "eval_lowercase_match_acc": 93.002, | |
| "eval_runtime": 3464.1623, | |
| "eval_samples_per_second": 6.39, | |
| "eval_steps_per_second": 3.195, | |
| "step": 64948 | |
| }, | |
| { | |
| "epoch": 13.01, | |
| "learning_rate": 7.397918334667735e-05, | |
| "loss": 0.0568, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 13.11, | |
| "learning_rate": 7.377902321857486e-05, | |
| "loss": 0.0485, | |
| "step": 65500 | |
| }, | |
| { | |
| "epoch": 13.21, | |
| "learning_rate": 7.357886309047239e-05, | |
| "loss": 0.0473, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 13.31, | |
| "learning_rate": 7.337870296236989e-05, | |
| "loss": 0.048, | |
| "step": 66500 | |
| }, | |
| { | |
| "epoch": 13.41, | |
| "learning_rate": 7.317854283426741e-05, | |
| "loss": 0.0509, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 13.51, | |
| "learning_rate": 7.297838270616494e-05, | |
| "loss": 0.0527, | |
| "step": 67500 | |
| }, | |
| { | |
| "epoch": 13.61, | |
| "learning_rate": 7.277822257806245e-05, | |
| "loss": 0.051, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 13.71, | |
| "learning_rate": 7.257806244995997e-05, | |
| "loss": 0.0512, | |
| "step": 68500 | |
| }, | |
| { | |
| "epoch": 13.81, | |
| "learning_rate": 7.237790232185749e-05, | |
| "loss": 0.0512, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 13.91, | |
| "learning_rate": 7.2177742193755e-05, | |
| "loss": 0.0575, | |
| "step": 69500 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 0.25704246759414673, | |
| "eval_lowercase_match_acc": 92.8168, | |
| "eval_runtime": 4630.5226, | |
| "eval_samples_per_second": 4.78, | |
| "eval_steps_per_second": 2.39, | |
| "step": 69944 | |
| }, | |
| { | |
| "epoch": 14.01, | |
| "learning_rate": 7.197758206565253e-05, | |
| "loss": 0.0517, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 14.11, | |
| "learning_rate": 7.177742193755004e-05, | |
| "loss": 0.0408, | |
| "step": 70500 | |
| }, | |
| { | |
| "epoch": 14.21, | |
| "learning_rate": 7.157726180944756e-05, | |
| "loss": 0.0457, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 14.31, | |
| "learning_rate": 7.137710168134508e-05, | |
| "loss": 0.047, | |
| "step": 71500 | |
| }, | |
| { | |
| "epoch": 14.41, | |
| "learning_rate": 7.11769415532426e-05, | |
| "loss": 0.0452, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 14.51, | |
| "learning_rate": 7.097678142514011e-05, | |
| "loss": 0.0458, | |
| "step": 72500 | |
| }, | |
| { | |
| "epoch": 14.61, | |
| "learning_rate": 7.077662129703764e-05, | |
| "loss": 0.0432, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 14.71, | |
| "learning_rate": 7.057646116893515e-05, | |
| "loss": 0.0494, | |
| "step": 73500 | |
| }, | |
| { | |
| "epoch": 14.81, | |
| "learning_rate": 7.037630104083268e-05, | |
| "loss": 0.0498, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 14.91, | |
| "learning_rate": 7.017614091273019e-05, | |
| "loss": 0.0475, | |
| "step": 74500 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 0.2623473107814789, | |
| "eval_lowercase_match_acc": 93.0562, | |
| "eval_runtime": 5358.3874, | |
| "eval_samples_per_second": 4.131, | |
| "eval_steps_per_second": 2.066, | |
| "step": 74940 | |
| }, | |
| { | |
| "epoch": 15.01, | |
| "learning_rate": 6.99759807846277e-05, | |
| "loss": 0.0486, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 15.11, | |
| "learning_rate": 6.977582065652523e-05, | |
| "loss": 0.0389, | |
| "step": 75500 | |
| }, | |
| { | |
| "epoch": 15.21, | |
| "learning_rate": 6.957566052842274e-05, | |
| "loss": 0.041, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 15.31, | |
| "learning_rate": 6.937550040032025e-05, | |
| "loss": 0.0394, | |
| "step": 76500 | |
| }, | |
| { | |
| "epoch": 15.41, | |
| "learning_rate": 6.917534027221778e-05, | |
| "loss": 0.0405, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 15.51, | |
| "learning_rate": 6.897518014411529e-05, | |
| "loss": 0.0427, | |
| "step": 77500 | |
| }, | |
| { | |
| "epoch": 15.61, | |
| "learning_rate": 6.877502001601282e-05, | |
| "loss": 0.0432, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 15.71, | |
| "learning_rate": 6.857485988791033e-05, | |
| "loss": 0.042, | |
| "step": 78500 | |
| }, | |
| { | |
| "epoch": 15.81, | |
| "learning_rate": 6.837469975980784e-05, | |
| "loss": 0.0417, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 15.91, | |
| "learning_rate": 6.817453963170537e-05, | |
| "loss": 0.0435, | |
| "step": 79500 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 0.26566237211227417, | |
| "eval_lowercase_match_acc": 92.9885, | |
| "eval_runtime": 5585.7722, | |
| "eval_samples_per_second": 3.963, | |
| "eval_steps_per_second": 1.981, | |
| "step": 79936 | |
| }, | |
| { | |
| "epoch": 16.01, | |
| "learning_rate": 6.797437950360288e-05, | |
| "loss": 0.044, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 16.11, | |
| "learning_rate": 6.777421937550041e-05, | |
| "loss": 0.0354, | |
| "step": 80500 | |
| }, | |
| { | |
| "epoch": 16.21, | |
| "learning_rate": 6.757405924739792e-05, | |
| "loss": 0.0392, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 16.31, | |
| "learning_rate": 6.737389911929544e-05, | |
| "loss": 0.0379, | |
| "step": 81500 | |
| }, | |
| { | |
| "epoch": 16.41, | |
| "learning_rate": 6.717373899119296e-05, | |
| "loss": 0.0406, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 16.51, | |
| "learning_rate": 6.697357886309047e-05, | |
| "loss": 0.0393, | |
| "step": 82500 | |
| }, | |
| { | |
| "epoch": 16.61, | |
| "learning_rate": 6.677341873498799e-05, | |
| "loss": 0.0381, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 16.71, | |
| "learning_rate": 6.657325860688551e-05, | |
| "loss": 0.0376, | |
| "step": 83500 | |
| }, | |
| { | |
| "epoch": 16.81, | |
| "learning_rate": 6.637309847878303e-05, | |
| "loss": 0.0384, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 16.91, | |
| "learning_rate": 6.617293835068055e-05, | |
| "loss": 0.04, | |
| "step": 84500 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 0.27961936593055725, | |
| "eval_lowercase_match_acc": 93.0653, | |
| "eval_runtime": 5010.3314, | |
| "eval_samples_per_second": 4.418, | |
| "eval_steps_per_second": 2.209, | |
| "step": 84932 | |
| }, | |
| { | |
| "epoch": 17.01, | |
| "learning_rate": 6.597277822257807e-05, | |
| "loss": 0.0363, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 17.11, | |
| "learning_rate": 6.577261809447558e-05, | |
| "loss": 0.0302, | |
| "step": 85500 | |
| }, | |
| { | |
| "epoch": 17.21, | |
| "learning_rate": 6.55724579663731e-05, | |
| "loss": 0.0361, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 17.31, | |
| "learning_rate": 6.537229783827062e-05, | |
| "loss": 0.0325, | |
| "step": 86500 | |
| }, | |
| { | |
| "epoch": 17.41, | |
| "learning_rate": 6.517213771016813e-05, | |
| "loss": 0.0356, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 17.51, | |
| "learning_rate": 6.497197758206566e-05, | |
| "loss": 0.0339, | |
| "step": 87500 | |
| }, | |
| { | |
| "epoch": 17.61, | |
| "learning_rate": 6.477181745396317e-05, | |
| "loss": 0.0357, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 17.71, | |
| "learning_rate": 6.45716573258607e-05, | |
| "loss": 0.036, | |
| "step": 88500 | |
| }, | |
| { | |
| "epoch": 17.81, | |
| "learning_rate": 6.437149719775821e-05, | |
| "loss": 0.0336, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 17.91, | |
| "learning_rate": 6.417133706965572e-05, | |
| "loss": 0.0336, | |
| "step": 89500 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 0.2810537815093994, | |
| "eval_lowercase_match_acc": 93.0382, | |
| "eval_runtime": 3682.9518, | |
| "eval_samples_per_second": 6.01, | |
| "eval_steps_per_second": 3.005, | |
| "step": 89928 | |
| }, | |
| { | |
| "epoch": 18.01, | |
| "learning_rate": 6.397117694155325e-05, | |
| "loss": 0.0336, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 18.11, | |
| "learning_rate": 6.377101681345077e-05, | |
| "loss": 0.0291, | |
| "step": 90500 | |
| }, | |
| { | |
| "epoch": 18.21, | |
| "learning_rate": 6.357085668534827e-05, | |
| "loss": 0.0293, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 18.31, | |
| "learning_rate": 6.33706965572458e-05, | |
| "loss": 0.0293, | |
| "step": 91500 | |
| }, | |
| { | |
| "epoch": 18.41, | |
| "learning_rate": 6.317053642914331e-05, | |
| "loss": 0.0324, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 18.51, | |
| "learning_rate": 6.297037630104084e-05, | |
| "loss": 0.0331, | |
| "step": 92500 | |
| }, | |
| { | |
| "epoch": 18.61, | |
| "learning_rate": 6.277021617293835e-05, | |
| "loss": 0.0334, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 18.71, | |
| "learning_rate": 6.257005604483587e-05, | |
| "loss": 0.0309, | |
| "step": 93500 | |
| }, | |
| { | |
| "epoch": 18.81, | |
| "learning_rate": 6.236989591673339e-05, | |
| "loss": 0.0329, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 18.91, | |
| "learning_rate": 6.216973578863092e-05, | |
| "loss": 0.0329, | |
| "step": 94500 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 0.2951154112815857, | |
| "eval_lowercase_match_acc": 93.1421, | |
| "eval_runtime": 4374.9093, | |
| "eval_samples_per_second": 5.06, | |
| "eval_steps_per_second": 2.53, | |
| "step": 94924 | |
| }, | |
| { | |
| "epoch": 19.02, | |
| "learning_rate": 6.196957566052842e-05, | |
| "loss": 0.0292, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 19.12, | |
| "learning_rate": 6.176941553242594e-05, | |
| "loss": 0.0312, | |
| "step": 95500 | |
| }, | |
| { | |
| "epoch": 19.22, | |
| "learning_rate": 6.156925540432347e-05, | |
| "loss": 0.0272, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 19.32, | |
| "learning_rate": 6.136909527622098e-05, | |
| "loss": 0.0286, | |
| "step": 96500 | |
| }, | |
| { | |
| "epoch": 19.42, | |
| "learning_rate": 6.11689351481185e-05, | |
| "loss": 0.0263, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 19.52, | |
| "learning_rate": 6.096877502001601e-05, | |
| "loss": 0.0307, | |
| "step": 97500 | |
| }, | |
| { | |
| "epoch": 19.62, | |
| "learning_rate": 6.0768614891913535e-05, | |
| "loss": 0.0282, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 19.72, | |
| "learning_rate": 6.0568454763811054e-05, | |
| "loss": 0.0279, | |
| "step": 98500 | |
| }, | |
| { | |
| "epoch": 19.82, | |
| "learning_rate": 6.036829463570857e-05, | |
| "loss": 0.0299, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 19.92, | |
| "learning_rate": 6.016813450760609e-05, | |
| "loss": 0.0329, | |
| "step": 99500 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 0.3092300593852997, | |
| "eval_lowercase_match_acc": 93.1105, | |
| "eval_runtime": 4507.9299, | |
| "eval_samples_per_second": 4.91, | |
| "eval_steps_per_second": 2.455, | |
| "step": 99920 | |
| }, | |
| { | |
| "epoch": 20.02, | |
| "learning_rate": 5.996797437950361e-05, | |
| "loss": 0.0273, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 20.12, | |
| "learning_rate": 5.976781425140112e-05, | |
| "loss": 0.024, | |
| "step": 100500 | |
| }, | |
| { | |
| "epoch": 20.22, | |
| "learning_rate": 5.9567654123298645e-05, | |
| "loss": 0.0258, | |
| "step": 101000 | |
| }, | |
| { | |
| "epoch": 20.32, | |
| "learning_rate": 5.936749399519616e-05, | |
| "loss": 0.0269, | |
| "step": 101500 | |
| }, | |
| { | |
| "epoch": 20.42, | |
| "learning_rate": 5.916733386709368e-05, | |
| "loss": 0.0278, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 20.52, | |
| "learning_rate": 5.89671737389912e-05, | |
| "loss": 0.0236, | |
| "step": 102500 | |
| }, | |
| { | |
| "epoch": 20.62, | |
| "learning_rate": 5.876701361088871e-05, | |
| "loss": 0.0244, | |
| "step": 103000 | |
| }, | |
| { | |
| "epoch": 20.72, | |
| "learning_rate": 5.856685348278623e-05, | |
| "loss": 0.0269, | |
| "step": 103500 | |
| }, | |
| { | |
| "epoch": 20.82, | |
| "learning_rate": 5.8366693354683756e-05, | |
| "loss": 0.0287, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 20.92, | |
| "learning_rate": 5.816653322658126e-05, | |
| "loss": 0.0283, | |
| "step": 104500 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_loss": 0.32634150981903076, | |
| "eval_lowercase_match_acc": 93.0382, | |
| "eval_runtime": 5218.5574, | |
| "eval_samples_per_second": 4.242, | |
| "eval_steps_per_second": 2.121, | |
| "step": 104916 | |
| }, | |
| { | |
| "epoch": 21.02, | |
| "learning_rate": 5.796637309847879e-05, | |
| "loss": 0.0266, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 21.12, | |
| "learning_rate": 5.77662129703763e-05, | |
| "loss": 0.0229, | |
| "step": 105500 | |
| }, | |
| { | |
| "epoch": 21.22, | |
| "learning_rate": 5.756605284227382e-05, | |
| "loss": 0.0246, | |
| "step": 106000 | |
| }, | |
| { | |
| "epoch": 21.32, | |
| "learning_rate": 5.736589271417134e-05, | |
| "loss": 0.0242, | |
| "step": 106500 | |
| }, | |
| { | |
| "epoch": 21.42, | |
| "learning_rate": 5.7165732586068854e-05, | |
| "loss": 0.0257, | |
| "step": 107000 | |
| }, | |
| { | |
| "epoch": 21.52, | |
| "learning_rate": 5.696557245796637e-05, | |
| "loss": 0.023, | |
| "step": 107500 | |
| }, | |
| { | |
| "epoch": 21.62, | |
| "learning_rate": 5.67654123298639e-05, | |
| "loss": 0.0241, | |
| "step": 108000 | |
| }, | |
| { | |
| "epoch": 21.72, | |
| "learning_rate": 5.656525220176141e-05, | |
| "loss": 0.0258, | |
| "step": 108500 | |
| }, | |
| { | |
| "epoch": 21.82, | |
| "learning_rate": 5.636509207365893e-05, | |
| "loss": 0.0252, | |
| "step": 109000 | |
| }, | |
| { | |
| "epoch": 21.92, | |
| "learning_rate": 5.6164931945556445e-05, | |
| "loss": 0.025, | |
| "step": 109500 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_loss": 0.33478838205337524, | |
| "eval_lowercase_match_acc": 93.1105, | |
| "eval_runtime": 4574.2489, | |
| "eval_samples_per_second": 4.839, | |
| "eval_steps_per_second": 2.42, | |
| "step": 109912 | |
| }, | |
| { | |
| "epoch": 22.02, | |
| "learning_rate": 5.5964771817453964e-05, | |
| "loss": 0.026, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 22.12, | |
| "learning_rate": 5.5764611689351484e-05, | |
| "loss": 0.0229, | |
| "step": 110500 | |
| }, | |
| { | |
| "epoch": 22.22, | |
| "learning_rate": 5.5564451561249e-05, | |
| "loss": 0.0201, | |
| "step": 111000 | |
| }, | |
| { | |
| "epoch": 22.32, | |
| "learning_rate": 5.536429143314652e-05, | |
| "loss": 0.0211, | |
| "step": 111500 | |
| }, | |
| { | |
| "epoch": 22.42, | |
| "learning_rate": 5.516413130504404e-05, | |
| "loss": 0.0209, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 22.52, | |
| "learning_rate": 5.4963971176941556e-05, | |
| "loss": 0.0197, | |
| "step": 112500 | |
| }, | |
| { | |
| "epoch": 22.62, | |
| "learning_rate": 5.4763811048839075e-05, | |
| "loss": 0.0245, | |
| "step": 113000 | |
| }, | |
| { | |
| "epoch": 22.72, | |
| "learning_rate": 5.456365092073659e-05, | |
| "loss": 0.0222, | |
| "step": 113500 | |
| }, | |
| { | |
| "epoch": 22.82, | |
| "learning_rate": 5.436349079263411e-05, | |
| "loss": 0.0253, | |
| "step": 114000 | |
| }, | |
| { | |
| "epoch": 22.92, | |
| "learning_rate": 5.4163330664531634e-05, | |
| "loss": 0.0202, | |
| "step": 114500 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_loss": 0.35109543800354004, | |
| "eval_lowercase_match_acc": 93.1873, | |
| "eval_runtime": 4159.2016, | |
| "eval_samples_per_second": 5.322, | |
| "eval_steps_per_second": 2.661, | |
| "step": 114908 | |
| }, | |
| { | |
| "epoch": 23.02, | |
| "learning_rate": 5.396317053642914e-05, | |
| "loss": 0.0199, | |
| "step": 115000 | |
| }, | |
| { | |
| "epoch": 23.12, | |
| "learning_rate": 5.3763010408326666e-05, | |
| "loss": 0.0173, | |
| "step": 115500 | |
| }, | |
| { | |
| "epoch": 23.22, | |
| "learning_rate": 5.3562850280224186e-05, | |
| "loss": 0.0191, | |
| "step": 116000 | |
| }, | |
| { | |
| "epoch": 23.32, | |
| "learning_rate": 5.33626901521217e-05, | |
| "loss": 0.0205, | |
| "step": 116500 | |
| }, | |
| { | |
| "epoch": 23.42, | |
| "learning_rate": 5.316253002401922e-05, | |
| "loss": 0.0214, | |
| "step": 117000 | |
| }, | |
| { | |
| "epoch": 23.52, | |
| "learning_rate": 5.296236989591674e-05, | |
| "loss": 0.0206, | |
| "step": 117500 | |
| }, | |
| { | |
| "epoch": 23.62, | |
| "learning_rate": 5.276220976781425e-05, | |
| "loss": 0.0206, | |
| "step": 118000 | |
| }, | |
| { | |
| "epoch": 23.72, | |
| "learning_rate": 5.256204963971178e-05, | |
| "loss": 0.0212, | |
| "step": 118500 | |
| }, | |
| { | |
| "epoch": 23.82, | |
| "learning_rate": 5.236188951160928e-05, | |
| "loss": 0.0227, | |
| "step": 119000 | |
| }, | |
| { | |
| "epoch": 23.92, | |
| "learning_rate": 5.216172938350681e-05, | |
| "loss": 0.0188, | |
| "step": 119500 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_loss": 0.362006276845932, | |
| "eval_lowercase_match_acc": 93.1466, | |
| "eval_runtime": 4253.911, | |
| "eval_samples_per_second": 5.203, | |
| "eval_steps_per_second": 2.602, | |
| "step": 119904 | |
| }, | |
| { | |
| "epoch": 24.02, | |
| "learning_rate": 5.196156925540433e-05, | |
| "loss": 0.0202, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 24.12, | |
| "learning_rate": 5.176140912730184e-05, | |
| "loss": 0.0173, | |
| "step": 120500 | |
| }, | |
| { | |
| "epoch": 24.22, | |
| "learning_rate": 5.156124899919936e-05, | |
| "loss": 0.0188, | |
| "step": 121000 | |
| }, | |
| { | |
| "epoch": 24.32, | |
| "learning_rate": 5.136108887109689e-05, | |
| "loss": 0.0171, | |
| "step": 121500 | |
| }, | |
| { | |
| "epoch": 24.42, | |
| "learning_rate": 5.1160928742994394e-05, | |
| "loss": 0.0202, | |
| "step": 122000 | |
| }, | |
| { | |
| "epoch": 24.52, | |
| "learning_rate": 5.096076861489192e-05, | |
| "loss": 0.0191, | |
| "step": 122500 | |
| }, | |
| { | |
| "epoch": 24.62, | |
| "learning_rate": 5.0760608486789427e-05, | |
| "loss": 0.0189, | |
| "step": 123000 | |
| }, | |
| { | |
| "epoch": 24.72, | |
| "learning_rate": 5.056044835868695e-05, | |
| "loss": 0.0212, | |
| "step": 123500 | |
| }, | |
| { | |
| "epoch": 24.82, | |
| "learning_rate": 5.036028823058447e-05, | |
| "loss": 0.0183, | |
| "step": 124000 | |
| }, | |
| { | |
| "epoch": 24.92, | |
| "learning_rate": 5.0160128102481985e-05, | |
| "loss": 0.0179, | |
| "step": 124500 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_loss": 0.3684503436088562, | |
| "eval_lowercase_match_acc": 93.1692, | |
| "eval_runtime": 4597.5953, | |
| "eval_samples_per_second": 4.814, | |
| "eval_steps_per_second": 2.407, | |
| "step": 124900 | |
| }, | |
| { | |
| "epoch": 25.02, | |
| "learning_rate": 4.9959967974379505e-05, | |
| "loss": 0.0189, | |
| "step": 125000 | |
| }, | |
| { | |
| "epoch": 25.12, | |
| "learning_rate": 4.9759807846277025e-05, | |
| "loss": 0.016, | |
| "step": 125500 | |
| }, | |
| { | |
| "epoch": 25.22, | |
| "learning_rate": 4.955964771817454e-05, | |
| "loss": 0.0162, | |
| "step": 126000 | |
| }, | |
| { | |
| "epoch": 25.32, | |
| "learning_rate": 4.9359487590072064e-05, | |
| "loss": 0.0162, | |
| "step": 126500 | |
| }, | |
| { | |
| "epoch": 25.42, | |
| "learning_rate": 4.9159327461969577e-05, | |
| "loss": 0.0151, | |
| "step": 127000 | |
| }, | |
| { | |
| "epoch": 25.52, | |
| "learning_rate": 4.8959167333867096e-05, | |
| "loss": 0.0165, | |
| "step": 127500 | |
| }, | |
| { | |
| "epoch": 25.62, | |
| "learning_rate": 4.875900720576461e-05, | |
| "loss": 0.0181, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 25.72, | |
| "learning_rate": 4.8558847077662135e-05, | |
| "loss": 0.0152, | |
| "step": 128500 | |
| }, | |
| { | |
| "epoch": 25.82, | |
| "learning_rate": 4.835868694955965e-05, | |
| "loss": 0.019, | |
| "step": 129000 | |
| }, | |
| { | |
| "epoch": 25.92, | |
| "learning_rate": 4.815852682145717e-05, | |
| "loss": 0.021, | |
| "step": 129500 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_loss": 0.3595723509788513, | |
| "eval_lowercase_match_acc": 93.2279, | |
| "eval_runtime": 5924.6722, | |
| "eval_samples_per_second": 3.736, | |
| "eval_steps_per_second": 1.868, | |
| "step": 129896 | |
| }, | |
| { | |
| "epoch": 26.02, | |
| "learning_rate": 4.795836669335468e-05, | |
| "loss": 0.0191, | |
| "step": 130000 | |
| }, | |
| { | |
| "epoch": 26.12, | |
| "learning_rate": 4.775820656525221e-05, | |
| "loss": 0.0131, | |
| "step": 130500 | |
| }, | |
| { | |
| "epoch": 26.22, | |
| "learning_rate": 4.755804643714972e-05, | |
| "loss": 0.0156, | |
| "step": 131000 | |
| }, | |
| { | |
| "epoch": 26.32, | |
| "learning_rate": 4.735788630904724e-05, | |
| "loss": 0.0154, | |
| "step": 131500 | |
| }, | |
| { | |
| "epoch": 26.42, | |
| "learning_rate": 4.715772618094476e-05, | |
| "loss": 0.0155, | |
| "step": 132000 | |
| }, | |
| { | |
| "epoch": 26.52, | |
| "learning_rate": 4.695756605284228e-05, | |
| "loss": 0.0156, | |
| "step": 132500 | |
| }, | |
| { | |
| "epoch": 26.62, | |
| "learning_rate": 4.675740592473979e-05, | |
| "loss": 0.0153, | |
| "step": 133000 | |
| }, | |
| { | |
| "epoch": 26.72, | |
| "learning_rate": 4.655724579663731e-05, | |
| "loss": 0.016, | |
| "step": 133500 | |
| }, | |
| { | |
| "epoch": 26.82, | |
| "learning_rate": 4.635708566853483e-05, | |
| "loss": 0.0172, | |
| "step": 134000 | |
| }, | |
| { | |
| "epoch": 26.92, | |
| "learning_rate": 4.615692554043235e-05, | |
| "loss": 0.0165, | |
| "step": 134500 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_loss": 0.3980076014995575, | |
| "eval_lowercase_match_acc": 93.1873, | |
| "eval_runtime": 4539.563, | |
| "eval_samples_per_second": 4.876, | |
| "eval_steps_per_second": 2.438, | |
| "step": 134892 | |
| }, | |
| { | |
| "epoch": 27.02, | |
| "learning_rate": 4.595676541232986e-05, | |
| "loss": 0.0168, | |
| "step": 135000 | |
| }, | |
| { | |
| "epoch": 27.12, | |
| "learning_rate": 4.575660528422738e-05, | |
| "loss": 0.0139, | |
| "step": 135500 | |
| }, | |
| { | |
| "epoch": 27.22, | |
| "learning_rate": 4.55564451561249e-05, | |
| "loss": 0.0136, | |
| "step": 136000 | |
| }, | |
| { | |
| "epoch": 27.32, | |
| "learning_rate": 4.535628502802242e-05, | |
| "loss": 0.0146, | |
| "step": 136500 | |
| }, | |
| { | |
| "epoch": 27.42, | |
| "learning_rate": 4.515612489991994e-05, | |
| "loss": 0.0143, | |
| "step": 137000 | |
| }, | |
| { | |
| "epoch": 27.52, | |
| "learning_rate": 4.4955964771817454e-05, | |
| "loss": 0.0173, | |
| "step": 137500 | |
| }, | |
| { | |
| "epoch": 27.62, | |
| "learning_rate": 4.4755804643714974e-05, | |
| "loss": 0.0148, | |
| "step": 138000 | |
| }, | |
| { | |
| "epoch": 27.72, | |
| "learning_rate": 4.4555644515612493e-05, | |
| "loss": 0.0143, | |
| "step": 138500 | |
| }, | |
| { | |
| "epoch": 27.82, | |
| "learning_rate": 4.435548438751001e-05, | |
| "loss": 0.0149, | |
| "step": 139000 | |
| }, | |
| { | |
| "epoch": 27.92, | |
| "learning_rate": 4.4155324259407526e-05, | |
| "loss": 0.0147, | |
| "step": 139500 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_loss": 0.4007766544818878, | |
| "eval_lowercase_match_acc": 93.0608, | |
| "eval_runtime": 5405.4624, | |
| "eval_samples_per_second": 4.095, | |
| "eval_steps_per_second": 2.048, | |
| "step": 139888 | |
| }, | |
| { | |
| "epoch": 28.02, | |
| "learning_rate": 4.3955164131305046e-05, | |
| "loss": 0.0096, | |
| "step": 140000 | |
| }, | |
| { | |
| "epoch": 28.12, | |
| "learning_rate": 4.3755004003202565e-05, | |
| "loss": 0.0118, | |
| "step": 140500 | |
| }, | |
| { | |
| "epoch": 28.22, | |
| "learning_rate": 4.3554843875100085e-05, | |
| "loss": 0.0134, | |
| "step": 141000 | |
| }, | |
| { | |
| "epoch": 28.32, | |
| "learning_rate": 4.33546837469976e-05, | |
| "loss": 0.0145, | |
| "step": 141500 | |
| }, | |
| { | |
| "epoch": 28.42, | |
| "learning_rate": 4.3154523618895124e-05, | |
| "loss": 0.0112, | |
| "step": 142000 | |
| }, | |
| { | |
| "epoch": 28.52, | |
| "learning_rate": 4.295436349079264e-05, | |
| "loss": 0.0165, | |
| "step": 142500 | |
| }, | |
| { | |
| "epoch": 28.62, | |
| "learning_rate": 4.2754203362690156e-05, | |
| "loss": 0.0151, | |
| "step": 143000 | |
| }, | |
| { | |
| "epoch": 28.72, | |
| "learning_rate": 4.255404323458767e-05, | |
| "loss": 0.0155, | |
| "step": 143500 | |
| }, | |
| { | |
| "epoch": 28.82, | |
| "learning_rate": 4.2353883106485196e-05, | |
| "loss": 0.0162, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 28.92, | |
| "learning_rate": 4.215372297838271e-05, | |
| "loss": 0.0149, | |
| "step": 144500 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_loss": 0.4174624979496002, | |
| "eval_lowercase_match_acc": 93.0337, | |
| "eval_runtime": 3557.364, | |
| "eval_samples_per_second": 6.222, | |
| "eval_steps_per_second": 3.111, | |
| "step": 144884 | |
| }, | |
| { | |
| "epoch": 29.02, | |
| "learning_rate": 4.195356285028023e-05, | |
| "loss": 0.0132, | |
| "step": 145000 | |
| }, | |
| { | |
| "epoch": 29.12, | |
| "learning_rate": 4.175340272217774e-05, | |
| "loss": 0.0158, | |
| "step": 145500 | |
| }, | |
| { | |
| "epoch": 29.22, | |
| "learning_rate": 4.155324259407527e-05, | |
| "loss": 0.0111, | |
| "step": 146000 | |
| }, | |
| { | |
| "epoch": 29.32, | |
| "learning_rate": 4.135308246597278e-05, | |
| "loss": 0.0118, | |
| "step": 146500 | |
| }, | |
| { | |
| "epoch": 29.42, | |
| "learning_rate": 4.11529223378703e-05, | |
| "loss": 0.0122, | |
| "step": 147000 | |
| }, | |
| { | |
| "epoch": 29.52, | |
| "learning_rate": 4.095276220976781e-05, | |
| "loss": 0.011, | |
| "step": 147500 | |
| }, | |
| { | |
| "epoch": 29.62, | |
| "learning_rate": 4.075260208166534e-05, | |
| "loss": 0.0148, | |
| "step": 148000 | |
| }, | |
| { | |
| "epoch": 29.72, | |
| "learning_rate": 4.055244195356285e-05, | |
| "loss": 0.0129, | |
| "step": 148500 | |
| }, | |
| { | |
| "epoch": 29.82, | |
| "learning_rate": 4.035228182546037e-05, | |
| "loss": 0.0142, | |
| "step": 149000 | |
| }, | |
| { | |
| "epoch": 29.92, | |
| "learning_rate": 4.0152121697357884e-05, | |
| "loss": 0.0126, | |
| "step": 149500 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_loss": 0.4186698794364929, | |
| "eval_lowercase_match_acc": 93.1963, | |
| "eval_runtime": 3676.3282, | |
| "eval_samples_per_second": 6.021, | |
| "eval_steps_per_second": 3.011, | |
| "step": 149880 | |
| }, | |
| { | |
| "epoch": 30.02, | |
| "learning_rate": 3.995196156925541e-05, | |
| "loss": 0.0141, | |
| "step": 150000 | |
| }, | |
| { | |
| "epoch": 30.12, | |
| "learning_rate": 3.975180144115292e-05, | |
| "loss": 0.0103, | |
| "step": 150500 | |
| }, | |
| { | |
| "epoch": 30.22, | |
| "learning_rate": 3.955164131305044e-05, | |
| "loss": 0.0131, | |
| "step": 151000 | |
| }, | |
| { | |
| "epoch": 30.32, | |
| "learning_rate": 3.9351481184947956e-05, | |
| "loss": 0.0108, | |
| "step": 151500 | |
| }, | |
| { | |
| "epoch": 30.42, | |
| "learning_rate": 3.915132105684548e-05, | |
| "loss": 0.0093, | |
| "step": 152000 | |
| }, | |
| { | |
| "epoch": 30.52, | |
| "learning_rate": 3.8951160928742995e-05, | |
| "loss": 0.0132, | |
| "step": 152500 | |
| }, | |
| { | |
| "epoch": 30.62, | |
| "learning_rate": 3.8751000800640514e-05, | |
| "loss": 0.0123, | |
| "step": 153000 | |
| }, | |
| { | |
| "epoch": 30.72, | |
| "learning_rate": 3.855084067253803e-05, | |
| "loss": 0.0126, | |
| "step": 153500 | |
| }, | |
| { | |
| "epoch": 30.82, | |
| "learning_rate": 3.8350680544435554e-05, | |
| "loss": 0.0097, | |
| "step": 154000 | |
| }, | |
| { | |
| "epoch": 30.92, | |
| "learning_rate": 3.8150520416333066e-05, | |
| "loss": 0.0139, | |
| "step": 154500 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_loss": 0.4269045889377594, | |
| "eval_lowercase_match_acc": 93.0788, | |
| "eval_runtime": 3725.6857, | |
| "eval_samples_per_second": 5.941, | |
| "eval_steps_per_second": 2.971, | |
| "step": 154876 | |
| }, | |
| { | |
| "epoch": 31.02, | |
| "learning_rate": 3.7950360288230586e-05, | |
| "loss": 0.0139, | |
| "step": 155000 | |
| }, | |
| { | |
| "epoch": 31.12, | |
| "learning_rate": 3.77502001601281e-05, | |
| "loss": 0.0113, | |
| "step": 155500 | |
| }, | |
| { | |
| "epoch": 31.22, | |
| "learning_rate": 3.7550040032025625e-05, | |
| "loss": 0.0108, | |
| "step": 156000 | |
| }, | |
| { | |
| "epoch": 31.33, | |
| "learning_rate": 3.734987990392314e-05, | |
| "loss": 0.0105, | |
| "step": 156500 | |
| }, | |
| { | |
| "epoch": 31.43, | |
| "learning_rate": 3.714971977582066e-05, | |
| "loss": 0.012, | |
| "step": 157000 | |
| }, | |
| { | |
| "epoch": 31.53, | |
| "learning_rate": 3.694955964771817e-05, | |
| "loss": 0.0119, | |
| "step": 157500 | |
| }, | |
| { | |
| "epoch": 31.63, | |
| "learning_rate": 3.67493995196157e-05, | |
| "loss": 0.0109, | |
| "step": 158000 | |
| }, | |
| { | |
| "epoch": 31.73, | |
| "learning_rate": 3.654923939151321e-05, | |
| "loss": 0.0131, | |
| "step": 158500 | |
| }, | |
| { | |
| "epoch": 31.83, | |
| "learning_rate": 3.634907926341073e-05, | |
| "loss": 0.011, | |
| "step": 159000 | |
| }, | |
| { | |
| "epoch": 31.93, | |
| "learning_rate": 3.614891913530825e-05, | |
| "loss": 0.0111, | |
| "step": 159500 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_loss": 0.43798354268074036, | |
| "eval_lowercase_match_acc": 93.1466, | |
| "eval_runtime": 3803.2601, | |
| "eval_samples_per_second": 5.82, | |
| "eval_steps_per_second": 2.91, | |
| "step": 159872 | |
| }, | |
| { | |
| "epoch": 32.03, | |
| "learning_rate": 3.594875900720577e-05, | |
| "loss": 0.0108, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 32.13, | |
| "learning_rate": 3.574859887910328e-05, | |
| "loss": 0.0092, | |
| "step": 160500 | |
| }, | |
| { | |
| "epoch": 32.23, | |
| "learning_rate": 3.55484387510008e-05, | |
| "loss": 0.0117, | |
| "step": 161000 | |
| }, | |
| { | |
| "epoch": 32.33, | |
| "learning_rate": 3.534827862289832e-05, | |
| "loss": 0.0103, | |
| "step": 161500 | |
| }, | |
| { | |
| "epoch": 32.43, | |
| "learning_rate": 3.514811849479584e-05, | |
| "loss": 0.0105, | |
| "step": 162000 | |
| }, | |
| { | |
| "epoch": 32.53, | |
| "learning_rate": 3.494795836669335e-05, | |
| "loss": 0.0114, | |
| "step": 162500 | |
| }, | |
| { | |
| "epoch": 32.63, | |
| "learning_rate": 3.474779823859087e-05, | |
| "loss": 0.0116, | |
| "step": 163000 | |
| }, | |
| { | |
| "epoch": 32.73, | |
| "learning_rate": 3.454763811048839e-05, | |
| "loss": 0.0103, | |
| "step": 163500 | |
| }, | |
| { | |
| "epoch": 32.83, | |
| "learning_rate": 3.434747798238591e-05, | |
| "loss": 0.0108, | |
| "step": 164000 | |
| }, | |
| { | |
| "epoch": 32.93, | |
| "learning_rate": 3.414731785428343e-05, | |
| "loss": 0.0108, | |
| "step": 164500 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_loss": 0.4487093687057495, | |
| "eval_lowercase_match_acc": 93.2776, | |
| "eval_runtime": 3787.9684, | |
| "eval_samples_per_second": 5.844, | |
| "eval_steps_per_second": 2.922, | |
| "step": 164868 | |
| } | |
| ], | |
| "max_steps": 249800, | |
| "num_train_epochs": 50, | |
| "total_flos": 6.948168358888673e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |