| { |
| "best_metric": 1.0082221031188965, |
| "best_model_checkpoint": "./output/checkpoints/2024-06-11_15-07-46/checkpoint-120", |
| "epoch": 3.0, |
| "eval_steps": 1, |
| "global_step": 129, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.023255813953488372, |
| "grad_norm": 3.230428695678711, |
| "learning_rate": 3.0769230769230774e-05, |
| "loss": 5.1513, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.023255813953488372, |
| "eval_loss": 5.098567485809326, |
| "eval_runtime": 10.4425, |
| "eval_samples_per_second": 11.204, |
| "eval_steps_per_second": 0.766, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.046511627906976744, |
| "grad_norm": 3.204726219177246, |
| "learning_rate": 6.153846153846155e-05, |
| "loss": 5.1556, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.046511627906976744, |
| "eval_loss": 5.000132083892822, |
| "eval_runtime": 10.4412, |
| "eval_samples_per_second": 11.206, |
| "eval_steps_per_second": 0.766, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.06976744186046512, |
| "grad_norm": 3.1961917877197266, |
| "learning_rate": 9.230769230769232e-05, |
| "loss": 4.9354, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.06976744186046512, |
| "eval_loss": 4.540091514587402, |
| "eval_runtime": 10.4665, |
| "eval_samples_per_second": 11.178, |
| "eval_steps_per_second": 0.764, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.09302325581395349, |
| "grad_norm": 3.3630478382110596, |
| "learning_rate": 0.0001230769230769231, |
| "loss": 4.5394, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.09302325581395349, |
| "eval_loss": 3.6481263637542725, |
| "eval_runtime": 10.5, |
| "eval_samples_per_second": 11.143, |
| "eval_steps_per_second": 0.762, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.11627906976744186, |
| "grad_norm": 3.4904136657714844, |
| "learning_rate": 0.00015384615384615385, |
| "loss": 3.6545, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.11627906976744186, |
| "eval_loss": 2.6286702156066895, |
| "eval_runtime": 10.4841, |
| "eval_samples_per_second": 11.16, |
| "eval_steps_per_second": 0.763, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.13953488372093023, |
| "grad_norm": 2.7318434715270996, |
| "learning_rate": 0.00018461538461538463, |
| "loss": 2.5645, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.13953488372093023, |
| "eval_loss": 2.047227144241333, |
| "eval_runtime": 10.5229, |
| "eval_samples_per_second": 11.119, |
| "eval_steps_per_second": 0.76, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.16279069767441862, |
| "grad_norm": 2.1703038215637207, |
| "learning_rate": 0.0002153846153846154, |
| "loss": 2.0145, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.16279069767441862, |
| "eval_loss": 1.6754586696624756, |
| "eval_runtime": 10.513, |
| "eval_samples_per_second": 11.129, |
| "eval_steps_per_second": 0.761, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.18604651162790697, |
| "grad_norm": 1.1857593059539795, |
| "learning_rate": 0.0002461538461538462, |
| "loss": 1.6469, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.18604651162790697, |
| "eval_loss": 1.4785383939743042, |
| "eval_runtime": 10.4789, |
| "eval_samples_per_second": 11.165, |
| "eval_steps_per_second": 0.763, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.20930232558139536, |
| "grad_norm": 0.94368976354599, |
| "learning_rate": 0.00027692307692307695, |
| "loss": 1.4676, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.20930232558139536, |
| "eval_loss": 1.3956246376037598, |
| "eval_runtime": 10.5914, |
| "eval_samples_per_second": 11.047, |
| "eval_steps_per_second": 0.755, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.23255813953488372, |
| "grad_norm": 1.3516250848770142, |
| "learning_rate": 0.0003076923076923077, |
| "loss": 1.377, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.23255813953488372, |
| "eval_loss": 1.2937995195388794, |
| "eval_runtime": 10.5422, |
| "eval_samples_per_second": 11.098, |
| "eval_steps_per_second": 0.759, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.2558139534883721, |
| "grad_norm": 0.21453160047531128, |
| "learning_rate": 0.00033846153846153846, |
| "loss": 1.2814, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.2558139534883721, |
| "eval_loss": 1.258020281791687, |
| "eval_runtime": 10.4428, |
| "eval_samples_per_second": 11.204, |
| "eval_steps_per_second": 0.766, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.27906976744186046, |
| "grad_norm": 0.1224498599767685, |
| "learning_rate": 0.00036923076923076927, |
| "loss": 1.2261, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.27906976744186046, |
| "eval_loss": 1.228270411491394, |
| "eval_runtime": 10.5707, |
| "eval_samples_per_second": 11.068, |
| "eval_steps_per_second": 0.757, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.3023255813953488, |
| "grad_norm": 0.11027181148529053, |
| "learning_rate": 0.0004, |
| "loss": 1.1848, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.3023255813953488, |
| "eval_loss": 1.2002977132797241, |
| "eval_runtime": 10.5152, |
| "eval_samples_per_second": 11.127, |
| "eval_steps_per_second": 0.761, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.32558139534883723, |
| "grad_norm": 0.14012101292610168, |
| "learning_rate": 0.0003965517241379311, |
| "loss": 1.1961, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.32558139534883723, |
| "eval_loss": 1.1754467487335205, |
| "eval_runtime": 10.5013, |
| "eval_samples_per_second": 11.141, |
| "eval_steps_per_second": 0.762, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.3488372093023256, |
| "grad_norm": 0.22193074226379395, |
| "learning_rate": 0.0003931034482758621, |
| "loss": 1.1407, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.3488372093023256, |
| "eval_loss": 1.1523548364639282, |
| "eval_runtime": 10.4708, |
| "eval_samples_per_second": 11.174, |
| "eval_steps_per_second": 0.764, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.37209302325581395, |
| "grad_norm": 0.15213920176029205, |
| "learning_rate": 0.00038965517241379313, |
| "loss": 1.1364, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.37209302325581395, |
| "eval_loss": 1.1305698156356812, |
| "eval_runtime": 10.5494, |
| "eval_samples_per_second": 11.091, |
| "eval_steps_per_second": 0.758, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.3953488372093023, |
| "grad_norm": 0.08833792805671692, |
| "learning_rate": 0.0003862068965517242, |
| "loss": 1.1057, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.3953488372093023, |
| "eval_loss": 1.1136623620986938, |
| "eval_runtime": 10.6102, |
| "eval_samples_per_second": 11.027, |
| "eval_steps_per_second": 0.754, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.4186046511627907, |
| "grad_norm": 0.07902093976736069, |
| "learning_rate": 0.0003827586206896552, |
| "loss": 1.089, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.4186046511627907, |
| "eval_loss": 1.10086989402771, |
| "eval_runtime": 10.5681, |
| "eval_samples_per_second": 11.071, |
| "eval_steps_per_second": 0.757, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.4418604651162791, |
| "grad_norm": 0.07194280624389648, |
| "learning_rate": 0.00037931034482758624, |
| "loss": 1.0849, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.4418604651162791, |
| "eval_loss": 1.091064691543579, |
| "eval_runtime": 10.5436, |
| "eval_samples_per_second": 11.097, |
| "eval_steps_per_second": 0.759, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.46511627906976744, |
| "grad_norm": 0.05419577285647392, |
| "learning_rate": 0.0003758620689655173, |
| "loss": 1.0729, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.46511627906976744, |
| "eval_loss": 1.0844314098358154, |
| "eval_runtime": 10.46, |
| "eval_samples_per_second": 11.185, |
| "eval_steps_per_second": 0.765, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.4883720930232558, |
| "grad_norm": 0.05308014526963234, |
| "learning_rate": 0.0003724137931034483, |
| "loss": 1.0576, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.4883720930232558, |
| "eval_loss": 1.0792510509490967, |
| "eval_runtime": 10.5659, |
| "eval_samples_per_second": 11.073, |
| "eval_steps_per_second": 0.757, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.5116279069767442, |
| "grad_norm": 0.05068132281303406, |
| "learning_rate": 0.00036896551724137935, |
| "loss": 1.0591, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.5116279069767442, |
| "eval_loss": 1.074510931968689, |
| "eval_runtime": 10.5969, |
| "eval_samples_per_second": 11.041, |
| "eval_steps_per_second": 0.755, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.5348837209302325, |
| "grad_norm": 0.05279520899057388, |
| "learning_rate": 0.00036551724137931036, |
| "loss": 1.0216, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.5348837209302325, |
| "eval_loss": 1.0699939727783203, |
| "eval_runtime": 10.5288, |
| "eval_samples_per_second": 11.112, |
| "eval_steps_per_second": 0.76, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.5581395348837209, |
| "grad_norm": 0.051589012145996094, |
| "learning_rate": 0.0003620689655172414, |
| "loss": 1.0384, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.5581395348837209, |
| "eval_loss": 1.0660674571990967, |
| "eval_runtime": 10.4984, |
| "eval_samples_per_second": 11.145, |
| "eval_steps_per_second": 0.762, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.5813953488372093, |
| "grad_norm": 0.04975143447518349, |
| "learning_rate": 0.0003586206896551724, |
| "loss": 1.0754, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.5813953488372093, |
| "eval_loss": 1.0627647638320923, |
| "eval_runtime": 10.5768, |
| "eval_samples_per_second": 11.062, |
| "eval_steps_per_second": 0.756, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.6046511627906976, |
| "grad_norm": 0.048871301114559174, |
| "learning_rate": 0.00035517241379310347, |
| "loss": 1.037, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.6046511627906976, |
| "eval_loss": 1.0597318410873413, |
| "eval_runtime": 10.4738, |
| "eval_samples_per_second": 11.171, |
| "eval_steps_per_second": 0.764, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.627906976744186, |
| "grad_norm": 0.05112334340810776, |
| "learning_rate": 0.00035172413793103447, |
| "loss": 1.0579, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.627906976744186, |
| "eval_loss": 1.0566964149475098, |
| "eval_runtime": 10.5953, |
| "eval_samples_per_second": 11.043, |
| "eval_steps_per_second": 0.755, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.6511627906976745, |
| "grad_norm": 0.08299978822469711, |
| "learning_rate": 0.0003482758620689655, |
| "loss": 1.039, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.6511627906976745, |
| "eval_loss": 1.053879976272583, |
| "eval_runtime": 10.5064, |
| "eval_samples_per_second": 11.136, |
| "eval_steps_per_second": 0.761, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.6744186046511628, |
| "grad_norm": 0.04733407124876976, |
| "learning_rate": 0.0003448275862068965, |
| "loss": 1.054, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.6744186046511628, |
| "eval_loss": 1.0513161420822144, |
| "eval_runtime": 10.5869, |
| "eval_samples_per_second": 11.051, |
| "eval_steps_per_second": 0.756, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.6976744186046512, |
| "grad_norm": 0.045666251331567764, |
| "learning_rate": 0.0003413793103448276, |
| "loss": 1.0237, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.6976744186046512, |
| "eval_loss": 1.0490825176239014, |
| "eval_runtime": 10.5294, |
| "eval_samples_per_second": 11.112, |
| "eval_steps_per_second": 0.76, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.7209302325581395, |
| "grad_norm": 0.04347428306937218, |
| "learning_rate": 0.00033793103448275864, |
| "loss": 1.0238, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.7209302325581395, |
| "eval_loss": 1.0473451614379883, |
| "eval_runtime": 10.4778, |
| "eval_samples_per_second": 11.166, |
| "eval_steps_per_second": 0.764, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.7441860465116279, |
| "grad_norm": 0.04594381898641586, |
| "learning_rate": 0.00033448275862068964, |
| "loss": 1.0339, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.7441860465116279, |
| "eval_loss": 1.0460575819015503, |
| "eval_runtime": 10.4914, |
| "eval_samples_per_second": 11.152, |
| "eval_steps_per_second": 0.763, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.7674418604651163, |
| "grad_norm": 0.049526289105415344, |
| "learning_rate": 0.0003310344827586207, |
| "loss": 1.0418, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.7674418604651163, |
| "eval_loss": 1.04463791847229, |
| "eval_runtime": 10.4747, |
| "eval_samples_per_second": 11.17, |
| "eval_steps_per_second": 0.764, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.7906976744186046, |
| "grad_norm": 0.04762812703847885, |
| "learning_rate": 0.00032758620689655175, |
| "loss": 1.0302, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.7906976744186046, |
| "eval_loss": 1.042962670326233, |
| "eval_runtime": 10.6089, |
| "eval_samples_per_second": 11.028, |
| "eval_steps_per_second": 0.754, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.813953488372093, |
| "grad_norm": 0.05331471934914589, |
| "learning_rate": 0.00032413793103448275, |
| "loss": 1.0401, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.813953488372093, |
| "eval_loss": 1.0412102937698364, |
| "eval_runtime": 10.4972, |
| "eval_samples_per_second": 11.146, |
| "eval_steps_per_second": 0.762, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.8372093023255814, |
| "grad_norm": 0.041780710220336914, |
| "learning_rate": 0.0003206896551724138, |
| "loss": 1.0038, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.8372093023255814, |
| "eval_loss": 1.0397316217422485, |
| "eval_runtime": 10.4649, |
| "eval_samples_per_second": 11.18, |
| "eval_steps_per_second": 0.764, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.8604651162790697, |
| "grad_norm": 0.04302731156349182, |
| "learning_rate": 0.00031724137931034486, |
| "loss": 1.0249, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.8604651162790697, |
| "eval_loss": 1.0385717153549194, |
| "eval_runtime": 10.5101, |
| "eval_samples_per_second": 11.132, |
| "eval_steps_per_second": 0.761, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.8837209302325582, |
| "grad_norm": 0.0549028106033802, |
| "learning_rate": 0.00031379310344827586, |
| "loss": 1.0128, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.8837209302325582, |
| "eval_loss": 1.0375303030014038, |
| "eval_runtime": 10.479, |
| "eval_samples_per_second": 11.165, |
| "eval_steps_per_second": 0.763, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.9069767441860465, |
| "grad_norm": 0.04620625823736191, |
| "learning_rate": 0.0003103448275862069, |
| "loss": 1.0278, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.9069767441860465, |
| "eval_loss": 1.03622567653656, |
| "eval_runtime": 10.496, |
| "eval_samples_per_second": 11.147, |
| "eval_steps_per_second": 0.762, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.9302325581395349, |
| "grad_norm": 0.04755247011780739, |
| "learning_rate": 0.00030689655172413797, |
| "loss": 1.0059, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.9302325581395349, |
| "eval_loss": 1.0347106456756592, |
| "eval_runtime": 10.522, |
| "eval_samples_per_second": 11.12, |
| "eval_steps_per_second": 0.76, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.9534883720930233, |
| "grad_norm": 0.04391615465283394, |
| "learning_rate": 0.00030344827586206897, |
| "loss": 1.0234, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.9534883720930233, |
| "eval_loss": 1.033333420753479, |
| "eval_runtime": 10.5498, |
| "eval_samples_per_second": 11.09, |
| "eval_steps_per_second": 0.758, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.9767441860465116, |
| "grad_norm": 0.04336484521627426, |
| "learning_rate": 0.00030000000000000003, |
| "loss": 0.9913, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.9767441860465116, |
| "eval_loss": 1.0323785543441772, |
| "eval_runtime": 10.5082, |
| "eval_samples_per_second": 11.134, |
| "eval_steps_per_second": 0.761, |
| "step": 42 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.07296782732009888, |
| "learning_rate": 0.0002965517241379311, |
| "loss": 0.9975, |
| "step": 43 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 1.0313116312026978, |
| "eval_runtime": 10.5008, |
| "eval_samples_per_second": 11.142, |
| "eval_steps_per_second": 0.762, |
| "step": 43 |
| }, |
| { |
| "epoch": 1.0232558139534884, |
| "grad_norm": 0.041788019239902496, |
| "learning_rate": 0.0002931034482758621, |
| "loss": 0.9841, |
| "step": 44 |
| }, |
| { |
| "epoch": 1.0232558139534884, |
| "eval_loss": 1.0304553508758545, |
| "eval_runtime": 10.4812, |
| "eval_samples_per_second": 11.163, |
| "eval_steps_per_second": 0.763, |
| "step": 44 |
| }, |
| { |
| "epoch": 1.0465116279069768, |
| "grad_norm": 0.044039350003004074, |
| "learning_rate": 0.00028965517241379314, |
| "loss": 0.9804, |
| "step": 45 |
| }, |
| { |
| "epoch": 1.0465116279069768, |
| "eval_loss": 1.0297547578811646, |
| "eval_runtime": 10.5179, |
| "eval_samples_per_second": 11.124, |
| "eval_steps_per_second": 0.761, |
| "step": 45 |
| }, |
| { |
| "epoch": 1.069767441860465, |
| "grad_norm": 0.04108603671193123, |
| "learning_rate": 0.0002862068965517242, |
| "loss": 0.9993, |
| "step": 46 |
| }, |
| { |
| "epoch": 1.069767441860465, |
| "eval_loss": 1.029006838798523, |
| "eval_runtime": 10.536, |
| "eval_samples_per_second": 11.105, |
| "eval_steps_per_second": 0.759, |
| "step": 46 |
| }, |
| { |
| "epoch": 1.0930232558139534, |
| "grad_norm": 0.04773078113794327, |
| "learning_rate": 0.0002827586206896552, |
| "loss": 0.9748, |
| "step": 47 |
| }, |
| { |
| "epoch": 1.0930232558139534, |
| "eval_loss": 1.028093695640564, |
| "eval_runtime": 10.5568, |
| "eval_samples_per_second": 11.083, |
| "eval_steps_per_second": 0.758, |
| "step": 47 |
| }, |
| { |
| "epoch": 1.1162790697674418, |
| "grad_norm": 0.04372379183769226, |
| "learning_rate": 0.0002793103448275862, |
| "loss": 1.0025, |
| "step": 48 |
| }, |
| { |
| "epoch": 1.1162790697674418, |
| "eval_loss": 1.027159333229065, |
| "eval_runtime": 10.4931, |
| "eval_samples_per_second": 11.15, |
| "eval_steps_per_second": 0.762, |
| "step": 48 |
| }, |
| { |
| "epoch": 1.1395348837209303, |
| "grad_norm": 0.05692731961607933, |
| "learning_rate": 0.00027586206896551725, |
| "loss": 1.0038, |
| "step": 49 |
| }, |
| { |
| "epoch": 1.1395348837209303, |
| "eval_loss": 1.0262141227722168, |
| "eval_runtime": 10.5803, |
| "eval_samples_per_second": 11.058, |
| "eval_steps_per_second": 0.756, |
| "step": 49 |
| }, |
| { |
| "epoch": 1.1627906976744187, |
| "grad_norm": 0.04124248027801514, |
| "learning_rate": 0.00027241379310344825, |
| "loss": 0.9848, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.1627906976744187, |
| "eval_loss": 1.0254372358322144, |
| "eval_runtime": 10.4687, |
| "eval_samples_per_second": 11.176, |
| "eval_steps_per_second": 0.764, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.1860465116279069, |
| "grad_norm": 0.04371722787618637, |
| "learning_rate": 0.0002689655172413793, |
| "loss": 1.0188, |
| "step": 51 |
| }, |
| { |
| "epoch": 1.1860465116279069, |
| "eval_loss": 1.024755597114563, |
| "eval_runtime": 10.5207, |
| "eval_samples_per_second": 11.121, |
| "eval_steps_per_second": 0.76, |
| "step": 51 |
| }, |
| { |
| "epoch": 1.2093023255813953, |
| "grad_norm": 0.04607950523495674, |
| "learning_rate": 0.00026551724137931036, |
| "loss": 1.0058, |
| "step": 52 |
| }, |
| { |
| "epoch": 1.2093023255813953, |
| "eval_loss": 1.0241938829421997, |
| "eval_runtime": 10.5231, |
| "eval_samples_per_second": 11.118, |
| "eval_steps_per_second": 0.76, |
| "step": 52 |
| }, |
| { |
| "epoch": 1.2325581395348837, |
| "grad_norm": 0.05415044724941254, |
| "learning_rate": 0.00026206896551724137, |
| "loss": 0.9923, |
| "step": 53 |
| }, |
| { |
| "epoch": 1.2325581395348837, |
| "eval_loss": 1.0235437154769897, |
| "eval_runtime": 10.6072, |
| "eval_samples_per_second": 11.03, |
| "eval_steps_per_second": 0.754, |
| "step": 53 |
| }, |
| { |
| "epoch": 1.255813953488372, |
| "grad_norm": 0.06359652429819107, |
| "learning_rate": 0.0002586206896551724, |
| "loss": 0.9948, |
| "step": 54 |
| }, |
| { |
| "epoch": 1.255813953488372, |
| "eval_loss": 1.0229169130325317, |
| "eval_runtime": 10.5202, |
| "eval_samples_per_second": 11.122, |
| "eval_steps_per_second": 0.76, |
| "step": 54 |
| }, |
| { |
| "epoch": 1.2790697674418605, |
| "grad_norm": 0.058946821838617325, |
| "learning_rate": 0.0002551724137931035, |
| "loss": 1.0188, |
| "step": 55 |
| }, |
| { |
| "epoch": 1.2790697674418605, |
| "eval_loss": 1.0223369598388672, |
| "eval_runtime": 10.4661, |
| "eval_samples_per_second": 11.179, |
| "eval_steps_per_second": 0.764, |
| "step": 55 |
| }, |
| { |
| "epoch": 1.302325581395349, |
| "grad_norm": 0.05592051148414612, |
| "learning_rate": 0.0002517241379310345, |
| "loss": 0.9933, |
| "step": 56 |
| }, |
| { |
| "epoch": 1.302325581395349, |
| "eval_loss": 1.0219457149505615, |
| "eval_runtime": 10.5373, |
| "eval_samples_per_second": 11.103, |
| "eval_steps_per_second": 0.759, |
| "step": 56 |
| }, |
| { |
| "epoch": 1.3255813953488373, |
| "grad_norm": 0.05216487497091293, |
| "learning_rate": 0.00024827586206896553, |
| "loss": 0.9942, |
| "step": 57 |
| }, |
| { |
| "epoch": 1.3255813953488373, |
| "eval_loss": 1.0214743614196777, |
| "eval_runtime": 10.5663, |
| "eval_samples_per_second": 11.073, |
| "eval_steps_per_second": 0.757, |
| "step": 57 |
| }, |
| { |
| "epoch": 1.3488372093023255, |
| "grad_norm": 0.04820263013243675, |
| "learning_rate": 0.00024482758620689653, |
| "loss": 0.9758, |
| "step": 58 |
| }, |
| { |
| "epoch": 1.3488372093023255, |
| "eval_loss": 1.0210070610046387, |
| "eval_runtime": 10.4802, |
| "eval_samples_per_second": 11.164, |
| "eval_steps_per_second": 0.763, |
| "step": 58 |
| }, |
| { |
| "epoch": 1.372093023255814, |
| "grad_norm": 0.04773212969303131, |
| "learning_rate": 0.0002413793103448276, |
| "loss": 1.0005, |
| "step": 59 |
| }, |
| { |
| "epoch": 1.372093023255814, |
| "eval_loss": 1.0203553438186646, |
| "eval_runtime": 10.5585, |
| "eval_samples_per_second": 11.081, |
| "eval_steps_per_second": 0.758, |
| "step": 59 |
| }, |
| { |
| "epoch": 1.3953488372093024, |
| "grad_norm": 0.05814950540661812, |
| "learning_rate": 0.00023793103448275864, |
| "loss": 0.9629, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.3953488372093024, |
| "eval_loss": 1.0196707248687744, |
| "eval_runtime": 10.4755, |
| "eval_samples_per_second": 11.169, |
| "eval_steps_per_second": 0.764, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.4186046511627908, |
| "grad_norm": 0.052802279591560364, |
| "learning_rate": 0.00023448275862068965, |
| "loss": 0.9707, |
| "step": 61 |
| }, |
| { |
| "epoch": 1.4186046511627908, |
| "eval_loss": 1.0190174579620361, |
| "eval_runtime": 10.5033, |
| "eval_samples_per_second": 11.139, |
| "eval_steps_per_second": 0.762, |
| "step": 61 |
| }, |
| { |
| "epoch": 1.441860465116279, |
| "grad_norm": 0.04725794866681099, |
| "learning_rate": 0.0002310344827586207, |
| "loss": 1.0164, |
| "step": 62 |
| }, |
| { |
| "epoch": 1.441860465116279, |
| "eval_loss": 1.0183162689208984, |
| "eval_runtime": 10.4911, |
| "eval_samples_per_second": 11.152, |
| "eval_steps_per_second": 0.763, |
| "step": 62 |
| }, |
| { |
| "epoch": 1.4651162790697674, |
| "grad_norm": 0.050118036568164825, |
| "learning_rate": 0.00022758620689655176, |
| "loss": 0.9985, |
| "step": 63 |
| }, |
| { |
| "epoch": 1.4651162790697674, |
| "eval_loss": 1.0176469087600708, |
| "eval_runtime": 10.5936, |
| "eval_samples_per_second": 11.044, |
| "eval_steps_per_second": 0.755, |
| "step": 63 |
| }, |
| { |
| "epoch": 1.4883720930232558, |
| "grad_norm": 0.049090269953012466, |
| "learning_rate": 0.00022413793103448276, |
| "loss": 0.9873, |
| "step": 64 |
| }, |
| { |
| "epoch": 1.4883720930232558, |
| "eval_loss": 1.017175555229187, |
| "eval_runtime": 10.5197, |
| "eval_samples_per_second": 11.122, |
| "eval_steps_per_second": 0.76, |
| "step": 64 |
| }, |
| { |
| "epoch": 1.5116279069767442, |
| "grad_norm": 0.050224512815475464, |
| "learning_rate": 0.0002206896551724138, |
| "loss": 0.9896, |
| "step": 65 |
| }, |
| { |
| "epoch": 1.5116279069767442, |
| "eval_loss": 1.0169633626937866, |
| "eval_runtime": 10.5178, |
| "eval_samples_per_second": 11.124, |
| "eval_steps_per_second": 0.761, |
| "step": 65 |
| }, |
| { |
| "epoch": 1.5348837209302326, |
| "grad_norm": 0.0501309297978878, |
| "learning_rate": 0.00021724137931034484, |
| "loss": 0.9798, |
| "step": 66 |
| }, |
| { |
| "epoch": 1.5348837209302326, |
| "eval_loss": 1.0167036056518555, |
| "eval_runtime": 10.5339, |
| "eval_samples_per_second": 11.107, |
| "eval_steps_per_second": 0.759, |
| "step": 66 |
| }, |
| { |
| "epoch": 1.558139534883721, |
| "grad_norm": 0.051808878779411316, |
| "learning_rate": 0.00021379310344827584, |
| "loss": 1.0014, |
| "step": 67 |
| }, |
| { |
| "epoch": 1.558139534883721, |
| "eval_loss": 1.0162760019302368, |
| "eval_runtime": 10.5275, |
| "eval_samples_per_second": 11.114, |
| "eval_steps_per_second": 0.76, |
| "step": 67 |
| }, |
| { |
| "epoch": 1.5813953488372094, |
| "grad_norm": 0.0500907227396965, |
| "learning_rate": 0.0002103448275862069, |
| "loss": 0.9933, |
| "step": 68 |
| }, |
| { |
| "epoch": 1.5813953488372094, |
| "eval_loss": 1.0156968832015991, |
| "eval_runtime": 10.5784, |
| "eval_samples_per_second": 11.06, |
| "eval_steps_per_second": 0.756, |
| "step": 68 |
| }, |
| { |
| "epoch": 1.6046511627906976, |
| "grad_norm": 0.04874541610479355, |
| "learning_rate": 0.00020689655172413795, |
| "loss": 0.9668, |
| "step": 69 |
| }, |
| { |
| "epoch": 1.6046511627906976, |
| "eval_loss": 1.0152900218963623, |
| "eval_runtime": 10.5885, |
| "eval_samples_per_second": 11.05, |
| "eval_steps_per_second": 0.756, |
| "step": 69 |
| }, |
| { |
| "epoch": 1.627906976744186, |
| "grad_norm": 0.05222810059785843, |
| "learning_rate": 0.00020344827586206895, |
| "loss": 0.9792, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.627906976744186, |
| "eval_loss": 1.0148221254348755, |
| "eval_runtime": 10.4824, |
| "eval_samples_per_second": 11.162, |
| "eval_steps_per_second": 0.763, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.6511627906976745, |
| "grad_norm": 0.05117630958557129, |
| "learning_rate": 0.0002, |
| "loss": 0.9519, |
| "step": 71 |
| }, |
| { |
| "epoch": 1.6511627906976745, |
| "eval_loss": 1.0145394802093506, |
| "eval_runtime": 10.46, |
| "eval_samples_per_second": 11.185, |
| "eval_steps_per_second": 0.765, |
| "step": 71 |
| }, |
| { |
| "epoch": 1.6744186046511627, |
| "grad_norm": 0.04879862442612648, |
| "learning_rate": 0.00019655172413793104, |
| "loss": 0.9833, |
| "step": 72 |
| }, |
| { |
| "epoch": 1.6744186046511627, |
| "eval_loss": 1.01435124874115, |
| "eval_runtime": 10.6034, |
| "eval_samples_per_second": 11.034, |
| "eval_steps_per_second": 0.754, |
| "step": 72 |
| }, |
| { |
| "epoch": 1.697674418604651, |
| "grad_norm": 0.055211760103702545, |
| "learning_rate": 0.0001931034482758621, |
| "loss": 0.9782, |
| "step": 73 |
| }, |
| { |
| "epoch": 1.697674418604651, |
| "eval_loss": 1.014180064201355, |
| "eval_runtime": 10.5781, |
| "eval_samples_per_second": 11.061, |
| "eval_steps_per_second": 0.756, |
| "step": 73 |
| }, |
| { |
| "epoch": 1.7209302325581395, |
| "grad_norm": 0.05374753847718239, |
| "learning_rate": 0.00018965517241379312, |
| "loss": 0.9824, |
| "step": 74 |
| }, |
| { |
| "epoch": 1.7209302325581395, |
| "eval_loss": 1.0137970447540283, |
| "eval_runtime": 10.5389, |
| "eval_samples_per_second": 11.102, |
| "eval_steps_per_second": 0.759, |
| "step": 74 |
| }, |
| { |
| "epoch": 1.744186046511628, |
| "grad_norm": 0.053574249148368835, |
| "learning_rate": 0.00018620689655172415, |
| "loss": 0.9748, |
| "step": 75 |
| }, |
| { |
| "epoch": 1.744186046511628, |
| "eval_loss": 1.013289213180542, |
| "eval_runtime": 10.5759, |
| "eval_samples_per_second": 11.063, |
| "eval_steps_per_second": 0.756, |
| "step": 75 |
| }, |
| { |
| "epoch": 1.7674418604651163, |
| "grad_norm": 0.05111626163125038, |
| "learning_rate": 0.00018275862068965518, |
| "loss": 0.9842, |
| "step": 76 |
| }, |
| { |
| "epoch": 1.7674418604651163, |
| "eval_loss": 1.0127779245376587, |
| "eval_runtime": 10.5155, |
| "eval_samples_per_second": 11.126, |
| "eval_steps_per_second": 0.761, |
| "step": 76 |
| }, |
| { |
| "epoch": 1.7906976744186047, |
| "grad_norm": 0.05558936670422554, |
| "learning_rate": 0.0001793103448275862, |
| "loss": 0.9905, |
| "step": 77 |
| }, |
| { |
| "epoch": 1.7906976744186047, |
| "eval_loss": 1.0122755765914917, |
| "eval_runtime": 10.4815, |
| "eval_samples_per_second": 11.162, |
| "eval_steps_per_second": 0.763, |
| "step": 77 |
| }, |
| { |
| "epoch": 1.8139534883720931, |
| "grad_norm": 0.053616516292095184, |
| "learning_rate": 0.00017586206896551723, |
| "loss": 0.9615, |
| "step": 78 |
| }, |
| { |
| "epoch": 1.8139534883720931, |
| "eval_loss": 1.011860728263855, |
| "eval_runtime": 10.5398, |
| "eval_samples_per_second": 11.101, |
| "eval_steps_per_second": 0.759, |
| "step": 78 |
| }, |
| { |
| "epoch": 1.8372093023255816, |
| "grad_norm": 0.05707163363695145, |
| "learning_rate": 0.00017241379310344826, |
| "loss": 0.9583, |
| "step": 79 |
| }, |
| { |
| "epoch": 1.8372093023255816, |
| "eval_loss": 1.0115560293197632, |
| "eval_runtime": 10.5278, |
| "eval_samples_per_second": 11.113, |
| "eval_steps_per_second": 0.76, |
| "step": 79 |
| }, |
| { |
| "epoch": 1.8604651162790697, |
| "grad_norm": 0.05251218378543854, |
| "learning_rate": 0.00016896551724137932, |
| "loss": 1.0081, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.8604651162790697, |
| "eval_loss": 1.01112699508667, |
| "eval_runtime": 10.5774, |
| "eval_samples_per_second": 11.061, |
| "eval_steps_per_second": 0.756, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.8837209302325582, |
| "grad_norm": 0.05201508849859238, |
| "learning_rate": 0.00016551724137931035, |
| "loss": 0.9725, |
| "step": 81 |
| }, |
| { |
| "epoch": 1.8837209302325582, |
| "eval_loss": 1.0107312202453613, |
| "eval_runtime": 10.5289, |
| "eval_samples_per_second": 11.112, |
| "eval_steps_per_second": 0.76, |
| "step": 81 |
| }, |
| { |
| "epoch": 1.9069767441860463, |
| "grad_norm": 0.05595965310931206, |
| "learning_rate": 0.00016206896551724137, |
| "loss": 0.9979, |
| "step": 82 |
| }, |
| { |
| "epoch": 1.9069767441860463, |
| "eval_loss": 1.0103439092636108, |
| "eval_runtime": 10.463, |
| "eval_samples_per_second": 11.182, |
| "eval_steps_per_second": 0.765, |
| "step": 82 |
| }, |
| { |
| "epoch": 1.9302325581395348, |
| "grad_norm": 0.05475016310811043, |
| "learning_rate": 0.00015862068965517243, |
| "loss": 0.9965, |
| "step": 83 |
| }, |
| { |
| "epoch": 1.9302325581395348, |
| "eval_loss": 1.0099685192108154, |
| "eval_runtime": 10.5842, |
| "eval_samples_per_second": 11.054, |
| "eval_steps_per_second": 0.756, |
| "step": 83 |
| }, |
| { |
| "epoch": 1.9534883720930232, |
| "grad_norm": 0.05614636465907097, |
| "learning_rate": 0.00015517241379310346, |
| "loss": 0.9761, |
| "step": 84 |
| }, |
| { |
| "epoch": 1.9534883720930232, |
| "eval_loss": 1.009726643562317, |
| "eval_runtime": 10.5108, |
| "eval_samples_per_second": 11.131, |
| "eval_steps_per_second": 0.761, |
| "step": 84 |
| }, |
| { |
| "epoch": 1.9767441860465116, |
| "grad_norm": 0.05425894260406494, |
| "learning_rate": 0.00015172413793103449, |
| "loss": 0.9665, |
| "step": 85 |
| }, |
| { |
| "epoch": 1.9767441860465116, |
| "eval_loss": 1.0094804763793945, |
| "eval_runtime": 10.5158, |
| "eval_samples_per_second": 11.126, |
| "eval_steps_per_second": 0.761, |
| "step": 85 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.08465206623077393, |
| "learning_rate": 0.00014827586206896554, |
| "loss": 0.9676, |
| "step": 86 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 1.0091900825500488, |
| "eval_runtime": 10.4594, |
| "eval_samples_per_second": 11.186, |
| "eval_steps_per_second": 0.765, |
| "step": 86 |
| }, |
| { |
| "epoch": 2.0232558139534884, |
| "grad_norm": 0.05495611950755119, |
| "learning_rate": 0.00014482758620689657, |
| "loss": 0.9548, |
| "step": 87 |
| }, |
| { |
| "epoch": 2.0232558139534884, |
| "eval_loss": 1.0090184211730957, |
| "eval_runtime": 10.5403, |
| "eval_samples_per_second": 11.1, |
| "eval_steps_per_second": 0.759, |
| "step": 87 |
| }, |
| { |
| "epoch": 2.046511627906977, |
| "grad_norm": 0.051615942269563675, |
| "learning_rate": 0.0001413793103448276, |
| "loss": 0.9413, |
| "step": 88 |
| }, |
| { |
| "epoch": 2.046511627906977, |
| "eval_loss": 1.0091454982757568, |
| "eval_runtime": 10.5362, |
| "eval_samples_per_second": 11.105, |
| "eval_steps_per_second": 0.759, |
| "step": 88 |
| }, |
| { |
| "epoch": 2.0697674418604652, |
| "grad_norm": 0.06363032013177872, |
| "learning_rate": 0.00013793103448275863, |
| "loss": 0.9604, |
| "step": 89 |
| }, |
| { |
| "epoch": 2.0697674418604652, |
| "eval_loss": 1.0093193054199219, |
| "eval_runtime": 10.599, |
| "eval_samples_per_second": 11.039, |
| "eval_steps_per_second": 0.755, |
| "step": 89 |
| }, |
| { |
| "epoch": 2.0930232558139537, |
| "grad_norm": 0.05618719756603241, |
| "learning_rate": 0.00013448275862068965, |
| "loss": 0.9627, |
| "step": 90 |
| }, |
| { |
| "epoch": 2.0930232558139537, |
| "eval_loss": 1.0094503164291382, |
| "eval_runtime": 10.5453, |
| "eval_samples_per_second": 11.095, |
| "eval_steps_per_second": 0.759, |
| "step": 90 |
| }, |
| { |
| "epoch": 2.116279069767442, |
| "grad_norm": 0.061273831874132156, |
| "learning_rate": 0.00013103448275862068, |
| "loss": 0.9428, |
| "step": 91 |
| }, |
| { |
| "epoch": 2.116279069767442, |
| "eval_loss": 1.0095981359481812, |
| "eval_runtime": 10.5143, |
| "eval_samples_per_second": 11.128, |
| "eval_steps_per_second": 0.761, |
| "step": 91 |
| }, |
| { |
| "epoch": 2.13953488372093, |
| "grad_norm": 0.05564780905842781, |
| "learning_rate": 0.00012758620689655174, |
| "loss": 0.9774, |
| "step": 92 |
| }, |
| { |
| "epoch": 2.13953488372093, |
| "eval_loss": 1.009597897529602, |
| "eval_runtime": 10.4849, |
| "eval_samples_per_second": 11.159, |
| "eval_steps_per_second": 0.763, |
| "step": 92 |
| }, |
| { |
| "epoch": 2.1627906976744184, |
| "grad_norm": 0.05518029257655144, |
| "learning_rate": 0.00012413793103448277, |
| "loss": 0.9407, |
| "step": 93 |
| }, |
| { |
| "epoch": 2.1627906976744184, |
| "eval_loss": 1.0096217393875122, |
| "eval_runtime": 10.6044, |
| "eval_samples_per_second": 11.033, |
| "eval_steps_per_second": 0.754, |
| "step": 93 |
| }, |
| { |
| "epoch": 2.186046511627907, |
| "grad_norm": 0.05853220447897911, |
| "learning_rate": 0.0001206896551724138, |
| "loss": 0.9396, |
| "step": 94 |
| }, |
| { |
| "epoch": 2.186046511627907, |
| "eval_loss": 1.00962233543396, |
| "eval_runtime": 10.5343, |
| "eval_samples_per_second": 11.107, |
| "eval_steps_per_second": 0.759, |
| "step": 94 |
| }, |
| { |
| "epoch": 2.2093023255813953, |
| "grad_norm": 0.06098194420337677, |
| "learning_rate": 0.00011724137931034482, |
| "loss": 0.9705, |
| "step": 95 |
| }, |
| { |
| "epoch": 2.2093023255813953, |
| "eval_loss": 1.0093858242034912, |
| "eval_runtime": 10.4224, |
| "eval_samples_per_second": 11.226, |
| "eval_steps_per_second": 0.768, |
| "step": 95 |
| }, |
| { |
| "epoch": 2.2325581395348837, |
| "grad_norm": 0.05779768154025078, |
| "learning_rate": 0.00011379310344827588, |
| "loss": 0.9427, |
| "step": 96 |
| }, |
| { |
| "epoch": 2.2325581395348837, |
| "eval_loss": 1.0092523097991943, |
| "eval_runtime": 10.6138, |
| "eval_samples_per_second": 11.023, |
| "eval_steps_per_second": 0.754, |
| "step": 96 |
| }, |
| { |
| "epoch": 2.255813953488372, |
| "grad_norm": 0.059211816638708115, |
| "learning_rate": 0.0001103448275862069, |
| "loss": 0.9689, |
| "step": 97 |
| }, |
| { |
| "epoch": 2.255813953488372, |
| "eval_loss": 1.0091252326965332, |
| "eval_runtime": 10.504, |
| "eval_samples_per_second": 11.139, |
| "eval_steps_per_second": 0.762, |
| "step": 97 |
| }, |
| { |
| "epoch": 2.2790697674418605, |
| "grad_norm": 0.058523572981357574, |
| "learning_rate": 0.00010689655172413792, |
| "loss": 0.9459, |
| "step": 98 |
| }, |
| { |
| "epoch": 2.2790697674418605, |
| "eval_loss": 1.0091090202331543, |
| "eval_runtime": 10.5529, |
| "eval_samples_per_second": 11.087, |
| "eval_steps_per_second": 0.758, |
| "step": 98 |
| }, |
| { |
| "epoch": 2.302325581395349, |
| "grad_norm": 0.06452349573373795, |
| "learning_rate": 0.00010344827586206898, |
| "loss": 0.9434, |
| "step": 99 |
| }, |
| { |
| "epoch": 2.302325581395349, |
| "eval_loss": 1.0091310739517212, |
| "eval_runtime": 10.5481, |
| "eval_samples_per_second": 11.092, |
| "eval_steps_per_second": 0.758, |
| "step": 99 |
| }, |
| { |
| "epoch": 2.3255813953488373, |
| "grad_norm": 0.06188109889626503, |
| "learning_rate": 0.0001, |
| "loss": 0.9453, |
| "step": 100 |
| }, |
| { |
| "epoch": 2.3255813953488373, |
| "eval_loss": 1.0090867280960083, |
| "eval_runtime": 10.5427, |
| "eval_samples_per_second": 11.098, |
| "eval_steps_per_second": 0.759, |
| "step": 100 |
| }, |
| { |
| "epoch": 2.3488372093023258, |
| "grad_norm": 0.061615802347660065, |
| "learning_rate": 9.655172413793105e-05, |
| "loss": 0.9675, |
| "step": 101 |
| }, |
| { |
| "epoch": 2.3488372093023258, |
| "eval_loss": 1.008958101272583, |
| "eval_runtime": 10.62, |
| "eval_samples_per_second": 11.017, |
| "eval_steps_per_second": 0.753, |
| "step": 101 |
| }, |
| { |
| "epoch": 2.3720930232558137, |
| "grad_norm": 0.06509216129779816, |
| "learning_rate": 9.310344827586207e-05, |
| "loss": 0.9571, |
| "step": 102 |
| }, |
| { |
| "epoch": 2.3720930232558137, |
| "eval_loss": 1.008782982826233, |
| "eval_runtime": 10.5067, |
| "eval_samples_per_second": 11.136, |
| "eval_steps_per_second": 0.761, |
| "step": 102 |
| }, |
| { |
| "epoch": 2.395348837209302, |
| "grad_norm": 0.07000201940536499, |
| "learning_rate": 8.96551724137931e-05, |
| "loss": 0.9669, |
| "step": 103 |
| }, |
| { |
| "epoch": 2.395348837209302, |
| "eval_loss": 1.0085687637329102, |
| "eval_runtime": 10.5369, |
| "eval_samples_per_second": 11.104, |
| "eval_steps_per_second": 0.759, |
| "step": 103 |
| }, |
| { |
| "epoch": 2.4186046511627906, |
| "grad_norm": 0.06144480034708977, |
| "learning_rate": 8.620689655172413e-05, |
| "loss": 0.9592, |
| "step": 104 |
| }, |
| { |
| "epoch": 2.4186046511627906, |
| "eval_loss": 1.0085170269012451, |
| "eval_runtime": 10.5319, |
| "eval_samples_per_second": 11.109, |
| "eval_steps_per_second": 0.76, |
| "step": 104 |
| }, |
| { |
| "epoch": 2.441860465116279, |
| "grad_norm": 0.06189959496259689, |
| "learning_rate": 8.275862068965517e-05, |
| "loss": 0.9259, |
| "step": 105 |
| }, |
| { |
| "epoch": 2.441860465116279, |
| "eval_loss": 1.0085593461990356, |
| "eval_runtime": 10.501, |
| "eval_samples_per_second": 11.142, |
| "eval_steps_per_second": 0.762, |
| "step": 105 |
| }, |
| { |
| "epoch": 2.4651162790697674, |
| "grad_norm": 0.06781314313411713, |
| "learning_rate": 7.931034482758621e-05, |
| "loss": 0.945, |
| "step": 106 |
| }, |
| { |
| "epoch": 2.4651162790697674, |
| "eval_loss": 1.0086591243743896, |
| "eval_runtime": 10.536, |
| "eval_samples_per_second": 11.105, |
| "eval_steps_per_second": 0.759, |
| "step": 106 |
| }, |
| { |
| "epoch": 2.488372093023256, |
| "grad_norm": 0.06491964310407639, |
| "learning_rate": 7.586206896551724e-05, |
| "loss": 0.948, |
| "step": 107 |
| }, |
| { |
| "epoch": 2.488372093023256, |
| "eval_loss": 1.0086618661880493, |
| "eval_runtime": 10.5398, |
| "eval_samples_per_second": 11.101, |
| "eval_steps_per_second": 0.759, |
| "step": 107 |
| }, |
| { |
| "epoch": 2.511627906976744, |
| "grad_norm": 0.13770791888237, |
| "learning_rate": 7.241379310344828e-05, |
| "loss": 0.9631, |
| "step": 108 |
| }, |
| { |
| "epoch": 2.511627906976744, |
| "eval_loss": 1.008668303489685, |
| "eval_runtime": 10.4916, |
| "eval_samples_per_second": 11.152, |
| "eval_steps_per_second": 0.763, |
| "step": 108 |
| }, |
| { |
| "epoch": 2.5348837209302326, |
| "grad_norm": 0.06982796639204025, |
| "learning_rate": 6.896551724137931e-05, |
| "loss": 0.9315, |
| "step": 109 |
| }, |
| { |
| "epoch": 2.5348837209302326, |
| "eval_loss": 1.008758783340454, |
| "eval_runtime": 10.4002, |
| "eval_samples_per_second": 11.25, |
| "eval_steps_per_second": 0.769, |
| "step": 109 |
| }, |
| { |
| "epoch": 2.558139534883721, |
| "grad_norm": 0.06349999457597733, |
| "learning_rate": 6.551724137931034e-05, |
| "loss": 0.9433, |
| "step": 110 |
| }, |
| { |
| "epoch": 2.558139534883721, |
| "eval_loss": 1.0088914632797241, |
| "eval_runtime": 10.5022, |
| "eval_samples_per_second": 11.141, |
| "eval_steps_per_second": 0.762, |
| "step": 110 |
| }, |
| { |
| "epoch": 2.5813953488372094, |
| "grad_norm": 0.06294334679841995, |
| "learning_rate": 6.206896551724138e-05, |
| "loss": 0.9484, |
| "step": 111 |
| }, |
| { |
| "epoch": 2.5813953488372094, |
| "eval_loss": 1.0089675188064575, |
| "eval_runtime": 10.4932, |
| "eval_samples_per_second": 11.15, |
| "eval_steps_per_second": 0.762, |
| "step": 111 |
| }, |
| { |
| "epoch": 2.604651162790698, |
| "grad_norm": 0.06499718874692917, |
| "learning_rate": 5.862068965517241e-05, |
| "loss": 0.9519, |
| "step": 112 |
| }, |
| { |
| "epoch": 2.604651162790698, |
| "eval_loss": 1.0090423822402954, |
| "eval_runtime": 10.5478, |
| "eval_samples_per_second": 11.092, |
| "eval_steps_per_second": 0.758, |
| "step": 112 |
| }, |
| { |
| "epoch": 2.6279069767441863, |
| "grad_norm": 0.06928952783346176, |
| "learning_rate": 5.517241379310345e-05, |
| "loss": 0.9551, |
| "step": 113 |
| }, |
| { |
| "epoch": 2.6279069767441863, |
| "eval_loss": 1.008984923362732, |
| "eval_runtime": 10.493, |
| "eval_samples_per_second": 11.15, |
| "eval_steps_per_second": 0.762, |
| "step": 113 |
| }, |
| { |
| "epoch": 2.6511627906976747, |
| "grad_norm": 0.06725452095270157, |
| "learning_rate": 5.172413793103449e-05, |
| "loss": 0.9404, |
| "step": 114 |
| }, |
| { |
| "epoch": 2.6511627906976747, |
| "eval_loss": 1.0089396238327026, |
| "eval_runtime": 10.479, |
| "eval_samples_per_second": 11.165, |
| "eval_steps_per_second": 0.763, |
| "step": 114 |
| }, |
| { |
| "epoch": 2.6744186046511627, |
| "grad_norm": 0.06509212404489517, |
| "learning_rate": 4.827586206896552e-05, |
| "loss": 0.9377, |
| "step": 115 |
| }, |
| { |
| "epoch": 2.6744186046511627, |
| "eval_loss": 1.0088380575180054, |
| "eval_runtime": 10.4542, |
| "eval_samples_per_second": 11.192, |
| "eval_steps_per_second": 0.765, |
| "step": 115 |
| }, |
| { |
| "epoch": 2.697674418604651, |
| "grad_norm": 0.06430088728666306, |
| "learning_rate": 4.482758620689655e-05, |
| "loss": 0.9447, |
| "step": 116 |
| }, |
| { |
| "epoch": 2.697674418604651, |
| "eval_loss": 1.008760929107666, |
| "eval_runtime": 10.529, |
| "eval_samples_per_second": 11.112, |
| "eval_steps_per_second": 0.76, |
| "step": 116 |
| }, |
| { |
| "epoch": 2.7209302325581395, |
| "grad_norm": 0.07184050977230072, |
| "learning_rate": 4.1379310344827587e-05, |
| "loss": 0.9608, |
| "step": 117 |
| }, |
| { |
| "epoch": 2.7209302325581395, |
| "eval_loss": 1.0085643529891968, |
| "eval_runtime": 10.5269, |
| "eval_samples_per_second": 11.114, |
| "eval_steps_per_second": 0.76, |
| "step": 117 |
| }, |
| { |
| "epoch": 2.744186046511628, |
| "grad_norm": 0.06626931577920914, |
| "learning_rate": 3.793103448275862e-05, |
| "loss": 0.9459, |
| "step": 118 |
| }, |
| { |
| "epoch": 2.744186046511628, |
| "eval_loss": 1.008436918258667, |
| "eval_runtime": 10.526, |
| "eval_samples_per_second": 11.115, |
| "eval_steps_per_second": 0.76, |
| "step": 118 |
| }, |
| { |
| "epoch": 2.7674418604651163, |
| "grad_norm": 0.07003094255924225, |
| "learning_rate": 3.4482758620689657e-05, |
| "loss": 0.9601, |
| "step": 119 |
| }, |
| { |
| "epoch": 2.7674418604651163, |
| "eval_loss": 1.0083117485046387, |
| "eval_runtime": 10.6067, |
| "eval_samples_per_second": 11.031, |
| "eval_steps_per_second": 0.754, |
| "step": 119 |
| }, |
| { |
| "epoch": 2.7906976744186047, |
| "grad_norm": 0.06969019770622253, |
| "learning_rate": 3.103448275862069e-05, |
| "loss": 0.9154, |
| "step": 120 |
| }, |
| { |
| "epoch": 2.7906976744186047, |
| "eval_loss": 1.0082221031188965, |
| "eval_runtime": 10.5347, |
| "eval_samples_per_second": 11.106, |
| "eval_steps_per_second": 0.759, |
| "step": 120 |
| }, |
| { |
| "epoch": 2.813953488372093, |
| "grad_norm": 0.06678508222103119, |
| "learning_rate": 2.7586206896551727e-05, |
| "loss": 0.964, |
| "step": 121 |
| }, |
| { |
| "epoch": 2.813953488372093, |
| "eval_loss": 1.00809907913208, |
| "eval_runtime": 10.5791, |
| "eval_samples_per_second": 11.06, |
| "eval_steps_per_second": 0.756, |
| "step": 121 |
| }, |
| { |
| "epoch": 2.8372093023255816, |
| "grad_norm": 0.06645270437002182, |
| "learning_rate": 2.413793103448276e-05, |
| "loss": 0.9593, |
| "step": 122 |
| }, |
| { |
| "epoch": 2.8372093023255816, |
| "eval_loss": 1.0079501867294312, |
| "eval_runtime": 10.5303, |
| "eval_samples_per_second": 11.111, |
| "eval_steps_per_second": 0.76, |
| "step": 122 |
| }, |
| { |
| "epoch": 2.8604651162790695, |
| "grad_norm": 0.06668780744075775, |
| "learning_rate": 2.0689655172413793e-05, |
| "loss": 0.9513, |
| "step": 123 |
| }, |
| { |
| "epoch": 2.8604651162790695, |
| "eval_loss": 1.0078498125076294, |
| "eval_runtime": 10.537, |
| "eval_samples_per_second": 11.104, |
| "eval_steps_per_second": 0.759, |
| "step": 123 |
| }, |
| { |
| "epoch": 2.883720930232558, |
| "grad_norm": 0.07333076000213623, |
| "learning_rate": 1.7241379310344828e-05, |
| "loss": 0.9319, |
| "step": 124 |
| }, |
| { |
| "epoch": 2.883720930232558, |
| "eval_loss": 1.0077686309814453, |
| "eval_runtime": 10.5258, |
| "eval_samples_per_second": 11.116, |
| "eval_steps_per_second": 0.76, |
| "step": 124 |
| }, |
| { |
| "epoch": 2.9069767441860463, |
| "grad_norm": 0.0677880272269249, |
| "learning_rate": 1.3793103448275863e-05, |
| "loss": 0.9456, |
| "step": 125 |
| }, |
| { |
| "epoch": 2.9069767441860463, |
| "eval_loss": 1.0076959133148193, |
| "eval_runtime": 10.5226, |
| "eval_samples_per_second": 11.119, |
| "eval_steps_per_second": 0.76, |
| "step": 125 |
| }, |
| { |
| "epoch": 2.9302325581395348, |
| "grad_norm": 0.06794837862253189, |
| "learning_rate": 1.0344827586206897e-05, |
| "loss": 0.9446, |
| "step": 126 |
| }, |
| { |
| "epoch": 2.9302325581395348, |
| "eval_loss": 1.0076078176498413, |
| "eval_runtime": 10.5921, |
| "eval_samples_per_second": 11.046, |
| "eval_steps_per_second": 0.755, |
| "step": 126 |
| }, |
| { |
| "epoch": 2.953488372093023, |
| "grad_norm": 0.0673353523015976, |
| "learning_rate": 6.896551724137932e-06, |
| "loss": 0.9215, |
| "step": 127 |
| }, |
| { |
| "epoch": 2.953488372093023, |
| "eval_loss": 1.007556676864624, |
| "eval_runtime": 10.5629, |
| "eval_samples_per_second": 11.077, |
| "eval_steps_per_second": 0.757, |
| "step": 127 |
| }, |
| { |
| "epoch": 2.9767441860465116, |
| "grad_norm": 0.06916272640228271, |
| "learning_rate": 3.448275862068966e-06, |
| "loss": 0.9492, |
| "step": 128 |
| }, |
| { |
| "epoch": 2.9767441860465116, |
| "eval_loss": 1.007544755935669, |
| "eval_runtime": 10.5461, |
| "eval_samples_per_second": 11.094, |
| "eval_steps_per_second": 0.759, |
| "step": 128 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.10813567787408829, |
| "learning_rate": 0.0, |
| "loss": 0.962, |
| "step": 129 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 1.0075572729110718, |
| "eval_runtime": 10.4988, |
| "eval_samples_per_second": 11.144, |
| "eval_steps_per_second": 0.762, |
| "step": 129 |
| }, |
| { |
| "epoch": 3.0, |
| "step": 129, |
| "total_flos": 4.714967128552243e+16, |
| "train_loss": 1.1705420798109483, |
| "train_runtime": 2551.3345, |
| "train_samples_per_second": 1.594, |
| "train_steps_per_second": 0.051 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 129, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 10, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 4.714967128552243e+16, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
