| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 4.0, |
| "eval_steps": 10, |
| "global_step": 1300, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.006153846153846154, |
| "eval_loss": 1.845949411392212, |
| "eval_runtime": 1.9761, |
| "eval_samples_per_second": 57.69, |
| "eval_steps_per_second": 3.036, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.03076923076923077, |
| "grad_norm": 29.46457290649414, |
| "learning_rate": 7.692307692307694e-07, |
| "loss": 1.944, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.03076923076923077, |
| "eval_loss": 1.7965577840805054, |
| "eval_runtime": 1.9506, |
| "eval_samples_per_second": 58.444, |
| "eval_steps_per_second": 3.076, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.06153846153846154, |
| "grad_norm": 14.49207878112793, |
| "learning_rate": 1.5384615384615387e-06, |
| "loss": 1.6999, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.06153846153846154, |
| "eval_loss": 1.5032916069030762, |
| "eval_runtime": 1.9599, |
| "eval_samples_per_second": 58.168, |
| "eval_steps_per_second": 3.061, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.09230769230769231, |
| "grad_norm": 11.355466842651367, |
| "learning_rate": 2.307692307692308e-06, |
| "loss": 1.1499, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.09230769230769231, |
| "eval_loss": 0.8391174674034119, |
| "eval_runtime": 1.9437, |
| "eval_samples_per_second": 58.65, |
| "eval_steps_per_second": 3.087, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.12307692307692308, |
| "grad_norm": 5.648468017578125, |
| "learning_rate": 3.0769230769230774e-06, |
| "loss": 0.7194, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.12307692307692308, |
| "eval_loss": 0.6716201305389404, |
| "eval_runtime": 1.9517, |
| "eval_samples_per_second": 58.411, |
| "eval_steps_per_second": 3.074, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.15384615384615385, |
| "grad_norm": 5.752841949462891, |
| "learning_rate": 3.846153846153847e-06, |
| "loss": 0.6811, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.15384615384615385, |
| "eval_loss": 0.6289324164390564, |
| "eval_runtime": 1.952, |
| "eval_samples_per_second": 58.401, |
| "eval_steps_per_second": 3.074, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.18461538461538463, |
| "grad_norm": 3.414722204208374, |
| "learning_rate": 4.615384615384616e-06, |
| "loss": 0.5924, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.18461538461538463, |
| "eval_loss": 0.6140013337135315, |
| "eval_runtime": 1.94, |
| "eval_samples_per_second": 58.762, |
| "eval_steps_per_second": 3.093, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.2153846153846154, |
| "grad_norm": 5.556036949157715, |
| "learning_rate": 5.384615384615385e-06, |
| "loss": 0.6135, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.2153846153846154, |
| "eval_loss": 0.6054026484489441, |
| "eval_runtime": 1.9659, |
| "eval_samples_per_second": 57.988, |
| "eval_steps_per_second": 3.052, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.24615384615384617, |
| "grad_norm": 4.436710834503174, |
| "learning_rate": 6.153846153846155e-06, |
| "loss": 0.5952, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.24615384615384617, |
| "eval_loss": 0.5986860990524292, |
| "eval_runtime": 1.9428, |
| "eval_samples_per_second": 58.677, |
| "eval_steps_per_second": 3.088, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.27692307692307694, |
| "grad_norm": 3.496018409729004, |
| "learning_rate": 6.923076923076923e-06, |
| "loss": 0.5887, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.27692307692307694, |
| "eval_loss": 0.594973623752594, |
| "eval_runtime": 1.9468, |
| "eval_samples_per_second": 58.558, |
| "eval_steps_per_second": 3.082, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.3076923076923077, |
| "grad_norm": 2.3540539741516113, |
| "learning_rate": 7.692307692307694e-06, |
| "loss": 0.5634, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.3076923076923077, |
| "eval_loss": 0.5954164266586304, |
| "eval_runtime": 1.948, |
| "eval_samples_per_second": 58.521, |
| "eval_steps_per_second": 3.08, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.3384615384615385, |
| "grad_norm": 2.9880635738372803, |
| "learning_rate": 8.461538461538462e-06, |
| "loss": 0.5827, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.3384615384615385, |
| "eval_loss": 0.5955133438110352, |
| "eval_runtime": 1.9432, |
| "eval_samples_per_second": 58.667, |
| "eval_steps_per_second": 3.088, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.36923076923076925, |
| "grad_norm": 1.9405996799468994, |
| "learning_rate": 9.230769230769232e-06, |
| "loss": 0.5726, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.36923076923076925, |
| "eval_loss": 0.5951128602027893, |
| "eval_runtime": 1.9715, |
| "eval_samples_per_second": 57.824, |
| "eval_steps_per_second": 3.043, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 1.9948021173477173, |
| "learning_rate": 1e-05, |
| "loss": 0.6488, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.4, |
| "eval_loss": 0.5964463949203491, |
| "eval_runtime": 2.1032, |
| "eval_samples_per_second": 54.203, |
| "eval_steps_per_second": 2.853, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.4307692307692308, |
| "grad_norm": 1.95350980758667, |
| "learning_rate": 1.076923076923077e-05, |
| "loss": 0.6218, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.4307692307692308, |
| "eval_loss": 0.5996471047401428, |
| "eval_runtime": 1.9539, |
| "eval_samples_per_second": 58.345, |
| "eval_steps_per_second": 3.071, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.46153846153846156, |
| "grad_norm": 3.840015411376953, |
| "learning_rate": 1.1538461538461538e-05, |
| "loss": 0.5585, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.46153846153846156, |
| "eval_loss": 0.6000372767448425, |
| "eval_runtime": 1.9457, |
| "eval_samples_per_second": 58.592, |
| "eval_steps_per_second": 3.084, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.49230769230769234, |
| "grad_norm": 2.345364809036255, |
| "learning_rate": 1.230769230769231e-05, |
| "loss": 0.5314, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.49230769230769234, |
| "eval_loss": 0.6025042533874512, |
| "eval_runtime": 1.9398, |
| "eval_samples_per_second": 58.768, |
| "eval_steps_per_second": 3.093, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.5230769230769231, |
| "grad_norm": 3.162071704864502, |
| "learning_rate": 1.3076923076923078e-05, |
| "loss": 0.6901, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.5230769230769231, |
| "eval_loss": 0.598171055316925, |
| "eval_runtime": 1.9419, |
| "eval_samples_per_second": 58.705, |
| "eval_steps_per_second": 3.09, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.5538461538461539, |
| "grad_norm": 3.9432108402252197, |
| "learning_rate": 1.3846153846153847e-05, |
| "loss": 0.6604, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.5538461538461539, |
| "eval_loss": 0.5974885821342468, |
| "eval_runtime": 1.9664, |
| "eval_samples_per_second": 57.975, |
| "eval_steps_per_second": 3.051, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.5846153846153846, |
| "grad_norm": 1.904718279838562, |
| "learning_rate": 1.4615384615384615e-05, |
| "loss": 0.5806, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.5846153846153846, |
| "eval_loss": 0.6012160778045654, |
| "eval_runtime": 2.082, |
| "eval_samples_per_second": 54.755, |
| "eval_steps_per_second": 2.882, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.6153846153846154, |
| "grad_norm": 2.2823173999786377, |
| "learning_rate": 1.5384615384615387e-05, |
| "loss": 0.588, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.6153846153846154, |
| "eval_loss": 0.6052933931350708, |
| "eval_runtime": 1.9613, |
| "eval_samples_per_second": 58.124, |
| "eval_steps_per_second": 3.059, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.6461538461538462, |
| "grad_norm": 1.8020161390304565, |
| "learning_rate": 1.6153846153846154e-05, |
| "loss": 0.5826, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.6461538461538462, |
| "eval_loss": 0.6047356724739075, |
| "eval_runtime": 1.9487, |
| "eval_samples_per_second": 58.5, |
| "eval_steps_per_second": 3.079, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.676923076923077, |
| "grad_norm": 1.8297995328903198, |
| "learning_rate": 1.6923076923076924e-05, |
| "loss": 0.5442, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.676923076923077, |
| "eval_loss": 0.6105689406394958, |
| "eval_runtime": 2.0567, |
| "eval_samples_per_second": 55.429, |
| "eval_steps_per_second": 2.917, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.7076923076923077, |
| "grad_norm": 1.8141131401062012, |
| "learning_rate": 1.7692307692307694e-05, |
| "loss": 0.602, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.7076923076923077, |
| "eval_loss": 0.6149886250495911, |
| "eval_runtime": 2.1951, |
| "eval_samples_per_second": 51.933, |
| "eval_steps_per_second": 2.733, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.7384615384615385, |
| "grad_norm": 2.093683958053589, |
| "learning_rate": 1.8461538461538465e-05, |
| "loss": 0.6103, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.7384615384615385, |
| "eval_loss": 0.621900200843811, |
| "eval_runtime": 1.9465, |
| "eval_samples_per_second": 58.567, |
| "eval_steps_per_second": 3.082, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.7692307692307693, |
| "grad_norm": 1.840038776397705, |
| "learning_rate": 1.923076923076923e-05, |
| "loss": 0.5775, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.7692307692307693, |
| "eval_loss": 0.6232128739356995, |
| "eval_runtime": 1.9883, |
| "eval_samples_per_second": 57.334, |
| "eval_steps_per_second": 3.018, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 1.7329185009002686, |
| "learning_rate": 2e-05, |
| "loss": 0.6808, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.8, |
| "eval_loss": 0.6226441264152527, |
| "eval_runtime": 1.9469, |
| "eval_samples_per_second": 58.553, |
| "eval_steps_per_second": 3.082, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.8307692307692308, |
| "grad_norm": 2.738678455352783, |
| "learning_rate": 1.999909877856721e-05, |
| "loss": 0.5833, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.8307692307692308, |
| "eval_loss": 0.6240194439888, |
| "eval_runtime": 1.9419, |
| "eval_samples_per_second": 58.706, |
| "eval_steps_per_second": 3.09, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.8615384615384616, |
| "grad_norm": 2.0359909534454346, |
| "learning_rate": 1.9996395276708856e-05, |
| "loss": 0.691, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.8615384615384616, |
| "eval_loss": 0.6267117857933044, |
| "eval_runtime": 1.939, |
| "eval_samples_per_second": 58.794, |
| "eval_steps_per_second": 3.094, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.8923076923076924, |
| "grad_norm": 1.7706685066223145, |
| "learning_rate": 1.9991889981715696e-05, |
| "loss": 0.6404, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.8923076923076924, |
| "eval_loss": 0.6222097873687744, |
| "eval_runtime": 1.9533, |
| "eval_samples_per_second": 58.363, |
| "eval_steps_per_second": 3.072, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.9230769230769231, |
| "grad_norm": 2.129652976989746, |
| "learning_rate": 1.9985583705641418e-05, |
| "loss": 0.7109, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.9230769230769231, |
| "eval_loss": 0.6229674816131592, |
| "eval_runtime": 1.9467, |
| "eval_samples_per_second": 58.561, |
| "eval_steps_per_second": 3.082, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.9538461538461539, |
| "grad_norm": 1.8439427614212036, |
| "learning_rate": 1.9977477585156252e-05, |
| "loss": 0.6623, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.9538461538461539, |
| "eval_loss": 0.6273208856582642, |
| "eval_runtime": 2.0985, |
| "eval_samples_per_second": 54.324, |
| "eval_steps_per_second": 2.859, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.9846153846153847, |
| "grad_norm": 2.1446306705474854, |
| "learning_rate": 1.9967573081342103e-05, |
| "loss": 0.5583, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.9846153846153847, |
| "eval_loss": 0.6260280013084412, |
| "eval_runtime": 1.9521, |
| "eval_samples_per_second": 58.398, |
| "eval_steps_per_second": 3.074, |
| "step": 320 |
| }, |
| { |
| "epoch": 1.0153846153846153, |
| "grad_norm": 1.9259562492370605, |
| "learning_rate": 1.9955871979429188e-05, |
| "loss": 0.4857, |
| "step": 330 |
| }, |
| { |
| "epoch": 1.0153846153846153, |
| "eval_loss": 0.6497873067855835, |
| "eval_runtime": 1.9489, |
| "eval_samples_per_second": 58.496, |
| "eval_steps_per_second": 3.079, |
| "step": 330 |
| }, |
| { |
| "epoch": 1.0461538461538462, |
| "grad_norm": 1.8625404834747314, |
| "learning_rate": 1.9942376388474282e-05, |
| "loss": 0.4152, |
| "step": 340 |
| }, |
| { |
| "epoch": 1.0461538461538462, |
| "eval_loss": 0.6430822014808655, |
| "eval_runtime": 1.9534, |
| "eval_samples_per_second": 58.358, |
| "eval_steps_per_second": 3.071, |
| "step": 340 |
| }, |
| { |
| "epoch": 1.0769230769230769, |
| "grad_norm": 1.1712415218353271, |
| "learning_rate": 1.992708874098054e-05, |
| "loss": 0.3459, |
| "step": 350 |
| }, |
| { |
| "epoch": 1.0769230769230769, |
| "eval_loss": 0.671064019203186, |
| "eval_runtime": 1.9772, |
| "eval_samples_per_second": 57.658, |
| "eval_steps_per_second": 3.035, |
| "step": 350 |
| }, |
| { |
| "epoch": 1.1076923076923078, |
| "grad_norm": 1.0710129737854004, |
| "learning_rate": 1.9910011792459086e-05, |
| "loss": 0.4307, |
| "step": 360 |
| }, |
| { |
| "epoch": 1.1076923076923078, |
| "eval_loss": 0.6545295119285583, |
| "eval_runtime": 2.0822, |
| "eval_samples_per_second": 54.749, |
| "eval_steps_per_second": 2.882, |
| "step": 360 |
| }, |
| { |
| "epoch": 1.1384615384615384, |
| "grad_norm": 1.839811086654663, |
| "learning_rate": 1.989114862093232e-05, |
| "loss": 0.4084, |
| "step": 370 |
| }, |
| { |
| "epoch": 1.1384615384615384, |
| "eval_loss": 0.6743721961975098, |
| "eval_runtime": 1.962, |
| "eval_samples_per_second": 58.105, |
| "eval_steps_per_second": 3.058, |
| "step": 370 |
| }, |
| { |
| "epoch": 1.1692307692307693, |
| "grad_norm": 2.2416107654571533, |
| "learning_rate": 1.9870502626379127e-05, |
| "loss": 0.4203, |
| "step": 380 |
| }, |
| { |
| "epoch": 1.1692307692307693, |
| "eval_loss": 0.6703702211380005, |
| "eval_runtime": 2.0871, |
| "eval_samples_per_second": 54.621, |
| "eval_steps_per_second": 2.875, |
| "step": 380 |
| }, |
| { |
| "epoch": 1.2, |
| "grad_norm": 1.8775320053100586, |
| "learning_rate": 1.9848077530122083e-05, |
| "loss": 0.3056, |
| "step": 390 |
| }, |
| { |
| "epoch": 1.2, |
| "eval_loss": 0.680027425289154, |
| "eval_runtime": 2.0739, |
| "eval_samples_per_second": 54.97, |
| "eval_steps_per_second": 2.893, |
| "step": 390 |
| }, |
| { |
| "epoch": 1.2307692307692308, |
| "grad_norm": 2.1544764041900635, |
| "learning_rate": 1.9823877374156647e-05, |
| "loss": 0.4332, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.2307692307692308, |
| "eval_loss": 0.6662920117378235, |
| "eval_runtime": 1.9498, |
| "eval_samples_per_second": 58.466, |
| "eval_steps_per_second": 3.077, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.2615384615384615, |
| "grad_norm": 1.740652084350586, |
| "learning_rate": 1.979790652042268e-05, |
| "loss": 0.3707, |
| "step": 410 |
| }, |
| { |
| "epoch": 1.2615384615384615, |
| "eval_loss": 0.6721649765968323, |
| "eval_runtime": 1.9421, |
| "eval_samples_per_second": 58.699, |
| "eval_steps_per_second": 3.089, |
| "step": 410 |
| }, |
| { |
| "epoch": 1.2923076923076924, |
| "grad_norm": 1.8645464181900024, |
| "learning_rate": 1.977016965001817e-05, |
| "loss": 0.412, |
| "step": 420 |
| }, |
| { |
| "epoch": 1.2923076923076924, |
| "eval_loss": 0.6605477333068848, |
| "eval_runtime": 1.9455, |
| "eval_samples_per_second": 58.597, |
| "eval_steps_per_second": 3.084, |
| "step": 420 |
| }, |
| { |
| "epoch": 1.323076923076923, |
| "grad_norm": 1.3930943012237549, |
| "learning_rate": 1.9740671762355548e-05, |
| "loss": 0.388, |
| "step": 430 |
| }, |
| { |
| "epoch": 1.323076923076923, |
| "eval_loss": 0.6649342775344849, |
| "eval_runtime": 1.9497, |
| "eval_samples_per_second": 58.471, |
| "eval_steps_per_second": 3.077, |
| "step": 430 |
| }, |
| { |
| "epoch": 1.353846153846154, |
| "grad_norm": 1.8291655778884888, |
| "learning_rate": 1.9709418174260523e-05, |
| "loss": 0.4118, |
| "step": 440 |
| }, |
| { |
| "epoch": 1.353846153846154, |
| "eval_loss": 0.6680696606636047, |
| "eval_runtime": 2.0262, |
| "eval_samples_per_second": 56.262, |
| "eval_steps_per_second": 2.961, |
| "step": 440 |
| }, |
| { |
| "epoch": 1.3846153846153846, |
| "grad_norm": 1.1135263442993164, |
| "learning_rate": 1.9676414519013782e-05, |
| "loss": 0.3205, |
| "step": 450 |
| }, |
| { |
| "epoch": 1.3846153846153846, |
| "eval_loss": 0.6739374995231628, |
| "eval_runtime": 1.9443, |
| "eval_samples_per_second": 58.633, |
| "eval_steps_per_second": 3.086, |
| "step": 450 |
| }, |
| { |
| "epoch": 1.4153846153846155, |
| "grad_norm": 2.233457326889038, |
| "learning_rate": 1.9641666745335626e-05, |
| "loss": 0.3591, |
| "step": 460 |
| }, |
| { |
| "epoch": 1.4153846153846155, |
| "eval_loss": 0.6751876473426819, |
| "eval_runtime": 1.9447, |
| "eval_samples_per_second": 58.622, |
| "eval_steps_per_second": 3.085, |
| "step": 460 |
| }, |
| { |
| "epoch": 1.4461538461538461, |
| "grad_norm": 1.815677523612976, |
| "learning_rate": 1.9605181116313725e-05, |
| "loss": 0.4107, |
| "step": 470 |
| }, |
| { |
| "epoch": 1.4461538461538461, |
| "eval_loss": 0.6670271158218384, |
| "eval_runtime": 1.9448, |
| "eval_samples_per_second": 58.618, |
| "eval_steps_per_second": 3.085, |
| "step": 470 |
| }, |
| { |
| "epoch": 1.476923076923077, |
| "grad_norm": 2.0177175998687744, |
| "learning_rate": 1.9566964208274254e-05, |
| "loss": 0.3954, |
| "step": 480 |
| }, |
| { |
| "epoch": 1.476923076923077, |
| "eval_loss": 0.6706439256668091, |
| "eval_runtime": 2.1454, |
| "eval_samples_per_second": 53.137, |
| "eval_steps_per_second": 2.797, |
| "step": 480 |
| }, |
| { |
| "epoch": 1.5076923076923077, |
| "grad_norm": 2.2797820568084717, |
| "learning_rate": 1.9527022909596537e-05, |
| "loss": 0.349, |
| "step": 490 |
| }, |
| { |
| "epoch": 1.5076923076923077, |
| "eval_loss": 0.6916453242301941, |
| "eval_runtime": 1.9454, |
| "eval_samples_per_second": 58.599, |
| "eval_steps_per_second": 3.084, |
| "step": 490 |
| }, |
| { |
| "epoch": 1.5384615384615383, |
| "grad_norm": 1.6123872995376587, |
| "learning_rate": 1.9485364419471454e-05, |
| "loss": 0.3796, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.5384615384615383, |
| "eval_loss": 0.6646614670753479, |
| "eval_runtime": 1.9525, |
| "eval_samples_per_second": 58.386, |
| "eval_steps_per_second": 3.073, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.5692307692307692, |
| "grad_norm": 2.039036989212036, |
| "learning_rate": 1.9441996246603848e-05, |
| "loss": 0.4163, |
| "step": 510 |
| }, |
| { |
| "epoch": 1.5692307692307692, |
| "eval_loss": 0.6671331524848938, |
| "eval_runtime": 1.9375, |
| "eval_samples_per_second": 58.84, |
| "eval_steps_per_second": 3.097, |
| "step": 510 |
| }, |
| { |
| "epoch": 1.6, |
| "grad_norm": 1.8493613004684448, |
| "learning_rate": 1.9396926207859085e-05, |
| "loss": 0.3768, |
| "step": 520 |
| }, |
| { |
| "epoch": 1.6, |
| "eval_loss": 0.6984831094741821, |
| "eval_runtime": 1.9384, |
| "eval_samples_per_second": 58.812, |
| "eval_steps_per_second": 3.095, |
| "step": 520 |
| }, |
| { |
| "epoch": 1.6307692307692307, |
| "grad_norm": 1.1424219608306885, |
| "learning_rate": 1.9350162426854152e-05, |
| "loss": 0.3985, |
| "step": 530 |
| }, |
| { |
| "epoch": 1.6307692307692307, |
| "eval_loss": 0.6629871726036072, |
| "eval_runtime": 1.9471, |
| "eval_samples_per_second": 58.549, |
| "eval_steps_per_second": 3.082, |
| "step": 530 |
| }, |
| { |
| "epoch": 1.6615384615384614, |
| "grad_norm": 1.8115930557250977, |
| "learning_rate": 1.9301713332493386e-05, |
| "loss": 0.397, |
| "step": 540 |
| }, |
| { |
| "epoch": 1.6615384615384614, |
| "eval_loss": 0.6737513542175293, |
| "eval_runtime": 1.9496, |
| "eval_samples_per_second": 58.473, |
| "eval_steps_per_second": 3.078, |
| "step": 540 |
| }, |
| { |
| "epoch": 1.6923076923076923, |
| "grad_norm": 1.7575629949569702, |
| "learning_rate": 1.925158765744924e-05, |
| "loss": 0.4624, |
| "step": 550 |
| }, |
| { |
| "epoch": 1.6923076923076923, |
| "eval_loss": 0.660962700843811, |
| "eval_runtime": 1.953, |
| "eval_samples_per_second": 58.372, |
| "eval_steps_per_second": 3.072, |
| "step": 550 |
| }, |
| { |
| "epoch": 1.7230769230769232, |
| "grad_norm": 1.7702680826187134, |
| "learning_rate": 1.9199794436588244e-05, |
| "loss": 0.3705, |
| "step": 560 |
| }, |
| { |
| "epoch": 1.7230769230769232, |
| "eval_loss": 0.663165807723999, |
| "eval_runtime": 1.9548, |
| "eval_samples_per_second": 58.319, |
| "eval_steps_per_second": 3.069, |
| "step": 560 |
| }, |
| { |
| "epoch": 1.7538461538461538, |
| "grad_norm": 1.4927833080291748, |
| "learning_rate": 1.9146343005342546e-05, |
| "loss": 0.3708, |
| "step": 570 |
| }, |
| { |
| "epoch": 1.7538461538461538, |
| "eval_loss": 0.673720121383667, |
| "eval_runtime": 1.9582, |
| "eval_samples_per_second": 58.216, |
| "eval_steps_per_second": 3.064, |
| "step": 570 |
| }, |
| { |
| "epoch": 1.7846153846153845, |
| "grad_norm": 1.6623133420944214, |
| "learning_rate": 1.909124299802724e-05, |
| "loss": 0.399, |
| "step": 580 |
| }, |
| { |
| "epoch": 1.7846153846153845, |
| "eval_loss": 0.6685453653335571, |
| "eval_runtime": 1.9645, |
| "eval_samples_per_second": 58.029, |
| "eval_steps_per_second": 3.054, |
| "step": 580 |
| }, |
| { |
| "epoch": 1.8153846153846154, |
| "grad_norm": 2.253755807876587, |
| "learning_rate": 1.9034504346103825e-05, |
| "loss": 0.3642, |
| "step": 590 |
| }, |
| { |
| "epoch": 1.8153846153846154, |
| "eval_loss": 0.6629040241241455, |
| "eval_runtime": 1.9527, |
| "eval_samples_per_second": 58.382, |
| "eval_steps_per_second": 3.073, |
| "step": 590 |
| }, |
| { |
| "epoch": 1.8461538461538463, |
| "grad_norm": 1.8123295307159424, |
| "learning_rate": 1.8976137276390145e-05, |
| "loss": 0.4213, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.8461538461538463, |
| "eval_loss": 0.6636160016059875, |
| "eval_runtime": 2.1305, |
| "eval_samples_per_second": 53.508, |
| "eval_steps_per_second": 2.816, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.876923076923077, |
| "grad_norm": 1.6377712488174438, |
| "learning_rate": 1.891615230921703e-05, |
| "loss": 0.3154, |
| "step": 610 |
| }, |
| { |
| "epoch": 1.876923076923077, |
| "eval_loss": 0.6621889472007751, |
| "eval_runtime": 1.9727, |
| "eval_samples_per_second": 57.789, |
| "eval_steps_per_second": 3.042, |
| "step": 610 |
| }, |
| { |
| "epoch": 1.9076923076923076, |
| "grad_norm": 2.1680402755737305, |
| "learning_rate": 1.8854560256532098e-05, |
| "loss": 0.421, |
| "step": 620 |
| }, |
| { |
| "epoch": 1.9076923076923076, |
| "eval_loss": 0.6584432721138, |
| "eval_runtime": 1.9532, |
| "eval_samples_per_second": 58.367, |
| "eval_steps_per_second": 3.072, |
| "step": 620 |
| }, |
| { |
| "epoch": 1.9384615384615385, |
| "grad_norm": 1.771596074104309, |
| "learning_rate": 1.879137221995095e-05, |
| "loss": 0.3625, |
| "step": 630 |
| }, |
| { |
| "epoch": 1.9384615384615385, |
| "eval_loss": 0.6574673652648926, |
| "eval_runtime": 1.9593, |
| "eval_samples_per_second": 58.185, |
| "eval_steps_per_second": 3.062, |
| "step": 630 |
| }, |
| { |
| "epoch": 1.9692307692307693, |
| "grad_norm": 1.6291016340255737, |
| "learning_rate": 1.8726599588756144e-05, |
| "loss": 0.3787, |
| "step": 640 |
| }, |
| { |
| "epoch": 1.9692307692307693, |
| "eval_loss": 0.6593620181083679, |
| "eval_runtime": 2.1362, |
| "eval_samples_per_second": 53.367, |
| "eval_steps_per_second": 2.809, |
| "step": 640 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 1.721921682357788, |
| "learning_rate": 1.866025403784439e-05, |
| "loss": 0.3923, |
| "step": 650 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.6485319137573242, |
| "eval_runtime": 1.967, |
| "eval_samples_per_second": 57.957, |
| "eval_steps_per_second": 3.05, |
| "step": 650 |
| }, |
| { |
| "epoch": 2.0307692307692307, |
| "grad_norm": 1.6391288042068481, |
| "learning_rate": 1.859234752562217e-05, |
| "loss": 0.2137, |
| "step": 660 |
| }, |
| { |
| "epoch": 2.0307692307692307, |
| "eval_loss": 0.7283760905265808, |
| "eval_runtime": 1.9428, |
| "eval_samples_per_second": 58.678, |
| "eval_steps_per_second": 3.088, |
| "step": 660 |
| }, |
| { |
| "epoch": 2.0615384615384613, |
| "grad_norm": 1.9791120290756226, |
| "learning_rate": 1.8522892291850335e-05, |
| "loss": 0.2221, |
| "step": 670 |
| }, |
| { |
| "epoch": 2.0615384615384613, |
| "eval_loss": 0.7443767189979553, |
| "eval_runtime": 1.9429, |
| "eval_samples_per_second": 58.676, |
| "eval_steps_per_second": 3.088, |
| "step": 670 |
| }, |
| { |
| "epoch": 2.0923076923076924, |
| "grad_norm": 2.0093741416931152, |
| "learning_rate": 1.845190085543795e-05, |
| "loss": 0.1777, |
| "step": 680 |
| }, |
| { |
| "epoch": 2.0923076923076924, |
| "eval_loss": 0.7445951700210571, |
| "eval_runtime": 1.9592, |
| "eval_samples_per_second": 58.186, |
| "eval_steps_per_second": 3.062, |
| "step": 680 |
| }, |
| { |
| "epoch": 2.123076923076923, |
| "grad_norm": 1.8424338102340698, |
| "learning_rate": 1.8379386012185813e-05, |
| "loss": 0.1755, |
| "step": 690 |
| }, |
| { |
| "epoch": 2.123076923076923, |
| "eval_loss": 0.7517443299293518, |
| "eval_runtime": 2.0747, |
| "eval_samples_per_second": 54.947, |
| "eval_steps_per_second": 2.892, |
| "step": 690 |
| }, |
| { |
| "epoch": 2.1538461538461537, |
| "grad_norm": 1.4635226726531982, |
| "learning_rate": 1.8305360832480118e-05, |
| "loss": 0.1742, |
| "step": 700 |
| }, |
| { |
| "epoch": 2.1538461538461537, |
| "eval_loss": 0.7649147510528564, |
| "eval_runtime": 1.9437, |
| "eval_samples_per_second": 58.65, |
| "eval_steps_per_second": 3.087, |
| "step": 700 |
| }, |
| { |
| "epoch": 2.184615384615385, |
| "grad_norm": 1.9029723405838013, |
| "learning_rate": 1.8229838658936566e-05, |
| "loss": 0.2037, |
| "step": 710 |
| }, |
| { |
| "epoch": 2.184615384615385, |
| "eval_loss": 0.7539044618606567, |
| "eval_runtime": 2.1243, |
| "eval_samples_per_second": 53.664, |
| "eval_steps_per_second": 2.824, |
| "step": 710 |
| }, |
| { |
| "epoch": 2.2153846153846155, |
| "grad_norm": 1.3570928573608398, |
| "learning_rate": 1.8152833103995443e-05, |
| "loss": 0.1954, |
| "step": 720 |
| }, |
| { |
| "epoch": 2.2153846153846155, |
| "eval_loss": 0.7460123300552368, |
| "eval_runtime": 2.1466, |
| "eval_samples_per_second": 53.108, |
| "eval_steps_per_second": 2.795, |
| "step": 720 |
| }, |
| { |
| "epoch": 2.246153846153846, |
| "grad_norm": 1.5055183172225952, |
| "learning_rate": 1.807435804746807e-05, |
| "loss": 0.2027, |
| "step": 730 |
| }, |
| { |
| "epoch": 2.246153846153846, |
| "eval_loss": 0.7585832476615906, |
| "eval_runtime": 2.1298, |
| "eval_samples_per_second": 53.525, |
| "eval_steps_per_second": 2.817, |
| "step": 730 |
| }, |
| { |
| "epoch": 2.276923076923077, |
| "grad_norm": 1.0890541076660156, |
| "learning_rate": 1.7994427634035016e-05, |
| "loss": 0.1867, |
| "step": 740 |
| }, |
| { |
| "epoch": 2.276923076923077, |
| "eval_loss": 0.7535340785980225, |
| "eval_runtime": 1.9471, |
| "eval_samples_per_second": 58.549, |
| "eval_steps_per_second": 3.082, |
| "step": 740 |
| }, |
| { |
| "epoch": 2.3076923076923075, |
| "grad_norm": 1.11017644405365, |
| "learning_rate": 1.791305627069662e-05, |
| "loss": 0.1875, |
| "step": 750 |
| }, |
| { |
| "epoch": 2.3076923076923075, |
| "eval_loss": 0.7587242126464844, |
| "eval_runtime": 1.9462, |
| "eval_samples_per_second": 58.575, |
| "eval_steps_per_second": 3.083, |
| "step": 750 |
| }, |
| { |
| "epoch": 2.3384615384615386, |
| "grad_norm": 1.7792816162109375, |
| "learning_rate": 1.7830258624176224e-05, |
| "loss": 0.1841, |
| "step": 760 |
| }, |
| { |
| "epoch": 2.3384615384615386, |
| "eval_loss": 0.7774962782859802, |
| "eval_runtime": 1.942, |
| "eval_samples_per_second": 58.703, |
| "eval_steps_per_second": 3.09, |
| "step": 760 |
| }, |
| { |
| "epoch": 2.3692307692307693, |
| "grad_norm": 1.384929895401001, |
| "learning_rate": 1.7746049618276545e-05, |
| "loss": 0.1724, |
| "step": 770 |
| }, |
| { |
| "epoch": 2.3692307692307693, |
| "eval_loss": 0.7517464756965637, |
| "eval_runtime": 2.0655, |
| "eval_samples_per_second": 55.191, |
| "eval_steps_per_second": 2.905, |
| "step": 770 |
| }, |
| { |
| "epoch": 2.4, |
| "grad_norm": 1.3608155250549316, |
| "learning_rate": 1.766044443118978e-05, |
| "loss": 0.1831, |
| "step": 780 |
| }, |
| { |
| "epoch": 2.4, |
| "eval_loss": 0.7726874351501465, |
| "eval_runtime": 1.952, |
| "eval_samples_per_second": 58.4, |
| "eval_steps_per_second": 3.074, |
| "step": 780 |
| }, |
| { |
| "epoch": 2.430769230769231, |
| "grad_norm": 0.9307472109794617, |
| "learning_rate": 1.7573458492761802e-05, |
| "loss": 0.1897, |
| "step": 790 |
| }, |
| { |
| "epoch": 2.430769230769231, |
| "eval_loss": 0.7573862075805664, |
| "eval_runtime": 1.9435, |
| "eval_samples_per_second": 58.658, |
| "eval_steps_per_second": 3.087, |
| "step": 790 |
| }, |
| { |
| "epoch": 2.4615384615384617, |
| "grad_norm": 1.0741816759109497, |
| "learning_rate": 1.7485107481711014e-05, |
| "loss": 0.1936, |
| "step": 800 |
| }, |
| { |
| "epoch": 2.4615384615384617, |
| "eval_loss": 0.7550384402275085, |
| "eval_runtime": 1.9506, |
| "eval_samples_per_second": 58.443, |
| "eval_steps_per_second": 3.076, |
| "step": 800 |
| }, |
| { |
| "epoch": 2.4923076923076923, |
| "grad_norm": 1.3956509828567505, |
| "learning_rate": 1.7395407322802374e-05, |
| "loss": 0.1969, |
| "step": 810 |
| }, |
| { |
| "epoch": 2.4923076923076923, |
| "eval_loss": 0.7733697295188904, |
| "eval_runtime": 1.9492, |
| "eval_samples_per_second": 58.484, |
| "eval_steps_per_second": 3.078, |
| "step": 810 |
| }, |
| { |
| "epoch": 2.523076923076923, |
| "grad_norm": 1.529106855392456, |
| "learning_rate": 1.7304374183977032e-05, |
| "loss": 0.2222, |
| "step": 820 |
| }, |
| { |
| "epoch": 2.523076923076923, |
| "eval_loss": 0.753304660320282, |
| "eval_runtime": 1.9648, |
| "eval_samples_per_second": 58.022, |
| "eval_steps_per_second": 3.054, |
| "step": 820 |
| }, |
| { |
| "epoch": 2.5538461538461537, |
| "grad_norm": 1.6149755716323853, |
| "learning_rate": 1.7212024473438145e-05, |
| "loss": 0.1956, |
| "step": 830 |
| }, |
| { |
| "epoch": 2.5538461538461537, |
| "eval_loss": 0.7569817900657654, |
| "eval_runtime": 1.9386, |
| "eval_samples_per_second": 58.804, |
| "eval_steps_per_second": 3.095, |
| "step": 830 |
| }, |
| { |
| "epoch": 2.5846153846153848, |
| "grad_norm": 0.9965218901634216, |
| "learning_rate": 1.7118374836693407e-05, |
| "loss": 0.1945, |
| "step": 840 |
| }, |
| { |
| "epoch": 2.5846153846153848, |
| "eval_loss": 0.7557573914527893, |
| "eval_runtime": 1.9446, |
| "eval_samples_per_second": 58.623, |
| "eval_steps_per_second": 3.085, |
| "step": 840 |
| }, |
| { |
| "epoch": 2.6153846153846154, |
| "grad_norm": 1.1858470439910889, |
| "learning_rate": 1.7023442153554776e-05, |
| "loss": 0.1964, |
| "step": 850 |
| }, |
| { |
| "epoch": 2.6153846153846154, |
| "eval_loss": 0.7555262446403503, |
| "eval_runtime": 1.9665, |
| "eval_samples_per_second": 57.971, |
| "eval_steps_per_second": 3.051, |
| "step": 850 |
| }, |
| { |
| "epoch": 2.646153846153846, |
| "grad_norm": 1.079675316810608, |
| "learning_rate": 1.6927243535095995e-05, |
| "loss": 0.2012, |
| "step": 860 |
| }, |
| { |
| "epoch": 2.646153846153846, |
| "eval_loss": 0.7503151893615723, |
| "eval_runtime": 1.9514, |
| "eval_samples_per_second": 58.421, |
| "eval_steps_per_second": 3.075, |
| "step": 860 |
| }, |
| { |
| "epoch": 2.676923076923077, |
| "grad_norm": 1.3259488344192505, |
| "learning_rate": 1.6829796320568416e-05, |
| "loss": 0.2022, |
| "step": 870 |
| }, |
| { |
| "epoch": 2.676923076923077, |
| "eval_loss": 0.7605793476104736, |
| "eval_runtime": 2.0581, |
| "eval_samples_per_second": 55.39, |
| "eval_steps_per_second": 2.915, |
| "step": 870 |
| }, |
| { |
| "epoch": 2.707692307692308, |
| "grad_norm": 1.1906328201293945, |
| "learning_rate": 1.67311180742757e-05, |
| "loss": 0.1874, |
| "step": 880 |
| }, |
| { |
| "epoch": 2.707692307692308, |
| "eval_loss": 0.767244815826416, |
| "eval_runtime": 1.9453, |
| "eval_samples_per_second": 58.602, |
| "eval_steps_per_second": 3.084, |
| "step": 880 |
| }, |
| { |
| "epoch": 2.7384615384615385, |
| "grad_norm": 1.5168702602386475, |
| "learning_rate": 1.6631226582407954e-05, |
| "loss": 0.1939, |
| "step": 890 |
| }, |
| { |
| "epoch": 2.7384615384615385, |
| "eval_loss": 0.7721065282821655, |
| "eval_runtime": 1.9592, |
| "eval_samples_per_second": 58.186, |
| "eval_steps_per_second": 3.062, |
| "step": 890 |
| }, |
| { |
| "epoch": 2.769230769230769, |
| "grad_norm": 1.5762079954147339, |
| "learning_rate": 1.653013984983585e-05, |
| "loss": 0.1887, |
| "step": 900 |
| }, |
| { |
| "epoch": 2.769230769230769, |
| "eval_loss": 0.7561252117156982, |
| "eval_runtime": 1.9488, |
| "eval_samples_per_second": 58.496, |
| "eval_steps_per_second": 3.079, |
| "step": 900 |
| }, |
| { |
| "epoch": 2.8, |
| "grad_norm": 1.2828755378723145, |
| "learning_rate": 1.6427876096865394e-05, |
| "loss": 0.2039, |
| "step": 910 |
| }, |
| { |
| "epoch": 2.8, |
| "eval_loss": 0.7597094178199768, |
| "eval_runtime": 1.9419, |
| "eval_samples_per_second": 58.706, |
| "eval_steps_per_second": 3.09, |
| "step": 910 |
| }, |
| { |
| "epoch": 2.830769230769231, |
| "grad_norm": 1.1010947227478027, |
| "learning_rate": 1.6324453755953772e-05, |
| "loss": 0.1845, |
| "step": 920 |
| }, |
| { |
| "epoch": 2.830769230769231, |
| "eval_loss": 0.7654496431350708, |
| "eval_runtime": 1.9494, |
| "eval_samples_per_second": 58.478, |
| "eval_steps_per_second": 3.078, |
| "step": 920 |
| }, |
| { |
| "epoch": 2.8615384615384616, |
| "grad_norm": 1.676522970199585, |
| "learning_rate": 1.621989146838704e-05, |
| "loss": 0.2192, |
| "step": 930 |
| }, |
| { |
| "epoch": 2.8615384615384616, |
| "eval_loss": 0.756608247756958, |
| "eval_runtime": 1.9502, |
| "eval_samples_per_second": 58.457, |
| "eval_steps_per_second": 3.077, |
| "step": 930 |
| }, |
| { |
| "epoch": 2.8923076923076922, |
| "grad_norm": 1.453100562095642, |
| "learning_rate": 1.6114208080920125e-05, |
| "loss": 0.2055, |
| "step": 940 |
| }, |
| { |
| "epoch": 2.8923076923076922, |
| "eval_loss": 0.7652134895324707, |
| "eval_runtime": 1.976, |
| "eval_samples_per_second": 57.692, |
| "eval_steps_per_second": 3.036, |
| "step": 940 |
| }, |
| { |
| "epoch": 2.9230769230769234, |
| "grad_norm": 1.3680988550186157, |
| "learning_rate": 1.600742264237979e-05, |
| "loss": 0.2038, |
| "step": 950 |
| }, |
| { |
| "epoch": 2.9230769230769234, |
| "eval_loss": 0.7622235417366028, |
| "eval_runtime": 1.9779, |
| "eval_samples_per_second": 57.638, |
| "eval_steps_per_second": 3.034, |
| "step": 950 |
| }, |
| { |
| "epoch": 2.953846153846154, |
| "grad_norm": 1.6015321016311646, |
| "learning_rate": 1.5899554400231233e-05, |
| "loss": 0.2149, |
| "step": 960 |
| }, |
| { |
| "epoch": 2.953846153846154, |
| "eval_loss": 0.7541946172714233, |
| "eval_runtime": 1.9407, |
| "eval_samples_per_second": 58.74, |
| "eval_steps_per_second": 3.092, |
| "step": 960 |
| }, |
| { |
| "epoch": 2.9846153846153847, |
| "grad_norm": 1.2561781406402588, |
| "learning_rate": 1.579062279710879e-05, |
| "loss": 0.1844, |
| "step": 970 |
| }, |
| { |
| "epoch": 2.9846153846153847, |
| "eval_loss": 0.7695141434669495, |
| "eval_runtime": 1.9507, |
| "eval_samples_per_second": 58.442, |
| "eval_steps_per_second": 3.076, |
| "step": 970 |
| }, |
| { |
| "epoch": 3.0153846153846153, |
| "grad_norm": 0.7629246711730957, |
| "learning_rate": 1.568064746731156e-05, |
| "loss": 0.1376, |
| "step": 980 |
| }, |
| { |
| "epoch": 3.0153846153846153, |
| "eval_loss": 0.7860725522041321, |
| "eval_runtime": 1.9563, |
| "eval_samples_per_second": 58.273, |
| "eval_steps_per_second": 3.067, |
| "step": 980 |
| }, |
| { |
| "epoch": 3.046153846153846, |
| "grad_norm": 0.9552655816078186, |
| "learning_rate": 1.5569648233264395e-05, |
| "loss": 0.1065, |
| "step": 990 |
| }, |
| { |
| "epoch": 3.046153846153846, |
| "eval_loss": 0.8531390428543091, |
| "eval_runtime": 1.9499, |
| "eval_samples_per_second": 58.465, |
| "eval_steps_per_second": 3.077, |
| "step": 990 |
| }, |
| { |
| "epoch": 3.076923076923077, |
| "grad_norm": 1.4238945245742798, |
| "learning_rate": 1.5457645101945046e-05, |
| "loss": 0.1083, |
| "step": 1000 |
| }, |
| { |
| "epoch": 3.076923076923077, |
| "eval_loss": 0.8417089581489563, |
| "eval_runtime": 2.0647, |
| "eval_samples_per_second": 55.214, |
| "eval_steps_per_second": 2.906, |
| "step": 1000 |
| }, |
| { |
| "epoch": 3.1076923076923078, |
| "grad_norm": 1.0638066530227661, |
| "learning_rate": 1.5344658261278013e-05, |
| "loss": 0.1054, |
| "step": 1010 |
| }, |
| { |
| "epoch": 3.1076923076923078, |
| "eval_loss": 0.8362419009208679, |
| "eval_runtime": 1.9429, |
| "eval_samples_per_second": 58.675, |
| "eval_steps_per_second": 3.088, |
| "step": 1010 |
| }, |
| { |
| "epoch": 3.1384615384615384, |
| "grad_norm": 1.2013343572616577, |
| "learning_rate": 1.5230708076495777e-05, |
| "loss": 0.1104, |
| "step": 1020 |
| }, |
| { |
| "epoch": 3.1384615384615384, |
| "eval_loss": 0.821545422077179, |
| "eval_runtime": 2.0667, |
| "eval_samples_per_second": 55.162, |
| "eval_steps_per_second": 2.903, |
| "step": 1020 |
| }, |
| { |
| "epoch": 3.169230769230769, |
| "grad_norm": 1.0717769861221313, |
| "learning_rate": 1.5115815086468103e-05, |
| "loss": 0.1094, |
| "step": 1030 |
| }, |
| { |
| "epoch": 3.169230769230769, |
| "eval_loss": 0.819724977016449, |
| "eval_runtime": 1.9507, |
| "eval_samples_per_second": 58.442, |
| "eval_steps_per_second": 3.076, |
| "step": 1030 |
| }, |
| { |
| "epoch": 3.2, |
| "grad_norm": 1.1035127639770508, |
| "learning_rate": 1.5000000000000002e-05, |
| "loss": 0.1044, |
| "step": 1040 |
| }, |
| { |
| "epoch": 3.2, |
| "eval_loss": 0.8392235636711121, |
| "eval_runtime": 2.0622, |
| "eval_samples_per_second": 55.281, |
| "eval_steps_per_second": 2.91, |
| "step": 1040 |
| }, |
| { |
| "epoch": 3.230769230769231, |
| "grad_norm": 0.8959378004074097, |
| "learning_rate": 1.4883283692099114e-05, |
| "loss": 0.1118, |
| "step": 1050 |
| }, |
| { |
| "epoch": 3.230769230769231, |
| "eval_loss": 0.8458349704742432, |
| "eval_runtime": 1.945, |
| "eval_samples_per_second": 58.612, |
| "eval_steps_per_second": 3.085, |
| "step": 1050 |
| }, |
| { |
| "epoch": 3.2615384615384615, |
| "grad_norm": 0.9646655917167664, |
| "learning_rate": 1.4765687200213079e-05, |
| "loss": 0.1052, |
| "step": 1060 |
| }, |
| { |
| "epoch": 3.2615384615384615, |
| "eval_loss": 0.8331754207611084, |
| "eval_runtime": 1.9403, |
| "eval_samples_per_second": 58.754, |
| "eval_steps_per_second": 3.092, |
| "step": 1060 |
| }, |
| { |
| "epoch": 3.292307692307692, |
| "grad_norm": 0.9311823844909668, |
| "learning_rate": 1.4647231720437687e-05, |
| "loss": 0.1096, |
| "step": 1070 |
| }, |
| { |
| "epoch": 3.292307692307692, |
| "eval_loss": 0.8387322425842285, |
| "eval_runtime": 2.0874, |
| "eval_samples_per_second": 54.614, |
| "eval_steps_per_second": 2.874, |
| "step": 1070 |
| }, |
| { |
| "epoch": 3.3230769230769233, |
| "grad_norm": 0.9276036024093628, |
| "learning_rate": 1.4527938603696376e-05, |
| "loss": 0.1193, |
| "step": 1080 |
| }, |
| { |
| "epoch": 3.3230769230769233, |
| "eval_loss": 0.835710346698761, |
| "eval_runtime": 1.952, |
| "eval_samples_per_second": 58.402, |
| "eval_steps_per_second": 3.074, |
| "step": 1080 |
| }, |
| { |
| "epoch": 3.353846153846154, |
| "grad_norm": 0.9336265921592712, |
| "learning_rate": 1.4407829351891858e-05, |
| "loss": 0.1196, |
| "step": 1090 |
| }, |
| { |
| "epoch": 3.353846153846154, |
| "eval_loss": 0.8234468698501587, |
| "eval_runtime": 1.9557, |
| "eval_samples_per_second": 58.29, |
| "eval_steps_per_second": 3.068, |
| "step": 1090 |
| }, |
| { |
| "epoch": 3.3846153846153846, |
| "grad_norm": 1.1978046894073486, |
| "learning_rate": 1.4286925614030542e-05, |
| "loss": 0.1212, |
| "step": 1100 |
| }, |
| { |
| "epoch": 3.3846153846153846, |
| "eval_loss": 0.8307368159294128, |
| "eval_runtime": 2.145, |
| "eval_samples_per_second": 53.147, |
| "eval_steps_per_second": 2.797, |
| "step": 1100 |
| }, |
| { |
| "epoch": 3.4153846153846152, |
| "grad_norm": 1.5773977041244507, |
| "learning_rate": 1.4165249182320401e-05, |
| "loss": 0.1153, |
| "step": 1110 |
| }, |
| { |
| "epoch": 3.4153846153846152, |
| "eval_loss": 0.8459444642066956, |
| "eval_runtime": 1.9411, |
| "eval_samples_per_second": 58.728, |
| "eval_steps_per_second": 3.091, |
| "step": 1110 |
| }, |
| { |
| "epoch": 3.4461538461538463, |
| "grad_norm": 1.0756422281265259, |
| "learning_rate": 1.404282198824305e-05, |
| "loss": 0.1169, |
| "step": 1120 |
| }, |
| { |
| "epoch": 3.4461538461538463, |
| "eval_loss": 0.8370065093040466, |
| "eval_runtime": 1.9365, |
| "eval_samples_per_second": 58.87, |
| "eval_steps_per_second": 3.098, |
| "step": 1120 |
| }, |
| { |
| "epoch": 3.476923076923077, |
| "grad_norm": 0.9122937917709351, |
| "learning_rate": 1.3919666098600753e-05, |
| "loss": 0.1089, |
| "step": 1130 |
| }, |
| { |
| "epoch": 3.476923076923077, |
| "eval_loss": 0.8352024555206299, |
| "eval_runtime": 1.9648, |
| "eval_samples_per_second": 58.02, |
| "eval_steps_per_second": 3.054, |
| "step": 1130 |
| }, |
| { |
| "epoch": 3.5076923076923077, |
| "grad_norm": 1.2896252870559692, |
| "learning_rate": 1.3795803711538966e-05, |
| "loss": 0.1072, |
| "step": 1140 |
| }, |
| { |
| "epoch": 3.5076923076923077, |
| "eval_loss": 0.8422742486000061, |
| "eval_runtime": 1.9414, |
| "eval_samples_per_second": 58.721, |
| "eval_steps_per_second": 3.091, |
| "step": 1140 |
| }, |
| { |
| "epoch": 3.5384615384615383, |
| "grad_norm": 0.7873758673667908, |
| "learning_rate": 1.3671257152545277e-05, |
| "loss": 0.1085, |
| "step": 1150 |
| }, |
| { |
| "epoch": 3.5384615384615383, |
| "eval_loss": 0.8508307933807373, |
| "eval_runtime": 1.9573, |
| "eval_samples_per_second": 58.242, |
| "eval_steps_per_second": 3.065, |
| "step": 1150 |
| }, |
| { |
| "epoch": 3.569230769230769, |
| "grad_norm": 1.2042518854141235, |
| "learning_rate": 1.3546048870425356e-05, |
| "loss": 0.1118, |
| "step": 1160 |
| }, |
| { |
| "epoch": 3.569230769230769, |
| "eval_loss": 0.849172830581665, |
| "eval_runtime": 1.9788, |
| "eval_samples_per_second": 57.61, |
| "eval_steps_per_second": 3.032, |
| "step": 1160 |
| }, |
| { |
| "epoch": 3.6, |
| "grad_norm": 1.1467583179473877, |
| "learning_rate": 1.342020143325669e-05, |
| "loss": 0.1105, |
| "step": 1170 |
| }, |
| { |
| "epoch": 3.6, |
| "eval_loss": 0.8496175408363342, |
| "eval_runtime": 1.9416, |
| "eval_samples_per_second": 58.715, |
| "eval_steps_per_second": 3.09, |
| "step": 1170 |
| }, |
| { |
| "epoch": 3.6307692307692307, |
| "grad_norm": 1.1640350818634033, |
| "learning_rate": 1.3293737524320798e-05, |
| "loss": 0.1157, |
| "step": 1180 |
| }, |
| { |
| "epoch": 3.6307692307692307, |
| "eval_loss": 0.8408421277999878, |
| "eval_runtime": 1.9531, |
| "eval_samples_per_second": 58.369, |
| "eval_steps_per_second": 3.072, |
| "step": 1180 |
| }, |
| { |
| "epoch": 3.6615384615384614, |
| "grad_norm": 1.022333025932312, |
| "learning_rate": 1.3166679938014728e-05, |
| "loss": 0.1126, |
| "step": 1190 |
| }, |
| { |
| "epoch": 3.6615384615384614, |
| "eval_loss": 0.8300553560256958, |
| "eval_runtime": 1.9507, |
| "eval_samples_per_second": 58.44, |
| "eval_steps_per_second": 3.076, |
| "step": 1190 |
| }, |
| { |
| "epoch": 3.6923076923076925, |
| "grad_norm": 1.0650651454925537, |
| "learning_rate": 1.303905157574247e-05, |
| "loss": 0.1123, |
| "step": 1200 |
| }, |
| { |
| "epoch": 3.6923076923076925, |
| "eval_loss": 0.8288592100143433, |
| "eval_runtime": 1.9663, |
| "eval_samples_per_second": 57.977, |
| "eval_steps_per_second": 3.051, |
| "step": 1200 |
| }, |
| { |
| "epoch": 3.723076923076923, |
| "grad_norm": 0.8549203276634216, |
| "learning_rate": 1.291087544178713e-05, |
| "loss": 0.1113, |
| "step": 1210 |
| }, |
| { |
| "epoch": 3.723076923076923, |
| "eval_loss": 0.8329548239707947, |
| "eval_runtime": 1.9441, |
| "eval_samples_per_second": 58.638, |
| "eval_steps_per_second": 3.086, |
| "step": 1210 |
| }, |
| { |
| "epoch": 3.753846153846154, |
| "grad_norm": 1.0669158697128296, |
| "learning_rate": 1.2782174639164528e-05, |
| "loss": 0.1114, |
| "step": 1220 |
| }, |
| { |
| "epoch": 3.753846153846154, |
| "eval_loss": 0.8303550481796265, |
| "eval_runtime": 2.0411, |
| "eval_samples_per_second": 55.851, |
| "eval_steps_per_second": 2.94, |
| "step": 1220 |
| }, |
| { |
| "epoch": 3.7846153846153845, |
| "grad_norm": 1.295453667640686, |
| "learning_rate": 1.2652972365459008e-05, |
| "loss": 0.1057, |
| "step": 1230 |
| }, |
| { |
| "epoch": 3.7846153846153845, |
| "eval_loss": 0.8316855430603027, |
| "eval_runtime": 2.0794, |
| "eval_samples_per_second": 54.823, |
| "eval_steps_per_second": 2.885, |
| "step": 1230 |
| }, |
| { |
| "epoch": 3.815384615384615, |
| "grad_norm": 1.1729763746261597, |
| "learning_rate": 1.2523291908642219e-05, |
| "loss": 0.119, |
| "step": 1240 |
| }, |
| { |
| "epoch": 3.815384615384615, |
| "eval_loss": 0.8399801850318909, |
| "eval_runtime": 1.9463, |
| "eval_samples_per_second": 58.572, |
| "eval_steps_per_second": 3.083, |
| "step": 1240 |
| }, |
| { |
| "epoch": 3.8461538461538463, |
| "grad_norm": 1.0446621179580688, |
| "learning_rate": 1.2393156642875579e-05, |
| "loss": 0.1178, |
| "step": 1250 |
| }, |
| { |
| "epoch": 3.8461538461538463, |
| "eval_loss": 0.8335243463516235, |
| "eval_runtime": 1.9474, |
| "eval_samples_per_second": 58.538, |
| "eval_steps_per_second": 3.081, |
| "step": 1250 |
| }, |
| { |
| "epoch": 3.876923076923077, |
| "grad_norm": 0.7862658500671387, |
| "learning_rate": 1.2262590024297226e-05, |
| "loss": 0.111, |
| "step": 1260 |
| }, |
| { |
| "epoch": 3.876923076923077, |
| "eval_loss": 0.8262643218040466, |
| "eval_runtime": 1.9486, |
| "eval_samples_per_second": 58.504, |
| "eval_steps_per_second": 3.079, |
| "step": 1260 |
| }, |
| { |
| "epoch": 3.9076923076923076, |
| "grad_norm": 1.2322797775268555, |
| "learning_rate": 1.2131615586794162e-05, |
| "loss": 0.1108, |
| "step": 1270 |
| }, |
| { |
| "epoch": 3.9076923076923076, |
| "eval_loss": 0.8384814262390137, |
| "eval_runtime": 1.9434, |
| "eval_samples_per_second": 58.659, |
| "eval_steps_per_second": 3.087, |
| "step": 1270 |
| }, |
| { |
| "epoch": 3.9384615384615387, |
| "grad_norm": 1.2308915853500366, |
| "learning_rate": 1.2000256937760446e-05, |
| "loss": 0.1083, |
| "step": 1280 |
| }, |
| { |
| "epoch": 3.9384615384615387, |
| "eval_loss": 0.8350539207458496, |
| "eval_runtime": 1.9475, |
| "eval_samples_per_second": 58.535, |
| "eval_steps_per_second": 3.081, |
| "step": 1280 |
| }, |
| { |
| "epoch": 3.9692307692307693, |
| "grad_norm": 1.1422042846679688, |
| "learning_rate": 1.1868537753842052e-05, |
| "loss": 0.1075, |
| "step": 1290 |
| }, |
| { |
| "epoch": 3.9692307692307693, |
| "eval_loss": 0.8435344099998474, |
| "eval_runtime": 1.9532, |
| "eval_samples_per_second": 58.367, |
| "eval_steps_per_second": 3.072, |
| "step": 1290 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 1.0442712306976318, |
| "learning_rate": 1.1736481776669307e-05, |
| "loss": 0.1202, |
| "step": 1300 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 0.8554986715316772, |
| "eval_runtime": 1.9512, |
| "eval_samples_per_second": 58.426, |
| "eval_steps_per_second": 3.075, |
| "step": 1300 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 2600, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 8, |
| "save_steps": 50, |
| "total_flos": 1.1318833868439552e+17, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
