| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 3375, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005925925925925926, | |
| "grad_norm": 0.73828125, | |
| "learning_rate": 2.9629629629629632e-08, | |
| "loss": 1.9405, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.011851851851851851, | |
| "grad_norm": 1.171875, | |
| "learning_rate": 5.9259259259259263e-08, | |
| "loss": 1.9345, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.017777777777777778, | |
| "grad_norm": 0.828125, | |
| "learning_rate": 8.88888888888889e-08, | |
| "loss": 2.0371, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.023703703703703703, | |
| "grad_norm": 0.8515625, | |
| "learning_rate": 1.1851851851851853e-07, | |
| "loss": 1.9599, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.02962962962962963, | |
| "grad_norm": 1.546875, | |
| "learning_rate": 1.4814814814814817e-07, | |
| "loss": 1.9826, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.035555555555555556, | |
| "grad_norm": 0.83203125, | |
| "learning_rate": 1.777777777777778e-07, | |
| "loss": 1.9455, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.04148148148148148, | |
| "grad_norm": 1.234375, | |
| "learning_rate": 2.074074074074074e-07, | |
| "loss": 2.0185, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.047407407407407405, | |
| "grad_norm": 1.015625, | |
| "learning_rate": 2.3703703703703705e-07, | |
| "loss": 1.8877, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.05333333333333334, | |
| "grad_norm": 0.79296875, | |
| "learning_rate": 2.666666666666667e-07, | |
| "loss": 2.0742, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.05925925925925926, | |
| "grad_norm": 0.69921875, | |
| "learning_rate": 2.9629629629629634e-07, | |
| "loss": 1.9178, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.06518518518518518, | |
| "grad_norm": 0.75390625, | |
| "learning_rate": 3.259259259259259e-07, | |
| "loss": 1.8998, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.07111111111111111, | |
| "grad_norm": 0.75, | |
| "learning_rate": 3.555555555555556e-07, | |
| "loss": 2.0155, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.07703703703703704, | |
| "grad_norm": 0.73828125, | |
| "learning_rate": 3.8518518518518525e-07, | |
| "loss": 2.0011, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.08296296296296296, | |
| "grad_norm": 1.3828125, | |
| "learning_rate": 4.148148148148148e-07, | |
| "loss": 1.9424, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.08888888888888889, | |
| "grad_norm": 1.0234375, | |
| "learning_rate": 4.444444444444445e-07, | |
| "loss": 1.8711, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.09481481481481481, | |
| "grad_norm": 0.98046875, | |
| "learning_rate": 4.740740740740741e-07, | |
| "loss": 1.902, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.10074074074074074, | |
| "grad_norm": 0.625, | |
| "learning_rate": 5.037037037037038e-07, | |
| "loss": 1.942, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.10666666666666667, | |
| "grad_norm": 0.96875, | |
| "learning_rate": 5.333333333333335e-07, | |
| "loss": 1.8852, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.11259259259259259, | |
| "grad_norm": 0.59765625, | |
| "learning_rate": 5.62962962962963e-07, | |
| "loss": 1.9527, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.11851851851851852, | |
| "grad_norm": 0.91796875, | |
| "learning_rate": 5.925925925925927e-07, | |
| "loss": 1.8927, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.12444444444444444, | |
| "grad_norm": 1.03125, | |
| "learning_rate": 6.222222222222223e-07, | |
| "loss": 1.9382, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.13037037037037036, | |
| "grad_norm": 0.61328125, | |
| "learning_rate": 6.518518518518518e-07, | |
| "loss": 1.906, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.1362962962962963, | |
| "grad_norm": 0.52734375, | |
| "learning_rate": 6.814814814814816e-07, | |
| "loss": 1.851, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.14222222222222222, | |
| "grad_norm": 0.59765625, | |
| "learning_rate": 7.111111111111112e-07, | |
| "loss": 1.901, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.14814814814814814, | |
| "grad_norm": 0.9765625, | |
| "learning_rate": 7.407407407407407e-07, | |
| "loss": 1.851, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.15407407407407409, | |
| "grad_norm": 0.7109375, | |
| "learning_rate": 7.703703703703705e-07, | |
| "loss": 1.809, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.5390625, | |
| "learning_rate": 8.000000000000001e-07, | |
| "loss": 1.8846, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.16592592592592592, | |
| "grad_norm": 0.39453125, | |
| "learning_rate": 8.296296296296296e-07, | |
| "loss": 1.8922, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.17185185185185184, | |
| "grad_norm": 0.388671875, | |
| "learning_rate": 8.592592592592593e-07, | |
| "loss": 1.9092, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.17777777777777778, | |
| "grad_norm": 0.33203125, | |
| "learning_rate": 8.88888888888889e-07, | |
| "loss": 1.868, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.1837037037037037, | |
| "grad_norm": 0.400390625, | |
| "learning_rate": 9.185185185185185e-07, | |
| "loss": 1.8768, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.18962962962962962, | |
| "grad_norm": 0.447265625, | |
| "learning_rate": 9.481481481481482e-07, | |
| "loss": 1.8321, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.19555555555555557, | |
| "grad_norm": 0.48828125, | |
| "learning_rate": 9.77777777777778e-07, | |
| "loss": 1.8788, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.20148148148148148, | |
| "grad_norm": 0.392578125, | |
| "learning_rate": 1.0074074074074076e-06, | |
| "loss": 1.8518, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.2074074074074074, | |
| "grad_norm": 0.65234375, | |
| "learning_rate": 1.0370370370370371e-06, | |
| "loss": 1.8652, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.21333333333333335, | |
| "grad_norm": 0.33984375, | |
| "learning_rate": 1.066666666666667e-06, | |
| "loss": 1.7996, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.21925925925925926, | |
| "grad_norm": 0.546875, | |
| "learning_rate": 1.0962962962962965e-06, | |
| "loss": 1.8566, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.22518518518518518, | |
| "grad_norm": 0.439453125, | |
| "learning_rate": 1.125925925925926e-06, | |
| "loss": 1.8537, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.2311111111111111, | |
| "grad_norm": 0.494140625, | |
| "learning_rate": 1.1555555555555556e-06, | |
| "loss": 1.8452, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.23703703703703705, | |
| "grad_norm": 0.46484375, | |
| "learning_rate": 1.1851851851851854e-06, | |
| "loss": 1.8393, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.24296296296296296, | |
| "grad_norm": 0.89453125, | |
| "learning_rate": 1.214814814814815e-06, | |
| "loss": 1.7721, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.24888888888888888, | |
| "grad_norm": 0.65234375, | |
| "learning_rate": 1.2444444444444445e-06, | |
| "loss": 1.8168, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.2548148148148148, | |
| "grad_norm": 0.65625, | |
| "learning_rate": 1.2740740740740743e-06, | |
| "loss": 1.8316, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.2607407407407407, | |
| "grad_norm": 0.73046875, | |
| "learning_rate": 1.3037037037037036e-06, | |
| "loss": 1.7708, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.26666666666666666, | |
| "grad_norm": 0.62109375, | |
| "learning_rate": 1.3333333333333334e-06, | |
| "loss": 1.7678, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.2725925925925926, | |
| "grad_norm": 0.5078125, | |
| "learning_rate": 1.3629629629629632e-06, | |
| "loss": 1.85, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.2785185185185185, | |
| "grad_norm": 0.70703125, | |
| "learning_rate": 1.3925925925925925e-06, | |
| "loss": 1.8612, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.28444444444444444, | |
| "grad_norm": 0.62109375, | |
| "learning_rate": 1.4222222222222223e-06, | |
| "loss": 1.8431, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.2903703703703704, | |
| "grad_norm": 0.546875, | |
| "learning_rate": 1.451851851851852e-06, | |
| "loss": 1.8036, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.2962962962962963, | |
| "grad_norm": 0.4453125, | |
| "learning_rate": 1.4814814814814815e-06, | |
| "loss": 1.7861, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.3022222222222222, | |
| "grad_norm": 0.4375, | |
| "learning_rate": 1.5111111111111112e-06, | |
| "loss": 1.8524, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.30814814814814817, | |
| "grad_norm": 0.56640625, | |
| "learning_rate": 1.540740740740741e-06, | |
| "loss": 1.7964, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.31407407407407406, | |
| "grad_norm": 0.66796875, | |
| "learning_rate": 1.5703703703703704e-06, | |
| "loss": 1.894, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.72265625, | |
| "learning_rate": 1.6000000000000001e-06, | |
| "loss": 1.7428, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.32592592592592595, | |
| "grad_norm": 0.51953125, | |
| "learning_rate": 1.62962962962963e-06, | |
| "loss": 1.7648, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.33185185185185184, | |
| "grad_norm": 0.57421875, | |
| "learning_rate": 1.6592592592592593e-06, | |
| "loss": 1.7671, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.3377777777777778, | |
| "grad_norm": 0.28515625, | |
| "learning_rate": 1.688888888888889e-06, | |
| "loss": 1.8195, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.3437037037037037, | |
| "grad_norm": 0.53515625, | |
| "learning_rate": 1.7185185185185186e-06, | |
| "loss": 1.7553, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.3496296296296296, | |
| "grad_norm": 0.369140625, | |
| "learning_rate": 1.7481481481481482e-06, | |
| "loss": 1.8649, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "grad_norm": 0.76171875, | |
| "learning_rate": 1.777777777777778e-06, | |
| "loss": 1.6996, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.36148148148148146, | |
| "grad_norm": 0.8125, | |
| "learning_rate": 1.8074074074074075e-06, | |
| "loss": 1.8027, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.3674074074074074, | |
| "grad_norm": 0.54296875, | |
| "learning_rate": 1.837037037037037e-06, | |
| "loss": 1.7646, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.37333333333333335, | |
| "grad_norm": 0.48828125, | |
| "learning_rate": 1.8666666666666669e-06, | |
| "loss": 1.6897, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.37925925925925924, | |
| "grad_norm": 0.38671875, | |
| "learning_rate": 1.8962962962962964e-06, | |
| "loss": 1.7192, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.3851851851851852, | |
| "grad_norm": 0.66015625, | |
| "learning_rate": 1.925925925925926e-06, | |
| "loss": 1.7491, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.39111111111111113, | |
| "grad_norm": 0.48828125, | |
| "learning_rate": 1.955555555555556e-06, | |
| "loss": 1.6689, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.397037037037037, | |
| "grad_norm": 0.6171875, | |
| "learning_rate": 1.985185185185185e-06, | |
| "loss": 1.6721, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.40296296296296297, | |
| "grad_norm": 0.486328125, | |
| "learning_rate": 2.014814814814815e-06, | |
| "loss": 1.7495, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.4088888888888889, | |
| "grad_norm": 0.5078125, | |
| "learning_rate": 2.0444444444444447e-06, | |
| "loss": 1.7475, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.4148148148148148, | |
| "grad_norm": 0.494140625, | |
| "learning_rate": 2.0740740740740742e-06, | |
| "loss": 1.7103, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.42074074074074075, | |
| "grad_norm": 0.5, | |
| "learning_rate": 2.103703703703704e-06, | |
| "loss": 1.6456, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.4266666666666667, | |
| "grad_norm": 0.62890625, | |
| "learning_rate": 2.133333333333334e-06, | |
| "loss": 1.7045, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.4325925925925926, | |
| "grad_norm": 0.458984375, | |
| "learning_rate": 2.162962962962963e-06, | |
| "loss": 1.6505, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.43851851851851853, | |
| "grad_norm": 0.51171875, | |
| "learning_rate": 2.192592592592593e-06, | |
| "loss": 1.5497, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 0.46875, | |
| "learning_rate": 2.222222222222222e-06, | |
| "loss": 1.5977, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.45037037037037037, | |
| "grad_norm": 0.310546875, | |
| "learning_rate": 2.251851851851852e-06, | |
| "loss": 1.5589, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.4562962962962963, | |
| "grad_norm": 0.421875, | |
| "learning_rate": 2.2814814814814816e-06, | |
| "loss": 1.5472, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.4622222222222222, | |
| "grad_norm": 0.26953125, | |
| "learning_rate": 2.311111111111111e-06, | |
| "loss": 1.6132, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.46814814814814815, | |
| "grad_norm": 0.435546875, | |
| "learning_rate": 2.3407407407407408e-06, | |
| "loss": 1.586, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.4740740740740741, | |
| "grad_norm": 0.51953125, | |
| "learning_rate": 2.3703703703703707e-06, | |
| "loss": 1.5127, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.67578125, | |
| "learning_rate": 2.4000000000000003e-06, | |
| "loss": 1.5141, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.48592592592592593, | |
| "grad_norm": 0.330078125, | |
| "learning_rate": 2.42962962962963e-06, | |
| "loss": 1.5157, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.4918518518518519, | |
| "grad_norm": 0.283203125, | |
| "learning_rate": 2.4592592592592594e-06, | |
| "loss": 1.5395, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.49777777777777776, | |
| "grad_norm": 0.5546875, | |
| "learning_rate": 2.488888888888889e-06, | |
| "loss": 1.4586, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.5037037037037037, | |
| "grad_norm": 0.30078125, | |
| "learning_rate": 2.5185185185185186e-06, | |
| "loss": 1.4836, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.5096296296296297, | |
| "grad_norm": 0.40625, | |
| "learning_rate": 2.5481481481481486e-06, | |
| "loss": 1.5109, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.5155555555555555, | |
| "grad_norm": 0.341796875, | |
| "learning_rate": 2.577777777777778e-06, | |
| "loss": 1.5414, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.5214814814814814, | |
| "grad_norm": 0.345703125, | |
| "learning_rate": 2.6074074074074073e-06, | |
| "loss": 1.5813, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.5274074074074074, | |
| "grad_norm": 0.28125, | |
| "learning_rate": 2.6370370370370373e-06, | |
| "loss": 1.5222, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.5333333333333333, | |
| "grad_norm": 0.376953125, | |
| "learning_rate": 2.666666666666667e-06, | |
| "loss": 1.5081, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.5392592592592592, | |
| "grad_norm": 0.279296875, | |
| "learning_rate": 2.6962962962962964e-06, | |
| "loss": 1.5026, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.5451851851851852, | |
| "grad_norm": 0.2578125, | |
| "learning_rate": 2.7259259259259264e-06, | |
| "loss": 1.5438, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.5511111111111111, | |
| "grad_norm": 0.4453125, | |
| "learning_rate": 2.755555555555556e-06, | |
| "loss": 1.476, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.557037037037037, | |
| "grad_norm": 0.263671875, | |
| "learning_rate": 2.785185185185185e-06, | |
| "loss": 1.4509, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.562962962962963, | |
| "grad_norm": 0.39453125, | |
| "learning_rate": 2.814814814814815e-06, | |
| "loss": 1.5576, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.5688888888888889, | |
| "grad_norm": 0.306640625, | |
| "learning_rate": 2.8444444444444446e-06, | |
| "loss": 1.5297, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.5748148148148148, | |
| "grad_norm": 0.283203125, | |
| "learning_rate": 2.874074074074074e-06, | |
| "loss": 1.4491, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.5807407407407408, | |
| "grad_norm": 0.416015625, | |
| "learning_rate": 2.903703703703704e-06, | |
| "loss": 1.59, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.5866666666666667, | |
| "grad_norm": 0.291015625, | |
| "learning_rate": 2.9333333333333338e-06, | |
| "loss": 1.4926, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 0.244140625, | |
| "learning_rate": 2.962962962962963e-06, | |
| "loss": 1.5031, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.5985185185185186, | |
| "grad_norm": 0.314453125, | |
| "learning_rate": 2.992592592592593e-06, | |
| "loss": 1.4425, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 0.6044444444444445, | |
| "grad_norm": 0.48046875, | |
| "learning_rate": 3.0222222222222225e-06, | |
| "loss": 1.5279, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 0.6103703703703703, | |
| "grad_norm": 0.255859375, | |
| "learning_rate": 3.051851851851852e-06, | |
| "loss": 1.5437, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 0.6162962962962963, | |
| "grad_norm": 0.400390625, | |
| "learning_rate": 3.081481481481482e-06, | |
| "loss": 1.4972, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 0.6222222222222222, | |
| "grad_norm": 0.38671875, | |
| "learning_rate": 3.1111111111111116e-06, | |
| "loss": 1.4935, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.6281481481481481, | |
| "grad_norm": 0.341796875, | |
| "learning_rate": 3.1407407407407407e-06, | |
| "loss": 1.595, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 0.6340740740740741, | |
| "grad_norm": 0.408203125, | |
| "learning_rate": 3.1703703703703707e-06, | |
| "loss": 1.4306, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.2119140625, | |
| "learning_rate": 3.2000000000000003e-06, | |
| "loss": 1.5468, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 0.6459259259259259, | |
| "grad_norm": 0.287109375, | |
| "learning_rate": 3.22962962962963e-06, | |
| "loss": 1.477, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 0.6518518518518519, | |
| "grad_norm": 0.458984375, | |
| "learning_rate": 3.25925925925926e-06, | |
| "loss": 1.4971, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.6577777777777778, | |
| "grad_norm": 0.255859375, | |
| "learning_rate": 3.2888888888888894e-06, | |
| "loss": 1.4715, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 0.6637037037037037, | |
| "grad_norm": 0.32421875, | |
| "learning_rate": 3.3185185185185185e-06, | |
| "loss": 1.4916, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 0.6696296296296296, | |
| "grad_norm": 0.34765625, | |
| "learning_rate": 3.348148148148148e-06, | |
| "loss": 1.5192, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 0.6755555555555556, | |
| "grad_norm": 0.19921875, | |
| "learning_rate": 3.377777777777778e-06, | |
| "loss": 1.4304, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 0.6814814814814815, | |
| "grad_norm": 0.287109375, | |
| "learning_rate": 3.4074074074074077e-06, | |
| "loss": 1.5796, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.6874074074074074, | |
| "grad_norm": 0.28515625, | |
| "learning_rate": 3.4370370370370372e-06, | |
| "loss": 1.5835, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 0.6933333333333334, | |
| "grad_norm": 0.259765625, | |
| "learning_rate": 3.4666666666666672e-06, | |
| "loss": 1.4515, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 0.6992592592592592, | |
| "grad_norm": 0.255859375, | |
| "learning_rate": 3.4962962962962964e-06, | |
| "loss": 1.4513, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 0.7051851851851851, | |
| "grad_norm": 0.296875, | |
| "learning_rate": 3.525925925925926e-06, | |
| "loss": 1.5401, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 0.7111111111111111, | |
| "grad_norm": 0.3515625, | |
| "learning_rate": 3.555555555555556e-06, | |
| "loss": 1.5242, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.717037037037037, | |
| "grad_norm": 0.3359375, | |
| "learning_rate": 3.5851851851851855e-06, | |
| "loss": 1.4171, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 0.7229629629629629, | |
| "grad_norm": 0.380859375, | |
| "learning_rate": 3.614814814814815e-06, | |
| "loss": 1.4914, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 0.7288888888888889, | |
| "grad_norm": 0.3203125, | |
| "learning_rate": 3.644444444444445e-06, | |
| "loss": 1.4023, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 0.7348148148148148, | |
| "grad_norm": 0.41015625, | |
| "learning_rate": 3.674074074074074e-06, | |
| "loss": 1.5467, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 0.7407407407407407, | |
| "grad_norm": 0.25, | |
| "learning_rate": 3.7037037037037037e-06, | |
| "loss": 1.5131, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.7466666666666667, | |
| "grad_norm": 0.34765625, | |
| "learning_rate": 3.7333333333333337e-06, | |
| "loss": 1.4868, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 0.7525925925925926, | |
| "grad_norm": 0.275390625, | |
| "learning_rate": 3.7629629629629633e-06, | |
| "loss": 1.5638, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 0.7585185185185185, | |
| "grad_norm": 0.306640625, | |
| "learning_rate": 3.792592592592593e-06, | |
| "loss": 1.5138, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 0.7644444444444445, | |
| "grad_norm": 0.3046875, | |
| "learning_rate": 3.8222222222222224e-06, | |
| "loss": 1.4604, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 0.7703703703703704, | |
| "grad_norm": 0.224609375, | |
| "learning_rate": 3.851851851851852e-06, | |
| "loss": 1.4806, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.7762962962962963, | |
| "grad_norm": 0.23046875, | |
| "learning_rate": 3.8814814814814816e-06, | |
| "loss": 1.5501, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 0.7822222222222223, | |
| "grad_norm": 0.2236328125, | |
| "learning_rate": 3.911111111111112e-06, | |
| "loss": 1.5254, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 0.7881481481481482, | |
| "grad_norm": 0.294921875, | |
| "learning_rate": 3.940740740740741e-06, | |
| "loss": 1.5049, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 0.794074074074074, | |
| "grad_norm": 0.322265625, | |
| "learning_rate": 3.97037037037037e-06, | |
| "loss": 1.3749, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.333984375, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 1.5036, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.8059259259259259, | |
| "grad_norm": 0.314453125, | |
| "learning_rate": 4.02962962962963e-06, | |
| "loss": 1.4699, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 0.8118518518518518, | |
| "grad_norm": 0.251953125, | |
| "learning_rate": 4.05925925925926e-06, | |
| "loss": 1.4729, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 0.8177777777777778, | |
| "grad_norm": 0.1904296875, | |
| "learning_rate": 4.088888888888889e-06, | |
| "loss": 1.4782, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 0.8237037037037037, | |
| "grad_norm": 0.392578125, | |
| "learning_rate": 4.118518518518519e-06, | |
| "loss": 1.4379, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 0.8296296296296296, | |
| "grad_norm": 0.240234375, | |
| "learning_rate": 4.1481481481481485e-06, | |
| "loss": 1.515, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.8355555555555556, | |
| "grad_norm": 0.2392578125, | |
| "learning_rate": 4.177777777777778e-06, | |
| "loss": 1.466, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 0.8414814814814815, | |
| "grad_norm": 0.275390625, | |
| "learning_rate": 4.207407407407408e-06, | |
| "loss": 1.4852, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 0.8474074074074074, | |
| "grad_norm": 0.275390625, | |
| "learning_rate": 4.237037037037037e-06, | |
| "loss": 1.5604, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 0.8533333333333334, | |
| "grad_norm": 0.296875, | |
| "learning_rate": 4.266666666666668e-06, | |
| "loss": 1.4395, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 0.8592592592592593, | |
| "grad_norm": 0.361328125, | |
| "learning_rate": 4.296296296296296e-06, | |
| "loss": 1.455, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.8651851851851852, | |
| "grad_norm": 0.26171875, | |
| "learning_rate": 4.325925925925926e-06, | |
| "loss": 1.5373, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 0.8711111111111111, | |
| "grad_norm": 0.208984375, | |
| "learning_rate": 4.3555555555555555e-06, | |
| "loss": 1.3663, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 0.8770370370370371, | |
| "grad_norm": 0.279296875, | |
| "learning_rate": 4.385185185185186e-06, | |
| "loss": 1.3726, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 0.882962962962963, | |
| "grad_norm": 0.2314453125, | |
| "learning_rate": 4.4148148148148154e-06, | |
| "loss": 1.4718, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 0.2421875, | |
| "learning_rate": 4.444444444444444e-06, | |
| "loss": 1.4882, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.8948148148148148, | |
| "grad_norm": 0.2109375, | |
| "learning_rate": 4.4740740740740746e-06, | |
| "loss": 1.535, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 0.9007407407407407, | |
| "grad_norm": 0.34765625, | |
| "learning_rate": 4.503703703703704e-06, | |
| "loss": 1.4269, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 0.9066666666666666, | |
| "grad_norm": 0.263671875, | |
| "learning_rate": 4.533333333333334e-06, | |
| "loss": 1.434, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 0.9125925925925926, | |
| "grad_norm": 0.2080078125, | |
| "learning_rate": 4.562962962962963e-06, | |
| "loss": 1.4714, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 0.9185185185185185, | |
| "grad_norm": 0.22265625, | |
| "learning_rate": 4.592592592592593e-06, | |
| "loss": 1.4427, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.9244444444444444, | |
| "grad_norm": 0.3203125, | |
| "learning_rate": 4.622222222222222e-06, | |
| "loss": 1.4902, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 0.9303703703703704, | |
| "grad_norm": 0.337890625, | |
| "learning_rate": 4.651851851851853e-06, | |
| "loss": 1.5026, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 0.9362962962962963, | |
| "grad_norm": 0.2373046875, | |
| "learning_rate": 4.6814814814814815e-06, | |
| "loss": 1.4131, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 0.9422222222222222, | |
| "grad_norm": 0.27734375, | |
| "learning_rate": 4.711111111111111e-06, | |
| "loss": 1.4583, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 0.9481481481481482, | |
| "grad_norm": 0.26953125, | |
| "learning_rate": 4.7407407407407415e-06, | |
| "loss": 1.5298, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.9540740740740741, | |
| "grad_norm": 0.2734375, | |
| "learning_rate": 4.770370370370371e-06, | |
| "loss": 1.4845, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.2490234375, | |
| "learning_rate": 4.800000000000001e-06, | |
| "loss": 1.5329, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 0.965925925925926, | |
| "grad_norm": 0.283203125, | |
| "learning_rate": 4.82962962962963e-06, | |
| "loss": 1.513, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 0.9718518518518519, | |
| "grad_norm": 0.2158203125, | |
| "learning_rate": 4.85925925925926e-06, | |
| "loss": 1.4065, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 0.9777777777777777, | |
| "grad_norm": 0.216796875, | |
| "learning_rate": 4.888888888888889e-06, | |
| "loss": 1.4303, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.9837037037037037, | |
| "grad_norm": 0.240234375, | |
| "learning_rate": 4.918518518518519e-06, | |
| "loss": 1.4025, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 0.9896296296296296, | |
| "grad_norm": 0.212890625, | |
| "learning_rate": 4.9481481481481485e-06, | |
| "loss": 1.5732, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 0.9955555555555555, | |
| "grad_norm": 0.287109375, | |
| "learning_rate": 4.977777777777778e-06, | |
| "loss": 1.5408, | |
| "step": 3360 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 16875, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "total_flos": 4.4539748890148045e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |