| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 9.98439937597504, | |
| "eval_steps": 500, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0998439937597504, | |
| "grad_norm": 0.33735999850516357, | |
| "learning_rate": 0.0, | |
| "loss": 2.0239, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1996879875195008, | |
| "grad_norm": 3.996268319859662, | |
| "learning_rate": 0.0001, | |
| "loss": 2.1481, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.2995319812792512, | |
| "grad_norm": 3.972078144391957, | |
| "learning_rate": 0.0001, | |
| "loss": 2.1474, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.3993759750390016, | |
| "grad_norm": 2.7286088582127235, | |
| "learning_rate": 9.897959183673469e-05, | |
| "loss": 2.1429, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.49921996879875197, | |
| "grad_norm": 4.297284692826526, | |
| "learning_rate": 9.79591836734694e-05, | |
| "loss": 2.2106, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5990639625585024, | |
| "grad_norm": 4.430982504708323, | |
| "learning_rate": 9.693877551020408e-05, | |
| "loss": 2.1834, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.6989079563182528, | |
| "grad_norm": 2.6687235846541064, | |
| "learning_rate": 9.591836734693878e-05, | |
| "loss": 2.1127, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.7987519500780031, | |
| "grad_norm": 1.2769742192031128, | |
| "learning_rate": 9.489795918367348e-05, | |
| "loss": 2.0969, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.8985959438377535, | |
| "grad_norm": 1.4823469261150688, | |
| "learning_rate": 9.387755102040817e-05, | |
| "loss": 2.0815, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.9984399375975039, | |
| "grad_norm": 2.036951250941504, | |
| "learning_rate": 9.285714285714286e-05, | |
| "loss": 2.0954, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.0982839313572543, | |
| "grad_norm": 1.9201925092786452, | |
| "learning_rate": 9.183673469387756e-05, | |
| "loss": 2.0938, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.1981279251170047, | |
| "grad_norm": 1.0750267735185661, | |
| "learning_rate": 9.081632653061225e-05, | |
| "loss": 2.0609, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.2979719188767551, | |
| "grad_norm": 0.7680234903130688, | |
| "learning_rate": 8.979591836734695e-05, | |
| "loss": 2.0664, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.3978159126365055, | |
| "grad_norm": 1.385815006248848, | |
| "learning_rate": 8.877551020408164e-05, | |
| "loss": 2.0705, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.497659906396256, | |
| "grad_norm": 1.7546578816659688, | |
| "learning_rate": 8.775510204081632e-05, | |
| "loss": 2.0676, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.5975039001560063, | |
| "grad_norm": 1.5801645828188804, | |
| "learning_rate": 8.673469387755102e-05, | |
| "loss": 2.0717, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.6973478939157567, | |
| "grad_norm": 0.6350567898174008, | |
| "learning_rate": 8.571428571428571e-05, | |
| "loss": 2.0445, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.797191887675507, | |
| "grad_norm": 0.769793586745769, | |
| "learning_rate": 8.469387755102041e-05, | |
| "loss": 2.0641, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.8970358814352575, | |
| "grad_norm": 0.9717953713720756, | |
| "learning_rate": 8.367346938775511e-05, | |
| "loss": 2.045, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.9968798751950079, | |
| "grad_norm": 0.8984304676609969, | |
| "learning_rate": 8.26530612244898e-05, | |
| "loss": 2.0571, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.0967238689547583, | |
| "grad_norm": 0.5175444394072088, | |
| "learning_rate": 8.163265306122449e-05, | |
| "loss": 2.041, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 2.1965678627145087, | |
| "grad_norm": 0.4541835423784387, | |
| "learning_rate": 8.061224489795919e-05, | |
| "loss": 2.0336, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.296411856474259, | |
| "grad_norm": 0.667841023508509, | |
| "learning_rate": 7.959183673469388e-05, | |
| "loss": 2.0495, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.3962558502340094, | |
| "grad_norm": 0.5788661227302379, | |
| "learning_rate": 7.857142857142858e-05, | |
| "loss": 2.0535, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.49609984399376, | |
| "grad_norm": 0.44773175799420883, | |
| "learning_rate": 7.755102040816327e-05, | |
| "loss": 2.0565, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.5959438377535102, | |
| "grad_norm": 0.36927161339954073, | |
| "learning_rate": 7.653061224489796e-05, | |
| "loss": 2.043, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.6957878315132606, | |
| "grad_norm": 0.41656375647295985, | |
| "learning_rate": 7.551020408163266e-05, | |
| "loss": 2.0508, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.795631825273011, | |
| "grad_norm": 0.5181702303959671, | |
| "learning_rate": 7.448979591836736e-05, | |
| "loss": 2.0421, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.8954758190327614, | |
| "grad_norm": 0.3514850743124221, | |
| "learning_rate": 7.346938775510205e-05, | |
| "loss": 2.0613, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.995319812792512, | |
| "grad_norm": 0.4107791530284269, | |
| "learning_rate": 7.244897959183675e-05, | |
| "loss": 2.0373, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 3.095163806552262, | |
| "grad_norm": 0.37199633406042804, | |
| "learning_rate": 7.142857142857143e-05, | |
| "loss": 2.0383, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 3.1950078003120126, | |
| "grad_norm": 0.4001809292131257, | |
| "learning_rate": 7.040816326530612e-05, | |
| "loss": 2.046, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 3.294851794071763, | |
| "grad_norm": 0.288426524415327, | |
| "learning_rate": 6.938775510204082e-05, | |
| "loss": 2.0397, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 3.3946957878315134, | |
| "grad_norm": 0.2430022517102903, | |
| "learning_rate": 6.836734693877551e-05, | |
| "loss": 2.0209, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 3.4945397815912638, | |
| "grad_norm": 0.21451368987973404, | |
| "learning_rate": 6.73469387755102e-05, | |
| "loss": 2.0321, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 3.594383775351014, | |
| "grad_norm": 0.216393318547338, | |
| "learning_rate": 6.63265306122449e-05, | |
| "loss": 2.034, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 3.6942277691107646, | |
| "grad_norm": 0.27185371030563144, | |
| "learning_rate": 6.530612244897959e-05, | |
| "loss": 2.0387, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 3.794071762870515, | |
| "grad_norm": 0.2697186164320835, | |
| "learning_rate": 6.428571428571429e-05, | |
| "loss": 2.0291, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 3.8939157566302653, | |
| "grad_norm": 0.24154490158801892, | |
| "learning_rate": 6.326530612244899e-05, | |
| "loss": 2.032, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 3.9937597503900157, | |
| "grad_norm": 0.19835514928005893, | |
| "learning_rate": 6.224489795918368e-05, | |
| "loss": 2.0378, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 4.093603744149766, | |
| "grad_norm": 0.202257495523738, | |
| "learning_rate": 6.122448979591838e-05, | |
| "loss": 2.0282, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 4.1934477379095165, | |
| "grad_norm": 0.29489887223631195, | |
| "learning_rate": 6.0204081632653065e-05, | |
| "loss": 2.0312, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 4.2932917316692665, | |
| "grad_norm": 0.24397101805150526, | |
| "learning_rate": 5.918367346938776e-05, | |
| "loss": 2.0279, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 4.393135725429017, | |
| "grad_norm": 0.18678468114794597, | |
| "learning_rate": 5.816326530612245e-05, | |
| "loss": 2.0322, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 4.492979719188767, | |
| "grad_norm": 0.20762719446936778, | |
| "learning_rate": 5.714285714285714e-05, | |
| "loss": 2.0319, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 4.592823712948518, | |
| "grad_norm": 0.22021149423424455, | |
| "learning_rate": 5.6122448979591836e-05, | |
| "loss": 2.0226, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 4.692667706708268, | |
| "grad_norm": 0.19683580500376263, | |
| "learning_rate": 5.510204081632653e-05, | |
| "loss": 2.0132, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 4.792511700468019, | |
| "grad_norm": 0.18067087727658598, | |
| "learning_rate": 5.408163265306123e-05, | |
| "loss": 2.0212, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 4.892355694227769, | |
| "grad_norm": 0.20548068001057151, | |
| "learning_rate": 5.3061224489795926e-05, | |
| "loss": 2.0297, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 4.99219968798752, | |
| "grad_norm": 0.21068796657056815, | |
| "learning_rate": 5.2040816326530614e-05, | |
| "loss": 2.024, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 5.09204368174727, | |
| "grad_norm": 0.18294872441473956, | |
| "learning_rate": 5.102040816326531e-05, | |
| "loss": 2.0165, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 5.1918876755070205, | |
| "grad_norm": 0.19829054181667702, | |
| "learning_rate": 5e-05, | |
| "loss": 2.0192, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 5.29173166926677, | |
| "grad_norm": 0.23253630377762147, | |
| "learning_rate": 4.89795918367347e-05, | |
| "loss": 2.0168, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 5.391575663026521, | |
| "grad_norm": 0.19977491013330723, | |
| "learning_rate": 4.795918367346939e-05, | |
| "loss": 2.0371, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 5.491419656786271, | |
| "grad_norm": 0.19839589028132484, | |
| "learning_rate": 4.6938775510204086e-05, | |
| "loss": 2.0241, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 5.591263650546022, | |
| "grad_norm": 0.19221135549659152, | |
| "learning_rate": 4.591836734693878e-05, | |
| "loss": 2.0155, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 5.691107644305772, | |
| "grad_norm": 0.18530533779964112, | |
| "learning_rate": 4.4897959183673474e-05, | |
| "loss": 2.0188, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 5.790951638065523, | |
| "grad_norm": 0.19542701225272013, | |
| "learning_rate": 4.387755102040816e-05, | |
| "loss": 2.0197, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 5.890795631825273, | |
| "grad_norm": 0.19627507477830436, | |
| "learning_rate": 4.2857142857142856e-05, | |
| "loss": 2.0273, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 5.990639625585024, | |
| "grad_norm": 0.19035619638095738, | |
| "learning_rate": 4.183673469387756e-05, | |
| "loss": 2.0219, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 6.090483619344774, | |
| "grad_norm": 0.2202319627016047, | |
| "learning_rate": 4.0816326530612245e-05, | |
| "loss": 2.0243, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 6.190327613104524, | |
| "grad_norm": 0.21161656218616026, | |
| "learning_rate": 3.979591836734694e-05, | |
| "loss": 2.0107, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 6.290171606864274, | |
| "grad_norm": 0.18165401696499975, | |
| "learning_rate": 3.8775510204081634e-05, | |
| "loss": 2.0139, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 6.390015600624025, | |
| "grad_norm": 0.2000226648720509, | |
| "learning_rate": 3.775510204081633e-05, | |
| "loss": 2.0213, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 6.489859594383775, | |
| "grad_norm": 0.21044890897157179, | |
| "learning_rate": 3.673469387755102e-05, | |
| "loss": 2.0191, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 6.589703588143526, | |
| "grad_norm": 0.19088424814099902, | |
| "learning_rate": 3.571428571428572e-05, | |
| "loss": 2.0242, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 6.689547581903276, | |
| "grad_norm": 0.21090169002189085, | |
| "learning_rate": 3.469387755102041e-05, | |
| "loss": 2.0129, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 6.789391575663027, | |
| "grad_norm": 0.17374408490589077, | |
| "learning_rate": 3.36734693877551e-05, | |
| "loss": 2.0137, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 6.889235569422777, | |
| "grad_norm": 0.19923758885188783, | |
| "learning_rate": 3.265306122448979e-05, | |
| "loss": 2.0246, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 6.9890795631825275, | |
| "grad_norm": 0.23509786711199504, | |
| "learning_rate": 3.1632653061224494e-05, | |
| "loss": 2.0217, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 7.0889235569422775, | |
| "grad_norm": 0.22682630866339715, | |
| "learning_rate": 3.061224489795919e-05, | |
| "loss": 2.0227, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 7.188767550702028, | |
| "grad_norm": 0.19506001365101278, | |
| "learning_rate": 2.959183673469388e-05, | |
| "loss": 2.0055, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 7.288611544461778, | |
| "grad_norm": 0.18843675103995558, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 2.009, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 7.388455538221529, | |
| "grad_norm": 0.3013340836030522, | |
| "learning_rate": 2.7551020408163265e-05, | |
| "loss": 2.0059, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 7.488299531981279, | |
| "grad_norm": 0.2196066974488878, | |
| "learning_rate": 2.6530612244897963e-05, | |
| "loss": 2.0146, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 7.58814352574103, | |
| "grad_norm": 0.29942455484876807, | |
| "learning_rate": 2.5510204081632654e-05, | |
| "loss": 2.028, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 7.68798751950078, | |
| "grad_norm": 0.2635978736170486, | |
| "learning_rate": 2.448979591836735e-05, | |
| "loss": 2.007, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 7.787831513260531, | |
| "grad_norm": 0.17048063706160105, | |
| "learning_rate": 2.3469387755102043e-05, | |
| "loss": 2.0178, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 7.887675507020281, | |
| "grad_norm": 0.2462988180698444, | |
| "learning_rate": 2.2448979591836737e-05, | |
| "loss": 2.0184, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 7.9875195007800315, | |
| "grad_norm": 0.18757769842389277, | |
| "learning_rate": 2.1428571428571428e-05, | |
| "loss": 2.0066, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 8.087363494539781, | |
| "grad_norm": 0.1838199763796138, | |
| "learning_rate": 2.0408163265306123e-05, | |
| "loss": 2.0086, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 8.187207488299531, | |
| "grad_norm": 0.18445305909507442, | |
| "learning_rate": 1.9387755102040817e-05, | |
| "loss": 2.0059, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 8.287051482059283, | |
| "grad_norm": 0.15914247815116395, | |
| "learning_rate": 1.836734693877551e-05, | |
| "loss": 2.0014, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 8.386895475819033, | |
| "grad_norm": 0.16618424435461218, | |
| "learning_rate": 1.7346938775510206e-05, | |
| "loss": 1.9989, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 8.486739469578783, | |
| "grad_norm": 0.18987830126280159, | |
| "learning_rate": 1.6326530612244897e-05, | |
| "loss": 2.014, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 8.586583463338533, | |
| "grad_norm": 0.17181919557458755, | |
| "learning_rate": 1.5306122448979594e-05, | |
| "loss": 2.0126, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 8.686427457098285, | |
| "grad_norm": 0.1803239869304924, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 2.0118, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 8.786271450858035, | |
| "grad_norm": 0.16809838859014387, | |
| "learning_rate": 1.3265306122448982e-05, | |
| "loss": 2.0241, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 8.886115444617785, | |
| "grad_norm": 0.20717433267642188, | |
| "learning_rate": 1.2244897959183674e-05, | |
| "loss": 2.0134, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 8.985959438377535, | |
| "grad_norm": 0.16293892544531494, | |
| "learning_rate": 1.1224489795918369e-05, | |
| "loss": 2.0117, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 9.085803432137286, | |
| "grad_norm": 0.16729720184195912, | |
| "learning_rate": 1.0204081632653061e-05, | |
| "loss": 2.0126, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 9.185647425897036, | |
| "grad_norm": 0.22526874784083245, | |
| "learning_rate": 9.183673469387756e-06, | |
| "loss": 2.0024, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 9.285491419656786, | |
| "grad_norm": 0.2184919299582014, | |
| "learning_rate": 8.163265306122448e-06, | |
| "loss": 1.9992, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 9.385335413416536, | |
| "grad_norm": 0.17270901831612614, | |
| "learning_rate": 7.142857142857143e-06, | |
| "loss": 1.9999, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 9.485179407176288, | |
| "grad_norm": 0.16098303914434564, | |
| "learning_rate": 6.122448979591837e-06, | |
| "loss": 2.0125, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 9.585023400936038, | |
| "grad_norm": 0.17807241926954062, | |
| "learning_rate": 5.102040816326531e-06, | |
| "loss": 2.012, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 9.684867394695788, | |
| "grad_norm": 0.21950474032603587, | |
| "learning_rate": 4.081632653061224e-06, | |
| "loss": 2.0172, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 9.784711388455538, | |
| "grad_norm": 0.18080305990015563, | |
| "learning_rate": 3.0612244897959185e-06, | |
| "loss": 1.9969, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 9.88455538221529, | |
| "grad_norm": 0.1715649658731182, | |
| "learning_rate": 2.040816326530612e-06, | |
| "loss": 2.0153, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 9.98439937597504, | |
| "grad_norm": 0.16882262984886745, | |
| "learning_rate": 1.020408163265306e-06, | |
| "loss": 2.0115, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |