| { | |
| "best_metric": 0.01722303405404091, | |
| "best_model_checkpoint": "saves/psy-course-doc/Qwen2.5-7B-Instruct/train/fold6/checkpoint-120", | |
| "epoch": 4.938271604938271, | |
| "eval_steps": 10, | |
| "global_step": 125, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03950617283950617, | |
| "grad_norm": 0.21943485736846924, | |
| "learning_rate": 7.692307692307694e-06, | |
| "loss": 0.1756, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07901234567901234, | |
| "grad_norm": 0.1591726690530777, | |
| "learning_rate": 1.5384615384615387e-05, | |
| "loss": 0.1363, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.11851851851851852, | |
| "grad_norm": 0.22766555845737457, | |
| "learning_rate": 2.307692307692308e-05, | |
| "loss": 0.177, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1580246913580247, | |
| "grad_norm": 0.15470461547374725, | |
| "learning_rate": 3.0769230769230774e-05, | |
| "loss": 0.1372, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.19753086419753085, | |
| "grad_norm": 0.14102992415428162, | |
| "learning_rate": 3.846153846153846e-05, | |
| "loss": 0.1216, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.23703703703703705, | |
| "grad_norm": 0.15640774369239807, | |
| "learning_rate": 4.615384615384616e-05, | |
| "loss": 0.1278, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2765432098765432, | |
| "grad_norm": 0.14861662685871124, | |
| "learning_rate": 5.384615384615385e-05, | |
| "loss": 0.1372, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3160493827160494, | |
| "grad_norm": 0.12894566357135773, | |
| "learning_rate": 6.153846153846155e-05, | |
| "loss": 0.1184, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "grad_norm": 0.12572047114372253, | |
| "learning_rate": 6.923076923076924e-05, | |
| "loss": 0.1137, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3950617283950617, | |
| "grad_norm": 0.14078351855278015, | |
| "learning_rate": 7.692307692307693e-05, | |
| "loss": 0.1126, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3950617283950617, | |
| "eval_loss": 0.12602683901786804, | |
| "eval_runtime": 25.9346, | |
| "eval_samples_per_second": 1.735, | |
| "eval_steps_per_second": 1.735, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4345679012345679, | |
| "grad_norm": 0.1199629083275795, | |
| "learning_rate": 8.461538461538461e-05, | |
| "loss": 0.1142, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.4740740740740741, | |
| "grad_norm": 0.10679922997951508, | |
| "learning_rate": 9.230769230769232e-05, | |
| "loss": 0.0972, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5135802469135803, | |
| "grad_norm": 0.09360916912555695, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0876, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5530864197530864, | |
| "grad_norm": 0.08126942813396454, | |
| "learning_rate": 9.998033131915266e-05, | |
| "loss": 0.0781, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 0.07326602935791016, | |
| "learning_rate": 9.992134075089084e-05, | |
| "loss": 0.0704, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6320987654320988, | |
| "grad_norm": 0.0696115791797638, | |
| "learning_rate": 9.982307470588098e-05, | |
| "loss": 0.0635, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.671604938271605, | |
| "grad_norm": 0.07988032698631287, | |
| "learning_rate": 9.968561049466214e-05, | |
| "loss": 0.0617, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.7111111111111111, | |
| "grad_norm": 0.09191024303436279, | |
| "learning_rate": 9.950905626682228e-05, | |
| "loss": 0.0637, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7506172839506173, | |
| "grad_norm": 0.0852058082818985, | |
| "learning_rate": 9.92935509259118e-05, | |
| "loss": 0.0606, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7901234567901234, | |
| "grad_norm": 0.07930584251880646, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.0588, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7901234567901234, | |
| "eval_loss": 0.05992984399199486, | |
| "eval_runtime": 25.862, | |
| "eval_samples_per_second": 1.74, | |
| "eval_steps_per_second": 1.74, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.8296296296296296, | |
| "grad_norm": 0.08693177998065948, | |
| "learning_rate": 9.874639560909117e-05, | |
| "loss": 0.057, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.8691358024691358, | |
| "grad_norm": 0.06873193383216858, | |
| "learning_rate": 9.841517610611309e-05, | |
| "loss": 0.0549, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.908641975308642, | |
| "grad_norm": 0.05944234877824783, | |
| "learning_rate": 9.804586609725499e-05, | |
| "loss": 0.0391, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.9481481481481482, | |
| "grad_norm": 0.0974101722240448, | |
| "learning_rate": 9.763875613614482e-05, | |
| "loss": 0.0505, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9876543209876543, | |
| "grad_norm": 0.06186546012759209, | |
| "learning_rate": 9.719416651541839e-05, | |
| "loss": 0.043, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.0271604938271606, | |
| "grad_norm": 0.09650241583585739, | |
| "learning_rate": 9.671244701472999e-05, | |
| "loss": 0.0638, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.0666666666666667, | |
| "grad_norm": 0.04897386208176613, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0303, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.106172839506173, | |
| "grad_norm": 0.046298798173666, | |
| "learning_rate": 9.563916325306594e-05, | |
| "loss": 0.0341, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.145679012345679, | |
| "grad_norm": 0.05863014981150627, | |
| "learning_rate": 9.504844339512095e-05, | |
| "loss": 0.0334, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.1851851851851851, | |
| "grad_norm": 0.05470599606633186, | |
| "learning_rate": 9.442228179894362e-05, | |
| "loss": 0.0306, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.1851851851851851, | |
| "eval_loss": 0.033436119556427, | |
| "eval_runtime": 25.8919, | |
| "eval_samples_per_second": 1.738, | |
| "eval_steps_per_second": 1.738, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.2246913580246914, | |
| "grad_norm": 0.059330571442842484, | |
| "learning_rate": 9.376117109543769e-05, | |
| "loss": 0.0357, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.2641975308641975, | |
| "grad_norm": 0.05388804152607918, | |
| "learning_rate": 9.306563141162046e-05, | |
| "loss": 0.028, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.3037037037037038, | |
| "grad_norm": 0.04978477954864502, | |
| "learning_rate": 9.233620996141421e-05, | |
| "loss": 0.0268, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.34320987654321, | |
| "grad_norm": 0.05924646928906441, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.0267, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.382716049382716, | |
| "grad_norm": 0.055464863777160645, | |
| "learning_rate": 9.077804344796302e-05, | |
| "loss": 0.0268, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.4222222222222223, | |
| "grad_norm": 0.06895492225885391, | |
| "learning_rate": 8.995052426791247e-05, | |
| "loss": 0.0253, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.4617283950617284, | |
| "grad_norm": 0.05984394624829292, | |
| "learning_rate": 8.90915741234015e-05, | |
| "loss": 0.0235, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.5012345679012347, | |
| "grad_norm": 0.06565533578395844, | |
| "learning_rate": 8.820186879108038e-05, | |
| "loss": 0.0257, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.5407407407407407, | |
| "grad_norm": 0.05269227176904678, | |
| "learning_rate": 8.728210824415827e-05, | |
| "loss": 0.0231, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.5802469135802468, | |
| "grad_norm": 0.05268261581659317, | |
| "learning_rate": 8.633301610170135e-05, | |
| "loss": 0.0232, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.5802469135802468, | |
| "eval_loss": 0.025375891476869583, | |
| "eval_runtime": 25.9029, | |
| "eval_samples_per_second": 1.737, | |
| "eval_steps_per_second": 1.737, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.6197530864197531, | |
| "grad_norm": 0.056495752185583115, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0261, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.6592592592592592, | |
| "grad_norm": 0.06019185855984688, | |
| "learning_rate": 8.434984630174509e-05, | |
| "loss": 0.0257, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.6987654320987655, | |
| "grad_norm": 0.05118177831172943, | |
| "learning_rate": 8.33173288976002e-05, | |
| "loss": 0.023, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.7382716049382716, | |
| "grad_norm": 0.05333544313907623, | |
| "learning_rate": 8.225859917710439e-05, | |
| "loss": 0.0253, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 0.06095046177506447, | |
| "learning_rate": 8.117449009293668e-05, | |
| "loss": 0.0257, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.817283950617284, | |
| "grad_norm": 0.043695252388715744, | |
| "learning_rate": 8.006585456492029e-05, | |
| "loss": 0.0163, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.8567901234567903, | |
| "grad_norm": 0.05009619891643524, | |
| "learning_rate": 7.89335648089903e-05, | |
| "loss": 0.0258, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.8962962962962964, | |
| "grad_norm": 0.04014035686850548, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.0165, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.9358024691358025, | |
| "grad_norm": 0.053761377930641174, | |
| "learning_rate": 7.660160382576683e-05, | |
| "loss": 0.0254, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.9753086419753085, | |
| "grad_norm": 0.05367910489439964, | |
| "learning_rate": 7.540376726232648e-05, | |
| "loss": 0.0189, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.9753086419753085, | |
| "eval_loss": 0.021527696400880814, | |
| "eval_runtime": 25.9007, | |
| "eval_samples_per_second": 1.737, | |
| "eval_steps_per_second": 1.737, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.0148148148148146, | |
| "grad_norm": 0.0713057592511177, | |
| "learning_rate": 7.4185944355262e-05, | |
| "loss": 0.0288, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 2.054320987654321, | |
| "grad_norm": 0.03315626457333565, | |
| "learning_rate": 7.294909322337689e-05, | |
| "loss": 0.0136, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.093827160493827, | |
| "grad_norm": 0.03830026090145111, | |
| "learning_rate": 7.169418695587791e-05, | |
| "loss": 0.0169, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.1333333333333333, | |
| "grad_norm": 0.04134984314441681, | |
| "learning_rate": 7.042221284679982e-05, | |
| "loss": 0.0194, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.1728395061728394, | |
| "grad_norm": 0.04015449061989784, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0173, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.212345679012346, | |
| "grad_norm": 0.03454513102769852, | |
| "learning_rate": 6.783107663311565e-05, | |
| "loss": 0.0129, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.251851851851852, | |
| "grad_norm": 0.04263680428266525, | |
| "learning_rate": 6.651395309775837e-05, | |
| "loss": 0.0165, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.291358024691358, | |
| "grad_norm": 0.04442084953188896, | |
| "learning_rate": 6.518383725548074e-05, | |
| "loss": 0.0221, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.330864197530864, | |
| "grad_norm": 0.03828935697674751, | |
| "learning_rate": 6.384177557124247e-05, | |
| "loss": 0.0194, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.3703703703703702, | |
| "grad_norm": 0.062412988394498825, | |
| "learning_rate": 6.248882390836135e-05, | |
| "loss": 0.0168, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.3703703703703702, | |
| "eval_loss": 0.019772132858633995, | |
| "eval_runtime": 25.9082, | |
| "eval_samples_per_second": 1.737, | |
| "eval_steps_per_second": 1.737, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.4098765432098768, | |
| "grad_norm": 0.04680776596069336, | |
| "learning_rate": 6.112604669781572e-05, | |
| "loss": 0.0175, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.449382716049383, | |
| "grad_norm": 0.043991029262542725, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.0178, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.488888888888889, | |
| "grad_norm": 0.04611797630786896, | |
| "learning_rate": 5.837531116523682e-05, | |
| "loss": 0.0222, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.528395061728395, | |
| "grad_norm": 0.04121099039912224, | |
| "learning_rate": 5.698951697677498e-05, | |
| "loss": 0.0146, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.567901234567901, | |
| "grad_norm": 0.04799938201904297, | |
| "learning_rate": 5.559822380516539e-05, | |
| "loss": 0.0143, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.6074074074074076, | |
| "grad_norm": 0.05085166543722153, | |
| "learning_rate": 5.420252624646238e-05, | |
| "loss": 0.0184, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.6469135802469137, | |
| "grad_norm": 0.04127015918493271, | |
| "learning_rate": 5.2803522361859594e-05, | |
| "loss": 0.0157, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.68641975308642, | |
| "grad_norm": 0.04294725880026817, | |
| "learning_rate": 5.140231281379345e-05, | |
| "loss": 0.0169, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.725925925925926, | |
| "grad_norm": 0.06253976374864578, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0194, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.765432098765432, | |
| "grad_norm": 0.046594616025686264, | |
| "learning_rate": 4.859768718620656e-05, | |
| "loss": 0.0201, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.765432098765432, | |
| "eval_loss": 0.018415603786706924, | |
| "eval_runtime": 25.9199, | |
| "eval_samples_per_second": 1.736, | |
| "eval_steps_per_second": 1.736, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.8049382716049385, | |
| "grad_norm": 0.04011939465999603, | |
| "learning_rate": 4.7196477638140404e-05, | |
| "loss": 0.0161, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.8444444444444446, | |
| "grad_norm": 0.04298004135489464, | |
| "learning_rate": 4.579747375353763e-05, | |
| "loss": 0.0127, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.8839506172839506, | |
| "grad_norm": 0.042985718697309494, | |
| "learning_rate": 4.4401776194834613e-05, | |
| "loss": 0.018, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 2.9234567901234567, | |
| "grad_norm": 0.03870657458901405, | |
| "learning_rate": 4.3010483023225045e-05, | |
| "loss": 0.015, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 2.962962962962963, | |
| "grad_norm": 0.03830299526453018, | |
| "learning_rate": 4.162468883476319e-05, | |
| "loss": 0.016, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 3.0024691358024693, | |
| "grad_norm": 0.08254650980234146, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.026, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 3.0419753086419754, | |
| "grad_norm": 0.04306948184967041, | |
| "learning_rate": 3.887395330218429e-05, | |
| "loss": 0.014, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 3.0814814814814815, | |
| "grad_norm": 0.04832775145769119, | |
| "learning_rate": 3.7511176091638653e-05, | |
| "loss": 0.0152, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 3.1209876543209876, | |
| "grad_norm": 0.03881710395216942, | |
| "learning_rate": 3.6158224428757535e-05, | |
| "loss": 0.0157, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 3.1604938271604937, | |
| "grad_norm": 0.05051282048225403, | |
| "learning_rate": 3.4816162744519263e-05, | |
| "loss": 0.0171, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.1604938271604937, | |
| "eval_loss": 0.01797771453857422, | |
| "eval_runtime": 25.9324, | |
| "eval_samples_per_second": 1.735, | |
| "eval_steps_per_second": 1.735, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "grad_norm": 0.03627981245517731, | |
| "learning_rate": 3.3486046902241664e-05, | |
| "loss": 0.01, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 3.2395061728395063, | |
| "grad_norm": 0.030452217906713486, | |
| "learning_rate": 3.216892336688435e-05, | |
| "loss": 0.0126, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 3.2790123456790123, | |
| "grad_norm": 0.04779364913702011, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0143, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 3.3185185185185184, | |
| "grad_norm": 0.04842763394117355, | |
| "learning_rate": 2.9577787153200197e-05, | |
| "loss": 0.0149, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 3.3580246913580245, | |
| "grad_norm": 0.040973685681819916, | |
| "learning_rate": 2.8305813044122097e-05, | |
| "loss": 0.0112, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 3.397530864197531, | |
| "grad_norm": 0.045584630221128464, | |
| "learning_rate": 2.705090677662311e-05, | |
| "loss": 0.0175, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 3.437037037037037, | |
| "grad_norm": 0.04598742723464966, | |
| "learning_rate": 2.581405564473801e-05, | |
| "loss": 0.0158, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 3.476543209876543, | |
| "grad_norm": 0.04630625247955322, | |
| "learning_rate": 2.459623273767354e-05, | |
| "loss": 0.0118, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 3.5160493827160493, | |
| "grad_norm": 0.04400630295276642, | |
| "learning_rate": 2.3398396174233178e-05, | |
| "loss": 0.0146, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "grad_norm": 0.05139096826314926, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0153, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "eval_loss": 0.01771390251815319, | |
| "eval_runtime": 25.9448, | |
| "eval_samples_per_second": 1.734, | |
| "eval_steps_per_second": 1.734, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.595061728395062, | |
| "grad_norm": 0.05596518516540527, | |
| "learning_rate": 2.1066435191009715e-05, | |
| "loss": 0.0166, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 3.634567901234568, | |
| "grad_norm": 0.036661356687545776, | |
| "learning_rate": 1.9934145435079702e-05, | |
| "loss": 0.0144, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 3.674074074074074, | |
| "grad_norm": 0.04676743596792221, | |
| "learning_rate": 1.8825509907063327e-05, | |
| "loss": 0.0129, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 3.71358024691358, | |
| "grad_norm": 0.04297291487455368, | |
| "learning_rate": 1.774140082289563e-05, | |
| "loss": 0.0141, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 3.753086419753086, | |
| "grad_norm": 0.04279183968901634, | |
| "learning_rate": 1.6682671102399805e-05, | |
| "loss": 0.0157, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 3.7925925925925927, | |
| "grad_norm": 0.047029346227645874, | |
| "learning_rate": 1.5650153698254916e-05, | |
| "loss": 0.0127, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 3.832098765432099, | |
| "grad_norm": 0.04095562919974327, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0127, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 3.871604938271605, | |
| "grad_norm": 0.043043311685323715, | |
| "learning_rate": 1.3666983898298657e-05, | |
| "loss": 0.018, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 3.911111111111111, | |
| "grad_norm": 0.04111286997795105, | |
| "learning_rate": 1.2717891755841722e-05, | |
| "loss": 0.014, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 3.950617283950617, | |
| "grad_norm": 0.04209229722619057, | |
| "learning_rate": 1.1798131208919627e-05, | |
| "loss": 0.0131, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.950617283950617, | |
| "eval_loss": 0.017345581203699112, | |
| "eval_runtime": 25.965, | |
| "eval_samples_per_second": 1.733, | |
| "eval_steps_per_second": 1.733, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.9901234567901236, | |
| "grad_norm": 0.05126246437430382, | |
| "learning_rate": 1.090842587659851e-05, | |
| "loss": 0.0169, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 4.029629629629629, | |
| "grad_norm": 0.09892018884420395, | |
| "learning_rate": 1.004947573208756e-05, | |
| "loss": 0.0245, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 4.069135802469136, | |
| "grad_norm": 0.0428558811545372, | |
| "learning_rate": 9.221956552036992e-06, | |
| "loss": 0.0129, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 4.108641975308642, | |
| "grad_norm": 0.039242979139089584, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0125, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 4.148148148148148, | |
| "grad_norm": 0.033157072961330414, | |
| "learning_rate": 7.663790038585793e-06, | |
| "loss": 0.0138, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 4.187654320987654, | |
| "grad_norm": 0.03438961133360863, | |
| "learning_rate": 6.934368588379553e-06, | |
| "loss": 0.01, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 4.22716049382716, | |
| "grad_norm": 0.03627100959420204, | |
| "learning_rate": 6.238828904562316e-06, | |
| "loss": 0.0139, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 4.266666666666667, | |
| "grad_norm": 0.041909441351890564, | |
| "learning_rate": 5.577718201056392e-06, | |
| "loss": 0.0126, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 4.306172839506173, | |
| "grad_norm": 0.0378437265753746, | |
| "learning_rate": 4.951556604879048e-06, | |
| "loss": 0.0133, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 4.345679012345679, | |
| "grad_norm": 0.046722784638404846, | |
| "learning_rate": 4.360836746934055e-06, | |
| "loss": 0.0143, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.345679012345679, | |
| "eval_loss": 0.017259059473872185, | |
| "eval_runtime": 25.9839, | |
| "eval_samples_per_second": 1.732, | |
| "eval_steps_per_second": 1.732, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.385185185185185, | |
| "grad_norm": 0.04061531275510788, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0126, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 4.424691358024692, | |
| "grad_norm": 0.026830753311514854, | |
| "learning_rate": 3.2875529852700147e-06, | |
| "loss": 0.0095, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 4.4641975308641975, | |
| "grad_norm": 0.03643717244267464, | |
| "learning_rate": 2.8058334845816213e-06, | |
| "loss": 0.0131, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 4.503703703703704, | |
| "grad_norm": 0.0387725755572319, | |
| "learning_rate": 2.361243863855184e-06, | |
| "loss": 0.0142, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 4.54320987654321, | |
| "grad_norm": 0.03656044602394104, | |
| "learning_rate": 1.9541339027450256e-06, | |
| "loss": 0.0151, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 4.582716049382716, | |
| "grad_norm": 0.04029763862490654, | |
| "learning_rate": 1.584823893886933e-06, | |
| "loss": 0.0149, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 4.622222222222222, | |
| "grad_norm": 0.04136398807168007, | |
| "learning_rate": 1.2536043909088191e-06, | |
| "loss": 0.0125, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 4.661728395061728, | |
| "grad_norm": 0.044925201684236526, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0143, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 4.701234567901235, | |
| "grad_norm": 0.03622278571128845, | |
| "learning_rate": 7.064490740882057e-07, | |
| "loss": 0.0138, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 4.7407407407407405, | |
| "grad_norm": 0.04068191349506378, | |
| "learning_rate": 4.909437331777179e-07, | |
| "loss": 0.0156, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.7407407407407405, | |
| "eval_loss": 0.01722303405404091, | |
| "eval_runtime": 26.004, | |
| "eval_samples_per_second": 1.731, | |
| "eval_steps_per_second": 1.731, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.780246913580247, | |
| "grad_norm": 0.04049716144800186, | |
| "learning_rate": 3.143895053378698e-07, | |
| "loss": 0.0132, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 4.8197530864197535, | |
| "grad_norm": 0.0428626723587513, | |
| "learning_rate": 1.7692529411904578e-07, | |
| "loss": 0.0144, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 4.859259259259259, | |
| "grad_norm": 0.042141228914260864, | |
| "learning_rate": 7.865924910916977e-08, | |
| "loss": 0.0143, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 4.898765432098766, | |
| "grad_norm": 0.048777248710393906, | |
| "learning_rate": 1.9668680847356735e-08, | |
| "loss": 0.0147, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "grad_norm": 0.03597211092710495, | |
| "learning_rate": 0.0, | |
| "loss": 0.0127, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "step": 125, | |
| "total_flos": 1.8817065711747072e+17, | |
| "train_loss": 0.03361496642231941, | |
| "train_runtime": 5228.875, | |
| "train_samples_per_second": 0.387, | |
| "train_steps_per_second": 0.024 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 125, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.8817065711747072e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |