| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 392, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002551020408163265, | |
| "grad_norm": 14000.175878727785, | |
| "learning_rate": 7.499999999999999e-06, | |
| "loss": 48.0695, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012755102040816327, | |
| "grad_norm": 3007.3104608903254, | |
| "learning_rate": 3.75e-05, | |
| "loss": 32.7037, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.025510204081632654, | |
| "grad_norm": 4753.9239460531635, | |
| "learning_rate": 7.5e-05, | |
| "loss": 27.6128, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03826530612244898, | |
| "grad_norm": 7672.954437161885, | |
| "learning_rate": 0.0001125, | |
| "loss": 118.424, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05102040816326531, | |
| "grad_norm": 2658.2281406370403, | |
| "learning_rate": 0.00015, | |
| "loss": 36.7995, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06377551020408163, | |
| "grad_norm": 301.82927722978826, | |
| "learning_rate": 0.00018749999999999998, | |
| "loss": 25.8987, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07653061224489796, | |
| "grad_norm": 261.2743806851815, | |
| "learning_rate": 0.000225, | |
| "loss": 19.7068, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08928571428571429, | |
| "grad_norm": 170.80865284544745, | |
| "learning_rate": 0.0002625, | |
| "loss": 16.2639, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.10204081632653061, | |
| "grad_norm": 371.9839372489695, | |
| "learning_rate": 0.0003, | |
| "loss": 14.8666, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11479591836734694, | |
| "grad_norm": 55.46043538057413, | |
| "learning_rate": 0.00029985067118498503, | |
| "loss": 13.883, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.12755102040816327, | |
| "grad_norm": 61.65936269712346, | |
| "learning_rate": 0.00029940298206120687, | |
| "loss": 11.3142, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.14030612244897958, | |
| "grad_norm": 49.78316202658068, | |
| "learning_rate": 0.0002986578240004834, | |
| "loss": 10.2446, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.15306122448979592, | |
| "grad_norm": 95.22883433955214, | |
| "learning_rate": 0.0002976166806504174, | |
| "loss": 9.2125, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.16581632653061223, | |
| "grad_norm": 87.6593544514716, | |
| "learning_rate": 0.00029628162498037856, | |
| "loss": 8.0024, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.17857142857142858, | |
| "grad_norm": 29.457366532379673, | |
| "learning_rate": 0.000294655315154116, | |
| "loss": 7.0794, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.1913265306122449, | |
| "grad_norm": 23.54866864598235, | |
| "learning_rate": 0.0002927409892372191, | |
| "loss": 6.428, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.20408163265306123, | |
| "grad_norm": 14.487277559435018, | |
| "learning_rate": 0.00029054245874996426, | |
| "loss": 6.0644, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.21683673469387754, | |
| "grad_norm": 11.612016698553127, | |
| "learning_rate": 0.00028806410107838377, | |
| "loss": 5.9737, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.22959183673469388, | |
| "grad_norm": 22.24847439069348, | |
| "learning_rate": 0.00028531085075866815, | |
| "loss": 5.6293, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.2423469387755102, | |
| "grad_norm": 25.32273350126865, | |
| "learning_rate": 0.0002822881896522532, | |
| "loss": 5.4368, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.25510204081632654, | |
| "grad_norm": 29.73658242449881, | |
| "learning_rate": 0.000279002136031155, | |
| "loss": 5.2007, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.26785714285714285, | |
| "grad_norm": 17.009329865460675, | |
| "learning_rate": 0.0002754592325952845, | |
| "loss": 4.9784, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.28061224489795916, | |
| "grad_norm": 17.65449666930728, | |
| "learning_rate": 0.00027166653344559883, | |
| "loss": 5.1761, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.29336734693877553, | |
| "grad_norm": 25.60749450078011, | |
| "learning_rate": 0.0002676315900390278, | |
| "loss": 4.981, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.30612244897959184, | |
| "grad_norm": 19.37666875758449, | |
| "learning_rate": 0.00026336243615313873, | |
| "loss": 4.883, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.31887755102040816, | |
| "grad_norm": 25.223445103235044, | |
| "learning_rate": 0.00025886757189047695, | |
| "loss": 4.6906, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.33163265306122447, | |
| "grad_norm": 24.827221258799884, | |
| "learning_rate": 0.0002541559467544291, | |
| "loss": 4.5962, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.34438775510204084, | |
| "grad_norm": 19.172749908950284, | |
| "learning_rate": 0.00024923694183030657, | |
| "loss": 4.4971, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.35714285714285715, | |
| "grad_norm": 17.803290735515485, | |
| "learning_rate": 0.0002441203511071278, | |
| "loss": 4.3923, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.36989795918367346, | |
| "grad_norm": 15.152588588737128, | |
| "learning_rate": 0.00023881636197728743, | |
| "loss": 4.2507, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.3826530612244898, | |
| "grad_norm": 28.266308285286772, | |
| "learning_rate": 0.0002333355349529403, | |
| "loss": 4.1071, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.39540816326530615, | |
| "grad_norm": 13.058293075351123, | |
| "learning_rate": 0.00022768878263948445, | |
| "loss": 4.0515, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.40816326530612246, | |
| "grad_norm": 14.87484760188348, | |
| "learning_rate": 0.00022188734800800852, | |
| "loss": 3.9059, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.42091836734693877, | |
| "grad_norm": 12.57655967452742, | |
| "learning_rate": 0.00021594278200996457, | |
| "loss": 3.876, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.4336734693877551, | |
| "grad_norm": 18.644576504823885, | |
| "learning_rate": 0.00020986692057863607, | |
| "loss": 3.703, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.44642857142857145, | |
| "grad_norm": 6.3705323701789265, | |
| "learning_rate": 0.000203671861063193, | |
| "loss": 3.6606, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.45918367346938777, | |
| "grad_norm": 9.945740907460738, | |
| "learning_rate": 0.00019736993814225374, | |
| "loss": 3.6781, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.4719387755102041, | |
| "grad_norm": 5.28597104720817, | |
| "learning_rate": 0.00019097369926491297, | |
| "loss": 3.5963, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.4846938775510204, | |
| "grad_norm": 5.570474507029548, | |
| "learning_rate": 0.00018449587966813208, | |
| "loss": 3.5206, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.49744897959183676, | |
| "grad_norm": 5.769299754282368, | |
| "learning_rate": 0.00017794937702023467, | |
| "loss": 3.3751, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.5102040816326531, | |
| "grad_norm": 7.514106159557929, | |
| "learning_rate": 0.00017134722574099276, | |
| "loss": 3.3315, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5229591836734694, | |
| "grad_norm": 5.467040990097222, | |
| "learning_rate": 0.0001647025710494341, | |
| "loss": 3.2297, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.5357142857142857, | |
| "grad_norm": 7.752282985206345, | |
| "learning_rate": 0.00015802864279104223, | |
| "loss": 3.1714, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.548469387755102, | |
| "grad_norm": 4.902568385413757, | |
| "learning_rate": 0.0001513387290964616, | |
| "loss": 3.076, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.5612244897959183, | |
| "grad_norm": 8.809433652257214, | |
| "learning_rate": 0.00014464614992415294, | |
| "loss": 3.0378, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5739795918367347, | |
| "grad_norm": 5.62075198192736, | |
| "learning_rate": 0.00013796423053967887, | |
| "loss": 2.946, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.5867346938775511, | |
| "grad_norm": 7.091999165572766, | |
| "learning_rate": 0.0001313062749844221, | |
| "loss": 2.9117, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5994897959183674, | |
| "grad_norm": 9.664621289964327, | |
| "learning_rate": 0.00012468553958656264, | |
| "loss": 2.7779, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.6122448979591837, | |
| "grad_norm": 8.079291607422778, | |
| "learning_rate": 0.00011811520656705348, | |
| "loss": 2.7627, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.625, | |
| "grad_norm": 9.132106023308898, | |
| "learning_rate": 0.00011160835779314889, | |
| "loss": 2.7464, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.6377551020408163, | |
| "grad_norm": 12.688497775305251, | |
| "learning_rate": 0.00010517794873174064, | |
| "loss": 2.6784, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.6505102040816326, | |
| "grad_norm": 7.508821446542865, | |
| "learning_rate": 9.883678265436473e-05, | |
| "loss": 2.6542, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.6632653061224489, | |
| "grad_norm": 7.288150995036509, | |
| "learning_rate": 9.259748514523653e-05, | |
| "loss": 2.5675, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.6760204081632653, | |
| "grad_norm": 2.598306498532322, | |
| "learning_rate": 8.647247896307018e-05, | |
| "loss": 2.5179, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.6887755102040817, | |
| "grad_norm": 2.9340097554582947, | |
| "learning_rate": 8.047395930673417e-05, | |
| "loss": 2.4673, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.701530612244898, | |
| "grad_norm": 3.520741961544552, | |
| "learning_rate": 7.46138695339903e-05, | |
| "loss": 2.5285, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.7142857142857143, | |
| "grad_norm": 4.635037745202294, | |
| "learning_rate": 6.890387738166041e-05, | |
| "loss": 2.3872, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.7270408163265306, | |
| "grad_norm": 3.987422126482862, | |
| "learning_rate": 6.335535173456914e-05, | |
| "loss": 2.3409, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.7397959183673469, | |
| "grad_norm": 3.0549621746230122, | |
| "learning_rate": 5.79793399895161e-05, | |
| "loss": 2.3254, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.7525510204081632, | |
| "grad_norm": 2.527266957929868, | |
| "learning_rate": 5.278654605934644e-05, | |
| "loss": 2.3429, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.7653061224489796, | |
| "grad_norm": 3.9761126497464083, | |
| "learning_rate": 4.778730906091632e-05, | |
| "loss": 2.2348, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7780612244897959, | |
| "grad_norm": 2.498797778043332, | |
| "learning_rate": 4.2991582729385174e-05, | |
| "loss": 2.2421, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.7908163265306123, | |
| "grad_norm": 2.5462712929101894, | |
| "learning_rate": 3.840891559982256e-05, | |
| "loss": 2.2751, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.8035714285714286, | |
| "grad_norm": 2.307072702085812, | |
| "learning_rate": 3.404843199558945e-05, | |
| "loss": 2.1867, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.8163265306122449, | |
| "grad_norm": 5.263562323908358, | |
| "learning_rate": 2.9918813861345952e-05, | |
| "loss": 2.181, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.8290816326530612, | |
| "grad_norm": 2.0011040214883575, | |
| "learning_rate": 2.6028283476858038e-05, | |
| "loss": 2.1732, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.8418367346938775, | |
| "grad_norm": 2.2471501177416116, | |
| "learning_rate": 2.238458708602039e-05, | |
| "loss": 2.1108, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.8545918367346939, | |
| "grad_norm": 1.66846134386125, | |
| "learning_rate": 1.8994979473690537e-05, | |
| "loss": 2.1007, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.8673469387755102, | |
| "grad_norm": 2.0450866177774976, | |
| "learning_rate": 1.5866209521043304e-05, | |
| "loss": 2.0334, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.8801020408163265, | |
| "grad_norm": 2.1608778408402807, | |
| "learning_rate": 1.3004506768205226e-05, | |
| "loss": 2.0735, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.8928571428571429, | |
| "grad_norm": 2.1504307790627912, | |
| "learning_rate": 1.0415569010922963e-05, | |
| "loss": 2.0473, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.9056122448979592, | |
| "grad_norm": 1.6880900496760922, | |
| "learning_rate": 8.104550955962469e-06, | |
| "loss": 2.029, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.9183673469387755, | |
| "grad_norm": 1.7900392749998477, | |
| "learning_rate": 6.076053957825411e-06, | |
| "loss": 2.0533, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.9311224489795918, | |
| "grad_norm": 1.5178075882516209, | |
| "learning_rate": 4.334116857218317e-06, | |
| "loss": 1.9693, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.9438775510204082, | |
| "grad_norm": 1.6874487405997367, | |
| "learning_rate": 2.882207939515435e-06, | |
| "loss": 1.9791, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.9566326530612245, | |
| "grad_norm": 1.4244094850155935, | |
| "learning_rate": 1.7232180292259369e-06, | |
| "loss": 1.9566, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.9693877551020408, | |
| "grad_norm": 1.302432101303747, | |
| "learning_rate": 8.594547342153979e-07, | |
| "loss": 1.9451, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.9821428571428571, | |
| "grad_norm": 1.2049628347309629, | |
| "learning_rate": 2.926378511411198e-07, | |
| "loss": 1.9952, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.9948979591836735, | |
| "grad_norm": 1.2981702353996074, | |
| "learning_rate": 2.3895941249507665e-08, | |
| "loss": 1.9687, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 6.496990203857422, | |
| "eval_runtime": 2.5179, | |
| "eval_samples_per_second": 3.972, | |
| "eval_steps_per_second": 0.397, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 392, | |
| "total_flos": 13478110691328.0, | |
| "train_loss": 7.205524507833987, | |
| "train_runtime": 9216.1272, | |
| "train_samples_per_second": 1.36, | |
| "train_steps_per_second": 0.043 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 392, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 13478110691328.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |