| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.4981467753891772, | |
| "eval_steps": 28, | |
| "global_step": 56, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008895478131949592, | |
| "grad_norm": 2.962439156483445, | |
| "learning_rate": 4.5454545454545457e-07, | |
| "loss": 1.8805, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008895478131949592, | |
| "eval_loss": 2.7425005435943604, | |
| "eval_runtime": 5.0857, | |
| "eval_samples_per_second": 14.354, | |
| "eval_steps_per_second": 2.556, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.017790956263899184, | |
| "grad_norm": 2.7396320345650156, | |
| "learning_rate": 9.090909090909091e-07, | |
| "loss": 1.8922, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.026686434395848776, | |
| "grad_norm": 2.8238110399477696, | |
| "learning_rate": 1.3636363636363636e-06, | |
| "loss": 1.8672, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03558191252779837, | |
| "grad_norm": 2.825892310577778, | |
| "learning_rate": 1.8181818181818183e-06, | |
| "loss": 1.9474, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04447739065974796, | |
| "grad_norm": 2.9182980055251515, | |
| "learning_rate": 2.2727272727272728e-06, | |
| "loss": 1.8873, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05337286879169755, | |
| "grad_norm": 1.825111219165535, | |
| "learning_rate": 2.7272727272727272e-06, | |
| "loss": 1.8892, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06226834692364715, | |
| "grad_norm": 1.603886963757723, | |
| "learning_rate": 3.181818181818182e-06, | |
| "loss": 1.8928, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.07116382505559674, | |
| "grad_norm": 1.9982114208239075, | |
| "learning_rate": 3.6363636363636366e-06, | |
| "loss": 1.8816, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.08005930318754632, | |
| "grad_norm": 2.2210111384360443, | |
| "learning_rate": 4.0909090909090915e-06, | |
| "loss": 1.814, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08895478131949593, | |
| "grad_norm": 1.8833804876805869, | |
| "learning_rate": 4.5454545454545455e-06, | |
| "loss": 1.8789, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09785025945144551, | |
| "grad_norm": 2.1696360746306986, | |
| "learning_rate": 5e-06, | |
| "loss": 1.8948, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1067457375833951, | |
| "grad_norm": 1.9189154524725964, | |
| "learning_rate": 5.4545454545454545e-06, | |
| "loss": 1.8899, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1156412157153447, | |
| "grad_norm": 1.5982373309558937, | |
| "learning_rate": 5.90909090909091e-06, | |
| "loss": 1.935, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1245366938472943, | |
| "grad_norm": 1.2867259496282597, | |
| "learning_rate": 6.363636363636364e-06, | |
| "loss": 1.8012, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.1334321719792439, | |
| "grad_norm": 1.3487164419710964, | |
| "learning_rate": 6.818181818181818e-06, | |
| "loss": 1.8439, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.14232765011119347, | |
| "grad_norm": 1.4367061847474465, | |
| "learning_rate": 7.272727272727273e-06, | |
| "loss": 1.8463, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.15122312824314307, | |
| "grad_norm": 1.3999547484681398, | |
| "learning_rate": 7.727272727272727e-06, | |
| "loss": 1.8302, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.16011860637509265, | |
| "grad_norm": 1.0580202838750912, | |
| "learning_rate": 8.181818181818183e-06, | |
| "loss": 1.8602, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.16901408450704225, | |
| "grad_norm": 1.0918338120114914, | |
| "learning_rate": 8.636363636363637e-06, | |
| "loss": 1.7858, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.17790956263899185, | |
| "grad_norm": 1.0275858730350056, | |
| "learning_rate": 9.090909090909091e-06, | |
| "loss": 1.8628, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.18680504077094143, | |
| "grad_norm": 1.061639393901565, | |
| "learning_rate": 9.545454545454547e-06, | |
| "loss": 1.8227, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.19570051890289103, | |
| "grad_norm": 0.9240081464912561, | |
| "learning_rate": 1e-05, | |
| "loss": 1.7978, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.20459599703484063, | |
| "grad_norm": 0.9652630279266269, | |
| "learning_rate": 9.999395316300748e-06, | |
| "loss": 1.7734, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2134914751667902, | |
| "grad_norm": 0.9039339352165564, | |
| "learning_rate": 9.99758141145994e-06, | |
| "loss": 1.849, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2223869532987398, | |
| "grad_norm": 0.9643956642662512, | |
| "learning_rate": 9.994558724213056e-06, | |
| "loss": 1.825, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2312824314306894, | |
| "grad_norm": 0.9167678356949895, | |
| "learning_rate": 9.990327985667972e-06, | |
| "loss": 1.7981, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.24017790956263899, | |
| "grad_norm": 0.8874816186232574, | |
| "learning_rate": 9.984890219128148e-06, | |
| "loss": 1.7821, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.2490733876945886, | |
| "grad_norm": 0.8787539356844203, | |
| "learning_rate": 9.978246739845095e-06, | |
| "loss": 1.7985, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.2490733876945886, | |
| "eval_loss": 2.290811777114868, | |
| "eval_runtime": 4.938, | |
| "eval_samples_per_second": 14.783, | |
| "eval_steps_per_second": 2.633, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.25796886582653816, | |
| "grad_norm": 0.838340542158105, | |
| "learning_rate": 9.970399154700264e-06, | |
| "loss": 1.7882, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.2668643439584878, | |
| "grad_norm": 0.8285328505624969, | |
| "learning_rate": 9.961349361816384e-06, | |
| "loss": 1.8555, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.27575982209043737, | |
| "grad_norm": 0.9331640421116788, | |
| "learning_rate": 9.951099550098349e-06, | |
| "loss": 1.7626, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.28465530022238694, | |
| "grad_norm": 0.7822775533301098, | |
| "learning_rate": 9.939652198703785e-06, | |
| "loss": 1.7815, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.2935507783543366, | |
| "grad_norm": 0.8091655666026496, | |
| "learning_rate": 9.927010076443408e-06, | |
| "loss": 1.7973, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.30244625648628615, | |
| "grad_norm": 0.8067559509453439, | |
| "learning_rate": 9.91317624111132e-06, | |
| "loss": 1.7843, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.3113417346182357, | |
| "grad_norm": 0.791639209925201, | |
| "learning_rate": 9.898154038745408e-06, | |
| "loss": 1.8203, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3202372127501853, | |
| "grad_norm": 0.8397439084797836, | |
| "learning_rate": 9.881947102818036e-06, | |
| "loss": 1.7982, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.3291326908821349, | |
| "grad_norm": 0.8069438258809916, | |
| "learning_rate": 9.864559353357189e-06, | |
| "loss": 1.7751, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.3380281690140845, | |
| "grad_norm": 0.8901339589432326, | |
| "learning_rate": 9.845994995998332e-06, | |
| "loss": 1.8393, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.3469236471460341, | |
| "grad_norm": 0.7778163619401842, | |
| "learning_rate": 9.826258520967178e-06, | |
| "loss": 1.6691, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.3558191252779837, | |
| "grad_norm": 0.8503632973674836, | |
| "learning_rate": 9.805354701993624e-06, | |
| "loss": 1.8385, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3647146034099333, | |
| "grad_norm": 0.8510317916033313, | |
| "learning_rate": 9.7832885951571e-06, | |
| "loss": 1.7921, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.37361008154188285, | |
| "grad_norm": 0.8242453476305008, | |
| "learning_rate": 9.76006553766365e-06, | |
| "loss": 1.7588, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.3825055596738325, | |
| "grad_norm": 0.8490334887805663, | |
| "learning_rate": 9.735691146555002e-06, | |
| "loss": 1.7596, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.39140103780578206, | |
| "grad_norm": 0.940027149340783, | |
| "learning_rate": 9.710171317349946e-06, | |
| "loss": 1.7265, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.40029651593773163, | |
| "grad_norm": 0.7800160596846283, | |
| "learning_rate": 9.683512222618376e-06, | |
| "loss": 1.8351, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.40919199406968126, | |
| "grad_norm": 0.8750191358059531, | |
| "learning_rate": 9.655720310488298e-06, | |
| "loss": 1.7463, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.41808747220163084, | |
| "grad_norm": 0.7890987028235364, | |
| "learning_rate": 9.62680230308621e-06, | |
| "loss": 1.7175, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.4269829503335804, | |
| "grad_norm": 0.9776075848478134, | |
| "learning_rate": 9.596765194911182e-06, | |
| "loss": 1.7658, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.43587842846553004, | |
| "grad_norm": 0.8025568758744139, | |
| "learning_rate": 9.565616251143094e-06, | |
| "loss": 1.7425, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.4447739065974796, | |
| "grad_norm": 0.8932281966392491, | |
| "learning_rate": 9.533363005885362e-06, | |
| "loss": 1.7751, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4536693847294292, | |
| "grad_norm": 0.8459501071139652, | |
| "learning_rate": 9.50001326034265e-06, | |
| "loss": 1.7298, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.4625648628613788, | |
| "grad_norm": 0.7921546527189047, | |
| "learning_rate": 9.465575080933959e-06, | |
| "loss": 1.7313, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.4714603409933284, | |
| "grad_norm": 0.8367967581956659, | |
| "learning_rate": 9.430056797341574e-06, | |
| "loss": 1.7492, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.48035581912527797, | |
| "grad_norm": 0.7931936215221228, | |
| "learning_rate": 9.393467000496345e-06, | |
| "loss": 1.7865, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.4892512972572276, | |
| "grad_norm": 0.984751704749124, | |
| "learning_rate": 9.355814540499753e-06, | |
| "loss": 1.7336, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.4981467753891772, | |
| "grad_norm": 0.8227951034631744, | |
| "learning_rate": 9.317108524483319e-06, | |
| "loss": 1.727, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.4981467753891772, | |
| "eval_loss": 2.1942620277404785, | |
| "eval_runtime": 4.9502, | |
| "eval_samples_per_second": 14.747, | |
| "eval_steps_per_second": 2.626, | |
| "step": 56 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 224, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 56, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.161627769254707e+16, | |
| "train_batch_size": 3, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |