| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.154178674351585, | |
| "eval_steps": 17, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005763688760806916, | |
| "eval_loss": NaN, | |
| "eval_runtime": 30.5345, | |
| "eval_samples_per_second": 9.596, | |
| "eval_steps_per_second": 1.212, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01729106628242075, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0345821325648415, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.05187319884726225, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.069164265129683, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.08645533141210375, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.09798270893371758, | |
| "eval_loss": NaN, | |
| "eval_runtime": 30.6108, | |
| "eval_samples_per_second": 9.572, | |
| "eval_steps_per_second": 1.209, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1037463976945245, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.12103746397694524, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.138328530259366, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.15561959654178675, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.1729106628242075, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.19020172910662825, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.19596541786743515, | |
| "eval_loss": NaN, | |
| "eval_runtime": 30.6305, | |
| "eval_samples_per_second": 9.566, | |
| "eval_steps_per_second": 1.208, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.207492795389049, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.22478386167146974, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.2420749279538905, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.25936599423631124, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.276657060518732, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.29394812680115273, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.894386393810563e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.29394812680115273, | |
| "eval_loss": NaN, | |
| "eval_runtime": 30.6247, | |
| "eval_samples_per_second": 9.567, | |
| "eval_steps_per_second": 1.208, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.3112391930835735, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.73410738492077e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.3285302593659942, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.564642241456986e-05, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.345821325648415, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.3631123919308357, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.199842702516583e-05, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.3804034582132565, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.005405736415126e-05, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.3919308357348703, | |
| "eval_loss": NaN, | |
| "eval_runtime": 30.6117, | |
| "eval_samples_per_second": 9.572, | |
| "eval_steps_per_second": 1.209, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.3976945244956772, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.803575286758364e-05, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.414985590778098, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.594847868906076e-05, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.4322766570605187, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.379736965185368e-05, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.4495677233429395, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.158771761692464e-05, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.4668587896253602, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.932495846462261e-05, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.484149855907781, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.701465872208216e-05, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.4899135446685879, | |
| "eval_loss": NaN, | |
| "eval_runtime": 30.6702, | |
| "eval_samples_per_second": 9.553, | |
| "eval_steps_per_second": 1.206, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.5014409221902018, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.466250186922325e-05, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.5187319884726225, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.227427435703997e-05, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.5360230547550432, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.985585137257401e-05, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.553314121037464, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.74131823855921e-05, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.5706051873198847, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.495227651252315e-05, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.5878962536023055, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.247918773366112e-05, | |
| "loss": 0.0, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.5878962536023055, | |
| "eval_loss": NaN, | |
| "eval_runtime": 30.6375, | |
| "eval_samples_per_second": 9.563, | |
| "eval_steps_per_second": 1.208, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.6051873198847262, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.622478386167147, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.7520812266338885e-05, | |
| "loss": 0.0, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.6397694524495677, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.504772348747687e-05, | |
| "loss": 0.0, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.6570605187319885, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2586817614407895e-05, | |
| "loss": 0.0, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.6743515850144092, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.0144148627425993e-05, | |
| "loss": 0.0, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.6858789625360231, | |
| "eval_loss": NaN, | |
| "eval_runtime": 30.6161, | |
| "eval_samples_per_second": 9.57, | |
| "eval_steps_per_second": 1.209, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.69164265129683, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.772572564296005e-05, | |
| "loss": 0.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.7089337175792507, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.533749813077677e-05, | |
| "loss": 0.0, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.7262247838616714, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.298534127791785e-05, | |
| "loss": 0.0, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.7435158501440923, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0675041535377405e-05, | |
| "loss": 0.0, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.760806916426513, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8412282383075363e-05, | |
| "loss": 0.0, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.7780979827089337, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6202630348146324e-05, | |
| "loss": 0.0, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.7838616714697406, | |
| "eval_loss": NaN, | |
| "eval_runtime": 30.6227, | |
| "eval_samples_per_second": 9.568, | |
| "eval_steps_per_second": 1.208, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.7953890489913544, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.405152131093926e-05, | |
| "loss": 0.0, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.8126801152737753, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.196424713241637e-05, | |
| "loss": 0.0, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.829971181556196, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9945942635848748e-05, | |
| "loss": 0.0, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.8472622478386167, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.800157297483417e-05, | |
| "loss": 0.0, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.8645533141210374, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6135921418712956e-05, | |
| "loss": 0.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.8818443804034583, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.435357758543015e-05, | |
| "loss": 0.0, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.8818443804034583, | |
| "eval_loss": NaN, | |
| "eval_runtime": 30.6493, | |
| "eval_samples_per_second": 9.56, | |
| "eval_steps_per_second": 1.207, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.899135446685879, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2658926150792322e-05, | |
| "loss": 0.0, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.9164265129682997, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1056136061894384e-05, | |
| "loss": 0.0, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.9337175792507204, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.0, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.9510086455331412, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.141676086873572e-06, | |
| "loss": 0.0, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.968299711815562, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.837175952121306e-06, | |
| "loss": 0.0, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.9798270893371758, | |
| "eval_loss": NaN, | |
| "eval_runtime": 30.6354, | |
| "eval_samples_per_second": 9.564, | |
| "eval_steps_per_second": 1.208, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.9855907780979827, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.6388590278194096e-06, | |
| "loss": 0.0, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 1.0043227665706052, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.549673247541875e-06, | |
| "loss": 0.0, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 1.021613832853026, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5722980755146517e-06, | |
| "loss": 0.0, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 1.0389048991354466, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7091379149682685e-06, | |
| "loss": 0.0, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.0561959654178674, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.962316193157593e-06, | |
| "loss": 0.0, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 1.0734870317002883, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.333670137599713e-06, | |
| "loss": 0.0, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 1.079250720461095, | |
| "eval_loss": NaN, | |
| "eval_runtime": 30.6268, | |
| "eval_samples_per_second": 9.567, | |
| "eval_steps_per_second": 1.208, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 1.0907780979827089, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.247462563808817e-07, | |
| "loss": 0.0, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 1.1080691642651297, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.367965336512403e-07, | |
| "loss": 0.0, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 1.1253602305475505, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7077534966650766e-07, | |
| "loss": 0.0, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 1.1426512968299711, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7337132953697554e-08, | |
| "loss": 0.0, | |
| "step": 198 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 17, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.6824360568160256e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |