| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.020617848183911207, | |
| "eval_steps": 500, | |
| "global_step": 300, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00048108312429126146, | |
| "grad_norm": 8.154312133789062, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 1.8456, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0009621662485825229, | |
| "grad_norm": 2.8053348064422607, | |
| "learning_rate": 8.666666666666668e-06, | |
| "loss": 1.0127, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0014432493728737843, | |
| "grad_norm": 5.31929349899292, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 0.791, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0019243324971650458, | |
| "grad_norm": 5.091348171234131, | |
| "learning_rate": 1.8e-05, | |
| "loss": 0.8497, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.002405415621456307, | |
| "grad_norm": 3.4551076889038086, | |
| "learning_rate": 2.2666666666666668e-05, | |
| "loss": 0.5847, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0028864987457475687, | |
| "grad_norm": 2.0914766788482666, | |
| "learning_rate": 2.733333333333333e-05, | |
| "loss": 0.6838, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.00336758187003883, | |
| "grad_norm": 4.122292518615723, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 0.5328, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0038486649943300917, | |
| "grad_norm": 4.441967964172363, | |
| "learning_rate": 3.6666666666666666e-05, | |
| "loss": 0.7609, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.004329748118621354, | |
| "grad_norm": 2.408400535583496, | |
| "learning_rate": 4.133333333333333e-05, | |
| "loss": 0.7353, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.004810831242912614, | |
| "grad_norm": 4.386236190795898, | |
| "learning_rate": 4.600000000000001e-05, | |
| "loss": 0.5822, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.005291914367203876, | |
| "grad_norm": 2.6810431480407715, | |
| "learning_rate": 5.0666666666666674e-05, | |
| "loss": 0.5084, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.005772997491495137, | |
| "grad_norm": 10.199173927307129, | |
| "learning_rate": 5.5333333333333334e-05, | |
| "loss": 1.0656, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.006254080615786399, | |
| "grad_norm": 2.62958025932312, | |
| "learning_rate": 6e-05, | |
| "loss": 0.9499, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.00673516374007766, | |
| "grad_norm": 3.928619861602783, | |
| "learning_rate": 6.466666666666666e-05, | |
| "loss": 0.7763, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.007216246864368922, | |
| "grad_norm": 7.499195098876953, | |
| "learning_rate": 6.933333333333334e-05, | |
| "loss": 1.0431, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.007697329988660183, | |
| "grad_norm": 1.4210686683654785, | |
| "learning_rate": 7.4e-05, | |
| "loss": 0.5441, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.008178413112951446, | |
| "grad_norm": 3.6974828243255615, | |
| "learning_rate": 7.866666666666666e-05, | |
| "loss": 0.6841, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.008659496237242707, | |
| "grad_norm": 7.652034282684326, | |
| "learning_rate": 8.333333333333334e-05, | |
| "loss": 0.8487, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.009140579361533967, | |
| "grad_norm": 11.174522399902344, | |
| "learning_rate": 8.800000000000001e-05, | |
| "loss": 0.9727, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.009621662485825229, | |
| "grad_norm": 11.040456771850586, | |
| "learning_rate": 9.266666666666666e-05, | |
| "loss": 1.122, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.01010274561011649, | |
| "grad_norm": 8.87497329711914, | |
| "learning_rate": 9.733333333333335e-05, | |
| "loss": 1.4102, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.010583828734407752, | |
| "grad_norm": 9.45786190032959, | |
| "learning_rate": 9.999878153526974e-05, | |
| "loss": 1.2933, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.011064911858699013, | |
| "grad_norm": 8.866625785827637, | |
| "learning_rate": 9.998646205897309e-05, | |
| "loss": 1.2747, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.011545994982990275, | |
| "grad_norm": 6.202242374420166, | |
| "learning_rate": 9.996087868740243e-05, | |
| "loss": 1.7031, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.012027078107281536, | |
| "grad_norm": 10.355546951293945, | |
| "learning_rate": 9.992203820909906e-05, | |
| "loss": 1.8137, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.012508161231572798, | |
| "grad_norm": 8.716798782348633, | |
| "learning_rate": 9.986995093037421e-05, | |
| "loss": 1.2634, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.01298924435586406, | |
| "grad_norm": 11.727725982666016, | |
| "learning_rate": 9.980463067257437e-05, | |
| "loss": 0.8589, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.01347032748015532, | |
| "grad_norm": 7.918148517608643, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 1.4014, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.013951410604446582, | |
| "grad_norm": 28.750410079956055, | |
| "learning_rate": 9.963436405737476e-05, | |
| "loss": 1.2997, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.014432493728737844, | |
| "grad_norm": 15.347841262817383, | |
| "learning_rate": 9.952946288017899e-05, | |
| "loss": 1.766, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.014913576853029105, | |
| "grad_norm": 7.8105950355529785, | |
| "learning_rate": 9.941141907232765e-05, | |
| "loss": 1.4616, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.015394659977320367, | |
| "grad_norm": 16.68589973449707, | |
| "learning_rate": 9.928026395671576e-05, | |
| "loss": 1.0106, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.01587574310161163, | |
| "grad_norm": 14.563543319702148, | |
| "learning_rate": 9.913603233532067e-05, | |
| "loss": 1.2966, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.01635682622590289, | |
| "grad_norm": 11.76324462890625, | |
| "learning_rate": 9.89787624799672e-05, | |
| "loss": 1.4801, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.016837909350194153, | |
| "grad_norm": 10.999220848083496, | |
| "learning_rate": 9.880849612217238e-05, | |
| "loss": 1.7505, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.017318992474485415, | |
| "grad_norm": 17.89532470703125, | |
| "learning_rate": 9.862527844207189e-05, | |
| "loss": 0.8774, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.017800075598776673, | |
| "grad_norm": 7.980606555938721, | |
| "learning_rate": 9.842915805643155e-05, | |
| "loss": 1.7281, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 0.018281158723067934, | |
| "grad_norm": 17.765323638916016, | |
| "learning_rate": 9.822018700574695e-05, | |
| "loss": 1.2403, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 0.018762241847359196, | |
| "grad_norm": 18.817676544189453, | |
| "learning_rate": 9.799842074043439e-05, | |
| "loss": 1.6112, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 0.019243324971650457, | |
| "grad_norm": 15.211094856262207, | |
| "learning_rate": 9.776391810611718e-05, | |
| "loss": 0.784, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.01972440809594172, | |
| "grad_norm": 13.791271209716797, | |
| "learning_rate": 9.751674132801107e-05, | |
| "loss": 1.5379, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 0.02020549122023298, | |
| "grad_norm": 12.567949295043945, | |
| "learning_rate": 9.725695599441258e-05, | |
| "loss": 1.7221, | |
| "step": 294 | |
| } | |
| ], | |
| "logging_steps": 7, | |
| "max_steps": 1500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 300, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.29657334448128e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |