| { | |
| "best_metric": 1.043031096458435, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.16339869281045752, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0032679738562091504, | |
| "grad_norm": 0.24469198286533356, | |
| "learning_rate": 1e-05, | |
| "loss": 1.4387, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0032679738562091504, | |
| "eval_loss": 1.4474108219146729, | |
| "eval_runtime": 12.294, | |
| "eval_samples_per_second": 41.89, | |
| "eval_steps_per_second": 10.493, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006535947712418301, | |
| "grad_norm": 0.2529772222042084, | |
| "learning_rate": 2e-05, | |
| "loss": 1.4012, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00980392156862745, | |
| "grad_norm": 0.26472678780555725, | |
| "learning_rate": 3e-05, | |
| "loss": 1.3954, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.013071895424836602, | |
| "grad_norm": 0.2510676681995392, | |
| "learning_rate": 4e-05, | |
| "loss": 1.3832, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.016339869281045753, | |
| "grad_norm": 0.2522083818912506, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0196078431372549, | |
| "grad_norm": 0.23163741827011108, | |
| "learning_rate": 6e-05, | |
| "loss": 1.383, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02287581699346405, | |
| "grad_norm": 0.24272429943084717, | |
| "learning_rate": 7e-05, | |
| "loss": 1.3874, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.026143790849673203, | |
| "grad_norm": 0.22741547226905823, | |
| "learning_rate": 8e-05, | |
| "loss": 1.3295, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.029411764705882353, | |
| "grad_norm": 0.21041825413703918, | |
| "learning_rate": 9e-05, | |
| "loss": 1.316, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.032679738562091505, | |
| "grad_norm": 0.19392521679401398, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2768, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03594771241830065, | |
| "grad_norm": 0.20608149468898773, | |
| "learning_rate": 9.999316524962345e-05, | |
| "loss": 1.2882, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0392156862745098, | |
| "grad_norm": 0.22623692452907562, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 1.2364, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.042483660130718956, | |
| "grad_norm": 0.26282697916030884, | |
| "learning_rate": 9.993849845741524e-05, | |
| "loss": 1.211, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0457516339869281, | |
| "grad_norm": 0.270076185464859, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 1.2835, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.049019607843137254, | |
| "grad_norm": 0.21397562325000763, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 1.2031, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05228758169934641, | |
| "grad_norm": 0.1848316192626953, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 1.1504, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05555555555555555, | |
| "grad_norm": 0.16563019156455994, | |
| "learning_rate": 9.966546331768191e-05, | |
| "loss": 1.1845, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.058823529411764705, | |
| "grad_norm": 0.17262709140777588, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 1.16, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.06209150326797386, | |
| "grad_norm": 0.16582638025283813, | |
| "learning_rate": 9.944739353007344e-05, | |
| "loss": 1.1903, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06535947712418301, | |
| "grad_norm": 0.15873746573925018, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 1.1438, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06862745098039216, | |
| "grad_norm": 0.17037732899188995, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 1.1243, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0718954248366013, | |
| "grad_norm": 0.16108785569667816, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 1.1485, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.07516339869281045, | |
| "grad_norm": 0.1587645560503006, | |
| "learning_rate": 9.884934153917997e-05, | |
| "loss": 1.1659, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0784313725490196, | |
| "grad_norm": 0.1613873392343521, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 1.1371, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.08169934640522876, | |
| "grad_norm": 0.14722518622875214, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 1.0705, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08496732026143791, | |
| "grad_norm": 0.14173099398612976, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 1.0695, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.08823529411764706, | |
| "grad_norm": 0.1377929449081421, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 1.1012, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0915032679738562, | |
| "grad_norm": 0.1335737556219101, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 1.076, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.09477124183006536, | |
| "grad_norm": 0.14067432284355164, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 1.0406, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.09803921568627451, | |
| "grad_norm": 0.1369902640581131, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 1.0285, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.10130718954248366, | |
| "grad_norm": 0.14028145372867584, | |
| "learning_rate": 9.701596950580806e-05, | |
| "loss": 1.0766, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.10457516339869281, | |
| "grad_norm": 0.1419658660888672, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 1.0549, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.10784313725490197, | |
| "grad_norm": 0.1403641402721405, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 1.1028, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1111111111111111, | |
| "grad_norm": 0.1402372419834137, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 1.0423, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.11437908496732026, | |
| "grad_norm": 0.1409500241279602, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 1.0762, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.11764705882352941, | |
| "grad_norm": 0.14114561676979065, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 1.0346, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.12091503267973856, | |
| "grad_norm": 0.12877798080444336, | |
| "learning_rate": 9.509956150664796e-05, | |
| "loss": 1.0531, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.12418300653594772, | |
| "grad_norm": 0.13515013456344604, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 0.9911, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.12745098039215685, | |
| "grad_norm": 0.1338815987110138, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 1.048, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.13071895424836602, | |
| "grad_norm": 0.1321924328804016, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 1.0316, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.13398692810457516, | |
| "grad_norm": 0.13545972108840942, | |
| "learning_rate": 9.357421218136386e-05, | |
| "loss": 1.0201, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.13725490196078433, | |
| "grad_norm": 0.1455843299627304, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 1.0314, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.14052287581699346, | |
| "grad_norm": 0.14777617156505585, | |
| "learning_rate": 9.273963562927695e-05, | |
| "loss": 1.0812, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.1437908496732026, | |
| "grad_norm": 0.1442340612411499, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 1.0044, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.14705882352941177, | |
| "grad_norm": 0.142796590924263, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 1.0788, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1503267973856209, | |
| "grad_norm": 0.14356712996959686, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 0.9699, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.15359477124183007, | |
| "grad_norm": 0.15727904438972473, | |
| "learning_rate": 9.093124073433463e-05, | |
| "loss": 1.103, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.1568627450980392, | |
| "grad_norm": 0.15104670822620392, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.991, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.16013071895424835, | |
| "grad_norm": 0.1587590128183365, | |
| "learning_rate": 8.995939984474624e-05, | |
| "loss": 0.9936, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.16339869281045752, | |
| "grad_norm": 0.3971143960952759, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 1.0333, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.16339869281045752, | |
| "eval_loss": 1.043031096458435, | |
| "eval_runtime": 12.3483, | |
| "eval_samples_per_second": 41.706, | |
| "eval_steps_per_second": 10.447, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.226560015171584e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |