| { | |
| "best_metric": 0.6693209409713745, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.35650623885918004, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0071301247771836, | |
| "grad_norm": 4.8426337242126465, | |
| "learning_rate": 1e-05, | |
| "loss": 2.2642, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0071301247771836, | |
| "eval_loss": 3.368955373764038, | |
| "eval_runtime": 17.4805, | |
| "eval_samples_per_second": 13.501, | |
| "eval_steps_per_second": 3.375, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0142602495543672, | |
| "grad_norm": 4.2209672927856445, | |
| "learning_rate": 2e-05, | |
| "loss": 2.4353, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0213903743315508, | |
| "grad_norm": 5.881971836090088, | |
| "learning_rate": 3e-05, | |
| "loss": 2.4871, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0285204991087344, | |
| "grad_norm": 4.883190155029297, | |
| "learning_rate": 4e-05, | |
| "loss": 2.3509, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.035650623885918005, | |
| "grad_norm": 3.3302810192108154, | |
| "learning_rate": 5e-05, | |
| "loss": 2.1371, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0427807486631016, | |
| "grad_norm": 3.647418737411499, | |
| "learning_rate": 6e-05, | |
| "loss": 1.785, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.049910873440285206, | |
| "grad_norm": 6.729278564453125, | |
| "learning_rate": 7e-05, | |
| "loss": 1.7518, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0570409982174688, | |
| "grad_norm": 7.104023456573486, | |
| "learning_rate": 8e-05, | |
| "loss": 1.846, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.06417112299465241, | |
| "grad_norm": 5.479939937591553, | |
| "learning_rate": 9e-05, | |
| "loss": 1.7269, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.07130124777183601, | |
| "grad_norm": 4.303497314453125, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1691, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0784313725490196, | |
| "grad_norm": 8.257266998291016, | |
| "learning_rate": 9.999316524962345e-05, | |
| "loss": 1.5674, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0855614973262032, | |
| "grad_norm": 4.5696797370910645, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 1.3183, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.09269162210338681, | |
| "grad_norm": 5.195154190063477, | |
| "learning_rate": 9.993849845741524e-05, | |
| "loss": 1.0984, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.09982174688057041, | |
| "grad_norm": 6.245325565338135, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 1.3965, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.10695187165775401, | |
| "grad_norm": 6.468475341796875, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 1.2189, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1140819964349376, | |
| "grad_norm": 7.070935249328613, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 1.2871, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.12121212121212122, | |
| "grad_norm": 5.198769569396973, | |
| "learning_rate": 9.966546331768191e-05, | |
| "loss": 1.1191, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.12834224598930483, | |
| "grad_norm": 4.482051849365234, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 0.8275, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1354723707664884, | |
| "grad_norm": 4.659496784210205, | |
| "learning_rate": 9.944739353007344e-05, | |
| "loss": 0.6453, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.14260249554367202, | |
| "grad_norm": 10.78939151763916, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 2.0706, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1497326203208556, | |
| "grad_norm": 7.3973164558410645, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 1.4084, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1568627450980392, | |
| "grad_norm": 15.801050186157227, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 1.3198, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.16399286987522282, | |
| "grad_norm": 13.212759017944336, | |
| "learning_rate": 9.884934153917997e-05, | |
| "loss": 1.3635, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.1711229946524064, | |
| "grad_norm": 8.838081359863281, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 1.4169, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.17825311942959002, | |
| "grad_norm": 8.929149627685547, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 1.7153, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.18538324420677363, | |
| "grad_norm": 6.735871315002441, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 1.1534, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.1925133689839572, | |
| "grad_norm": 3.1337316036224365, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 0.8431, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.19964349376114082, | |
| "grad_norm": 4.328713417053223, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 0.917, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.20677361853832443, | |
| "grad_norm": 17.148948669433594, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 1.551, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.21390374331550802, | |
| "grad_norm": 16.10226058959961, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 1.9147, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.22103386809269163, | |
| "grad_norm": 8.083459854125977, | |
| "learning_rate": 9.701596950580806e-05, | |
| "loss": 1.429, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.2281639928698752, | |
| "grad_norm": 18.02008819580078, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 2.2392, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.23529411764705882, | |
| "grad_norm": 9.912565231323242, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 1.2989, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.24242424242424243, | |
| "grad_norm": 7.664438247680664, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 0.9611, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.24955436720142601, | |
| "grad_norm": 7.64049768447876, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 0.8516, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.25668449197860965, | |
| "grad_norm": 17.550363540649414, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 2.9945, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.2638146167557932, | |
| "grad_norm": 13.104034423828125, | |
| "learning_rate": 9.509956150664796e-05, | |
| "loss": 2.3501, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.2709447415329768, | |
| "grad_norm": 9.25308895111084, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 1.6601, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.27807486631016043, | |
| "grad_norm": 4.239262104034424, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 0.8481, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.28520499108734404, | |
| "grad_norm": 2.5438952445983887, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 0.6431, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.29233511586452765, | |
| "grad_norm": 2.9467761516571045, | |
| "learning_rate": 9.357421218136386e-05, | |
| "loss": 0.5759, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.2994652406417112, | |
| "grad_norm": 2.582361936569214, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 0.555, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.3065953654188948, | |
| "grad_norm": 3.7745120525360107, | |
| "learning_rate": 9.273963562927695e-05, | |
| "loss": 0.6859, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.3137254901960784, | |
| "grad_norm": 2.906780481338501, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 0.5011, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.32085561497326204, | |
| "grad_norm": 2.0319948196411133, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 0.3182, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.32798573975044565, | |
| "grad_norm": 4.595136642456055, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 0.5804, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.33511586452762926, | |
| "grad_norm": 3.3042995929718018, | |
| "learning_rate": 9.093124073433463e-05, | |
| "loss": 0.5566, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.3422459893048128, | |
| "grad_norm": 2.7046265602111816, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.4686, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3493761140819964, | |
| "grad_norm": 2.852973222732544, | |
| "learning_rate": 8.995939984474624e-05, | |
| "loss": 0.206, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.35650623885918004, | |
| "grad_norm": 3.929203987121582, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 0.2773, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.35650623885918004, | |
| "eval_loss": 0.6693209409713745, | |
| "eval_runtime": 17.8065, | |
| "eval_samples_per_second": 13.254, | |
| "eval_steps_per_second": 3.313, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 7.54256789372928e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |