| { | |
| "best_metric": 0.6329964995384216, | |
| "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": 4.860265731811523, | |
| "learning_rate": 1e-05, | |
| "loss": 2.2642, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0071301247771836, | |
| "eval_loss": 3.368955373764038, | |
| "eval_runtime": 17.5564, | |
| "eval_samples_per_second": 13.442, | |
| "eval_steps_per_second": 3.361, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0142602495543672, | |
| "grad_norm": 4.241779327392578, | |
| "learning_rate": 2e-05, | |
| "loss": 2.4353, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0213903743315508, | |
| "grad_norm": 5.996744632720947, | |
| "learning_rate": 3e-05, | |
| "loss": 2.4873, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0285204991087344, | |
| "grad_norm": 4.913257122039795, | |
| "learning_rate": 4e-05, | |
| "loss": 2.3505, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.035650623885918005, | |
| "grad_norm": 3.3362646102905273, | |
| "learning_rate": 5e-05, | |
| "loss": 2.137, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0427807486631016, | |
| "grad_norm": 3.666640281677246, | |
| "learning_rate": 6e-05, | |
| "loss": 1.7876, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.049910873440285206, | |
| "grad_norm": 6.828310012817383, | |
| "learning_rate": 7e-05, | |
| "loss": 1.755, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0570409982174688, | |
| "grad_norm": 7.097423553466797, | |
| "learning_rate": 8e-05, | |
| "loss": 1.853, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.06417112299465241, | |
| "grad_norm": 5.807572364807129, | |
| "learning_rate": 9e-05, | |
| "loss": 1.7299, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.07130124777183601, | |
| "grad_norm": 4.308953285217285, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1758, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0784313725490196, | |
| "grad_norm": 8.310755729675293, | |
| "learning_rate": 9.999316524962345e-05, | |
| "loss": 1.5666, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0855614973262032, | |
| "grad_norm": 4.563036918640137, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 1.3147, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.09269162210338681, | |
| "grad_norm": 5.149623394012451, | |
| "learning_rate": 9.993849845741524e-05, | |
| "loss": 1.0886, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.09982174688057041, | |
| "grad_norm": 5.882086753845215, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 1.386, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.10695187165775401, | |
| "grad_norm": 12.239624977111816, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 1.2012, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1140819964349376, | |
| "grad_norm": 7.540602207183838, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 1.2995, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.12121212121212122, | |
| "grad_norm": 5.4989423751831055, | |
| "learning_rate": 9.966546331768191e-05, | |
| "loss": 1.1511, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.12834224598930483, | |
| "grad_norm": 6.216000556945801, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 0.8327, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1354723707664884, | |
| "grad_norm": 4.877588748931885, | |
| "learning_rate": 9.944739353007344e-05, | |
| "loss": 0.6784, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.14260249554367202, | |
| "grad_norm": 10.093413352966309, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 2.0459, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1497326203208556, | |
| "grad_norm": 7.529651165008545, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 1.4024, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1568627450980392, | |
| "grad_norm": 15.220786094665527, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 1.3263, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.16399286987522282, | |
| "grad_norm": 9.120606422424316, | |
| "learning_rate": 9.884934153917997e-05, | |
| "loss": 1.2663, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.1711229946524064, | |
| "grad_norm": 7.058254718780518, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 1.3212, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.17825311942959002, | |
| "grad_norm": 9.098106384277344, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 1.6655, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.18538324420677363, | |
| "grad_norm": 6.505765914916992, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 1.1041, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.1925133689839572, | |
| "grad_norm": 3.545391321182251, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 0.7916, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.19964349376114082, | |
| "grad_norm": 4.667784214019775, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 0.8798, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.20677361853832443, | |
| "grad_norm": 15.075148582458496, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 1.6309, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.21390374331550802, | |
| "grad_norm": 16.655683517456055, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 1.8559, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.22103386809269163, | |
| "grad_norm": 7.557066440582275, | |
| "learning_rate": 9.701596950580806e-05, | |
| "loss": 1.3669, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.2281639928698752, | |
| "grad_norm": 16.793487548828125, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 2.2009, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.23529411764705882, | |
| "grad_norm": 7.860363483428955, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 1.2864, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.24242424242424243, | |
| "grad_norm": 6.455472946166992, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 1.0194, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.24955436720142601, | |
| "grad_norm": 5.507026672363281, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 0.7551, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.25668449197860965, | |
| "grad_norm": 17.20283317565918, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 2.9312, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.2638146167557932, | |
| "grad_norm": 14.8767728805542, | |
| "learning_rate": 9.509956150664796e-05, | |
| "loss": 2.2403, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.2709447415329768, | |
| "grad_norm": 9.64128303527832, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 1.6086, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.27807486631016043, | |
| "grad_norm": 4.818795680999756, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 0.8585, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.28520499108734404, | |
| "grad_norm": 3.329906940460205, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 0.6471, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.29233511586452765, | |
| "grad_norm": 3.4146223068237305, | |
| "learning_rate": 9.357421218136386e-05, | |
| "loss": 0.5584, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.2994652406417112, | |
| "grad_norm": 2.892646551132202, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 0.541, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.3065953654188948, | |
| "grad_norm": 6.643548488616943, | |
| "learning_rate": 9.273963562927695e-05, | |
| "loss": 0.7923, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.3137254901960784, | |
| "grad_norm": 3.204444646835327, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 0.5552, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.32085561497326204, | |
| "grad_norm": 2.1902480125427246, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 0.373, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.32798573975044565, | |
| "grad_norm": 3.2742395401000977, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 0.5669, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.33511586452762926, | |
| "grad_norm": 2.8352434635162354, | |
| "learning_rate": 9.093124073433463e-05, | |
| "loss": 0.5118, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.3422459893048128, | |
| "grad_norm": 3.1886863708496094, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.4386, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3493761140819964, | |
| "grad_norm": 2.8913755416870117, | |
| "learning_rate": 8.995939984474624e-05, | |
| "loss": 0.2077, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.35650623885918004, | |
| "grad_norm": 4.413907527923584, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 0.2928, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.35650623885918004, | |
| "eval_loss": 0.6329964995384216, | |
| "eval_runtime": 17.9761, | |
| "eval_samples_per_second": 13.129, | |
| "eval_steps_per_second": 3.282, | |
| "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 | |
| } | |