| { | |
| "best_metric": 11.929637908935547, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-75", | |
| "epoch": 0.6417112299465241, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008556149732620321, | |
| "grad_norm": 0.009288904257118702, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 11.9327, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008556149732620321, | |
| "eval_loss": 11.932464599609375, | |
| "eval_runtime": 0.3021, | |
| "eval_samples_per_second": 165.526, | |
| "eval_steps_per_second": 43.037, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.017112299465240642, | |
| "grad_norm": 0.010134869255125523, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 11.933, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.025668449197860963, | |
| "grad_norm": 0.010271006263792515, | |
| "learning_rate": 0.0001, | |
| "loss": 11.933, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.034224598930481284, | |
| "grad_norm": 0.009835214354097843, | |
| "learning_rate": 9.99571699711836e-05, | |
| "loss": 11.9322, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0427807486631016, | |
| "grad_norm": 0.009670325554907322, | |
| "learning_rate": 9.982876141412856e-05, | |
| "loss": 11.9327, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.051336898395721926, | |
| "grad_norm": 0.011487636715173721, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 11.9314, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.059893048128342244, | |
| "grad_norm": 0.010688673704862595, | |
| "learning_rate": 9.931634888554937e-05, | |
| "loss": 11.931, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.06844919786096257, | |
| "grad_norm": 0.013804799877107143, | |
| "learning_rate": 9.893332032039701e-05, | |
| "loss": 11.9308, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.07700534759358289, | |
| "grad_norm": 0.015089892782270908, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 11.9296, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0855614973262032, | |
| "grad_norm": 0.017095373943448067, | |
| "learning_rate": 9.791726278367022e-05, | |
| "loss": 11.9317, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09411764705882353, | |
| "grad_norm": 0.01961982436478138, | |
| "learning_rate": 9.728616793536588e-05, | |
| "loss": 11.9299, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.10267379679144385, | |
| "grad_norm": 0.024940676987171173, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 11.9306, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.11122994652406418, | |
| "grad_norm": 0.008828448131680489, | |
| "learning_rate": 9.578385041664925e-05, | |
| "loss": 11.9322, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.11978609625668449, | |
| "grad_norm": 0.008848758414387703, | |
| "learning_rate": 9.491548749301997e-05, | |
| "loss": 11.9324, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.12834224598930483, | |
| "grad_norm": 0.008904277347028255, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 11.9322, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.13689839572192514, | |
| "grad_norm": 0.00932358205318451, | |
| "learning_rate": 9.295261506157986e-05, | |
| "loss": 11.9328, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.14545454545454545, | |
| "grad_norm": 0.010712096467614174, | |
| "learning_rate": 9.186184199300464e-05, | |
| "loss": 11.9316, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.15401069518716579, | |
| "grad_norm": 0.01194374542683363, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 11.9323, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1625668449197861, | |
| "grad_norm": 0.011681217700242996, | |
| "learning_rate": 8.947199994035401e-05, | |
| "loss": 11.9319, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.1711229946524064, | |
| "grad_norm": 0.014581509865820408, | |
| "learning_rate": 8.817748015645558e-05, | |
| "loss": 11.9319, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.17967914438502675, | |
| "grad_norm": 0.014579634182155132, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 11.9313, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.18823529411764706, | |
| "grad_norm": 0.021312598139047623, | |
| "learning_rate": 8.540155934270471e-05, | |
| "loss": 11.9307, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.19679144385026737, | |
| "grad_norm": 0.0245517548173666, | |
| "learning_rate": 8.392544243589427e-05, | |
| "loss": 11.9313, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2053475935828877, | |
| "grad_norm": 0.030098047107458115, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 11.9298, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.21390374331550802, | |
| "grad_norm": 0.044641703367233276, | |
| "learning_rate": 8.081093963579707e-05, | |
| "loss": 11.9284, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.21390374331550802, | |
| "eval_loss": 11.931540489196777, | |
| "eval_runtime": 0.2821, | |
| "eval_samples_per_second": 177.232, | |
| "eval_steps_per_second": 46.08, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.22245989304812835, | |
| "grad_norm": 0.014012838713824749, | |
| "learning_rate": 7.917848237560709e-05, | |
| "loss": 11.9322, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.23101604278074866, | |
| "grad_norm": 0.013886277563869953, | |
| "learning_rate": 7.75e-05, | |
| "loss": 11.932, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.23957219251336898, | |
| "grad_norm": 0.014223024249076843, | |
| "learning_rate": 7.577868759557654e-05, | |
| "loss": 11.9318, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.24812834224598931, | |
| "grad_norm": 0.017355216667056084, | |
| "learning_rate": 7.401782177833148e-05, | |
| "loss": 11.9315, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.25668449197860965, | |
| "grad_norm": 0.016897931694984436, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 11.9319, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.26524064171122996, | |
| "grad_norm": 0.021244890987873077, | |
| "learning_rate": 7.03909064496551e-05, | |
| "loss": 11.9316, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.2737967914438503, | |
| "grad_norm": 0.025067226961255074, | |
| "learning_rate": 6.853176097769229e-05, | |
| "loss": 11.9318, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.2823529411764706, | |
| "grad_norm": 0.024520905688405037, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 11.9305, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.2909090909090909, | |
| "grad_norm": 0.02878713048994541, | |
| "learning_rate": 6.473978262721463e-05, | |
| "loss": 11.9313, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.2994652406417112, | |
| "grad_norm": 0.02808881178498268, | |
| "learning_rate": 6.281416799501188e-05, | |
| "loss": 11.9304, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.30802139037433157, | |
| "grad_norm": 0.04868848994374275, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 11.9279, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.3165775401069519, | |
| "grad_norm": 0.05509665235877037, | |
| "learning_rate": 5.8922008423644624e-05, | |
| "loss": 11.9273, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.3251336898395722, | |
| "grad_norm": 0.02182912267744541, | |
| "learning_rate": 5.696287243144013e-05, | |
| "loss": 11.9315, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.3336898395721925, | |
| "grad_norm": 0.022058000788092613, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 11.9315, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.3422459893048128, | |
| "grad_norm": 0.023784028366208076, | |
| "learning_rate": 5.303712756855988e-05, | |
| "loss": 11.9312, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3508021390374332, | |
| "grad_norm": 0.025254419073462486, | |
| "learning_rate": 5.107799157635538e-05, | |
| "loss": 11.9313, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.3593582887700535, | |
| "grad_norm": 0.026260606944561005, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 11.9319, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.3679144385026738, | |
| "grad_norm": 0.032988063991069794, | |
| "learning_rate": 4.718583200498814e-05, | |
| "loss": 11.9318, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.3764705882352941, | |
| "grad_norm": 0.03395548462867737, | |
| "learning_rate": 4.526021737278538e-05, | |
| "loss": 11.9308, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.3850267379679144, | |
| "grad_norm": 0.02984875999391079, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 11.9305, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.39358288770053473, | |
| "grad_norm": 0.044708915054798126, | |
| "learning_rate": 4.146823902230772e-05, | |
| "loss": 11.9295, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.4021390374331551, | |
| "grad_norm": 0.04110679030418396, | |
| "learning_rate": 3.960909355034491e-05, | |
| "loss": 11.9314, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.4106951871657754, | |
| "grad_norm": 0.05050275847315788, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 11.9294, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.4192513368983957, | |
| "grad_norm": 0.06777117401361465, | |
| "learning_rate": 3.598217822166854e-05, | |
| "loss": 11.93, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.42780748663101603, | |
| "grad_norm": 0.07418351620435715, | |
| "learning_rate": 3.422131240442349e-05, | |
| "loss": 11.9268, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.42780748663101603, | |
| "eval_loss": 11.930290222167969, | |
| "eval_runtime": 0.3001, | |
| "eval_samples_per_second": 166.609, | |
| "eval_steps_per_second": 43.318, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.43636363636363634, | |
| "grad_norm": 0.030816154554486275, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 11.9314, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.4449197860962567, | |
| "grad_norm": 0.029961062595248222, | |
| "learning_rate": 3.082151762439293e-05, | |
| "loss": 11.9309, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.453475935828877, | |
| "grad_norm": 0.03276418522000313, | |
| "learning_rate": 2.9189060364202943e-05, | |
| "loss": 11.931, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.46203208556149733, | |
| "grad_norm": 0.03670096769928932, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 11.9305, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.47058823529411764, | |
| "grad_norm": 0.03524468466639519, | |
| "learning_rate": 2.6074557564105727e-05, | |
| "loss": 11.9306, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.47914438502673795, | |
| "grad_norm": 0.03465661406517029, | |
| "learning_rate": 2.459844065729529e-05, | |
| "loss": 11.9299, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.48770053475935826, | |
| "grad_norm": 0.03583734482526779, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 11.93, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.49625668449197863, | |
| "grad_norm": 0.04339265450835228, | |
| "learning_rate": 2.1822519843544424e-05, | |
| "loss": 11.9287, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.5048128342245989, | |
| "grad_norm": 0.05683796480298042, | |
| "learning_rate": 2.0528000059645997e-05, | |
| "loss": 11.9283, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.5133689839572193, | |
| "grad_norm": 0.05965341255068779, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 11.9289, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5219251336898396, | |
| "grad_norm": 0.07276409864425659, | |
| "learning_rate": 1.8138158006995364e-05, | |
| "loss": 11.9283, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.5304812834224599, | |
| "grad_norm": 0.08142941445112228, | |
| "learning_rate": 1.7047384938420154e-05, | |
| "loss": 11.9266, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.5390374331550802, | |
| "grad_norm": 0.03713444247841835, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 11.9308, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.5475935828877005, | |
| "grad_norm": 0.03590025380253792, | |
| "learning_rate": 1.5084512506980026e-05, | |
| "loss": 11.9305, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.5561497326203209, | |
| "grad_norm": 0.03694842755794525, | |
| "learning_rate": 1.4216149583350754e-05, | |
| "loss": 11.9306, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.5647058823529412, | |
| "grad_norm": 0.03804150968790054, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 11.9306, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.5732620320855615, | |
| "grad_norm": 0.03732200339436531, | |
| "learning_rate": 1.2713832064634126e-05, | |
| "loss": 11.9306, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.5818181818181818, | |
| "grad_norm": 0.03894832730293274, | |
| "learning_rate": 1.2082737216329794e-05, | |
| "loss": 11.9305, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.5903743315508021, | |
| "grad_norm": 0.046566810458898544, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 11.9297, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.5989304812834224, | |
| "grad_norm": 0.05046457797288895, | |
| "learning_rate": 1.1066679679603e-05, | |
| "loss": 11.9285, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6074866310160428, | |
| "grad_norm": 0.053379662334918976, | |
| "learning_rate": 1.0683651114450641e-05, | |
| "loss": 11.9297, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.6160427807486631, | |
| "grad_norm": 0.0545305497944355, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 11.9284, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.6245989304812835, | |
| "grad_norm": 0.05352730304002762, | |
| "learning_rate": 1.017123858587145e-05, | |
| "loss": 11.9282, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.6331550802139038, | |
| "grad_norm": 0.06697743386030197, | |
| "learning_rate": 1.00428300288164e-05, | |
| "loss": 11.9294, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.6417112299465241, | |
| "grad_norm": 0.09596454352140427, | |
| "learning_rate": 1e-05, | |
| "loss": 11.9246, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.6417112299465241, | |
| "eval_loss": 11.929637908935547, | |
| "eval_runtime": 0.2899, | |
| "eval_samples_per_second": 172.451, | |
| "eval_steps_per_second": 44.837, | |
| "step": 75 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1563741388800.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |