| { | |
| "best_metric": 2.6709249019622803, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 2.3952095808383236, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04790419161676647, | |
| "grad_norm": 72.69557189941406, | |
| "learning_rate": 5e-05, | |
| "loss": 110.774, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04790419161676647, | |
| "eval_loss": 6.629335403442383, | |
| "eval_runtime": 4.7098, | |
| "eval_samples_per_second": 10.616, | |
| "eval_steps_per_second": 2.76, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.09580838323353294, | |
| "grad_norm": 77.63043975830078, | |
| "learning_rate": 0.0001, | |
| "loss": 132.2435, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.1437125748502994, | |
| "grad_norm": 61.427513122558594, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 110.0578, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.19161676646706588, | |
| "grad_norm": 58.1811408996582, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 73.205, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.23952095808383234, | |
| "grad_norm": 49.155845642089844, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 69.1511, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2874251497005988, | |
| "grad_norm": 69.05171966552734, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 81.67, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.33532934131736525, | |
| "grad_norm": 65.2494125366211, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 81.5417, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.38323353293413176, | |
| "grad_norm": 44.927223205566406, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 77.4983, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.4311377245508982, | |
| "grad_norm": 49.93047332763672, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 50.0204, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.47904191616766467, | |
| "grad_norm": 24.84800910949707, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 47.9566, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5269461077844312, | |
| "grad_norm": 32.10044479370117, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 61.4778, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.5748502994011976, | |
| "grad_norm": 33.61887741088867, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 60.2869, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.6227544910179641, | |
| "grad_norm": 33.13056564331055, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 57.6085, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.6706586826347305, | |
| "grad_norm": 31.026601791381836, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 46.9569, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.718562874251497, | |
| "grad_norm": 24.52080726623535, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 48.4615, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.7664670658682635, | |
| "grad_norm": 22.692081451416016, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 51.3721, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.8143712574850299, | |
| "grad_norm": 24.40343475341797, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 56.1307, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.8622754491017964, | |
| "grad_norm": 18.565412521362305, | |
| "learning_rate": 7.75e-05, | |
| "loss": 49.8746, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.9101796407185628, | |
| "grad_norm": 19.204238891601562, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 47.3317, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.9580838323353293, | |
| "grad_norm": 15.976109504699707, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 48.1495, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.0059880239520957, | |
| "grad_norm": 14.779011726379395, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 47.8621, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.0538922155688624, | |
| "grad_norm": 15.715991973876953, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 46.5982, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.1017964071856288, | |
| "grad_norm": 18.653337478637695, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 48.7768, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.1497005988023952, | |
| "grad_norm": 16.096193313598633, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 49.1443, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.1976047904191618, | |
| "grad_norm": 12.494379043579102, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 41.1292, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.1976047904191618, | |
| "eval_loss": 2.79341983795166, | |
| "eval_runtime": 4.5515, | |
| "eval_samples_per_second": 10.985, | |
| "eval_steps_per_second": 2.856, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.2455089820359282, | |
| "grad_norm": 13.066014289855957, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 43.7104, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.2934131736526946, | |
| "grad_norm": 15.47722053527832, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 42.2966, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.341317365269461, | |
| "grad_norm": 18.106525421142578, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 47.1484, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.3892215568862276, | |
| "grad_norm": 17.03740692138672, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 42.2896, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.437125748502994, | |
| "grad_norm": 15.306708335876465, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 41.9534, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.4850299401197604, | |
| "grad_norm": 14.26751708984375, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 45.2017, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.532934131736527, | |
| "grad_norm": 17.206789016723633, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 43.9349, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.5808383233532934, | |
| "grad_norm": 18.50804901123047, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 45.4069, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.6287425149700598, | |
| "grad_norm": 20.458311080932617, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 44.5455, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.6766467065868262, | |
| "grad_norm": 15.671262741088867, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 42.9807, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.7245508982035929, | |
| "grad_norm": 14.376961708068848, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 45.5037, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.7724550898203593, | |
| "grad_norm": 15.421966552734375, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 42.4266, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.8203592814371259, | |
| "grad_norm": 21.55309295654297, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 48.5389, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.8682634730538923, | |
| "grad_norm": 15.796401977539062, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 41.4078, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.9161676646706587, | |
| "grad_norm": 16.036413192749023, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 42.5856, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.964071856287425, | |
| "grad_norm": 14.152937889099121, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 39.9044, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.0119760479041915, | |
| "grad_norm": 15.67934513092041, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 43.7522, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.059880239520958, | |
| "grad_norm": 15.741512298583984, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 39.6389, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.1077844311377247, | |
| "grad_norm": 17.636999130249023, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 41.9672, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.155688622754491, | |
| "grad_norm": 20.343563079833984, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 43.9301, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.2035928143712575, | |
| "grad_norm": 15.532905578613281, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 41.1395, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.251497005988024, | |
| "grad_norm": 14.655294418334961, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 38.4739, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.2994011976047903, | |
| "grad_norm": 16.103124618530273, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 38.3927, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.3473053892215567, | |
| "grad_norm": 20.670578002929688, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 43.2779, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.3952095808383236, | |
| "grad_norm": 15.122425079345703, | |
| "learning_rate": 1e-05, | |
| "loss": 40.8576, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.3952095808383236, | |
| "eval_loss": 2.6709249019622803, | |
| "eval_runtime": 4.9264, | |
| "eval_samples_per_second": 10.149, | |
| "eval_steps_per_second": 2.639, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 7.875509431335649e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |