| { | |
| "best_metric": 0.3421801030635834, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.5151515151515151, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.030303030303030304, | |
| "grad_norm": 45.50777816772461, | |
| "learning_rate": 5e-05, | |
| "loss": 40.6014, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.030303030303030304, | |
| "eval_loss": 3.0981926918029785, | |
| "eval_runtime": 2.8779, | |
| "eval_samples_per_second": 17.374, | |
| "eval_steps_per_second": 4.517, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06060606060606061, | |
| "grad_norm": 44.33837127685547, | |
| "learning_rate": 0.0001, | |
| "loss": 42.2201, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.09090909090909091, | |
| "grad_norm": 41.29526138305664, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 42.4166, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.12121212121212122, | |
| "grad_norm": 32.975379943847656, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 39.2189, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.15151515151515152, | |
| "grad_norm": 27.534719467163086, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 34.6668, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.18181818181818182, | |
| "grad_norm": 28.966054916381836, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 31.13, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.21212121212121213, | |
| "grad_norm": 30.903053283691406, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 29.8711, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.24242424242424243, | |
| "grad_norm": 37.19826889038086, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 33.1635, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.2727272727272727, | |
| "grad_norm": 18.28540802001953, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 20.5149, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.30303030303030304, | |
| "grad_norm": 18.609952926635742, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 19.7805, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": 18.108304977416992, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 18.1504, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.36363636363636365, | |
| "grad_norm": 18.777435302734375, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 16.6851, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.3939393939393939, | |
| "grad_norm": 16.09988784790039, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 15.5709, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.42424242424242425, | |
| "grad_norm": 24.070369720458984, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 14.8605, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.45454545454545453, | |
| "grad_norm": 25.2645320892334, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 14.4109, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.48484848484848486, | |
| "grad_norm": 22.638652801513672, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 15.4409, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.5151515151515151, | |
| "grad_norm": 9.952996253967285, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 10.7666, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.5454545454545454, | |
| "grad_norm": 10.131386756896973, | |
| "learning_rate": 7.75e-05, | |
| "loss": 10.4648, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.5757575757575758, | |
| "grad_norm": 11.31190299987793, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 10.6267, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.6060606060606061, | |
| "grad_norm": 8.688138008117676, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 9.5293, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6363636363636364, | |
| "grad_norm": 9.379395484924316, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 9.7673, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 9.105935096740723, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 9.007, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.696969696969697, | |
| "grad_norm": 8.894107818603516, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 8.464, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "grad_norm": 15.59160041809082, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 9.3377, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.7575757575757576, | |
| "grad_norm": 9.485807418823242, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 7.1434, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.7575757575757576, | |
| "eval_loss": 0.5379838347434998, | |
| "eval_runtime": 2.9089, | |
| "eval_samples_per_second": 17.189, | |
| "eval_steps_per_second": 4.469, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.7878787878787878, | |
| "grad_norm": 7.8287858963012695, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 7.0069, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.8181818181818182, | |
| "grad_norm": 6.974181175231934, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 7.1145, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.8484848484848485, | |
| "grad_norm": 7.5937042236328125, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 7.1062, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.8787878787878788, | |
| "grad_norm": 7.260517120361328, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 6.4217, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.9090909090909091, | |
| "grad_norm": 8.329216003417969, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 6.5431, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.9393939393939394, | |
| "grad_norm": 10.283854484558105, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 6.9686, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.9696969696969697, | |
| "grad_norm": 14.778830528259277, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 7.7959, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 8.504195213317871, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 6.2998, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.0303030303030303, | |
| "grad_norm": 8.065375328063965, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 5.3917, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.0606060606060606, | |
| "grad_norm": 6.932098865509033, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 5.1002, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.0909090909090908, | |
| "grad_norm": 6.426107883453369, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 5.1781, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.121212121212121, | |
| "grad_norm": 6.368813514709473, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 5.3515, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.1515151515151516, | |
| "grad_norm": 7.844695091247559, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 5.2342, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.1818181818181819, | |
| "grad_norm": 6.590551853179932, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 4.9267, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.2121212121212122, | |
| "grad_norm": 7.364800930023193, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 4.9535, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.2424242424242424, | |
| "grad_norm": 9.986160278320312, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 5.5483, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.2727272727272727, | |
| "grad_norm": 6.83111572265625, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 4.6277, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.303030303030303, | |
| "grad_norm": 7.230846405029297, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 4.6809, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 6.264194488525391, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 4.6497, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.3636363636363638, | |
| "grad_norm": 5.941837787628174, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 4.6859, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.393939393939394, | |
| "grad_norm": 7.431611061096191, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 4.8694, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.4242424242424243, | |
| "grad_norm": 7.033977031707764, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 4.5204, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.4545454545454546, | |
| "grad_norm": 8.80021858215332, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 4.8541, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.4848484848484849, | |
| "grad_norm": 14.710296630859375, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 5.174, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.5151515151515151, | |
| "grad_norm": 5.271395683288574, | |
| "learning_rate": 1e-05, | |
| "loss": 4.0463, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.5151515151515151, | |
| "eval_loss": 0.3421801030635834, | |
| "eval_runtime": 2.9426, | |
| "eval_samples_per_second": 16.992, | |
| "eval_steps_per_second": 4.418, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 5.259156315439104e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |