| { | |
| "best_metric": 1.5829479694366455, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.024680693527488123, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004936138705497624, | |
| "grad_norm": 8.768486976623535, | |
| "learning_rate": 5e-05, | |
| "loss": 3.2997, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004936138705497624, | |
| "eval_loss": 3.618351697921753, | |
| "eval_runtime": 2.0991, | |
| "eval_samples_per_second": 23.819, | |
| "eval_steps_per_second": 6.193, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009872277410995249, | |
| "grad_norm": 9.801698684692383, | |
| "learning_rate": 0.0001, | |
| "loss": 3.4302, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0014808416116492873, | |
| "grad_norm": 6.741608619689941, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 3.0394, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0019744554821990497, | |
| "grad_norm": 3.156365394592285, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.2221, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002468069352748812, | |
| "grad_norm": 1.9786056280136108, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.953, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0029616832232985746, | |
| "grad_norm": 1.8328018188476562, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.1868, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003455297093848337, | |
| "grad_norm": 1.7074838876724243, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.9537, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0039489109643980995, | |
| "grad_norm": 1.3485358953475952, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.7351, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004442524834947862, | |
| "grad_norm": 1.3995983600616455, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.8539, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004936138705497624, | |
| "grad_norm": 1.318764090538025, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.7079, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005429752576047387, | |
| "grad_norm": 1.1518501043319702, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.8379, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.005923366446597149, | |
| "grad_norm": 1.0455611944198608, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.783, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.006416980317146912, | |
| "grad_norm": 1.0783802270889282, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.6697, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.006910594187696674, | |
| "grad_norm": 0.9238178730010986, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.7253, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.007404208058246437, | |
| "grad_norm": 1.0212122201919556, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.7036, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007897821928796199, | |
| "grad_norm": 0.8407418131828308, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.6878, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.008391435799345962, | |
| "grad_norm": 0.9576005339622498, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.5537, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.008885049669895725, | |
| "grad_norm": 1.025448203086853, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.6559, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.009378663540445486, | |
| "grad_norm": 0.9760903120040894, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.7869, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.009872277410995249, | |
| "grad_norm": 0.804629921913147, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.6535, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.010365891281545012, | |
| "grad_norm": 0.8852335214614868, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.6866, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.010859505152094774, | |
| "grad_norm": 0.884780764579773, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.5915, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.011353119022644536, | |
| "grad_norm": 0.8966594338417053, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.482, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.011846732893194298, | |
| "grad_norm": 0.8586313724517822, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.5839, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.012340346763744061, | |
| "grad_norm": 0.9354428052902222, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.5071, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.012340346763744061, | |
| "eval_loss": 1.6219940185546875, | |
| "eval_runtime": 2.1426, | |
| "eval_samples_per_second": 23.336, | |
| "eval_steps_per_second": 6.067, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.012833960634293824, | |
| "grad_norm": 0.8619699478149414, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.6531, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.013327574504843585, | |
| "grad_norm": 0.8271181583404541, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 1.6839, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.013821188375393348, | |
| "grad_norm": 0.8570282459259033, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 1.4859, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.014314802245943111, | |
| "grad_norm": 0.8331882953643799, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 1.6899, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.014808416116492874, | |
| "grad_norm": 0.7136693000793457, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 1.4245, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.015302029987042635, | |
| "grad_norm": 0.7932525873184204, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 1.5425, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.015795643857592398, | |
| "grad_norm": 0.8250367641448975, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.5708, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.01628925772814216, | |
| "grad_norm": 0.7967509627342224, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.5401, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.016782871598691924, | |
| "grad_norm": 0.8470743298530579, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.5565, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.017276485469241685, | |
| "grad_norm": 0.8121418356895447, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 1.5739, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01777009933979145, | |
| "grad_norm": 0.8498193621635437, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 1.5876, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.01826371321034121, | |
| "grad_norm": 0.9225755333900452, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 1.5783, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.01875732708089097, | |
| "grad_norm": 0.7638592720031738, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 1.4589, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.019250940951440736, | |
| "grad_norm": 0.7743381261825562, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 1.5623, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.019744554821990497, | |
| "grad_norm": 0.7764542698860168, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 1.5379, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.020238168692540262, | |
| "grad_norm": 0.7662834525108337, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 1.4034, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.020731782563090023, | |
| "grad_norm": 0.7414330244064331, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.4841, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.021225396433639784, | |
| "grad_norm": 0.7455458045005798, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 1.5619, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.02171901030418955, | |
| "grad_norm": 0.8360099196434021, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.5544, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.02221262417473931, | |
| "grad_norm": 0.795028805732727, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 1.5429, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02270623804528907, | |
| "grad_norm": 0.7889432907104492, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 1.4098, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.023199851915838836, | |
| "grad_norm": 0.7665262222290039, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 1.4591, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.023693465786388597, | |
| "grad_norm": 0.7203249335289001, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 1.4405, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.02418707965693836, | |
| "grad_norm": 0.8871418237686157, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 1.5467, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.024680693527488123, | |
| "grad_norm": 0.9818035364151001, | |
| "learning_rate": 1e-05, | |
| "loss": 1.5304, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.024680693527488123, | |
| "eval_loss": 1.5829479694366455, | |
| "eval_runtime": 2.1198, | |
| "eval_samples_per_second": 23.588, | |
| "eval_steps_per_second": 6.133, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "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": 1.62480894509056e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |