| { | |
| "best_metric": 4.59688663482666, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.06876396768093519, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0013752793536187038, | |
| "grad_norm": 1.3573954105377197, | |
| "learning_rate": 5e-05, | |
| "loss": 5.4569, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013752793536187038, | |
| "eval_loss": 5.800675868988037, | |
| "eval_runtime": 4.4274, | |
| "eval_samples_per_second": 11.293, | |
| "eval_steps_per_second": 2.936, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0027505587072374077, | |
| "grad_norm": 1.1038050651550293, | |
| "learning_rate": 0.0001, | |
| "loss": 5.5196, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0041258380608561115, | |
| "grad_norm": 1.128781795501709, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 5.537, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005501117414474815, | |
| "grad_norm": 1.1495604515075684, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 5.4791, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006876396768093519, | |
| "grad_norm": 1.0771335363388062, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 5.3432, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008251676121712223, | |
| "grad_norm": 1.124253511428833, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 5.2646, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009626955475330927, | |
| "grad_norm": 0.999345600605011, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 5.0927, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01100223482894963, | |
| "grad_norm": 1.0835942029953003, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 5.1607, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.012377514182568335, | |
| "grad_norm": 0.7795541882514954, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 5.0415, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.013752793536187038, | |
| "grad_norm": 1.2778282165527344, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 5.1147, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.015128072889805742, | |
| "grad_norm": 1.7453047037124634, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 5.1534, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.016503352243424446, | |
| "grad_norm": 1.9628040790557861, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 5.2754, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01787863159704315, | |
| "grad_norm": 2.570558547973633, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 5.0466, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.019253910950661854, | |
| "grad_norm": 1.3346421718597412, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 4.4947, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.020629190304280558, | |
| "grad_norm": 2.2572271823883057, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 4.45, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02200446965789926, | |
| "grad_norm": 1.0499677658081055, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 4.5362, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.023379749011517965, | |
| "grad_norm": 2.3192594051361084, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 4.553, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.02475502836513667, | |
| "grad_norm": 1.927417516708374, | |
| "learning_rate": 7.75e-05, | |
| "loss": 4.5915, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.026130307718755373, | |
| "grad_norm": 0.3943534195423126, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 4.6225, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.027505587072374077, | |
| "grad_norm": 1.8378969430923462, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 4.7635, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02888086642599278, | |
| "grad_norm": 1.5817768573760986, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 4.7496, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.030256145779611485, | |
| "grad_norm": 0.7282426953315735, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 4.7856, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03163142513323019, | |
| "grad_norm": 1.0822144746780396, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 4.8682, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03300670448684889, | |
| "grad_norm": 0.6497578620910645, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 5.0268, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.034381983840467596, | |
| "grad_norm": 1.9047386646270752, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 5.3267, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.034381983840467596, | |
| "eval_loss": 4.630157470703125, | |
| "eval_runtime": 4.4751, | |
| "eval_samples_per_second": 11.173, | |
| "eval_steps_per_second": 2.905, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0357572631940863, | |
| "grad_norm": 3.5470054149627686, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 4.4535, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.037132542547705004, | |
| "grad_norm": 3.0198135375976562, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 4.5103, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03850782190132371, | |
| "grad_norm": 1.6239436864852905, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 4.5091, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03988310125494241, | |
| "grad_norm": 0.7438290119171143, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 4.5166, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.041258380608561115, | |
| "grad_norm": 1.5961905717849731, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 4.549, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04263365996217982, | |
| "grad_norm": 1.9019944667816162, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 4.6353, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.04400893931579852, | |
| "grad_norm": 1.608849048614502, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 4.6285, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.04538421866941723, | |
| "grad_norm": 0.9246691465377808, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 4.7333, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.04675949802303593, | |
| "grad_norm": 0.5985221862792969, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 4.7893, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.048134777376654635, | |
| "grad_norm": 1.3541096448898315, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 4.8817, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04951005673027334, | |
| "grad_norm": 1.3304661512374878, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 4.8802, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.05088533608389204, | |
| "grad_norm": 0.7560667395591736, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 5.1148, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.052260615437510746, | |
| "grad_norm": 0.7408563494682312, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 4.8291, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.05363589479112945, | |
| "grad_norm": 1.689084529876709, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 4.4322, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.055011174144748154, | |
| "grad_norm": 1.04849112033844, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 4.4272, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05638645349836686, | |
| "grad_norm": 0.40013745427131653, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 4.4528, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.05776173285198556, | |
| "grad_norm": 0.9821546673774719, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 4.5102, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.059137012205604265, | |
| "grad_norm": 1.4204320907592773, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 4.6064, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.06051229155922297, | |
| "grad_norm": 1.5107200145721436, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 4.5763, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.06188757091284167, | |
| "grad_norm": 1.8442341089248657, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 4.7101, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.06326285026646038, | |
| "grad_norm": 1.6146044731140137, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 4.6966, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.06463812962007907, | |
| "grad_norm": 1.5591859817504883, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 4.8572, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.06601340897369778, | |
| "grad_norm": 1.0972256660461426, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 4.9027, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.06738868832731648, | |
| "grad_norm": 1.1528632640838623, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 4.9912, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.06876396768093519, | |
| "grad_norm": 0.9311072826385498, | |
| "learning_rate": 1e-05, | |
| "loss": 5.3241, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06876396768093519, | |
| "eval_loss": 4.59688663482666, | |
| "eval_runtime": 4.4655, | |
| "eval_samples_per_second": 11.197, | |
| "eval_steps_per_second": 2.911, | |
| "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": 2.654149397184512e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |