| { | |
| "best_metric": 4.621637344360352, | |
| "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": 47.247737884521484, | |
| "learning_rate": 5e-05, | |
| "loss": 90.7898, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013752793536187038, | |
| "eval_loss": 6.071027755737305, | |
| "eval_runtime": 2.9009, | |
| "eval_samples_per_second": 17.236, | |
| "eval_steps_per_second": 4.481, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0027505587072374077, | |
| "grad_norm": 50.189151763916016, | |
| "learning_rate": 0.0001, | |
| "loss": 94.6107, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0041258380608561115, | |
| "grad_norm": 45.00249099731445, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 93.878, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005501117414474815, | |
| "grad_norm": 31.018747329711914, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 87.0647, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006876396768093519, | |
| "grad_norm": 25.834840774536133, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 85.2583, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008251676121712223, | |
| "grad_norm": 23.79578971862793, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 82.2246, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009626955475330927, | |
| "grad_norm": 24.951824188232422, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 79.9058, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01100223482894963, | |
| "grad_norm": 14.284527778625488, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 79.1301, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.012377514182568335, | |
| "grad_norm": 49.100196838378906, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 78.4692, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.013752793536187038, | |
| "grad_norm": 85.69519805908203, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 78.4167, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.015128072889805742, | |
| "grad_norm": 82.62657165527344, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 80.1901, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.016503352243424446, | |
| "grad_norm": 35.43754196166992, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 81.3278, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01787863159704315, | |
| "grad_norm": 30.274520874023438, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 76.5465, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.019253910950661854, | |
| "grad_norm": 24.64078140258789, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 72.6522, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.020629190304280558, | |
| "grad_norm": 24.059825897216797, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 72.8096, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02200446965789926, | |
| "grad_norm": 14.653773307800293, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 73.2995, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.023379749011517965, | |
| "grad_norm": 8.644264221191406, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 74.0428, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.02475502836513667, | |
| "grad_norm": 31.19290542602539, | |
| "learning_rate": 7.75e-05, | |
| "loss": 74.5504, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.026130307718755373, | |
| "grad_norm": 24.381179809570312, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 75.5478, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.027505587072374077, | |
| "grad_norm": 40.15234375, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 76.11, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02888086642599278, | |
| "grad_norm": 24.75045394897461, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 75.888, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.030256145779611485, | |
| "grad_norm": 11.645346641540527, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 76.7001, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03163142513323019, | |
| "grad_norm": 18.211610794067383, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 78.1607, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03300670448684889, | |
| "grad_norm": 22.749834060668945, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 78.6751, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.034381983840467596, | |
| "grad_norm": 14.634866714477539, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 80.3792, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.034381983840467596, | |
| "eval_loss": 4.626386642456055, | |
| "eval_runtime": 2.9216, | |
| "eval_samples_per_second": 17.114, | |
| "eval_steps_per_second": 4.45, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0357572631940863, | |
| "grad_norm": 17.571855545043945, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 71.1024, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.037132542547705004, | |
| "grad_norm": 44.00326156616211, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 72.3466, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03850782190132371, | |
| "grad_norm": 70.81744384765625, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 74.5078, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03988310125494241, | |
| "grad_norm": 51.877384185791016, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 74.2768, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.041258380608561115, | |
| "grad_norm": 19.11564064025879, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 74.1218, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04263365996217982, | |
| "grad_norm": 27.261991500854492, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 75.4165, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.04400893931579852, | |
| "grad_norm": 48.26954650878906, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 74.5459, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.04538421866941723, | |
| "grad_norm": 38.06425476074219, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 76.8192, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.04675949802303593, | |
| "grad_norm": 18.26669692993164, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 76.9858, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.048134777376654635, | |
| "grad_norm": 10.748762130737305, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 77.5933, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04951005673027334, | |
| "grad_norm": 30.8355655670166, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 78.0878, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.05088533608389204, | |
| "grad_norm": 31.517621994018555, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 78.3195, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.052260615437510746, | |
| "grad_norm": 5.85664176940918, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 76.3249, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.05363589479112945, | |
| "grad_norm": 24.378793716430664, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 71.3614, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.055011174144748154, | |
| "grad_norm": 30.349285125732422, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 73.0253, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05638645349836686, | |
| "grad_norm": 23.223705291748047, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 73.2813, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.05776173285198556, | |
| "grad_norm": 5.5575785636901855, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 73.9555, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.059137012205604265, | |
| "grad_norm": 13.843238830566406, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 74.1518, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.06051229155922297, | |
| "grad_norm": 19.540786743164062, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 74.4265, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.06188757091284167, | |
| "grad_norm": 22.034353256225586, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 74.6505, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.06326285026646038, | |
| "grad_norm": 18.099666595458984, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 75.1105, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.06463812962007907, | |
| "grad_norm": 7.462347030639648, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 77.1888, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.06601340897369778, | |
| "grad_norm": 5.528837203979492, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 77.7504, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.06738868832731648, | |
| "grad_norm": 19.01416015625, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 79.3957, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.06876396768093519, | |
| "grad_norm": 10.58906078338623, | |
| "learning_rate": 1e-05, | |
| "loss": 81.2795, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06876396768093519, | |
| "eval_loss": 4.621637344360352, | |
| "eval_runtime": 2.9236, | |
| "eval_samples_per_second": 17.102, | |
| "eval_steps_per_second": 4.447, | |
| "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": 5.259104775831552e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |