| { | |
| "best_metric": 1.0602198839187622, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.025039907352342797, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005007981470468559, | |
| "grad_norm": 7.45435905456543, | |
| "learning_rate": 5e-05, | |
| "loss": 27.672, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005007981470468559, | |
| "eval_loss": 1.6920984983444214, | |
| "eval_runtime": 2.2692, | |
| "eval_samples_per_second": 22.035, | |
| "eval_steps_per_second": 5.729, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010015962940937118, | |
| "grad_norm": 10.010887145996094, | |
| "learning_rate": 0.0001, | |
| "loss": 28.8918, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0015023944411405679, | |
| "grad_norm": 6.914218425750732, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 23.5377, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0020031925881874237, | |
| "grad_norm": 6.591081142425537, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 23.4905, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0025039907352342795, | |
| "grad_norm": 6.64627742767334, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 22.9004, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0030047888822811357, | |
| "grad_norm": 5.685656547546387, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 22.2604, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0035055870293279915, | |
| "grad_norm": 5.233028411865234, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 21.6732, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004006385176374847, | |
| "grad_norm": 4.9397501945495605, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 20.1599, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004507183323421703, | |
| "grad_norm": 4.317351818084717, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 22.0404, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005007981470468559, | |
| "grad_norm": 5.655327796936035, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 21.491, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005508779617515415, | |
| "grad_norm": 5.512872695922852, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 18.0564, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0060095777645622715, | |
| "grad_norm": 4.752590656280518, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 16.1569, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.006510375911609127, | |
| "grad_norm": 8.018436431884766, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 21.9283, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.007011174058655983, | |
| "grad_norm": 7.043315887451172, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 22.6641, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.007511972205702839, | |
| "grad_norm": 5.599305152893066, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 19.4054, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.008012770352749695, | |
| "grad_norm": 4.370555400848389, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 17.4796, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.00851356849979655, | |
| "grad_norm": 5.408305644989014, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 18.28, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.009014366646843406, | |
| "grad_norm": 4.4130330085754395, | |
| "learning_rate": 7.75e-05, | |
| "loss": 18.1072, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.009515164793890262, | |
| "grad_norm": 4.670492649078369, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 18.552, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.010015962940937118, | |
| "grad_norm": 4.140300273895264, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 18.2147, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.010516761087983974, | |
| "grad_norm": 3.7229697704315186, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 18.5504, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.01101755923503083, | |
| "grad_norm": 3.4629743099212646, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 17.8376, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.011518357382077687, | |
| "grad_norm": 3.7055418491363525, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 18.2517, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.012019155529124543, | |
| "grad_norm": 3.7786102294921875, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 17.3617, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.012519953676171399, | |
| "grad_norm": 6.0467963218688965, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 18.454, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.012519953676171399, | |
| "eval_loss": 1.1061513423919678, | |
| "eval_runtime": 2.3374, | |
| "eval_samples_per_second": 21.391, | |
| "eval_steps_per_second": 5.562, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.013020751823218255, | |
| "grad_norm": 6.150357246398926, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 20.203, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.01352154997026511, | |
| "grad_norm": 7.324110984802246, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 20.2245, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.014022348117311966, | |
| "grad_norm": 4.4846391677856445, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 17.0902, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.014523146264358822, | |
| "grad_norm": 4.2537126541137695, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 17.783, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.015023944411405678, | |
| "grad_norm": 3.3687477111816406, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 19.8318, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.015524742558452534, | |
| "grad_norm": 3.4171719551086426, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 17.4442, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.01602554070549939, | |
| "grad_norm": 4.006035327911377, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 17.9844, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.016526338852546247, | |
| "grad_norm": 4.396282196044922, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 18.255, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0170271369995931, | |
| "grad_norm": 4.883106231689453, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 18.8518, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.01752793514663996, | |
| "grad_norm": 5.509437561035156, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 17.9827, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.018028733293686813, | |
| "grad_norm": 4.919665813446045, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 15.706, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.01852953144073367, | |
| "grad_norm": 6.44651460647583, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 16.1781, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.019030329587780524, | |
| "grad_norm": 5.128076553344727, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 21.4918, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.019531127734827382, | |
| "grad_norm": 9.525840759277344, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 21.2966, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.020031925881874236, | |
| "grad_norm": 3.75991153717041, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 17.6723, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.020532724028921093, | |
| "grad_norm": 3.4625003337860107, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 15.4358, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.021033522175967947, | |
| "grad_norm": 4.435390472412109, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 17.5912, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.021534320323014805, | |
| "grad_norm": 4.710116386413574, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 16.8838, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.02203511847006166, | |
| "grad_norm": 4.531633377075195, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 17.465, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.022535916617108517, | |
| "grad_norm": 3.9686601161956787, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 17.882, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.023036714764155374, | |
| "grad_norm": 3.2548906803131104, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 17.3054, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.02353751291120223, | |
| "grad_norm": 3.3293542861938477, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 16.5476, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.024038311058249086, | |
| "grad_norm": 3.773627996444702, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 16.9503, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.02453910920529594, | |
| "grad_norm": 3.537731647491455, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 14.9813, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.025039907352342797, | |
| "grad_norm": 6.06915283203125, | |
| "learning_rate": 1e-05, | |
| "loss": 17.1321, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.025039907352342797, | |
| "eval_loss": 1.0602198839187622, | |
| "eval_runtime": 2.2315, | |
| "eval_samples_per_second": 22.407, | |
| "eval_steps_per_second": 5.826, | |
| "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": 5.9050464574754e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |