| { | |
| "best_metric": 2.300698757171631, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.018412815319462345, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003682563063892469, | |
| "grad_norm": 1.91280996799469, | |
| "learning_rate": 5e-05, | |
| "loss": 2.1982, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003682563063892469, | |
| "eval_loss": 3.6061596870422363, | |
| "eval_runtime": 1.5161, | |
| "eval_samples_per_second": 32.978, | |
| "eval_steps_per_second": 8.574, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007365126127784938, | |
| "grad_norm": 2.0957469940185547, | |
| "learning_rate": 0.0001, | |
| "loss": 2.4763, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0011047689191677407, | |
| "grad_norm": 1.9613713026046753, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 2.5186, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0014730252255569876, | |
| "grad_norm": 1.4553881883621216, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.4343, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0018412815319462346, | |
| "grad_norm": 1.5710747241973877, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.3533, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0022095378383354815, | |
| "grad_norm": 1.426024317741394, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.2975, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0025777941447247283, | |
| "grad_norm": 1.3779783248901367, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 2.4956, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.002946050451113975, | |
| "grad_norm": 1.282586693763733, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 2.5275, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0033143067575032224, | |
| "grad_norm": 1.0497735738754272, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 2.6698, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0036825630638924692, | |
| "grad_norm": 1.044584035873413, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 2.7479, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004050819370281716, | |
| "grad_norm": 1.3881807327270508, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 2.9648, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.004419075676670963, | |
| "grad_norm": 2.0393691062927246, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 3.2128, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00478733198306021, | |
| "grad_norm": 0.870771050453186, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.7127, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.005155588289449457, | |
| "grad_norm": 0.8859942555427551, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.8588, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.005523844595838704, | |
| "grad_norm": 0.8486651182174683, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 2.0634, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00589210090222795, | |
| "grad_norm": 0.7893238663673401, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 2.0783, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0062603572086171975, | |
| "grad_norm": 0.6707751154899597, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 2.106, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.006628613515006445, | |
| "grad_norm": 0.6826125979423523, | |
| "learning_rate": 7.75e-05, | |
| "loss": 2.2365, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.006996869821395691, | |
| "grad_norm": 0.6989638209342957, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 2.1631, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0073651261277849385, | |
| "grad_norm": 0.7944750785827637, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 2.2346, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007733382434174185, | |
| "grad_norm": 0.7866911292076111, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 2.1823, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.008101638740563431, | |
| "grad_norm": 0.8714109659194946, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 2.3636, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.00846989504695268, | |
| "grad_norm": 1.1833001375198364, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 2.7353, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.008838151353341926, | |
| "grad_norm": 1.4409525394439697, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 3.0607, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.009206407659731172, | |
| "grad_norm": 2.9500479698181152, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 3.1293, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.009206407659731172, | |
| "eval_loss": 2.3962597846984863, | |
| "eval_runtime": 1.475, | |
| "eval_samples_per_second": 33.898, | |
| "eval_steps_per_second": 8.813, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00957466396612042, | |
| "grad_norm": 0.6010366678237915, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.6247, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.009942920272509667, | |
| "grad_norm": 0.8184590935707092, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 1.8737, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.010311176578898913, | |
| "grad_norm": 0.7789363265037537, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 2.0136, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.010679432885288161, | |
| "grad_norm": 0.6929258108139038, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 2.0049, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.011047689191677408, | |
| "grad_norm": 0.6341331601142883, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 2.0244, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.011415945498066654, | |
| "grad_norm": 0.6360584497451782, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 2.0533, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0117842018044559, | |
| "grad_norm": 0.6871073246002197, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 2.193, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.012152458110845149, | |
| "grad_norm": 0.7307798862457275, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 2.1686, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.012520714417234395, | |
| "grad_norm": 0.8923740386962891, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 2.2811, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.012888970723623642, | |
| "grad_norm": 1.1610867977142334, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 2.533, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01325722703001289, | |
| "grad_norm": 1.322665810585022, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 2.8074, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.013625483336402136, | |
| "grad_norm": 1.953356385231018, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 2.9117, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.013993739642791382, | |
| "grad_norm": 0.6058061122894287, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 1.6222, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.014361995949180629, | |
| "grad_norm": 0.48876795172691345, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 1.7171, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.014730252255569877, | |
| "grad_norm": 0.5596562623977661, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 1.8393, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.015098508561959123, | |
| "grad_norm": 0.540923535823822, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 1.9241, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.01546676486834837, | |
| "grad_norm": 0.6124505996704102, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.9227, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.015835021174737618, | |
| "grad_norm": 0.6569370031356812, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 1.9246, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.016203277481126863, | |
| "grad_norm": 0.6232062578201294, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 2.0976, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.01657153378751611, | |
| "grad_norm": 0.7638946175575256, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 2.0661, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.01693979009390536, | |
| "grad_norm": 0.7543624639511108, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 2.2258, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.017308046400294604, | |
| "grad_norm": 0.8359889984130859, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 2.2464, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.01767630270668385, | |
| "grad_norm": 0.983206033706665, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 2.4463, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0180445590130731, | |
| "grad_norm": 1.324151873588562, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 2.7316, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.018412815319462345, | |
| "grad_norm": 3.246047258377075, | |
| "learning_rate": 1e-05, | |
| "loss": 3.102, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.018412815319462345, | |
| "eval_loss": 2.300698757171631, | |
| "eval_runtime": 1.4858, | |
| "eval_samples_per_second": 33.653, | |
| "eval_steps_per_second": 8.75, | |
| "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": 1.5899604877626573e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |