| { | |
| "best_metric": 2.119436794600915e-05, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.11301031219098742, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0022602062438197485, | |
| "grad_norm": 36.50872039794922, | |
| "learning_rate": 5e-05, | |
| "loss": 34.755, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0022602062438197485, | |
| "eval_loss": 2.0624725818634033, | |
| "eval_runtime": 2.928, | |
| "eval_samples_per_second": 17.076, | |
| "eval_steps_per_second": 4.44, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004520412487639497, | |
| "grad_norm": 39.20931625366211, | |
| "learning_rate": 0.0001, | |
| "loss": 33.4694, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006780618731459246, | |
| "grad_norm": 33.71365737915039, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 31.6819, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009040824975278994, | |
| "grad_norm": 37.54655456542969, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 25.8034, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.011301031219098742, | |
| "grad_norm": 38.01105880737305, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 18.9234, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.013561237462918492, | |
| "grad_norm": 31.474199295043945, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 12.3176, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01582144370673824, | |
| "grad_norm": 21.290525436401367, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 7.4779, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.018081649950557988, | |
| "grad_norm": 16.17531967163086, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 4.8246, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.020341856194377738, | |
| "grad_norm": 15.527769088745117, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 2.7513, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.022602062438197484, | |
| "grad_norm": 8.276153564453125, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.4711, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.024862268682017234, | |
| "grad_norm": 5.247931003570557, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.5401, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.027122474925836984, | |
| "grad_norm": 2.8925697803497314, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.264, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.02938268116965673, | |
| "grad_norm": 1.5590310096740723, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.2219, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03164288741347648, | |
| "grad_norm": 0.8110895752906799, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.0774, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03390309365729623, | |
| "grad_norm": 0.80513596534729, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.062, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.036163299901115976, | |
| "grad_norm": 0.6620855927467346, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.0128, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.038423506144935726, | |
| "grad_norm": 0.6907656788825989, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.0116, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.040683712388755476, | |
| "grad_norm": 0.4166719913482666, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.0053, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.042943918632575226, | |
| "grad_norm": 0.42982903122901917, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.0056, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04520412487639497, | |
| "grad_norm": 0.32655465602874756, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.0029, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04746433112021472, | |
| "grad_norm": 0.1056491881608963, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.0016, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.04972453736403447, | |
| "grad_norm": 0.028798570856451988, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.0012, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.05198474360785422, | |
| "grad_norm": 0.014183205552399158, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.0006, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.05424494985167397, | |
| "grad_norm": 0.02514360472559929, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.0007, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.05650515609549371, | |
| "grad_norm": 0.015000662766397, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.0006, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05650515609549371, | |
| "eval_loss": 3.281138924648985e-05, | |
| "eval_runtime": 2.9755, | |
| "eval_samples_per_second": 16.804, | |
| "eval_steps_per_second": 4.369, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05876536233931346, | |
| "grad_norm": 0.04972488060593605, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.001, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.06102556858313321, | |
| "grad_norm": 0.048093147575855255, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.0006, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.06328577482695295, | |
| "grad_norm": 0.0384451225399971, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.0006, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.06554598107077271, | |
| "grad_norm": 0.1282583624124527, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.0016, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.06780618731459245, | |
| "grad_norm": 0.02835065871477127, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.0009, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07006639355841221, | |
| "grad_norm": 0.025677639991044998, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.0007, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.07232659980223195, | |
| "grad_norm": 0.011029267683625221, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.0004, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0745868060460517, | |
| "grad_norm": 0.029804445803165436, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.0008, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.07684701228987145, | |
| "grad_norm": 0.02739046700298786, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.0005, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0791072185336912, | |
| "grad_norm": 0.03442985564470291, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.0006, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08136742477751095, | |
| "grad_norm": 0.011169228702783585, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.0004, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0836276310213307, | |
| "grad_norm": 0.008100761100649834, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.0003, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.08588783726515045, | |
| "grad_norm": 0.6260887384414673, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.1661, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0881480435089702, | |
| "grad_norm": 1.2297857999801636, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.0128, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.09040824975278994, | |
| "grad_norm": 1.5309454202651978, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.0229, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0926684559966097, | |
| "grad_norm": 1.832742691040039, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.14, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.09492866224042944, | |
| "grad_norm": 0.0456574372947216, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.0007, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0971888684842492, | |
| "grad_norm": 0.037164654582738876, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.0006, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.09944907472806894, | |
| "grad_norm": 0.024082988500595093, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.0009, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.10170928097188868, | |
| "grad_norm": 0.009204435162246227, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.0005, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.10396948721570844, | |
| "grad_norm": 0.008595156483352184, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.0004, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.10622969345952818, | |
| "grad_norm": 0.00714592169970274, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.0005, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.10848989970334794, | |
| "grad_norm": 0.016524558886885643, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.0004, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.11075010594716768, | |
| "grad_norm": 0.009992051869630814, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.0003, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.11301031219098742, | |
| "grad_norm": 0.009089923463761806, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0004, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.11301031219098742, | |
| "eval_loss": 2.119436794600915e-05, | |
| "eval_runtime": 2.9422, | |
| "eval_samples_per_second": 16.994, | |
| "eval_steps_per_second": 4.419, | |
| "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": 5.259156315439104e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |