{ "best_metric": 0.7129375338554382, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.12965964343598055, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.002593192868719611, "grad_norm": 1.2221038341522217, "learning_rate": 5e-05, "loss": 12.0554, "step": 1 }, { "epoch": 0.002593192868719611, "eval_loss": 0.9376727938652039, "eval_runtime": 2.9516, "eval_samples_per_second": 16.94, "eval_steps_per_second": 4.404, "step": 1 }, { "epoch": 0.005186385737439222, "grad_norm": 1.3244926929473877, "learning_rate": 0.0001, "loss": 12.2617, "step": 2 }, { "epoch": 0.007779578606158833, "grad_norm": 1.3263732194900513, "learning_rate": 9.990365154573717e-05, "loss": 12.1544, "step": 3 }, { "epoch": 0.010372771474878443, "grad_norm": 1.413618564605713, "learning_rate": 9.961501876182148e-05, "loss": 12.0064, "step": 4 }, { "epoch": 0.012965964343598054, "grad_norm": 1.49678373336792, "learning_rate": 9.913533761814537e-05, "loss": 11.8896, "step": 5 }, { "epoch": 0.015559157212317666, "grad_norm": 1.7596981525421143, "learning_rate": 9.846666218300807e-05, "loss": 11.5783, "step": 6 }, { "epoch": 0.01815235008103728, "grad_norm": 2.3761210441589355, "learning_rate": 9.761185582727977e-05, "loss": 12.3222, "step": 7 }, { "epoch": 0.020745542949756886, "grad_norm": 2.4527528285980225, "learning_rate": 9.657457896300791e-05, "loss": 11.2562, "step": 8 }, { "epoch": 0.023338735818476498, "grad_norm": 3.086982250213623, "learning_rate": 9.535927336897098e-05, "loss": 11.6443, "step": 9 }, { "epoch": 0.02593192868719611, "grad_norm": 4.789784908294678, "learning_rate": 9.397114317029975e-05, "loss": 11.8207, "step": 10 }, { "epoch": 0.02852512155591572, "grad_norm": 6.406594276428223, "learning_rate": 9.241613255361455e-05, "loss": 10.4593, "step": 11 }, { "epoch": 0.03111831442463533, "grad_norm": 10.306538581848145, "learning_rate": 9.070090031310558e-05, "loss": 12.1444, "step": 12 }, { "epoch": 0.033711507293354946, "grad_norm": 11.822031021118164, "learning_rate": 8.883279133655399e-05, "loss": 15.4635, "step": 13 }, { "epoch": 0.03630470016207456, "grad_norm": 6.1410346031188965, "learning_rate": 8.681980515339464e-05, "loss": 11.7146, "step": 14 }, { "epoch": 0.03889789303079417, "grad_norm": 6.397449970245361, "learning_rate": 8.467056167950311e-05, "loss": 12.3685, "step": 15 }, { "epoch": 0.04149108589951377, "grad_norm": 6.054007530212402, "learning_rate": 8.239426430539243e-05, "loss": 11.6277, "step": 16 }, { "epoch": 0.044084278768233384, "grad_norm": 4.884012699127197, "learning_rate": 8.000066048588211e-05, "loss": 10.9926, "step": 17 }, { "epoch": 0.046677471636952995, "grad_norm": 4.088375091552734, "learning_rate": 7.75e-05, "loss": 10.976, "step": 18 }, { "epoch": 0.04927066450567261, "grad_norm": 3.259921073913574, "learning_rate": 7.490299105985507e-05, "loss": 11.5746, "step": 19 }, { "epoch": 0.05186385737439222, "grad_norm": 2.864664077758789, "learning_rate": 7.222075445642904e-05, "loss": 10.3915, "step": 20 }, { "epoch": 0.05445705024311183, "grad_norm": 2.5738425254821777, "learning_rate": 6.946477593864228e-05, "loss": 10.6986, "step": 21 }, { "epoch": 0.05705024311183144, "grad_norm": 2.686957597732544, "learning_rate": 6.664685702961344e-05, "loss": 10.359, "step": 22 }, { "epoch": 0.05964343598055105, "grad_norm": 4.167721271514893, "learning_rate": 6.377906449072578e-05, "loss": 9.1868, "step": 23 }, { "epoch": 0.06223662884927066, "grad_norm": 5.8084540367126465, "learning_rate": 6.087367864990233e-05, "loss": 10.2571, "step": 24 }, { "epoch": 0.06482982171799027, "grad_norm": 20.483627319335938, "learning_rate": 5.794314081535644e-05, "loss": 13.1801, "step": 25 }, { "epoch": 0.06482982171799027, "eval_loss": 0.751792848110199, "eval_runtime": 2.9889, "eval_samples_per_second": 16.729, "eval_steps_per_second": 4.349, "step": 25 }, { "epoch": 0.06742301458670989, "grad_norm": 1.1765886545181274, "learning_rate": 5.500000000000001e-05, "loss": 10.5108, "step": 26 }, { "epoch": 0.0700162074554295, "grad_norm": 1.3730372190475464, "learning_rate": 5.205685918464356e-05, "loss": 11.427, "step": 27 }, { "epoch": 0.07260940032414911, "grad_norm": 1.078452706336975, "learning_rate": 4.912632135009769e-05, "loss": 10.4443, "step": 28 }, { "epoch": 0.07520259319286872, "grad_norm": 1.0745612382888794, "learning_rate": 4.6220935509274235e-05, "loss": 10.8648, "step": 29 }, { "epoch": 0.07779578606158834, "grad_norm": 1.2040302753448486, "learning_rate": 4.3353142970386564e-05, "loss": 10.7814, "step": 30 }, { "epoch": 0.08038897893030794, "grad_norm": 1.2691534757614136, "learning_rate": 4.053522406135775e-05, "loss": 10.2031, "step": 31 }, { "epoch": 0.08298217179902755, "grad_norm": 1.609654426574707, "learning_rate": 3.777924554357096e-05, "loss": 10.1928, "step": 32 }, { "epoch": 0.08557536466774716, "grad_norm": 1.7437150478363037, "learning_rate": 3.509700894014496e-05, "loss": 10.2497, "step": 33 }, { "epoch": 0.08816855753646677, "grad_norm": 2.2530760765075684, "learning_rate": 3.250000000000001e-05, "loss": 9.4398, "step": 34 }, { "epoch": 0.09076175040518639, "grad_norm": 4.513284206390381, "learning_rate": 2.9999339514117912e-05, "loss": 9.8228, "step": 35 }, { "epoch": 0.09335494327390599, "grad_norm": 5.1368536949157715, "learning_rate": 2.760573569460757e-05, "loss": 8.9785, "step": 36 }, { "epoch": 0.09594813614262561, "grad_norm": 8.476035118103027, "learning_rate": 2.53294383204969e-05, "loss": 10.3183, "step": 37 }, { "epoch": 0.09854132901134521, "grad_norm": 11.310976028442383, "learning_rate": 2.3180194846605367e-05, "loss": 12.9887, "step": 38 }, { "epoch": 0.10113452188006483, "grad_norm": 1.1918339729309082, "learning_rate": 2.1167208663446025e-05, "loss": 11.2354, "step": 39 }, { "epoch": 0.10372771474878444, "grad_norm": 1.146219253540039, "learning_rate": 1.9299099686894423e-05, "loss": 10.5345, "step": 40 }, { "epoch": 0.10632090761750405, "grad_norm": 1.2467947006225586, "learning_rate": 1.758386744638546e-05, "loss": 10.6546, "step": 41 }, { "epoch": 0.10891410048622366, "grad_norm": 1.2855454683303833, "learning_rate": 1.602885682970026e-05, "loss": 10.1265, "step": 42 }, { "epoch": 0.11150729335494328, "grad_norm": 1.4412370920181274, "learning_rate": 1.464072663102903e-05, "loss": 10.0749, "step": 43 }, { "epoch": 0.11410048622366288, "grad_norm": 1.6290322542190552, "learning_rate": 1.3425421036992098e-05, "loss": 10.445, "step": 44 }, { "epoch": 0.1166936790923825, "grad_norm": 1.820227026939392, "learning_rate": 1.2388144172720251e-05, "loss": 10.4432, "step": 45 }, { "epoch": 0.1192868719611021, "grad_norm": 2.2414534091949463, "learning_rate": 1.1533337816991932e-05, "loss": 9.1642, "step": 46 }, { "epoch": 0.12188006482982172, "grad_norm": 2.7672858238220215, "learning_rate": 1.0864662381854632e-05, "loss": 9.3451, "step": 47 }, { "epoch": 0.12447325769854133, "grad_norm": 3.4407408237457275, "learning_rate": 1.0384981238178534e-05, "loss": 8.1439, "step": 48 }, { "epoch": 0.12706645056726093, "grad_norm": 5.926863193511963, "learning_rate": 1.0096348454262845e-05, "loss": 10.3794, "step": 49 }, { "epoch": 0.12965964343598055, "grad_norm": 10.669682502746582, "learning_rate": 1e-05, "loss": 11.1949, "step": 50 }, { "epoch": 0.12965964343598055, "eval_loss": 0.7129375338554382, "eval_runtime": 2.9843, "eval_samples_per_second": 16.754, "eval_steps_per_second": 4.356, "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": 5.2706607182014054e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }