{ "best_metric": 0.785561203956604, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.020337087220682816, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00040674174441365633, "grad_norm": 8.134831428527832, "learning_rate": 5e-05, "loss": 30.7105, "step": 1 }, { "epoch": 0.00040674174441365633, "eval_loss": 1.0818605422973633, "eval_runtime": 5.4926, "eval_samples_per_second": 9.103, "eval_steps_per_second": 2.367, "step": 1 }, { "epoch": 0.0008134834888273127, "grad_norm": 9.657185554504395, "learning_rate": 0.0001, "loss": 34.9448, "step": 2 }, { "epoch": 0.001220225233240969, "grad_norm": 11.752535820007324, "learning_rate": 9.990365154573717e-05, "loss": 38.8809, "step": 3 }, { "epoch": 0.0016269669776546253, "grad_norm": 10.446924209594727, "learning_rate": 9.961501876182148e-05, "loss": 34.4503, "step": 4 }, { "epoch": 0.002033708722068282, "grad_norm": 8.943187713623047, "learning_rate": 9.913533761814537e-05, "loss": 34.302, "step": 5 }, { "epoch": 0.002440450466481938, "grad_norm": 11.026077270507812, "learning_rate": 9.846666218300807e-05, "loss": 34.1141, "step": 6 }, { "epoch": 0.0028471922108955945, "grad_norm": 10.112325668334961, "learning_rate": 9.761185582727977e-05, "loss": 32.6408, "step": 7 }, { "epoch": 0.0032539339553092506, "grad_norm": 11.064627647399902, "learning_rate": 9.657457896300791e-05, "loss": 31.5896, "step": 8 }, { "epoch": 0.003660675699722907, "grad_norm": 11.275084495544434, "learning_rate": 9.535927336897098e-05, "loss": 30.3779, "step": 9 }, { "epoch": 0.004067417444136564, "grad_norm": 9.342720031738281, "learning_rate": 9.397114317029975e-05, "loss": 28.3568, "step": 10 }, { "epoch": 0.00447415918855022, "grad_norm": 7.750696182250977, "learning_rate": 9.241613255361455e-05, "loss": 26.8884, "step": 11 }, { "epoch": 0.004880900932963876, "grad_norm": 9.470782279968262, "learning_rate": 9.070090031310558e-05, "loss": 27.3203, "step": 12 }, { "epoch": 0.005287642677377533, "grad_norm": 9.924007415771484, "learning_rate": 8.883279133655399e-05, "loss": 25.5589, "step": 13 }, { "epoch": 0.005694384421791189, "grad_norm": 8.166966438293457, "learning_rate": 8.681980515339464e-05, "loss": 28.4931, "step": 14 }, { "epoch": 0.006101126166204845, "grad_norm": 7.052664756774902, "learning_rate": 8.467056167950311e-05, "loss": 29.6954, "step": 15 }, { "epoch": 0.006507867910618501, "grad_norm": 7.844839572906494, "learning_rate": 8.239426430539243e-05, "loss": 32.5574, "step": 16 }, { "epoch": 0.006914609655032158, "grad_norm": 6.125011920928955, "learning_rate": 8.000066048588211e-05, "loss": 31.4065, "step": 17 }, { "epoch": 0.007321351399445814, "grad_norm": 5.7255072593688965, "learning_rate": 7.75e-05, "loss": 32.075, "step": 18 }, { "epoch": 0.0077280931438594705, "grad_norm": 5.69492244720459, "learning_rate": 7.490299105985507e-05, "loss": 31.2579, "step": 19 }, { "epoch": 0.008134834888273127, "grad_norm": 5.781980514526367, "learning_rate": 7.222075445642904e-05, "loss": 28.9906, "step": 20 }, { "epoch": 0.008541576632686784, "grad_norm": 6.6225714683532715, "learning_rate": 6.946477593864228e-05, "loss": 29.0088, "step": 21 }, { "epoch": 0.00894831837710044, "grad_norm": 6.627343654632568, "learning_rate": 6.664685702961344e-05, "loss": 26.0142, "step": 22 }, { "epoch": 0.009355060121514096, "grad_norm": 6.749255180358887, "learning_rate": 6.377906449072578e-05, "loss": 26.3757, "step": 23 }, { "epoch": 0.009761801865927752, "grad_norm": 7.801572322845459, "learning_rate": 6.087367864990233e-05, "loss": 27.8033, "step": 24 }, { "epoch": 0.010168543610341408, "grad_norm": 8.078119277954102, "learning_rate": 5.794314081535644e-05, "loss": 25.3571, "step": 25 }, { "epoch": 0.010168543610341408, "eval_loss": 0.8185915350914001, "eval_runtime": 5.2933, "eval_samples_per_second": 9.446, "eval_steps_per_second": 2.456, "step": 25 }, { "epoch": 0.010575285354755066, "grad_norm": 4.994813442230225, "learning_rate": 5.500000000000001e-05, "loss": 24.9078, "step": 26 }, { "epoch": 0.010982027099168722, "grad_norm": 5.219534397125244, "learning_rate": 5.205685918464356e-05, "loss": 28.395, "step": 27 }, { "epoch": 0.011388768843582378, "grad_norm": 5.788186073303223, "learning_rate": 4.912632135009769e-05, "loss": 30.7909, "step": 28 }, { "epoch": 0.011795510587996034, "grad_norm": 6.449784278869629, "learning_rate": 4.6220935509274235e-05, "loss": 30.4489, "step": 29 }, { "epoch": 0.01220225233240969, "grad_norm": 5.068568706512451, "learning_rate": 4.3353142970386564e-05, "loss": 28.3087, "step": 30 }, { "epoch": 0.012608994076823346, "grad_norm": 7.565436840057373, "learning_rate": 4.053522406135775e-05, "loss": 29.5816, "step": 31 }, { "epoch": 0.013015735821237003, "grad_norm": 5.332314968109131, "learning_rate": 3.777924554357096e-05, "loss": 27.4378, "step": 32 }, { "epoch": 0.01342247756565066, "grad_norm": 6.02372932434082, "learning_rate": 3.509700894014496e-05, "loss": 29.1633, "step": 33 }, { "epoch": 0.013829219310064316, "grad_norm": 6.785523891448975, "learning_rate": 3.250000000000001e-05, "loss": 28.2066, "step": 34 }, { "epoch": 0.014235961054477973, "grad_norm": 6.292851448059082, "learning_rate": 2.9999339514117912e-05, "loss": 25.9299, "step": 35 }, { "epoch": 0.014642702798891629, "grad_norm": 5.5777716636657715, "learning_rate": 2.760573569460757e-05, "loss": 24.8049, "step": 36 }, { "epoch": 0.015049444543305285, "grad_norm": 7.278702259063721, "learning_rate": 2.53294383204969e-05, "loss": 24.2338, "step": 37 }, { "epoch": 0.015456186287718941, "grad_norm": 6.606675148010254, "learning_rate": 2.3180194846605367e-05, "loss": 23.7511, "step": 38 }, { "epoch": 0.015862928032132597, "grad_norm": 3.8052306175231934, "learning_rate": 2.1167208663446025e-05, "loss": 25.953, "step": 39 }, { "epoch": 0.016269669776546255, "grad_norm": 4.5456953048706055, "learning_rate": 1.9299099686894423e-05, "loss": 28.1611, "step": 40 }, { "epoch": 0.01667641152095991, "grad_norm": 4.992256164550781, "learning_rate": 1.758386744638546e-05, "loss": 28.9608, "step": 41 }, { "epoch": 0.017083153265373567, "grad_norm": 4.703763484954834, "learning_rate": 1.602885682970026e-05, "loss": 27.5949, "step": 42 }, { "epoch": 0.017489895009787225, "grad_norm": 4.844160556793213, "learning_rate": 1.464072663102903e-05, "loss": 28.8721, "step": 43 }, { "epoch": 0.01789663675420088, "grad_norm": 5.016782283782959, "learning_rate": 1.3425421036992098e-05, "loss": 27.4048, "step": 44 }, { "epoch": 0.018303378498614537, "grad_norm": 5.641413688659668, "learning_rate": 1.2388144172720251e-05, "loss": 27.7797, "step": 45 }, { "epoch": 0.01871012024302819, "grad_norm": 6.395452976226807, "learning_rate": 1.1533337816991932e-05, "loss": 27.9617, "step": 46 }, { "epoch": 0.01911686198744185, "grad_norm": 6.129427433013916, "learning_rate": 1.0864662381854632e-05, "loss": 25.9191, "step": 47 }, { "epoch": 0.019523603731855504, "grad_norm": 5.464219093322754, "learning_rate": 1.0384981238178534e-05, "loss": 25.7966, "step": 48 }, { "epoch": 0.01993034547626916, "grad_norm": 6.133424758911133, "learning_rate": 1.0096348454262845e-05, "loss": 25.617, "step": 49 }, { "epoch": 0.020337087220682816, "grad_norm": 7.993808269500732, "learning_rate": 1e-05, "loss": 22.7906, "step": 50 }, { "epoch": 0.020337087220682816, "eval_loss": 0.785561203956604, "eval_runtime": 5.4563, "eval_samples_per_second": 9.164, "eval_steps_per_second": 2.383, "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": 6.73658452077183e+17, "train_batch_size": 1, "trial_name": null, "trial_params": null }