| { | |
| "best_metric": 11.923685073852539, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.06441742491343909, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0012883484982687816, | |
| "grad_norm": 0.048539936542510986, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9281, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012883484982687816, | |
| "eval_loss": 11.9253511428833, | |
| "eval_runtime": 0.4089, | |
| "eval_samples_per_second": 122.268, | |
| "eval_steps_per_second": 31.79, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0025766969965375633, | |
| "grad_norm": 0.053119681775569916, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9278, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0038650454948063453, | |
| "grad_norm": 0.05989433825016022, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 11.9329, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0051533939930751265, | |
| "grad_norm": 0.062168803066015244, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 11.932, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006441742491343909, | |
| "grad_norm": 0.07310941815376282, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 11.9291, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007730090989612691, | |
| "grad_norm": 0.05801079422235489, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 11.9289, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009018439487881473, | |
| "grad_norm": 0.06138140708208084, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 11.9358, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.010306787986150253, | |
| "grad_norm": 0.07306931912899017, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 11.9331, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.011595136484419035, | |
| "grad_norm": 0.05695130676031113, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 11.9326, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.012883484982687817, | |
| "grad_norm": 0.09059657156467438, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 11.9373, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0141718334809566, | |
| "grad_norm": 0.09676135331392288, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 11.9358, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.015460181979225381, | |
| "grad_norm": 0.10840746760368347, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 11.9286, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.016748530477494163, | |
| "grad_norm": 0.052489735186100006, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 11.9236, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.018036878975762945, | |
| "grad_norm": 0.056314706802368164, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 11.9293, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.019325227474031724, | |
| "grad_norm": 0.05119406431913376, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 11.9303, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.020613575972300506, | |
| "grad_norm": 0.06829789280891418, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 11.9298, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.021901924470569288, | |
| "grad_norm": 0.06619300693273544, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 11.9338, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.02319027296883807, | |
| "grad_norm": 0.05443047732114792, | |
| "learning_rate": 7.75e-05, | |
| "loss": 11.9327, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.024478621467106852, | |
| "grad_norm": 0.06553514301776886, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 11.9294, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.025766969965375634, | |
| "grad_norm": 0.06389756500720978, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 11.9326, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.027055318463644416, | |
| "grad_norm": 0.08612143993377686, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 11.933, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0283436669619132, | |
| "grad_norm": 0.08408196270465851, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 11.9328, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.02963201546018198, | |
| "grad_norm": 0.07887254655361176, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 11.9295, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.030920363958450763, | |
| "grad_norm": 0.10497775673866272, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 11.9335, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.032208712456719545, | |
| "grad_norm": 0.1221204474568367, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 11.9234, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.032208712456719545, | |
| "eval_loss": 11.924160957336426, | |
| "eval_runtime": 0.3975, | |
| "eval_samples_per_second": 125.773, | |
| "eval_steps_per_second": 32.701, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03349706095498833, | |
| "grad_norm": 0.0387251116335392, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 11.9256, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.03478540945325711, | |
| "grad_norm": 0.05117788165807724, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 11.9301, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03607375795152589, | |
| "grad_norm": 0.06159388646483421, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 11.9291, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03736210644979467, | |
| "grad_norm": 0.05920449271798134, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 11.9297, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.03865045494806345, | |
| "grad_norm": 0.05900543928146362, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 11.9322, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03993880344633223, | |
| "grad_norm": 0.07509998232126236, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 11.9318, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.04122715194460101, | |
| "grad_norm": 0.05402457341551781, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 11.9332, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.042515500442869794, | |
| "grad_norm": 0.07642818242311478, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 11.9317, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.043803848941138576, | |
| "grad_norm": 0.07618825137615204, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 11.9314, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.04509219743940736, | |
| "grad_norm": 0.07970647513866425, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 11.9298, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04638054593767614, | |
| "grad_norm": 0.09614846855401993, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 11.9282, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.04766889443594492, | |
| "grad_norm": 0.09132824838161469, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 11.9314, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.048957242934213704, | |
| "grad_norm": 0.05499568209052086, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 11.9266, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.050245591432482486, | |
| "grad_norm": 0.06326848268508911, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 11.9281, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.05153393993075127, | |
| "grad_norm": 0.0581451915204525, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 11.9286, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05282228842902005, | |
| "grad_norm": 0.05580763891339302, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 11.9348, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.05411063692728883, | |
| "grad_norm": 0.05445316061377525, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 11.9312, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.055398985425557615, | |
| "grad_norm": 0.06570111215114594, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 11.9303, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0566873339238264, | |
| "grad_norm": 0.05715864524245262, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 11.9305, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.05797568242209518, | |
| "grad_norm": 0.08479540795087814, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 11.9322, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.05926403092036396, | |
| "grad_norm": 0.07357271760702133, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 11.9323, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.06055237941863274, | |
| "grad_norm": 0.08492587506771088, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 11.9285, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.061840727916901525, | |
| "grad_norm": 0.094068244099617, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 11.9307, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.06312907641517031, | |
| "grad_norm": 0.08566364645957947, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 11.9367, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.06441742491343909, | |
| "grad_norm": 0.13023607432842255, | |
| "learning_rate": 1e-05, | |
| "loss": 11.9288, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06441742491343909, | |
| "eval_loss": 11.923685073852539, | |
| "eval_runtime": 0.4067, | |
| "eval_samples_per_second": 122.955, | |
| "eval_steps_per_second": 31.968, | |
| "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": 1042494259200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |