| { | |
| "best_metric": 2.9392035007476807, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.0818581807019339, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001637163614038678, | |
| "grad_norm": 28.32300567626953, | |
| "learning_rate": 5e-05, | |
| "loss": 5.0117, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001637163614038678, | |
| "eval_loss": 5.147194862365723, | |
| "eval_runtime": 2.2544, | |
| "eval_samples_per_second": 22.179, | |
| "eval_steps_per_second": 5.767, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003274327228077356, | |
| "grad_norm": 29.588274002075195, | |
| "learning_rate": 0.0001, | |
| "loss": 5.1001, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004911490842116034, | |
| "grad_norm": 7.590843677520752, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 4.2258, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006548654456154712, | |
| "grad_norm": 18.889446258544922, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 3.7787, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00818581807019339, | |
| "grad_norm": 6.354706287384033, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 3.365, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.009822981684232068, | |
| "grad_norm": 14.165648460388184, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 3.2361, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011460145298270746, | |
| "grad_norm": 10.230278968811035, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 3.1784, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.013097308912309424, | |
| "grad_norm": 9.195906639099121, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 3.1697, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.014734472526348102, | |
| "grad_norm": 9.030292510986328, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 3.2337, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01637163614038678, | |
| "grad_norm": 5.071252822875977, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 3.0394, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01800879975442546, | |
| "grad_norm": 2.1605753898620605, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 3.0335, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.019645963368464137, | |
| "grad_norm": 3.5285463333129883, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 3.0583, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.021283126982502815, | |
| "grad_norm": 4.790886402130127, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 3.0196, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.022920290596541493, | |
| "grad_norm": 2.627012252807617, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 3.0275, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.02455745421058017, | |
| "grad_norm": 1.0107060670852661, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 2.986, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02619461782461885, | |
| "grad_norm": 5.672317028045654, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 3.0447, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.027831781438657527, | |
| "grad_norm": 3.998746156692505, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 3.0285, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.029468945052696205, | |
| "grad_norm": 2.002378225326538, | |
| "learning_rate": 7.75e-05, | |
| "loss": 3.0233, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.031106108666734883, | |
| "grad_norm": 3.4826583862304688, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 2.9907, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.03274327228077356, | |
| "grad_norm": 1.492121696472168, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 3.0531, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03438043589481224, | |
| "grad_norm": 2.4119012355804443, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 3.0389, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.03601759950885092, | |
| "grad_norm": 3.34322452545166, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 3.03, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.037654763122889595, | |
| "grad_norm": 1.457808494567871, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 3.0592, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03929192673692827, | |
| "grad_norm": 1.8635289669036865, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 2.977, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.04092909035096695, | |
| "grad_norm": 0.6546595096588135, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 2.9863, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04092909035096695, | |
| "eval_loss": 2.9409637451171875, | |
| "eval_runtime": 2.3161, | |
| "eval_samples_per_second": 21.588, | |
| "eval_steps_per_second": 5.613, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04256625396500563, | |
| "grad_norm": 1.1100581884384155, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 2.9468, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.04420341757904431, | |
| "grad_norm": 0.9862481355667114, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 2.9487, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.045840581193082985, | |
| "grad_norm": 1.2358273267745972, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 2.9564, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.04747774480712166, | |
| "grad_norm": 0.9344875812530518, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 2.9207, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.04911490842116034, | |
| "grad_norm": 0.8685237169265747, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 2.9744, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05075207203519902, | |
| "grad_norm": 2.7281575202941895, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 2.9912, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0523892356492377, | |
| "grad_norm": 1.0124826431274414, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 2.9551, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.054026399263276376, | |
| "grad_norm": 0.9179672598838806, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 2.9473, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.055663562877315054, | |
| "grad_norm": 1.4163392782211304, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 2.9576, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.05730072649135373, | |
| "grad_norm": 1.061346173286438, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 2.9498, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.05893789010539241, | |
| "grad_norm": 1.157851219177246, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 2.9763, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.06057505371943109, | |
| "grad_norm": 2.304241180419922, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 2.9774, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.062212217333469766, | |
| "grad_norm": 0.8605313301086426, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 2.9791, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.06384938094750844, | |
| "grad_norm": 1.7160407304763794, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 2.9454, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.06548654456154712, | |
| "grad_norm": 1.476172685623169, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 2.9368, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0671237081755858, | |
| "grad_norm": 1.650292992591858, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 2.9679, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.06876087178962448, | |
| "grad_norm": 1.0009685754776, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 2.9895, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.07039803540366316, | |
| "grad_norm": 1.6898332834243774, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 2.9291, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.07203519901770183, | |
| "grad_norm": 1.084354043006897, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 2.9211, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.07367236263174051, | |
| "grad_norm": 0.9894816875457764, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 2.952, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.07530952624577919, | |
| "grad_norm": 0.7082793116569519, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 2.9281, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.07694668985981787, | |
| "grad_norm": 1.433164119720459, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 2.9442, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.07858385347385655, | |
| "grad_norm": 0.9894217848777771, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 2.9341, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.08022101708789522, | |
| "grad_norm": 0.9443101286888123, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 2.947, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0818581807019339, | |
| "grad_norm": 1.3589372634887695, | |
| "learning_rate": 1e-05, | |
| "loss": 2.9448, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0818581807019339, | |
| "eval_loss": 2.9392035007476807, | |
| "eval_runtime": 2.3169, | |
| "eval_samples_per_second": 21.58, | |
| "eval_steps_per_second": 5.611, | |
| "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": 6.174479344467968e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |