| { | |
| "best_metric": 0.42325812578201294, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.7259528130671506, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.014519056261343012, | |
| "grad_norm": 2.657820224761963, | |
| "learning_rate": 5e-05, | |
| "loss": 7.5981, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.014519056261343012, | |
| "eval_loss": 0.6531733870506287, | |
| "eval_runtime": 2.9331, | |
| "eval_samples_per_second": 17.047, | |
| "eval_steps_per_second": 4.432, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.029038112522686024, | |
| "grad_norm": 3.6074953079223633, | |
| "learning_rate": 0.0001, | |
| "loss": 8.0365, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.043557168784029036, | |
| "grad_norm": 3.2320640087127686, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 8.8113, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05807622504537205, | |
| "grad_norm": 2.4059534072875977, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 8.5977, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.07259528130671507, | |
| "grad_norm": 2.85628080368042, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 8.418, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08711433756805807, | |
| "grad_norm": 2.938264846801758, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 8.5648, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.10163339382940109, | |
| "grad_norm": 2.9559366703033447, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 8.8896, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.1161524500907441, | |
| "grad_norm": 2.9382541179656982, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 8.3741, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1306715063520871, | |
| "grad_norm": 2.7987473011016846, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 8.1946, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.14519056261343014, | |
| "grad_norm": 3.0692875385284424, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 7.9118, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.15970961887477314, | |
| "grad_norm": 3.259798049926758, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 8.1635, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.17422867513611615, | |
| "grad_norm": 3.6493375301361084, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 7.9403, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.18874773139745918, | |
| "grad_norm": 4.820369243621826, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 7.0339, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.20326678765880218, | |
| "grad_norm": 2.4591588973999023, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 6.8247, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.2177858439201452, | |
| "grad_norm": 2.336448907852173, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 7.1584, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2323049001814882, | |
| "grad_norm": 2.1682724952697754, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 6.947, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.24682395644283123, | |
| "grad_norm": 2.0687825679779053, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 7.5692, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.2613430127041742, | |
| "grad_norm": 1.9462329149246216, | |
| "learning_rate": 7.75e-05, | |
| "loss": 7.4073, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.27586206896551724, | |
| "grad_norm": 2.077258586883545, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 7.6801, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.29038112522686027, | |
| "grad_norm": 2.139176845550537, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 7.3446, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.30490018148820325, | |
| "grad_norm": 2.1667635440826416, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 7.4394, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.3194192377495463, | |
| "grad_norm": 2.3544504642486572, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 7.3981, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3339382940108893, | |
| "grad_norm": 2.452507972717285, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 7.2098, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3484573502722323, | |
| "grad_norm": 2.830589532852173, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 7.2659, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3629764065335753, | |
| "grad_norm": 3.9729185104370117, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 7.6919, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3629764065335753, | |
| "eval_loss": 0.44446834921836853, | |
| "eval_runtime": 3.0044, | |
| "eval_samples_per_second": 16.642, | |
| "eval_steps_per_second": 4.327, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.37749546279491836, | |
| "grad_norm": 1.2319997549057007, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 6.0149, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.39201451905626133, | |
| "grad_norm": 1.5031059980392456, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 6.6979, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.40653357531760437, | |
| "grad_norm": 1.725165843963623, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 6.7276, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": 1.559391736984253, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 6.9098, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.4355716878402904, | |
| "grad_norm": 1.6204358339309692, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 7.266, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4500907441016334, | |
| "grad_norm": 1.7478471994400024, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 7.3426, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.4646098003629764, | |
| "grad_norm": 1.859602451324463, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 7.0126, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.4791288566243194, | |
| "grad_norm": 1.9271974563598633, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 7.0889, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.49364791288566245, | |
| "grad_norm": 2.088104009628296, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 6.8118, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.5081669691470054, | |
| "grad_norm": 2.275719404220581, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 7.0964, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.5226860254083484, | |
| "grad_norm": 2.5453503131866455, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 6.7696, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5372050816696915, | |
| "grad_norm": 3.2486155033111572, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 6.8947, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5517241379310345, | |
| "grad_norm": 3.0056145191192627, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 5.952, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5662431941923775, | |
| "grad_norm": 1.3381630182266235, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 6.1744, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5807622504537205, | |
| "grad_norm": 1.6222202777862549, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 6.6613, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5952813067150635, | |
| "grad_norm": 1.715443730354309, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 6.4672, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.6098003629764065, | |
| "grad_norm": 1.7360793352127075, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 7.3668, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.6243194192377496, | |
| "grad_norm": 1.8243736028671265, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 6.5175, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.6388384754990926, | |
| "grad_norm": 1.931254506111145, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 6.7514, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6533575317604355, | |
| "grad_norm": 2.2752747535705566, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 7.2249, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6678765880217786, | |
| "grad_norm": 2.2827963829040527, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 7.4122, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6823956442831216, | |
| "grad_norm": 2.2568490505218506, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 6.6329, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6969147005444646, | |
| "grad_norm": 2.7081212997436523, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 6.6874, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.7114337568058077, | |
| "grad_norm": 2.533864974975586, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 6.7553, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.7259528130671506, | |
| "grad_norm": 3.477332353591919, | |
| "learning_rate": 1e-05, | |
| "loss": 7.084, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7259528130671506, | |
| "eval_loss": 0.42325812578201294, | |
| "eval_runtime": 3.0213, | |
| "eval_samples_per_second": 16.549, | |
| "eval_steps_per_second": 4.303, | |
| "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": 5.2936176405210726e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |