| { | |
| "best_metric": 2.102243423461914, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.0437636761487963, | |
| "eval_steps": 25, | |
| "global_step": 43, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0700218818380744, | |
| "grad_norm": 1.633942723274231, | |
| "learning_rate": 5e-05, | |
| "loss": 2.6952, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0700218818380744, | |
| "eval_loss": 3.6040544509887695, | |
| "eval_runtime": 3.2655, | |
| "eval_samples_per_second": 15.312, | |
| "eval_steps_per_second": 3.981, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1400437636761488, | |
| "grad_norm": 2.6368229389190674, | |
| "learning_rate": 0.0001, | |
| "loss": 3.3777, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.2100656455142232, | |
| "grad_norm": 3.303011894226074, | |
| "learning_rate": 9.986796105326832e-05, | |
| "loss": 3.7999, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.2800875273522976, | |
| "grad_norm": 1.2726417779922485, | |
| "learning_rate": 9.947261907011569e-05, | |
| "loss": 2.3031, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.350109409190372, | |
| "grad_norm": 1.2783796787261963, | |
| "learning_rate": 9.881629407450006e-05, | |
| "loss": 2.3962, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.4201312910284464, | |
| "grad_norm": 1.3582242727279663, | |
| "learning_rate": 9.790283764247188e-05, | |
| "loss": 2.6746, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.49015317286652077, | |
| "grad_norm": 1.5070379972457886, | |
| "learning_rate": 9.673761029959427e-05, | |
| "loss": 2.8905, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.5601750547045952, | |
| "grad_norm": 0.6870237588882446, | |
| "learning_rate": 9.53274500632475e-05, | |
| "loss": 2.0523, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.6301969365426696, | |
| "grad_norm": 0.9523475766181946, | |
| "learning_rate": 9.368063231442406e-05, | |
| "loss": 2.2519, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.700218818380744, | |
| "grad_norm": 1.1165454387664795, | |
| "learning_rate": 9.18068212345023e-05, | |
| "loss": 2.393, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.7702407002188184, | |
| "grad_norm": 0.695467472076416, | |
| "learning_rate": 8.971701309198744e-05, | |
| "loss": 2.0263, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.8402625820568927, | |
| "grad_norm": 0.6714878678321838, | |
| "learning_rate": 8.742347171203542e-05, | |
| "loss": 2.1084, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.9102844638949672, | |
| "grad_norm": 0.6725563406944275, | |
| "learning_rate": 8.493965650745043e-05, | |
| "loss": 2.1664, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.9803063457330415, | |
| "grad_norm": 1.050344705581665, | |
| "learning_rate": 8.228014349349872e-05, | |
| "loss": 2.3538, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.061269146608315, | |
| "grad_norm": 0.7588531374931335, | |
| "learning_rate": 7.946053975005496e-05, | |
| "loss": 3.6319, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.1312910284463895, | |
| "grad_norm": 0.4252834618091583, | |
| "learning_rate": 7.649739183305184e-05, | |
| "loss": 1.9929, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.201312910284464, | |
| "grad_norm": 0.513961136341095, | |
| "learning_rate": 7.34080886727103e-05, | |
| "loss": 2.2055, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.2713347921225382, | |
| "grad_norm": 0.293118417263031, | |
| "learning_rate": 7.021075952838262e-05, | |
| "loss": 1.8496, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.3413566739606126, | |
| "grad_norm": 0.4085014760494232, | |
| "learning_rate": 6.692416759884978e-05, | |
| "loss": 2.108, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.411378555798687, | |
| "grad_norm": 0.4628095328807831, | |
| "learning_rate": 6.356759991241008e-05, | |
| "loss": 2.0348, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.4814004376367615, | |
| "grad_norm": 0.7262138724327087, | |
| "learning_rate": 6.016075414292803e-05, | |
| "loss": 2.1714, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.551422319474836, | |
| "grad_norm": 0.3327035903930664, | |
| "learning_rate": 5.6723623016051596e-05, | |
| "loss": 1.9761, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.6214442013129102, | |
| "grad_norm": 0.351529598236084, | |
| "learning_rate": 5.3276376983948415e-05, | |
| "loss": 1.878, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.6914660831509847, | |
| "grad_norm": 0.45825445652008057, | |
| "learning_rate": 4.9839245857071994e-05, | |
| "loss": 2.03, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.7614879649890591, | |
| "grad_norm": 0.24266967177391052, | |
| "learning_rate": 4.643240008758992e-05, | |
| "loss": 1.7572, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.7614879649890591, | |
| "eval_loss": 2.102243423461914, | |
| "eval_runtime": 3.3017, | |
| "eval_samples_per_second": 15.144, | |
| "eval_steps_per_second": 3.937, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.8315098468271334, | |
| "grad_norm": 0.3337806165218353, | |
| "learning_rate": 4.307583240115024e-05, | |
| "loss": 2.0728, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.901531728665208, | |
| "grad_norm": 0.43844571709632874, | |
| "learning_rate": 3.9789240471617385e-05, | |
| "loss": 1.9171, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.9715536105032823, | |
| "grad_norm": 0.5971593856811523, | |
| "learning_rate": 3.659191132728971e-05, | |
| "loss": 2.1899, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.052516411378556, | |
| "grad_norm": 0.7736691832542419, | |
| "learning_rate": 3.350260816694816e-05, | |
| "loss": 3.8533, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.12253829321663, | |
| "grad_norm": 0.3334587812423706, | |
| "learning_rate": 3.0539460249945056e-05, | |
| "loss": 1.8422, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.192560175054705, | |
| "grad_norm": 0.4259639382362366, | |
| "learning_rate": 2.7719856506501306e-05, | |
| "loss": 2.0188, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.262582056892779, | |
| "grad_norm": 0.28523826599121094, | |
| "learning_rate": 2.5060343492549566e-05, | |
| "loss": 1.5945, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.3326039387308533, | |
| "grad_norm": 0.3401303291320801, | |
| "learning_rate": 2.257652828796459e-05, | |
| "loss": 2.1662, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.402625820568928, | |
| "grad_norm": 0.34653013944625854, | |
| "learning_rate": 2.0282986908012567e-05, | |
| "loss": 1.8795, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.472647702407002, | |
| "grad_norm": 0.5113685131072998, | |
| "learning_rate": 1.819317876549771e-05, | |
| "loss": 2.206, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.5426695842450764, | |
| "grad_norm": 0.3015807271003723, | |
| "learning_rate": 1.631936768557596e-05, | |
| "loss": 1.9851, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.612691466083151, | |
| "grad_norm": 0.300365149974823, | |
| "learning_rate": 1.4672549936752506e-05, | |
| "loss": 1.79, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.6827133479212253, | |
| "grad_norm": 0.3971630036830902, | |
| "learning_rate": 1.3262389700405744e-05, | |
| "loss": 1.9846, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.7527352297593, | |
| "grad_norm": 0.28160360455513, | |
| "learning_rate": 1.2097162357528127e-05, | |
| "loss": 1.569, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.822757111597374, | |
| "grad_norm": 0.31801754236221313, | |
| "learning_rate": 1.1183705925499948e-05, | |
| "loss": 2.2266, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.8927789934354484, | |
| "grad_norm": 0.34148961305618286, | |
| "learning_rate": 1.0527380929884324e-05, | |
| "loss": 1.8258, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.962800875273523, | |
| "grad_norm": 0.5395845770835876, | |
| "learning_rate": 1.013203894673168e-05, | |
| "loss": 2.0107, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 3.0437636761487963, | |
| "grad_norm": 0.8781525492668152, | |
| "learning_rate": 1e-05, | |
| "loss": 3.6523, | |
| "step": 43 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 43, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "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": 4.5753652022870016e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |