| { | |
| "best_metric": 2.1035513877868652, | |
| "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": 1.607485055923462, | |
| "learning_rate": 5e-05, | |
| "loss": 2.6952, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0700218818380744, | |
| "eval_loss": 3.6040544509887695, | |
| "eval_runtime": 3.2415, | |
| "eval_samples_per_second": 15.425, | |
| "eval_steps_per_second": 4.011, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1400437636761488, | |
| "grad_norm": 2.5791707038879395, | |
| "learning_rate": 0.0001, | |
| "loss": 3.3777, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.2100656455142232, | |
| "grad_norm": 3.2545909881591797, | |
| "learning_rate": 9.986796105326832e-05, | |
| "loss": 3.803, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.2800875273522976, | |
| "grad_norm": 1.2896122932434082, | |
| "learning_rate": 9.947261907011569e-05, | |
| "loss": 2.3061, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.350109409190372, | |
| "grad_norm": 1.3053289651870728, | |
| "learning_rate": 9.881629407450006e-05, | |
| "loss": 2.3994, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.4201312910284464, | |
| "grad_norm": 1.433174729347229, | |
| "learning_rate": 9.790283764247188e-05, | |
| "loss": 2.6779, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.49015317286652077, | |
| "grad_norm": 1.5237914323806763, | |
| "learning_rate": 9.673761029959427e-05, | |
| "loss": 2.8931, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.5601750547045952, | |
| "grad_norm": 0.6750289797782898, | |
| "learning_rate": 9.53274500632475e-05, | |
| "loss": 2.0532, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.6301969365426696, | |
| "grad_norm": 0.9610247015953064, | |
| "learning_rate": 9.368063231442406e-05, | |
| "loss": 2.2542, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.700218818380744, | |
| "grad_norm": 1.1329214572906494, | |
| "learning_rate": 9.18068212345023e-05, | |
| "loss": 2.3939, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.7702407002188184, | |
| "grad_norm": 0.7043794393539429, | |
| "learning_rate": 8.971701309198744e-05, | |
| "loss": 2.0261, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.8402625820568927, | |
| "grad_norm": 0.6860369443893433, | |
| "learning_rate": 8.742347171203542e-05, | |
| "loss": 2.1089, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.9102844638949672, | |
| "grad_norm": 0.6755335330963135, | |
| "learning_rate": 8.493965650745043e-05, | |
| "loss": 2.1665, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.9803063457330415, | |
| "grad_norm": 1.143149733543396, | |
| "learning_rate": 8.228014349349872e-05, | |
| "loss": 2.3539, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.061269146608315, | |
| "grad_norm": 0.7558560967445374, | |
| "learning_rate": 7.946053975005496e-05, | |
| "loss": 3.6319, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.1312910284463895, | |
| "grad_norm": 0.42343437671661377, | |
| "learning_rate": 7.649739183305184e-05, | |
| "loss": 1.9934, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.201312910284464, | |
| "grad_norm": 0.5155521631240845, | |
| "learning_rate": 7.34080886727103e-05, | |
| "loss": 2.206, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.2713347921225382, | |
| "grad_norm": 0.29460009932518005, | |
| "learning_rate": 7.021075952838262e-05, | |
| "loss": 1.85, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.3413566739606126, | |
| "grad_norm": 0.40457290410995483, | |
| "learning_rate": 6.692416759884978e-05, | |
| "loss": 2.1079, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.411378555798687, | |
| "grad_norm": 0.4749963879585266, | |
| "learning_rate": 6.356759991241008e-05, | |
| "loss": 2.0364, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.4814004376367615, | |
| "grad_norm": 0.7398020625114441, | |
| "learning_rate": 6.016075414292803e-05, | |
| "loss": 2.1746, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.551422319474836, | |
| "grad_norm": 0.3198608458042145, | |
| "learning_rate": 5.6723623016051596e-05, | |
| "loss": 1.976, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.6214442013129102, | |
| "grad_norm": 0.35151830315589905, | |
| "learning_rate": 5.3276376983948415e-05, | |
| "loss": 1.8765, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.6914660831509847, | |
| "grad_norm": 0.4493955075740814, | |
| "learning_rate": 4.9839245857071994e-05, | |
| "loss": 2.0302, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.7614879649890591, | |
| "grad_norm": 0.25013086199760437, | |
| "learning_rate": 4.643240008758992e-05, | |
| "loss": 1.7574, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.7614879649890591, | |
| "eval_loss": 2.1035513877868652, | |
| "eval_runtime": 3.2837, | |
| "eval_samples_per_second": 15.227, | |
| "eval_steps_per_second": 3.959, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.8315098468271334, | |
| "grad_norm": 0.3228803277015686, | |
| "learning_rate": 4.307583240115024e-05, | |
| "loss": 2.0718, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.901531728665208, | |
| "grad_norm": 0.43157458305358887, | |
| "learning_rate": 3.9789240471617385e-05, | |
| "loss": 1.9175, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.9715536105032823, | |
| "grad_norm": 0.6008814573287964, | |
| "learning_rate": 3.659191132728971e-05, | |
| "loss": 2.1905, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.052516411378556, | |
| "grad_norm": 0.7690155506134033, | |
| "learning_rate": 3.350260816694816e-05, | |
| "loss": 3.8515, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.12253829321663, | |
| "grad_norm": 0.3333316743373871, | |
| "learning_rate": 3.0539460249945056e-05, | |
| "loss": 1.8417, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.192560175054705, | |
| "grad_norm": 0.4248466491699219, | |
| "learning_rate": 2.7719856506501306e-05, | |
| "loss": 2.0182, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.262582056892779, | |
| "grad_norm": 0.28588610887527466, | |
| "learning_rate": 2.5060343492549566e-05, | |
| "loss": 1.595, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.3326039387308533, | |
| "grad_norm": 0.3386515974998474, | |
| "learning_rate": 2.257652828796459e-05, | |
| "loss": 2.166, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.402625820568928, | |
| "grad_norm": 0.34300777316093445, | |
| "learning_rate": 2.0282986908012567e-05, | |
| "loss": 1.8786, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.472647702407002, | |
| "grad_norm": 0.5166144967079163, | |
| "learning_rate": 1.819317876549771e-05, | |
| "loss": 2.2071, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.5426695842450764, | |
| "grad_norm": 0.30271419882774353, | |
| "learning_rate": 1.631936768557596e-05, | |
| "loss": 1.9849, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.612691466083151, | |
| "grad_norm": 0.3006140887737274, | |
| "learning_rate": 1.4672549936752506e-05, | |
| "loss": 1.79, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.6827133479212253, | |
| "grad_norm": 0.3940806984901428, | |
| "learning_rate": 1.3262389700405744e-05, | |
| "loss": 1.9845, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.7527352297593, | |
| "grad_norm": 0.28143924474716187, | |
| "learning_rate": 1.2097162357528127e-05, | |
| "loss": 1.5694, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.822757111597374, | |
| "grad_norm": 0.31365570425987244, | |
| "learning_rate": 1.1183705925499948e-05, | |
| "loss": 2.2253, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.8927789934354484, | |
| "grad_norm": 0.34873420000076294, | |
| "learning_rate": 1.0527380929884324e-05, | |
| "loss": 1.8256, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.962800875273523, | |
| "grad_norm": 0.5362803339958191, | |
| "learning_rate": 1.013203894673168e-05, | |
| "loss": 2.0108, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 3.0437636761487963, | |
| "grad_norm": 0.8738157153129578, | |
| "learning_rate": 1e-05, | |
| "loss": 3.6501, | |
| "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 | |
| } | |