| { | |
| "best_metric": 10.675261497497559, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.018867924528302, | |
| "eval_steps": 25, | |
| "global_step": 40, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07547169811320754, | |
| "grad_norm": 20.11607551574707, | |
| "learning_rate": 5e-05, | |
| "loss": 177.181, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07547169811320754, | |
| "eval_loss": 11.08830451965332, | |
| "eval_runtime": 1.0151, | |
| "eval_samples_per_second": 49.254, | |
| "eval_steps_per_second": 12.806, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1509433962264151, | |
| "grad_norm": 24.11052703857422, | |
| "learning_rate": 0.0001, | |
| "loss": 177.3502, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.22641509433962265, | |
| "grad_norm": 32.91762161254883, | |
| "learning_rate": 9.984630218530014e-05, | |
| "loss": 177.6314, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.3018867924528302, | |
| "grad_norm": 22.010360717773438, | |
| "learning_rate": 9.938625865312251e-05, | |
| "loss": 176.9671, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.37735849056603776, | |
| "grad_norm": 23.758106231689453, | |
| "learning_rate": 9.862301196726987e-05, | |
| "loss": 176.1839, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.4528301886792453, | |
| "grad_norm": 32.97089767456055, | |
| "learning_rate": 9.756177587652856e-05, | |
| "loss": 176.2955, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.5283018867924528, | |
| "grad_norm": 25.22259521484375, | |
| "learning_rate": 9.620979969947759e-05, | |
| "loss": 175.8945, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.6037735849056604, | |
| "grad_norm": 21.06655502319336, | |
| "learning_rate": 9.4576318804292e-05, | |
| "loss": 175.4053, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.6792452830188679, | |
| "grad_norm": 34.35733413696289, | |
| "learning_rate": 9.267249152181379e-05, | |
| "loss": 175.1699, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.7547169811320755, | |
| "grad_norm": 29.270862579345703, | |
| "learning_rate": 9.051132292283771e-05, | |
| "loss": 174.6092, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.8301886792452831, | |
| "grad_norm": 20.378381729125977, | |
| "learning_rate": 8.810757598029093e-05, | |
| "loss": 174.6108, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.9056603773584906, | |
| "grad_norm": 27.257905960083008, | |
| "learning_rate": 8.547767072315835e-05, | |
| "loss": 173.9752, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.9811320754716981, | |
| "grad_norm": 33.881919860839844, | |
| "learning_rate": 8.263957207103507e-05, | |
| "loss": 173.0851, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.0566037735849056, | |
| "grad_norm": 20.409860610961914, | |
| "learning_rate": 7.961266711550922e-05, | |
| "loss": 174.0382, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.1320754716981132, | |
| "grad_norm": 23.455223083496094, | |
| "learning_rate": 7.641763268666831e-05, | |
| "loss": 173.1041, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.2075471698113207, | |
| "grad_norm": 31.66672706604004, | |
| "learning_rate": 7.307629410938363e-05, | |
| "loss": 172.1156, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.2830188679245282, | |
| "grad_norm": 24.061498641967773, | |
| "learning_rate": 6.961147611421075e-05, | |
| "loss": 172.6154, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.3584905660377358, | |
| "grad_norm": 20.246477127075195, | |
| "learning_rate": 6.604684692133597e-05, | |
| "loss": 172.9048, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.4339622641509435, | |
| "grad_norm": 30.62285804748535, | |
| "learning_rate": 6.240675656263303e-05, | |
| "loss": 171.2423, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.509433962264151, | |
| "grad_norm": 26.93360137939453, | |
| "learning_rate": 5.8716070546254966e-05, | |
| "loss": 171.2233, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.5849056603773586, | |
| "grad_norm": 19.017606735229492, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 172.4291, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.6603773584905661, | |
| "grad_norm": 24.209728240966797, | |
| "learning_rate": 5.128392945374505e-05, | |
| "loss": 171.0764, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.7358490566037736, | |
| "grad_norm": 30.523046493530273, | |
| "learning_rate": 4.7593243437366975e-05, | |
| "loss": 169.7665, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.8113207547169812, | |
| "grad_norm": 18.54237937927246, | |
| "learning_rate": 4.395315307866405e-05, | |
| "loss": 172.3214, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.8867924528301887, | |
| "grad_norm": 22.909931182861328, | |
| "learning_rate": 4.0388523885789256e-05, | |
| "loss": 170.5708, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.8867924528301887, | |
| "eval_loss": 10.675261497497559, | |
| "eval_runtime": 0.126, | |
| "eval_samples_per_second": 396.832, | |
| "eval_steps_per_second": 103.176, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.9622641509433962, | |
| "grad_norm": 28.307985305786133, | |
| "learning_rate": 3.692370589061639e-05, | |
| "loss": 169.2845, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.0377358490566038, | |
| "grad_norm": 19.4202938079834, | |
| "learning_rate": 3.358236731333169e-05, | |
| "loss": 171.071, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.1132075471698113, | |
| "grad_norm": 20.111217498779297, | |
| "learning_rate": 3.0387332884490805e-05, | |
| "loss": 171.2749, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.188679245283019, | |
| "grad_norm": 27.161666870117188, | |
| "learning_rate": 2.736042792896495e-05, | |
| "loss": 169.209, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.2641509433962264, | |
| "grad_norm": 24.207616806030273, | |
| "learning_rate": 2.4522329276841663e-05, | |
| "loss": 169.4579, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.339622641509434, | |
| "grad_norm": 17.929601669311523, | |
| "learning_rate": 2.189242401970908e-05, | |
| "loss": 171.2735, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.4150943396226414, | |
| "grad_norm": 24.393522262573242, | |
| "learning_rate": 1.9488677077162295e-05, | |
| "loss": 169.3934, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.490566037735849, | |
| "grad_norm": 27.657506942749023, | |
| "learning_rate": 1.7327508478186218e-05, | |
| "loss": 168.3053, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.5660377358490565, | |
| "grad_norm": 17.512022018432617, | |
| "learning_rate": 1.5423681195707997e-05, | |
| "loss": 171.456, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.641509433962264, | |
| "grad_norm": 20.39818000793457, | |
| "learning_rate": 1.3790200300522413e-05, | |
| "loss": 169.7444, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.7169811320754715, | |
| "grad_norm": 26.587793350219727, | |
| "learning_rate": 1.2438224123471442e-05, | |
| "loss": 168.1875, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.7924528301886795, | |
| "grad_norm": 18.13593101501465, | |
| "learning_rate": 1.1376988032730134e-05, | |
| "loss": 170.666, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.867924528301887, | |
| "grad_norm": 19.847274780273438, | |
| "learning_rate": 1.0613741346877497e-05, | |
| "loss": 169.8308, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.9433962264150946, | |
| "grad_norm": 26.68253517150879, | |
| "learning_rate": 1.0153697814699859e-05, | |
| "loss": 167.9355, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 3.018867924528302, | |
| "grad_norm": 20.943115234375, | |
| "learning_rate": 1e-05, | |
| "loss": 169.3668, | |
| "step": 40 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 40, | |
| "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": 34883588063232.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |