| { | |
| "best_metric": 1.1626672744750977, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.684931506849315, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0136986301369863, | |
| "grad_norm": 2.2717444896698, | |
| "learning_rate": 1e-05, | |
| "loss": 2.6772, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0136986301369863, | |
| "eval_loss": 2.6535723209381104, | |
| "eval_runtime": 17.3536, | |
| "eval_samples_per_second": 7.088, | |
| "eval_steps_per_second": 1.786, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0273972602739726, | |
| "grad_norm": 2.250619411468506, | |
| "learning_rate": 2e-05, | |
| "loss": 2.5427, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0410958904109589, | |
| "grad_norm": 2.453151226043701, | |
| "learning_rate": 3e-05, | |
| "loss": 2.6224, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0547945205479452, | |
| "grad_norm": 2.7786638736724854, | |
| "learning_rate": 4e-05, | |
| "loss": 2.4309, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0684931506849315, | |
| "grad_norm": 1.7362089157104492, | |
| "learning_rate": 5e-05, | |
| "loss": 2.3675, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0821917808219178, | |
| "grad_norm": 1.2283235788345337, | |
| "learning_rate": 6e-05, | |
| "loss": 2.2369, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0958904109589041, | |
| "grad_norm": 0.7412413954734802, | |
| "learning_rate": 7e-05, | |
| "loss": 2.0749, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.1095890410958904, | |
| "grad_norm": 0.505423367023468, | |
| "learning_rate": 8e-05, | |
| "loss": 2.2423, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1232876712328767, | |
| "grad_norm": 0.6371145844459534, | |
| "learning_rate": 9e-05, | |
| "loss": 2.0761, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.136986301369863, | |
| "grad_norm": 0.6269663572311401, | |
| "learning_rate": 0.0001, | |
| "loss": 1.9824, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1506849315068493, | |
| "grad_norm": 0.7009660005569458, | |
| "learning_rate": 9.999316524962345e-05, | |
| "loss": 1.9261, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1643835616438356, | |
| "grad_norm": 0.6795275211334229, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 2.0029, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1780821917808219, | |
| "grad_norm": 0.6740257740020752, | |
| "learning_rate": 9.993849845741524e-05, | |
| "loss": 1.982, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1917808219178082, | |
| "grad_norm": 0.5217537879943848, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 1.689, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.2054794520547945, | |
| "grad_norm": 0.6331390738487244, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 1.8042, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2191780821917808, | |
| "grad_norm": 0.6667072772979736, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 1.9436, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.2328767123287671, | |
| "grad_norm": 0.700835108757019, | |
| "learning_rate": 9.966546331768191e-05, | |
| "loss": 1.8068, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.2465753424657534, | |
| "grad_norm": 0.8332269787788391, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 1.7354, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2602739726027397, | |
| "grad_norm": 0.5449076294898987, | |
| "learning_rate": 9.944739353007344e-05, | |
| "loss": 1.635, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.273972602739726, | |
| "grad_norm": 0.5995677709579468, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 1.5748, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2876712328767123, | |
| "grad_norm": 0.5445329546928406, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 1.4626, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.3013698630136986, | |
| "grad_norm": 0.46622234582901, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 1.5722, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3150684931506849, | |
| "grad_norm": 0.48886317014694214, | |
| "learning_rate": 9.884934153917997e-05, | |
| "loss": 1.4759, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3287671232876712, | |
| "grad_norm": 0.46129897236824036, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 1.5249, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3424657534246575, | |
| "grad_norm": 0.465733140707016, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 1.4628, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3561643835616438, | |
| "grad_norm": 0.537723958492279, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 1.2661, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.3698630136986301, | |
| "grad_norm": 0.4723285734653473, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 1.4456, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.3835616438356164, | |
| "grad_norm": 0.46580037474632263, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 1.4272, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.3972602739726027, | |
| "grad_norm": 0.5159716606140137, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 1.3328, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.410958904109589, | |
| "grad_norm": 0.5439394116401672, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 1.2224, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4246575342465753, | |
| "grad_norm": 0.5588265657424927, | |
| "learning_rate": 9.701596950580806e-05, | |
| "loss": 1.3708, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.4383561643835616, | |
| "grad_norm": 0.5192043781280518, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 1.2998, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.4520547945205479, | |
| "grad_norm": 0.5172075033187866, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 1.2921, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.4657534246575342, | |
| "grad_norm": 0.6348913311958313, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 1.286, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.4794520547945205, | |
| "grad_norm": 0.5998979210853577, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 1.3788, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4931506849315068, | |
| "grad_norm": 0.7929552793502808, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 1.3353, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5068493150684932, | |
| "grad_norm": 0.5097240209579468, | |
| "learning_rate": 9.509956150664796e-05, | |
| "loss": 1.3159, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5205479452054794, | |
| "grad_norm": 0.46544161438941956, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 1.2599, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5342465753424658, | |
| "grad_norm": 0.5282853841781616, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 1.208, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.547945205479452, | |
| "grad_norm": 0.45313742756843567, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 1.188, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5616438356164384, | |
| "grad_norm": 0.5271946787834167, | |
| "learning_rate": 9.357421218136386e-05, | |
| "loss": 1.19, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5753424657534246, | |
| "grad_norm": 0.4225820302963257, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 1.2526, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.589041095890411, | |
| "grad_norm": 0.45803770422935486, | |
| "learning_rate": 9.273963562927695e-05, | |
| "loss": 1.2882, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.6027397260273972, | |
| "grad_norm": 0.4383608400821686, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 1.1984, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6164383561643836, | |
| "grad_norm": 0.37650492787361145, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 1.0522, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6301369863013698, | |
| "grad_norm": 0.47872722148895264, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 1.0916, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6438356164383562, | |
| "grad_norm": 0.6601381301879883, | |
| "learning_rate": 9.093124073433463e-05, | |
| "loss": 1.25, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6575342465753424, | |
| "grad_norm": 0.4518599808216095, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.1809, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6712328767123288, | |
| "grad_norm": 0.4847405254840851, | |
| "learning_rate": 8.995939984474624e-05, | |
| "loss": 1.1609, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.684931506849315, | |
| "grad_norm": 0.4608555734157562, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 1.0136, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.684931506849315, | |
| "eval_loss": 1.1626672744750977, | |
| "eval_runtime": 17.6106, | |
| "eval_samples_per_second": 6.984, | |
| "eval_steps_per_second": 1.76, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.3898961899225088e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |