| { | |
| "best_metric": 1.3211801052093506, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.0026203734032099572, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 5.240746806419915e-05, | |
| "grad_norm": 0.1738579273223877, | |
| "learning_rate": 0.0001, | |
| "loss": 1.3403, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 5.240746806419915e-05, | |
| "eval_loss": 1.598608374595642, | |
| "eval_runtime": 820.1786, | |
| "eval_samples_per_second": 9.797, | |
| "eval_steps_per_second": 4.899, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001048149361283983, | |
| "grad_norm": 0.20513613522052765, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1966, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00015722240419259744, | |
| "grad_norm": 0.20996616780757904, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 1.3571, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0002096298722567966, | |
| "grad_norm": 0.2220926582813263, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 1.2344, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00026203734032099573, | |
| "grad_norm": 0.24656227231025696, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 1.4127, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00031444480838519487, | |
| "grad_norm": 0.24758820235729218, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 1.4265, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00036685227644939406, | |
| "grad_norm": 0.24943935871124268, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 1.2982, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0004192597445135932, | |
| "grad_norm": 0.24972639977931976, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 1.2243, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00047166721257779233, | |
| "grad_norm": 0.2653735280036926, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 1.1996, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0005240746806419915, | |
| "grad_norm": 0.29955682158470154, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 1.1895, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0005764821487061906, | |
| "grad_norm": 0.2780078947544098, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 1.1721, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0006288896167703897, | |
| "grad_norm": 0.3014898896217346, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 1.3355, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0006812970848345889, | |
| "grad_norm": 0.3645365536212921, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 1.1965, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0007337045528987881, | |
| "grad_norm": 0.34544700384140015, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.0024, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0007861120209629873, | |
| "grad_norm": 0.35733968019485474, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 1.2473, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0008385194890271864, | |
| "grad_norm": 0.3587718605995178, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 1.2417, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0008909269570913855, | |
| "grad_norm": 0.3632557988166809, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 1.063, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0009433344251555847, | |
| "grad_norm": 0.29989340901374817, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.0668, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0009957418932197838, | |
| "grad_norm": 0.3830617368221283, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 1.1489, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.001048149361283983, | |
| "grad_norm": 0.46538257598876953, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 1.2864, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.001100556829348182, | |
| "grad_norm": 0.3305760622024536, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 1.1292, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0011529642974123812, | |
| "grad_norm": 0.36099550127983093, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 1.2849, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0012053717654765803, | |
| "grad_norm": 0.4047800898551941, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 1.3647, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0012577792335407795, | |
| "grad_norm": 0.3234100937843323, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 1.2295, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0013101867016049786, | |
| "grad_norm": 0.35075563192367554, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 1.2979, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0013101867016049786, | |
| "eval_loss": 1.3386822938919067, | |
| "eval_runtime": 823.3662, | |
| "eval_samples_per_second": 9.759, | |
| "eval_steps_per_second": 4.88, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0013625941696691778, | |
| "grad_norm": 0.39403942227363586, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2445, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.001415001637733377, | |
| "grad_norm": 0.43036386370658875, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 1.2675, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0014674091057975762, | |
| "grad_norm": 0.36898255348205566, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 1.2681, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0015198165738617754, | |
| "grad_norm": 0.48340263962745667, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 1.1686, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0015722240419259745, | |
| "grad_norm": 0.413663387298584, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 1.2895, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0016246315099901737, | |
| "grad_norm": 0.4055498242378235, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 1.2696, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0016770389780543728, | |
| "grad_norm": 0.4815317988395691, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 1.3778, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.001729446446118572, | |
| "grad_norm": 0.4714352786540985, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 1.345, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.001781853914182771, | |
| "grad_norm": 0.48492833971977234, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.3, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0018342613822469702, | |
| "grad_norm": 0.5202695727348328, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 1.3596, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0018866688503111693, | |
| "grad_norm": 0.5492162108421326, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 1.3763, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0019390763183753685, | |
| "grad_norm": 0.5086742043495178, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 1.3309, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0019914837864395676, | |
| "grad_norm": 0.6512495279312134, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 1.2766, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.002043891254503767, | |
| "grad_norm": 0.5928826332092285, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 1.2372, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.002096298722567966, | |
| "grad_norm": 0.9627623558044434, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 1.3238, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0021487061906321652, | |
| "grad_norm": 1.0270004272460938, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 1.4212, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.002201113658696364, | |
| "grad_norm": 1.0594191551208496, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 1.1272, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0022535211267605635, | |
| "grad_norm": 1.4876549243927002, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 1.3084, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0023059285948247624, | |
| "grad_norm": 2.034849166870117, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 1.5273, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0023583360628889618, | |
| "grad_norm": 1.6223154067993164, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 1.4066, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0024107435309531607, | |
| "grad_norm": 1.6114851236343384, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 1.2965, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.00246315099901736, | |
| "grad_norm": 1.6107181310653687, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 1.4148, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.002515558467081559, | |
| "grad_norm": 1.9817970991134644, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 1.6692, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0025679659351457583, | |
| "grad_norm": 5.455220699310303, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 2.7254, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0026203734032099572, | |
| "grad_norm": 7.535577297210693, | |
| "learning_rate": 0.0, | |
| "loss": 2.5626, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0026203734032099572, | |
| "eval_loss": 1.3211801052093506, | |
| "eval_runtime": 823.1773, | |
| "eval_samples_per_second": 9.761, | |
| "eval_steps_per_second": 4.881, | |
| "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": 1.02936877203456e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |