| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 296, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.016891891891891893, | |
| "grad_norm": 7.82988987444574, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 1.2398, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.033783783783783786, | |
| "grad_norm": 3.3573634596072273, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.0752, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05067567567567568, | |
| "grad_norm": 3.3415007647224853, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0326, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.06756756756756757, | |
| "grad_norm": 2.908273898627516, | |
| "learning_rate": 4.9964854757667645e-05, | |
| "loss": 1.0739, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08445945945945946, | |
| "grad_norm": 2.6965407638337644, | |
| "learning_rate": 4.985952882516468e-05, | |
| "loss": 1.0738, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.10135135135135136, | |
| "grad_norm": 2.5010143912708998, | |
| "learning_rate": 4.9684351242973035e-05, | |
| "loss": 1.0438, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11824324324324324, | |
| "grad_norm": 2.44594685714455, | |
| "learning_rate": 4.943986926963291e-05, | |
| "loss": 1.0468, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.13513513513513514, | |
| "grad_norm": 2.2563440174008362, | |
| "learning_rate": 4.9126846672095325e-05, | |
| "loss": 1.0263, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.15202702702702703, | |
| "grad_norm": 2.130481918545586, | |
| "learning_rate": 4.87462613396977e-05, | |
| "loss": 1.0542, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.16891891891891891, | |
| "grad_norm": 2.1741230988593045, | |
| "learning_rate": 4.8299302229216506e-05, | |
| "loss": 1.022, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1858108108108108, | |
| "grad_norm": 2.216458763551228, | |
| "learning_rate": 4.7787365650540663e-05, | |
| "loss": 0.9784, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.20270270270270271, | |
| "grad_norm": 2.181227003643349, | |
| "learning_rate": 4.721205090456941e-05, | |
| "loss": 0.9879, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2195945945945946, | |
| "grad_norm": 1.9319935723192643, | |
| "learning_rate": 4.657515528696183e-05, | |
| "loss": 0.9703, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.23648648648648649, | |
| "grad_norm": 2.326459218447553, | |
| "learning_rate": 4.5878668473346464e-05, | |
| "loss": 0.9915, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.2533783783783784, | |
| "grad_norm": 1.7593142639554442, | |
| "learning_rate": 4.512476630353183e-05, | |
| "loss": 0.9678, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.2702702702702703, | |
| "grad_norm": 1.7875914414870993, | |
| "learning_rate": 4.4315803984135965e-05, | |
| "loss": 0.9596, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.28716216216216217, | |
| "grad_norm": 1.9567831550447699, | |
| "learning_rate": 4.345430873087026e-05, | |
| "loss": 0.9542, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.30405405405405406, | |
| "grad_norm": 1.8334603557415488, | |
| "learning_rate": 4.2542971873463075e-05, | |
| "loss": 0.9216, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.32094594594594594, | |
| "grad_norm": 1.9365108546192842, | |
| "learning_rate": 4.158464044788774e-05, | |
| "loss": 0.9221, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.33783783783783783, | |
| "grad_norm": 1.8139690377066564, | |
| "learning_rate": 4.058230830216084e-05, | |
| "loss": 0.932, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3547297297297297, | |
| "grad_norm": 1.7705655846493107, | |
| "learning_rate": 3.953910674349652e-05, | |
| "loss": 0.9252, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.3716216216216216, | |
| "grad_norm": 1.7041153435382332, | |
| "learning_rate": 3.8458294756035284e-05, | |
| "loss": 0.9264, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.3885135135135135, | |
| "grad_norm": 1.816586519511634, | |
| "learning_rate": 3.734324881970736e-05, | |
| "loss": 0.9329, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.40540540540540543, | |
| "grad_norm": 1.7153882113242487, | |
| "learning_rate": 3.619745236203666e-05, | |
| "loss": 0.8784, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.4222972972972973, | |
| "grad_norm": 1.8233978984102126, | |
| "learning_rate": 3.5024484875838145e-05, | |
| "loss": 0.8923, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.4391891891891892, | |
| "grad_norm": 1.779296796444449, | |
| "learning_rate": 3.3828010736805185e-05, | |
| "loss": 0.9095, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.4560810810810811, | |
| "grad_norm": 1.6239162071795656, | |
| "learning_rate": 3.261176775592097e-05, | |
| "loss": 0.8743, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.47297297297297297, | |
| "grad_norm": 1.4989182734644073, | |
| "learning_rate": 3.137955550245643e-05, | |
| "loss": 0.8681, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.48986486486486486, | |
| "grad_norm": 1.7183481374237066, | |
| "learning_rate": 3.0135223434034053e-05, | |
| "loss": 0.8889, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.5067567567567568, | |
| "grad_norm": 1.6795771031342455, | |
| "learning_rate": 2.8882658870839326e-05, | |
| "loss": 0.8992, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.5236486486486487, | |
| "grad_norm": 1.6530323754476526, | |
| "learning_rate": 2.7625774851548708e-05, | |
| "loss": 0.8336, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.5405405405405406, | |
| "grad_norm": 1.3946635254127566, | |
| "learning_rate": 2.6368497908912592e-05, | |
| "loss": 0.8207, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.5574324324324325, | |
| "grad_norm": 1.4796148274585628, | |
| "learning_rate": 2.511475580318233e-05, | |
| "loss": 0.8416, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.5743243243243243, | |
| "grad_norm": 1.49852650796059, | |
| "learning_rate": 2.386846525170263e-05, | |
| "loss": 0.84, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.5912162162162162, | |
| "grad_norm": 1.7728899100041309, | |
| "learning_rate": 2.2633519693002247e-05, | |
| "loss": 0.8052, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.6081081081081081, | |
| "grad_norm": 1.6520731494327665, | |
| "learning_rate": 2.1413777123608103e-05, | |
| "loss": 0.8317, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.625, | |
| "grad_norm": 1.5621396776802188, | |
| "learning_rate": 2.0213048045581014e-05, | |
| "loss": 0.7999, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.6418918918918919, | |
| "grad_norm": 1.6437350513388274, | |
| "learning_rate": 1.903508356242525e-05, | |
| "loss": 0.7832, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.6587837837837838, | |
| "grad_norm": 1.5761998076820292, | |
| "learning_rate": 1.78835636605603e-05, | |
| "loss": 0.7842, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.6756756756756757, | |
| "grad_norm": 1.5923154631394858, | |
| "learning_rate": 1.676208571296408e-05, | |
| "loss": 0.777, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.6925675675675675, | |
| "grad_norm": 1.5164569892106903, | |
| "learning_rate": 1.5674153240902257e-05, | |
| "loss": 0.7824, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.7094594594594594, | |
| "grad_norm": 1.4696651769808067, | |
| "learning_rate": 1.4623164968852327e-05, | |
| "loss": 0.7942, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.7263513513513513, | |
| "grad_norm": 1.505023224027423, | |
| "learning_rate": 1.3612404206815144e-05, | |
| "loss": 0.7628, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.7432432432432432, | |
| "grad_norm": 1.5620699336060837, | |
| "learning_rate": 1.2645028593183763e-05, | |
| "loss": 0.7528, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.7601351351351351, | |
| "grad_norm": 1.4813405293506552, | |
| "learning_rate": 1.1724060230213075e-05, | |
| "loss": 0.7415, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.777027027027027, | |
| "grad_norm": 1.5050749965559966, | |
| "learning_rate": 1.085237624290726e-05, | |
| "loss": 0.7425, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.793918918918919, | |
| "grad_norm": 1.4047518899511175, | |
| "learning_rate": 1.0032699790819288e-05, | |
| "loss": 0.7537, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.8108108108108109, | |
| "grad_norm": 1.4042082435446637, | |
| "learning_rate": 9.267591560841876e-06, | |
| "loss": 0.7277, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.8277027027027027, | |
| "grad_norm": 1.4871007843706388, | |
| "learning_rate": 8.559441767566378e-06, | |
| "loss": 0.7242, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.8445945945945946, | |
| "grad_norm": 1.5261738142982841, | |
| "learning_rate": 7.91046268620102e-06, | |
| "loss": 0.7699, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.8614864864864865, | |
| "grad_norm": 1.4626883984050318, | |
| "learning_rate": 7.322681741375405e-06, | |
| "loss": 0.732, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.8783783783783784, | |
| "grad_norm": 1.3656077607874797, | |
| "learning_rate": 6.797935173422361e-06, | |
| "loss": 0.7076, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.8952702702702703, | |
| "grad_norm": 1.4853495313270089, | |
| "learning_rate": 6.337862301923552e-06, | |
| "loss": 0.725, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.9121621621621622, | |
| "grad_norm": 1.4027238880507935, | |
| "learning_rate": 5.943900404439816e-06, | |
| "loss": 0.699, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.9290540540540541, | |
| "grad_norm": 1.42471410908483, | |
| "learning_rate": 5.617280226425088e-06, | |
| "loss": 0.6982, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.9459459459459459, | |
| "grad_norm": 1.4600014265794161, | |
| "learning_rate": 5.3590221363510965e-06, | |
| "loss": 0.6991, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.9628378378378378, | |
| "grad_norm": 1.3793123305032942, | |
| "learning_rate": 5.169932938054281e-06, | |
| "loss": 0.6947, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.9797297297297297, | |
| "grad_norm": 1.4174944247128423, | |
| "learning_rate": 5.050603350263229e-06, | |
| "loss": 0.6896, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.9966216216216216, | |
| "grad_norm": 1.5509303055221733, | |
| "learning_rate": 5.001406161180633e-06, | |
| "loss": 0.6857, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 296, | |
| "total_flos": 137372044492800.0, | |
| "train_loss": 0.8683076865366988, | |
| "train_runtime": 5339.1126, | |
| "train_samples_per_second": 1.772, | |
| "train_steps_per_second": 0.055 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 296, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 137372044492800.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |