| { | |
| "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": 8.13028513496866, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 1.2798, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.033783783783783786, | |
| "grad_norm": 3.5620083115927548, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.0801, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05067567567567568, | |
| "grad_norm": 3.3093983044774724, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0286, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.06756756756756757, | |
| "grad_norm": 2.9259388634182364, | |
| "learning_rate": 4.9964854757667645e-05, | |
| "loss": 1.0634, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08445945945945946, | |
| "grad_norm": 2.8065338500049846, | |
| "learning_rate": 4.985952882516468e-05, | |
| "loss": 1.0742, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.10135135135135136, | |
| "grad_norm": 2.562306586379742, | |
| "learning_rate": 4.9684351242973035e-05, | |
| "loss": 1.0474, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11824324324324324, | |
| "grad_norm": 2.650398108922061, | |
| "learning_rate": 4.943986926963291e-05, | |
| "loss": 1.0506, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.13513513513513514, | |
| "grad_norm": 2.292721416732774, | |
| "learning_rate": 4.9126846672095325e-05, | |
| "loss": 1.0221, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.15202702702702703, | |
| "grad_norm": 2.147422350521184, | |
| "learning_rate": 4.87462613396977e-05, | |
| "loss": 1.0509, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.16891891891891891, | |
| "grad_norm": 2.160055777676169, | |
| "learning_rate": 4.8299302229216506e-05, | |
| "loss": 1.0222, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1858108108108108, | |
| "grad_norm": 2.127693396380588, | |
| "learning_rate": 4.7787365650540663e-05, | |
| "loss": 0.9793, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.20270270270270271, | |
| "grad_norm": 2.07524575548144, | |
| "learning_rate": 4.721205090456941e-05, | |
| "loss": 0.9856, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2195945945945946, | |
| "grad_norm": 1.876482179181115, | |
| "learning_rate": 4.657515528696183e-05, | |
| "loss": 0.9715, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.23648648648648649, | |
| "grad_norm": 2.2104621839173846, | |
| "learning_rate": 4.5878668473346464e-05, | |
| "loss": 0.9883, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.2533783783783784, | |
| "grad_norm": 1.7760907365714962, | |
| "learning_rate": 4.512476630353183e-05, | |
| "loss": 0.9657, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.2702702702702703, | |
| "grad_norm": 1.8221427632245704, | |
| "learning_rate": 4.4315803984135965e-05, | |
| "loss": 0.9592, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.28716216216216217, | |
| "grad_norm": 1.9046050199248852, | |
| "learning_rate": 4.345430873087026e-05, | |
| "loss": 0.9513, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.30405405405405406, | |
| "grad_norm": 1.7830292324773953, | |
| "learning_rate": 4.2542971873463075e-05, | |
| "loss": 0.9195, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.32094594594594594, | |
| "grad_norm": 1.841247803426208, | |
| "learning_rate": 4.158464044788774e-05, | |
| "loss": 0.9224, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.33783783783783783, | |
| "grad_norm": 1.8694269639200451, | |
| "learning_rate": 4.058230830216084e-05, | |
| "loss": 0.9314, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3547297297297297, | |
| "grad_norm": 1.8736222919460577, | |
| "learning_rate": 3.953910674349652e-05, | |
| "loss": 0.9304, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.3716216216216216, | |
| "grad_norm": 1.6350257989779668, | |
| "learning_rate": 3.8458294756035284e-05, | |
| "loss": 0.9279, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.3885135135135135, | |
| "grad_norm": 1.803012265683364, | |
| "learning_rate": 3.734324881970736e-05, | |
| "loss": 0.9349, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.40540540540540543, | |
| "grad_norm": 1.8064493652132048, | |
| "learning_rate": 3.619745236203666e-05, | |
| "loss": 0.8794, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.4222972972972973, | |
| "grad_norm": 1.7963697461824464, | |
| "learning_rate": 3.5024484875838145e-05, | |
| "loss": 0.8911, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.4391891891891892, | |
| "grad_norm": 1.776261712635235, | |
| "learning_rate": 3.3828010736805185e-05, | |
| "loss": 0.9079, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.4560810810810811, | |
| "grad_norm": 1.6092978364007704, | |
| "learning_rate": 3.261176775592097e-05, | |
| "loss": 0.8745, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.47297297297297297, | |
| "grad_norm": 1.5079004831852607, | |
| "learning_rate": 3.137955550245643e-05, | |
| "loss": 0.8652, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.48986486486486486, | |
| "grad_norm": 1.6792811022830822, | |
| "learning_rate": 3.0135223434034053e-05, | |
| "loss": 0.8882, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.5067567567567568, | |
| "grad_norm": 1.6638882399627897, | |
| "learning_rate": 2.8882658870839326e-05, | |
| "loss": 0.8961, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.5236486486486487, | |
| "grad_norm": 1.6445982084590969, | |
| "learning_rate": 2.7625774851548708e-05, | |
| "loss": 0.8333, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.5405405405405406, | |
| "grad_norm": 1.3995403314995896, | |
| "learning_rate": 2.6368497908912592e-05, | |
| "loss": 0.8184, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.5574324324324325, | |
| "grad_norm": 1.4804077164539369, | |
| "learning_rate": 2.511475580318233e-05, | |
| "loss": 0.84, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.5743243243243243, | |
| "grad_norm": 1.5022073909572482, | |
| "learning_rate": 2.386846525170263e-05, | |
| "loss": 0.8374, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.5912162162162162, | |
| "grad_norm": 1.7168462642599709, | |
| "learning_rate": 2.2633519693002247e-05, | |
| "loss": 0.8018, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.6081081081081081, | |
| "grad_norm": 1.6168306870973288, | |
| "learning_rate": 2.1413777123608103e-05, | |
| "loss": 0.8316, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.625, | |
| "grad_norm": 1.594518741356322, | |
| "learning_rate": 2.0213048045581014e-05, | |
| "loss": 0.8005, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.6418918918918919, | |
| "grad_norm": 1.6309292174197987, | |
| "learning_rate": 1.903508356242525e-05, | |
| "loss": 0.7838, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.6587837837837838, | |
| "grad_norm": 1.5472838462411251, | |
| "learning_rate": 1.78835636605603e-05, | |
| "loss": 0.7833, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.6756756756756757, | |
| "grad_norm": 1.4645171972887558, | |
| "learning_rate": 1.676208571296408e-05, | |
| "loss": 0.7703, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.6925675675675675, | |
| "grad_norm": 1.544406833425164, | |
| "learning_rate": 1.5674153240902257e-05, | |
| "loss": 0.7837, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.7094594594594594, | |
| "grad_norm": 1.5227639810165863, | |
| "learning_rate": 1.4623164968852327e-05, | |
| "loss": 0.7935, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.7263513513513513, | |
| "grad_norm": 1.466593262947162, | |
| "learning_rate": 1.3612404206815144e-05, | |
| "loss": 0.7625, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.7432432432432432, | |
| "grad_norm": 1.5122312078520845, | |
| "learning_rate": 1.2645028593183763e-05, | |
| "loss": 0.7523, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.7601351351351351, | |
| "grad_norm": 1.4925416635497781, | |
| "learning_rate": 1.1724060230213075e-05, | |
| "loss": 0.7408, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.777027027027027, | |
| "grad_norm": 1.486253191645707, | |
| "learning_rate": 1.085237624290726e-05, | |
| "loss": 0.7423, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.793918918918919, | |
| "grad_norm": 1.385533463280539, | |
| "learning_rate": 1.0032699790819288e-05, | |
| "loss": 0.7508, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.8108108108108109, | |
| "grad_norm": 1.4094819946848187, | |
| "learning_rate": 9.267591560841876e-06, | |
| "loss": 0.7251, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.8277027027027027, | |
| "grad_norm": 1.5065956940993193, | |
| "learning_rate": 8.559441767566378e-06, | |
| "loss": 0.7249, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.8445945945945946, | |
| "grad_norm": 1.5597571594417456, | |
| "learning_rate": 7.91046268620102e-06, | |
| "loss": 0.7681, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.8614864864864865, | |
| "grad_norm": 1.4344047894033067, | |
| "learning_rate": 7.322681741375405e-06, | |
| "loss": 0.729, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.8783783783783784, | |
| "grad_norm": 1.406848470364391, | |
| "learning_rate": 6.797935173422361e-06, | |
| "loss": 0.707, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.8952702702702703, | |
| "grad_norm": 1.473371363524701, | |
| "learning_rate": 6.337862301923552e-06, | |
| "loss": 0.7237, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.9121621621621622, | |
| "grad_norm": 1.4053578084417369, | |
| "learning_rate": 5.943900404439816e-06, | |
| "loss": 0.7005, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.9290540540540541, | |
| "grad_norm": 1.4260858889219359, | |
| "learning_rate": 5.617280226425088e-06, | |
| "loss": 0.6978, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.9459459459459459, | |
| "grad_norm": 1.458565550822819, | |
| "learning_rate": 5.3590221363510965e-06, | |
| "loss": 0.6992, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.9628378378378378, | |
| "grad_norm": 1.3712460796459922, | |
| "learning_rate": 5.169932938054281e-06, | |
| "loss": 0.6935, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.9797297297297297, | |
| "grad_norm": 1.4140757719345507, | |
| "learning_rate": 5.050603350263229e-06, | |
| "loss": 0.6866, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.9966216216216216, | |
| "grad_norm": 1.56665314387651, | |
| "learning_rate": 5.001406161180633e-06, | |
| "loss": 0.687, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 296, | |
| "total_flos": 120899332866048.0, | |
| "train_loss": 0.8681221529841423, | |
| "train_runtime": 4929.6945, | |
| "train_samples_per_second": 1.919, | |
| "train_steps_per_second": 0.06 | |
| } | |
| ], | |
| "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": 120899332866048.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |