| { | |
| "best_metric": 2.505044460296631, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.23837902264600716, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004767580452920143, | |
| "grad_norm": 3.17598819732666, | |
| "learning_rate": 1e-05, | |
| "loss": 2.7102, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004767580452920143, | |
| "eval_loss": 4.050970077514648, | |
| "eval_runtime": 24.7205, | |
| "eval_samples_per_second": 14.32, | |
| "eval_steps_per_second": 3.6, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009535160905840286, | |
| "grad_norm": 3.5215253829956055, | |
| "learning_rate": 2e-05, | |
| "loss": 2.6229, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.014302741358760428, | |
| "grad_norm": 1.8396703004837036, | |
| "learning_rate": 3e-05, | |
| "loss": 2.5976, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01907032181168057, | |
| "grad_norm": 1.822470784187317, | |
| "learning_rate": 4e-05, | |
| "loss": 2.8094, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.023837902264600714, | |
| "grad_norm": 1.784137487411499, | |
| "learning_rate": 5e-05, | |
| "loss": 2.7152, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.028605482717520857, | |
| "grad_norm": 1.5671970844268799, | |
| "learning_rate": 6e-05, | |
| "loss": 2.8053, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.033373063170441, | |
| "grad_norm": 1.2720322608947754, | |
| "learning_rate": 7e-05, | |
| "loss": 2.7655, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03814064362336114, | |
| "grad_norm": 1.3592026233673096, | |
| "learning_rate": 8e-05, | |
| "loss": 2.852, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04290822407628129, | |
| "grad_norm": 1.2666702270507812, | |
| "learning_rate": 9e-05, | |
| "loss": 2.8961, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04767580452920143, | |
| "grad_norm": 1.1434534788131714, | |
| "learning_rate": 0.0001, | |
| "loss": 2.5641, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.052443384982121574, | |
| "grad_norm": 1.2260290384292603, | |
| "learning_rate": 9.999316524962345e-05, | |
| "loss": 2.7242, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.057210965435041714, | |
| "grad_norm": 1.1492360830307007, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 2.6978, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.06197854588796186, | |
| "grad_norm": 1.1313751935958862, | |
| "learning_rate": 9.993849845741524e-05, | |
| "loss": 2.4025, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.066746126340882, | |
| "grad_norm": 1.216576099395752, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 2.5651, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.07151370679380215, | |
| "grad_norm": 1.0459645986557007, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 2.5407, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07628128724672228, | |
| "grad_norm": 1.1250581741333008, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 2.5113, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.08104886769964244, | |
| "grad_norm": 1.1516832113265991, | |
| "learning_rate": 9.966546331768191e-05, | |
| "loss": 2.5224, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.08581644815256258, | |
| "grad_norm": 0.9984982013702393, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 2.5051, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.09058402860548272, | |
| "grad_norm": 0.9816920161247253, | |
| "learning_rate": 9.944739353007344e-05, | |
| "loss": 2.5969, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.09535160905840286, | |
| "grad_norm": 1.113448977470398, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 2.4411, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.10011918951132301, | |
| "grad_norm": 1.2237359285354614, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 2.5044, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.10488676996424315, | |
| "grad_norm": 1.055956482887268, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 2.3804, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.10965435041716329, | |
| "grad_norm": 1.0263848304748535, | |
| "learning_rate": 9.884934153917997e-05, | |
| "loss": 2.3218, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.11442193087008343, | |
| "grad_norm": 1.0815330743789673, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 2.4918, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.11918951132300358, | |
| "grad_norm": 1.05085289478302, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 2.2042, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.12395709177592372, | |
| "grad_norm": 1.147608757019043, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 2.4462, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.12872467222884387, | |
| "grad_norm": 1.1940661668777466, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 2.4366, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.133492252681764, | |
| "grad_norm": 1.2002006769180298, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 2.3046, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.13825983313468415, | |
| "grad_norm": 1.225758671760559, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 2.344, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.1430274135876043, | |
| "grad_norm": 1.453913927078247, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 2.3262, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.14779499404052443, | |
| "grad_norm": 1.2313761711120605, | |
| "learning_rate": 9.701596950580806e-05, | |
| "loss": 2.2569, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.15256257449344457, | |
| "grad_norm": 1.3174500465393066, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 2.0015, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.1573301549463647, | |
| "grad_norm": 1.4254320859909058, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 2.2475, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.16209773539928488, | |
| "grad_norm": 2.1407878398895264, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 2.4093, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.16686531585220502, | |
| "grad_norm": 1.4871824979782104, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 2.2877, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.17163289630512515, | |
| "grad_norm": 1.8685574531555176, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 2.1265, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.1764004767580453, | |
| "grad_norm": 1.6461660861968994, | |
| "learning_rate": 9.509956150664796e-05, | |
| "loss": 2.4455, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.18116805721096543, | |
| "grad_norm": 1.6946738958358765, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 2.4016, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.18593563766388557, | |
| "grad_norm": 1.6008548736572266, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 2.5618, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1907032181168057, | |
| "grad_norm": 1.5371747016906738, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 2.4849, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.19547079856972585, | |
| "grad_norm": 1.770545244216919, | |
| "learning_rate": 9.357421218136386e-05, | |
| "loss": 2.3975, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.20023837902264602, | |
| "grad_norm": 1.924229621887207, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 2.7272, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.20500595947556616, | |
| "grad_norm": 1.900739073753357, | |
| "learning_rate": 9.273963562927695e-05, | |
| "loss": 2.8349, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.2097735399284863, | |
| "grad_norm": 2.0874862670898438, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 2.7109, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.21454112038140644, | |
| "grad_norm": 1.8650916814804077, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 2.6047, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.21930870083432658, | |
| "grad_norm": 2.0557563304901123, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 2.5962, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.22407628128724671, | |
| "grad_norm": 1.7432714700698853, | |
| "learning_rate": 9.093124073433463e-05, | |
| "loss": 2.3363, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.22884386174016685, | |
| "grad_norm": 2.252993583679199, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 2.5628, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.23361144219308702, | |
| "grad_norm": 2.2323484420776367, | |
| "learning_rate": 8.995939984474624e-05, | |
| "loss": 2.4012, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.23837902264600716, | |
| "grad_norm": 4.776430606842041, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 2.2413, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.23837902264600716, | |
| "eval_loss": 2.505044460296631, | |
| "eval_runtime": 25.1253, | |
| "eval_samples_per_second": 14.089, | |
| "eval_steps_per_second": 3.542, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 6.743754247923302e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |