| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.05959475566150179, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011918951132300357, | |
| "grad_norm": 2.9031435226589246, | |
| "learning_rate": 2e-05, | |
| "loss": 2.1072, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0023837902264600714, | |
| "grad_norm": 2.7150248182983923, | |
| "learning_rate": 1.9979453927503366e-05, | |
| "loss": 2.101, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.003575685339690107, | |
| "grad_norm": 1.6481585515596062, | |
| "learning_rate": 1.991790013823246e-05, | |
| "loss": 2.0284, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004767580452920143, | |
| "grad_norm": 2.290158944264602, | |
| "learning_rate": 1.9815591569910654e-05, | |
| "loss": 2.0343, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0059594755661501785, | |
| "grad_norm": 1.620010410362664, | |
| "learning_rate": 1.9672948630390296e-05, | |
| "loss": 2.022, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007151370679380214, | |
| "grad_norm": 1.2963689571694739, | |
| "learning_rate": 1.949055747010669e-05, | |
| "loss": 2.0615, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00834326579261025, | |
| "grad_norm": 1.1986327536123562, | |
| "learning_rate": 1.926916757346022e-05, | |
| "loss": 2.0193, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.009535160905840286, | |
| "grad_norm": 0.7287087756055839, | |
| "learning_rate": 1.900968867902419e-05, | |
| "loss": 1.9835, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.010727056019070322, | |
| "grad_norm": 0.7584838316893223, | |
| "learning_rate": 1.8713187041233896e-05, | |
| "loss": 2.0048, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.011918951132300357, | |
| "grad_norm": 0.6198276917269713, | |
| "learning_rate": 1.8380881048918406e-05, | |
| "loss": 1.9825, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.013110846245530394, | |
| "grad_norm": 0.46373328707102957, | |
| "learning_rate": 1.8014136218679566e-05, | |
| "loss": 1.9862, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.014302741358760428, | |
| "grad_norm": 0.5577755717812845, | |
| "learning_rate": 1.7614459583691346e-05, | |
| "loss": 1.9776, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.015494636471990465, | |
| "grad_norm": 0.5939670606164611, | |
| "learning_rate": 1.7183493500977277e-05, | |
| "loss": 1.9674, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0166865315852205, | |
| "grad_norm": 0.4628705732184792, | |
| "learning_rate": 1.672300890261317e-05, | |
| "loss": 1.9734, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.017878426698450536, | |
| "grad_norm": 0.485766773190629, | |
| "learning_rate": 1.6234898018587336e-05, | |
| "loss": 1.9846, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01907032181168057, | |
| "grad_norm": 0.5223550727317597, | |
| "learning_rate": 1.5721166601221697e-05, | |
| "loss": 1.9647, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.02026221692491061, | |
| "grad_norm": 0.4433368830898489, | |
| "learning_rate": 1.5183925683105254e-05, | |
| "loss": 1.9842, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.021454112038140644, | |
| "grad_norm": 0.3532051409411447, | |
| "learning_rate": 1.4625382902408356e-05, | |
| "loss": 1.9792, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02264600715137068, | |
| "grad_norm": 0.3750713272673884, | |
| "learning_rate": 1.4047833431223938e-05, | |
| "loss": 1.992, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.023837902264600714, | |
| "grad_norm": 0.3478672288559764, | |
| "learning_rate": 1.3453650544213078e-05, | |
| "loss": 2.0017, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.025029797377830752, | |
| "grad_norm": 0.3124495293347313, | |
| "learning_rate": 1.2845275866310325e-05, | |
| "loss": 1.9654, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.026221692491060787, | |
| "grad_norm": 0.30827848535728997, | |
| "learning_rate": 1.2225209339563144e-05, | |
| "loss": 1.9742, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.027413587604290822, | |
| "grad_norm": 0.3531950759587543, | |
| "learning_rate": 1.1595998950333794e-05, | |
| "loss": 1.9899, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.028605482717520857, | |
| "grad_norm": 0.3222872371524797, | |
| "learning_rate": 1.0960230259076819e-05, | |
| "loss": 1.982, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.029797377830750895, | |
| "grad_norm": 0.28066157317874146, | |
| "learning_rate": 1.0320515775716556e-05, | |
| "loss": 1.989, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03098927294398093, | |
| "grad_norm": 0.28664391299284936, | |
| "learning_rate": 9.67948422428345e-06, | |
| "loss": 1.9926, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.03218116805721097, | |
| "grad_norm": 0.32690441539002585, | |
| "learning_rate": 9.039769740923183e-06, | |
| "loss": 1.9977, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.033373063170441, | |
| "grad_norm": 0.26400158066485074, | |
| "learning_rate": 8.404001049666211e-06, | |
| "loss": 2.0056, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03456495828367104, | |
| "grad_norm": 0.23533776552109373, | |
| "learning_rate": 7.774790660436857e-06, | |
| "loss": 1.9724, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.03575685339690107, | |
| "grad_norm": 0.22178984088070275, | |
| "learning_rate": 7.154724133689677e-06, | |
| "loss": 1.9487, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03694874851013111, | |
| "grad_norm": 0.23840728595761607, | |
| "learning_rate": 6.546349455786926e-06, | |
| "loss": 1.9871, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.03814064362336114, | |
| "grad_norm": 0.2270923288108359, | |
| "learning_rate": 5.952166568776062e-06, | |
| "loss": 2.0023, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.03933253873659118, | |
| "grad_norm": 0.21128333879501035, | |
| "learning_rate": 5.37461709759165e-06, | |
| "loss": 1.9781, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.04052443384982122, | |
| "grad_norm": 0.20025698249162766, | |
| "learning_rate": 4.81607431689475e-06, | |
| "loss": 2.0167, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.041716328963051254, | |
| "grad_norm": 0.19545125950438635, | |
| "learning_rate": 4.278833398778306e-06, | |
| "loss": 2.0014, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04290822407628129, | |
| "grad_norm": 0.21003372321244757, | |
| "learning_rate": 3.7651019814126656e-06, | |
| "loss": 2.0307, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.04410011918951132, | |
| "grad_norm": 0.20875875072814898, | |
| "learning_rate": 3.2769910973868314e-06, | |
| "loss": 1.9922, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.04529201430274136, | |
| "grad_norm": 0.20086863185331044, | |
| "learning_rate": 2.8165064990227255e-06, | |
| "loss": 2.009, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.04648390941597139, | |
| "grad_norm": 0.19637651354676247, | |
| "learning_rate": 2.3855404163086558e-06, | |
| "loss": 2.0069, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.04767580452920143, | |
| "grad_norm": 0.19298356773047148, | |
| "learning_rate": 1.9858637813204352e-06, | |
| "loss": 1.9649, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04886769964243146, | |
| "grad_norm": 0.18616123249372152, | |
| "learning_rate": 1.6191189510815942e-06, | |
| "loss": 1.988, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.050059594755661505, | |
| "grad_norm": 0.17608440957049246, | |
| "learning_rate": 1.286812958766106e-06, | |
| "loss": 1.9493, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.05125148986889154, | |
| "grad_norm": 0.17839806165567934, | |
| "learning_rate": 9.903113209758098e-07, | |
| "loss": 1.9827, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.052443384982121574, | |
| "grad_norm": 0.171992208968052, | |
| "learning_rate": 7.308324265397837e-07, | |
| "loss": 2.0005, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.05363528009535161, | |
| "grad_norm": 0.20157026593925115, | |
| "learning_rate": 5.094425298933136e-07, | |
| "loss": 1.9962, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.054827175208581644, | |
| "grad_norm": 0.17529676457850735, | |
| "learning_rate": 3.2705136960970554e-07, | |
| "loss": 2.0125, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.05601907032181168, | |
| "grad_norm": 0.1769836489001342, | |
| "learning_rate": 1.844084300893456e-07, | |
| "loss": 1.9917, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.057210965435041714, | |
| "grad_norm": 0.17274305549148233, | |
| "learning_rate": 8.209986176753947e-08, | |
| "loss": 1.9941, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.058402860548271755, | |
| "grad_norm": 0.1777317862287471, | |
| "learning_rate": 2.054607249663665e-08, | |
| "loss": 1.9912, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.05959475566150179, | |
| "grad_norm": 0.17680142652753666, | |
| "learning_rate": 0.0, | |
| "loss": 2.0301, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05959475566150179, | |
| "step": 50, | |
| "total_flos": 106890730143744.0, | |
| "train_loss": 1.9979763078689574, | |
| "train_runtime": 1596.1705, | |
| "train_samples_per_second": 58.139, | |
| "train_steps_per_second": 0.031 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 106890730143744.0, | |
| "train_batch_size": 58, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |