| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.881844380403458, | |
| "eval_steps": 500, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05763688760806916, | |
| "grad_norm": 4.8593597412109375, | |
| "learning_rate": 0.000125, | |
| "loss": 1.0043, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11527377521613832, | |
| "grad_norm": 0.14300437271595, | |
| "learning_rate": 0.00019841427155599603, | |
| "loss": 0.5844, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1729106628242075, | |
| "grad_norm": 0.11132702976465225, | |
| "learning_rate": 0.00019444995044598612, | |
| "loss": 0.4951, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.23054755043227665, | |
| "grad_norm": 0.15473473072052002, | |
| "learning_rate": 0.0001904856293359762, | |
| "loss": 0.4809, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.2881844380403458, | |
| "grad_norm": 0.12199735641479492, | |
| "learning_rate": 0.00018652130822596633, | |
| "loss": 0.4703, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.345821325648415, | |
| "grad_norm": 0.11592856794595718, | |
| "learning_rate": 0.0001825569871159564, | |
| "loss": 0.4622, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.4034582132564842, | |
| "grad_norm": 0.11163052916526794, | |
| "learning_rate": 0.00017859266600594648, | |
| "loss": 0.4527, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.4610951008645533, | |
| "grad_norm": 0.11111810058355331, | |
| "learning_rate": 0.00017462834489593657, | |
| "loss": 0.451, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.5187319884726225, | |
| "grad_norm": 0.11076587438583374, | |
| "learning_rate": 0.00017066402378592668, | |
| "loss": 0.4447, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.5763688760806917, | |
| "grad_norm": 0.09930027276277542, | |
| "learning_rate": 0.00016669970267591675, | |
| "loss": 0.4486, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.6340057636887608, | |
| "grad_norm": 0.09756297618150711, | |
| "learning_rate": 0.00016273538156590683, | |
| "loss": 0.4369, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.69164265129683, | |
| "grad_norm": 0.11096686124801636, | |
| "learning_rate": 0.00015877106045589692, | |
| "loss": 0.4412, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.7492795389048992, | |
| "grad_norm": 0.09731573611497879, | |
| "learning_rate": 0.00015480673934588704, | |
| "loss": 0.4407, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.8069164265129684, | |
| "grad_norm": 0.10571198165416718, | |
| "learning_rate": 0.0001508424182358771, | |
| "loss": 0.4376, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.8645533141210374, | |
| "grad_norm": 0.09965088218450546, | |
| "learning_rate": 0.0001468780971258672, | |
| "loss": 0.4368, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.9221902017291066, | |
| "grad_norm": 0.09912007302045822, | |
| "learning_rate": 0.0001429137760158573, | |
| "loss": 0.4294, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.9798270893371758, | |
| "grad_norm": 0.09754997491836548, | |
| "learning_rate": 0.0001389494549058474, | |
| "loss": 0.4309, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.037463976945245, | |
| "grad_norm": 0.10138026624917984, | |
| "learning_rate": 0.00013498513379583746, | |
| "loss": 0.4188, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.0951008645533142, | |
| "grad_norm": 0.09764310717582703, | |
| "learning_rate": 0.00013102081268582754, | |
| "loss": 0.4167, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.1527377521613833, | |
| "grad_norm": 0.10624668747186661, | |
| "learning_rate": 0.00012705649157581766, | |
| "loss": 0.4167, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.2103746397694524, | |
| "grad_norm": 0.1042829230427742, | |
| "learning_rate": 0.00012309217046580775, | |
| "loss": 0.42, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.2680115273775217, | |
| "grad_norm": 0.09762328863143921, | |
| "learning_rate": 0.00011912784935579781, | |
| "loss": 0.4147, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.3256484149855907, | |
| "grad_norm": 0.1053580567240715, | |
| "learning_rate": 0.00011516352824578791, | |
| "loss": 0.4173, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.38328530259366, | |
| "grad_norm": 0.09830950945615768, | |
| "learning_rate": 0.000111199207135778, | |
| "loss": 0.4107, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.440922190201729, | |
| "grad_norm": 0.1017039492726326, | |
| "learning_rate": 0.0001072348860257681, | |
| "loss": 0.4129, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.4985590778097984, | |
| "grad_norm": 0.10052554309368134, | |
| "learning_rate": 0.00010327056491575817, | |
| "loss": 0.4115, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.5561959654178674, | |
| "grad_norm": 0.09901268035173416, | |
| "learning_rate": 9.930624380574827e-05, | |
| "loss": 0.4113, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.6138328530259365, | |
| "grad_norm": 0.0998842865228653, | |
| "learning_rate": 9.534192269573836e-05, | |
| "loss": 0.4075, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.6714697406340058, | |
| "grad_norm": 0.10228322446346283, | |
| "learning_rate": 9.137760158572845e-05, | |
| "loss": 0.4103, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.729106628242075, | |
| "grad_norm": 0.10224767029285431, | |
| "learning_rate": 8.741328047571854e-05, | |
| "loss": 0.4097, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.7867435158501441, | |
| "grad_norm": 0.10533642023801804, | |
| "learning_rate": 8.344895936570862e-05, | |
| "loss": 0.4069, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.8443804034582132, | |
| "grad_norm": 0.11008591949939728, | |
| "learning_rate": 7.948463825569871e-05, | |
| "loss": 0.4043, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.9020172910662825, | |
| "grad_norm": 0.1080278530716896, | |
| "learning_rate": 7.55203171456888e-05, | |
| "loss": 0.4058, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.9596541786743515, | |
| "grad_norm": 0.10025861114263535, | |
| "learning_rate": 7.155599603567889e-05, | |
| "loss": 0.4035, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 2.0172910662824206, | |
| "grad_norm": 0.1050715371966362, | |
| "learning_rate": 6.759167492566898e-05, | |
| "loss": 0.3953, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.07492795389049, | |
| "grad_norm": 0.10905614495277405, | |
| "learning_rate": 6.362735381565907e-05, | |
| "loss": 0.3898, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 2.132564841498559, | |
| "grad_norm": 0.11501201242208481, | |
| "learning_rate": 5.966303270564916e-05, | |
| "loss": 0.3916, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 2.1902017291066285, | |
| "grad_norm": 0.10602011531591415, | |
| "learning_rate": 5.569871159563925e-05, | |
| "loss": 0.3902, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 2.2478386167146973, | |
| "grad_norm": 0.11458944529294968, | |
| "learning_rate": 5.1734390485629335e-05, | |
| "loss": 0.391, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 2.3054755043227666, | |
| "grad_norm": 0.10967529565095901, | |
| "learning_rate": 4.7770069375619424e-05, | |
| "loss": 0.3882, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.363112391930836, | |
| "grad_norm": 0.11452831327915192, | |
| "learning_rate": 4.380574826560951e-05, | |
| "loss": 0.3924, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 2.4207492795389047, | |
| "grad_norm": 0.11521276086568832, | |
| "learning_rate": 3.98414271555996e-05, | |
| "loss": 0.3884, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 2.478386167146974, | |
| "grad_norm": 0.11083399504423141, | |
| "learning_rate": 3.587710604558969e-05, | |
| "loss": 0.391, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.5360230547550433, | |
| "grad_norm": 0.1139487475156784, | |
| "learning_rate": 3.191278493557978e-05, | |
| "loss": 0.3903, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.5936599423631126, | |
| "grad_norm": 0.11477449536323547, | |
| "learning_rate": 2.794846382556987e-05, | |
| "loss": 0.3897, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.6512968299711814, | |
| "grad_norm": 0.11389576643705368, | |
| "learning_rate": 2.3984142715559964e-05, | |
| "loss": 0.3882, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.7089337175792507, | |
| "grad_norm": 0.11239298433065414, | |
| "learning_rate": 2.0019821605550053e-05, | |
| "loss": 0.388, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.76657060518732, | |
| "grad_norm": 0.10633145272731781, | |
| "learning_rate": 1.605550049554014e-05, | |
| "loss": 0.3823, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.824207492795389, | |
| "grad_norm": 0.12195642292499542, | |
| "learning_rate": 1.2091179385530229e-05, | |
| "loss": 0.3878, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.881844380403458, | |
| "grad_norm": 0.1192099004983902, | |
| "learning_rate": 8.126858275520318e-06, | |
| "loss": 0.3877, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 1041, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.450003270942065e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |