| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.6174958944320679, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.5017, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.6429479122161865, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 0.4915, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.49867865443229675, | |
| "learning_rate": 0.0002, | |
| "loss": 0.428, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.5035229921340942, | |
| "learning_rate": 0.00019977668786231534, | |
| "loss": 0.4537, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.45080244541168213, | |
| "learning_rate": 0.000199107748815478, | |
| "loss": 0.4549, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.4055653214454651, | |
| "learning_rate": 0.0001979961705036587, | |
| "loss": 0.4596, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.41731277108192444, | |
| "learning_rate": 0.00019644691750543767, | |
| "loss": 0.4274, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.3783501982688904, | |
| "learning_rate": 0.0001944669091607919, | |
| "loss": 0.4789, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.37090209126472473, | |
| "learning_rate": 0.00019206498866764288, | |
| "loss": 0.4522, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.3544338345527649, | |
| "learning_rate": 0.00018925188358598813, | |
| "loss": 0.4677, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 0.3952384889125824, | |
| "learning_rate": 0.00018604015792601396, | |
| "loss": 0.4454, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.3702380657196045, | |
| "learning_rate": 0.00018244415603417603, | |
| "loss": 0.4508, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 0.36494874954223633, | |
| "learning_rate": 0.0001784799385278661, | |
| "loss": 0.4466, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.34794506430625916, | |
| "learning_rate": 0.00017416521056479577, | |
| "loss": 0.4429, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.3768218159675598, | |
| "learning_rate": 0.00016951924276746425, | |
| "loss": 0.451, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.37294796109199524, | |
| "learning_rate": 0.00016456278515588024, | |
| "loss": 0.4359, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 0.3664343059062958, | |
| "learning_rate": 0.00015931797447293552, | |
| "loss": 0.4223, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.38887134194374084, | |
| "learning_rate": 0.00015380823531633729, | |
| "loss": 0.4317, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 0.3960750699043274, | |
| "learning_rate": 0.00014805817551866838, | |
| "loss": 0.4302, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.3703005611896515, | |
| "learning_rate": 0.0001420934762428335, | |
| "loss": 0.4238, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 0.3697049617767334, | |
| "learning_rate": 0.00013594077728375128, | |
| "loss": 0.4275, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.3797580897808075, | |
| "learning_rate": 0.00012962755808856342, | |
| "loss": 0.4295, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 0.37148579955101013, | |
| "learning_rate": 0.00012318201502675285, | |
| "loss": 0.413, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.36919766664505005, | |
| "learning_rate": 0.00011663293545831302, | |
| "loss": 0.418, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.36413446068763733, | |
| "learning_rate": 0.00011000956916240985, | |
| "loss": 0.3946, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 0.37875810265541077, | |
| "learning_rate": 0.00010334149770076747, | |
| "loss": 0.4423, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 0.3651341497898102, | |
| "learning_rate": 9.665850229923258e-05, | |
| "loss": 0.4193, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.36425620317459106, | |
| "learning_rate": 8.999043083759017e-05, | |
| "loss": 0.4126, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 0.3773588538169861, | |
| "learning_rate": 8.336706454168701e-05, | |
| "loss": 0.3913, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.3708311915397644, | |
| "learning_rate": 7.681798497324716e-05, | |
| "loss": 0.4078, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 0.38130757212638855, | |
| "learning_rate": 7.037244191143661e-05, | |
| "loss": 0.4229, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.3573770821094513, | |
| "learning_rate": 6.405922271624874e-05, | |
| "loss": 0.4117, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 0.3715918958187103, | |
| "learning_rate": 5.790652375716652e-05, | |
| "loss": 0.3888, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 0.371981143951416, | |
| "learning_rate": 5.1941824481331626e-05, | |
| "loss": 0.3819, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 0.3743939995765686, | |
| "learning_rate": 4.6191764683662744e-05, | |
| "loss": 0.4123, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.3548343777656555, | |
| "learning_rate": 4.0682025527064486e-05, | |
| "loss": 0.3768, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 0.34915444254875183, | |
| "learning_rate": 3.543721484411976e-05, | |
| "loss": 0.3836, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.36232128739356995, | |
| "learning_rate": 3.0480757232535772e-05, | |
| "loss": 0.3905, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 0.3516843020915985, | |
| "learning_rate": 2.5834789435204243e-05, | |
| "loss": 0.4018, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.35692131519317627, | |
| "learning_rate": 2.1520061472133902e-05, | |
| "loss": 0.4125, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 0.366886168718338, | |
| "learning_rate": 1.7555843965823992e-05, | |
| "loss": 0.3963, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 0.3520941436290741, | |
| "learning_rate": 1.3959842073986085e-05, | |
| "loss": 0.3923, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 0.3794335424900055, | |
| "learning_rate": 1.0748116414011888e-05, | |
| "loss": 0.4048, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 0.34629887342453003, | |
| "learning_rate": 7.935011332357112e-06, | |
| "loss": 0.3738, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 0.3593948185443878, | |
| "learning_rate": 5.533090839208133e-06, | |
| "loss": 0.3967, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 0.33537453413009644, | |
| "learning_rate": 3.5530824945623542e-06, | |
| "loss": 0.3729, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 0.3365356922149658, | |
| "learning_rate": 2.003829496341325e-06, | |
| "loss": 0.3799, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.3586476147174835, | |
| "learning_rate": 8.922511845219971e-07, | |
| "loss": 0.4037, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 0.3276454508304596, | |
| "learning_rate": 2.2331213768468363e-07, | |
| "loss": 0.3982, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.3641741871833801, | |
| "learning_rate": 0.0, | |
| "loss": 0.388, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "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": 7.469785844519731e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |