| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.7916872835230084, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01583374567046017, | |
| "grad_norm": 0.005832806695252657, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9318, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01583374567046017, | |
| "eval_loss": 11.93154239654541, | |
| "eval_runtime": 3.4314, | |
| "eval_samples_per_second": 124.147, | |
| "eval_steps_per_second": 31.182, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03166749134092034, | |
| "grad_norm": 0.008129135705530643, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9307, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0475012370113805, | |
| "grad_norm": 0.007459758780896664, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 11.9313, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.06333498268184068, | |
| "grad_norm": 0.008444393053650856, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 11.9304, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.07916872835230084, | |
| "grad_norm": 0.007906494662165642, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 11.9314, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.095002474022761, | |
| "grad_norm": 0.006466949358582497, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 11.9307, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.11083621969322117, | |
| "grad_norm": 0.006579251494258642, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 11.9307, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.12666996536368136, | |
| "grad_norm": 0.006140752229839563, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 11.9325, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1425037110341415, | |
| "grad_norm": 0.006685135420411825, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 11.9317, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.15833745670460167, | |
| "grad_norm": 0.0067346105352044106, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 11.9311, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.17417120237506184, | |
| "grad_norm": 0.007974086329340935, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 11.9301, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.190004948045522, | |
| "grad_norm": 0.007118863519281149, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 11.9311, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.20583869371598218, | |
| "grad_norm": 0.0049477843567729, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 11.9308, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.20583869371598218, | |
| "eval_loss": 11.931408882141113, | |
| "eval_runtime": 3.5271, | |
| "eval_samples_per_second": 120.78, | |
| "eval_steps_per_second": 30.337, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.22167243938644235, | |
| "grad_norm": 0.0061904569156467915, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 11.931, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.23750618505690252, | |
| "grad_norm": 0.006974657066166401, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 11.9318, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2533399307273627, | |
| "grad_norm": 0.00557992747053504, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 11.9317, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.26917367639782286, | |
| "grad_norm": 0.0053142402321100235, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 11.931, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.285007422068283, | |
| "grad_norm": 0.007350199855864048, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 11.9303, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.3008411677387432, | |
| "grad_norm": 0.004690493457019329, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 11.9311, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.31667491340920334, | |
| "grad_norm": 0.006520365830510855, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 11.931, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.33250865907966354, | |
| "grad_norm": 0.006246721837669611, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 11.9294, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.3483424047501237, | |
| "grad_norm": 0.00684422766789794, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 11.9314, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3641761504205839, | |
| "grad_norm": 0.005832418333739042, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 11.9314, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.380009896091044, | |
| "grad_norm": 0.007443716749548912, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 11.931, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3958436417615042, | |
| "grad_norm": 0.006380151025950909, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 11.9311, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.41167738743196436, | |
| "grad_norm": 0.0062307147309184074, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9312, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.41167738743196436, | |
| "eval_loss": 11.931290626525879, | |
| "eval_runtime": 3.5015, | |
| "eval_samples_per_second": 121.662, | |
| "eval_steps_per_second": 30.558, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.42751113310242456, | |
| "grad_norm": 0.00884031318128109, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 11.931, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.4433448787728847, | |
| "grad_norm": 0.007135901600122452, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 11.931, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.4591786244433449, | |
| "grad_norm": 0.007375482469797134, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 11.9303, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.47501237011380504, | |
| "grad_norm": 0.019206728786230087, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 11.9285, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.49084611578426524, | |
| "grad_norm": 0.00676517840474844, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 11.9313, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.5066798614547254, | |
| "grad_norm": 0.0074449400417506695, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 11.9308, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.5225136071251856, | |
| "grad_norm": 0.006442636717110872, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 11.931, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.5383473527956457, | |
| "grad_norm": 0.0078086163848638535, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 11.9313, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.5541810984661059, | |
| "grad_norm": 0.007814242504537106, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 11.9313, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.570014844136566, | |
| "grad_norm": 0.008247659541666508, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 11.9309, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5858485898070263, | |
| "grad_norm": 0.006319059990346432, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 11.9309, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.6016823354774864, | |
| "grad_norm": 0.0059829698875546455, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 11.9316, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.6175160811479465, | |
| "grad_norm": 0.006849578581750393, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 11.9299, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.6175160811479465, | |
| "eval_loss": 11.931235313415527, | |
| "eval_runtime": 3.5072, | |
| "eval_samples_per_second": 121.464, | |
| "eval_steps_per_second": 30.509, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.6333498268184067, | |
| "grad_norm": 0.008273452520370483, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 11.9306, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6491835724888669, | |
| "grad_norm": 0.0072366236709058285, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 11.9315, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.6650173181593271, | |
| "grad_norm": 0.007517676800489426, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 11.9309, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.6808510638297872, | |
| "grad_norm": 0.00758866872638464, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 11.9314, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.6966848095002474, | |
| "grad_norm": 0.006661114748567343, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 11.9313, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.7125185551707076, | |
| "grad_norm": 0.007711367215961218, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 11.9301, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.7283523008411678, | |
| "grad_norm": 0.005763665772974491, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 11.9307, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.7441860465116279, | |
| "grad_norm": 0.006471547763794661, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 11.9307, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.760019792182088, | |
| "grad_norm": 0.00781251024454832, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 11.9312, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.7758535378525483, | |
| "grad_norm": 0.0064762914553284645, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 11.931, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.7916872835230084, | |
| "grad_norm": 0.00732074398547411, | |
| "learning_rate": 0.0, | |
| "loss": 11.9304, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1208519884800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |