| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.012697337791509713, | |
| "eval_steps": 6, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002539467558301943, | |
| "grad_norm": 2.3970961570739746, | |
| "learning_rate": 1e-05, | |
| "loss": 66.6603, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002539467558301943, | |
| "eval_loss": 11.107478141784668, | |
| "eval_runtime": 18.8123, | |
| "eval_samples_per_second": 264.454, | |
| "eval_steps_per_second": 66.127, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005078935116603886, | |
| "grad_norm": 2.4752585887908936, | |
| "learning_rate": 2e-05, | |
| "loss": 66.6705, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0007618402674905828, | |
| "grad_norm": 2.5148186683654785, | |
| "learning_rate": 3e-05, | |
| "loss": 66.6682, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0010157870233207772, | |
| "grad_norm": 2.3080971240997314, | |
| "learning_rate": 4e-05, | |
| "loss": 66.5837, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0012697337791509713, | |
| "grad_norm": 2.354560613632202, | |
| "learning_rate": 5e-05, | |
| "loss": 66.6436, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0015236805349811656, | |
| "grad_norm": 2.5473434925079346, | |
| "learning_rate": 6e-05, | |
| "loss": 66.6068, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0015236805349811656, | |
| "eval_loss": 11.101515769958496, | |
| "eval_runtime": 18.1722, | |
| "eval_samples_per_second": 273.77, | |
| "eval_steps_per_second": 68.456, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00177762729081136, | |
| "grad_norm": 2.5556399822235107, | |
| "learning_rate": 7e-05, | |
| "loss": 66.6045, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0020315740466415543, | |
| "grad_norm": 2.6539461612701416, | |
| "learning_rate": 8e-05, | |
| "loss": 66.6228, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0022855208024717484, | |
| "grad_norm": 2.602025032043457, | |
| "learning_rate": 9e-05, | |
| "loss": 66.4995, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0025394675583019426, | |
| "grad_norm": 2.4404804706573486, | |
| "learning_rate": 0.0001, | |
| "loss": 66.5529, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002793414314132137, | |
| "grad_norm": 2.2321112155914307, | |
| "learning_rate": 9.98458666866564e-05, | |
| "loss": 66.4916, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0030473610699623312, | |
| "grad_norm": 2.796868085861206, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 66.4966, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0030473610699623312, | |
| "eval_loss": 11.079522132873535, | |
| "eval_runtime": 18.1003, | |
| "eval_samples_per_second": 274.858, | |
| "eval_steps_per_second": 68.728, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0033013078257925254, | |
| "grad_norm": 2.591143846511841, | |
| "learning_rate": 9.861849601988383e-05, | |
| "loss": 66.4451, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.00355525458162272, | |
| "grad_norm": 2.323777675628662, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 66.4647, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.003809201337452914, | |
| "grad_norm": 2.9256598949432373, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 66.3829, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004063148093283109, | |
| "grad_norm": 2.4250593185424805, | |
| "learning_rate": 9.45503262094184e-05, | |
| "loss": 66.4283, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004317094849113303, | |
| "grad_norm": 2.607290029525757, | |
| "learning_rate": 9.263200821770461e-05, | |
| "loss": 66.2636, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.004571041604943497, | |
| "grad_norm": 2.8356802463531494, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 66.2697, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.004571041604943497, | |
| "eval_loss": 11.051901817321777, | |
| "eval_runtime": 18.1634, | |
| "eval_samples_per_second": 273.902, | |
| "eval_steps_per_second": 68.489, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.004824988360773691, | |
| "grad_norm": 2.4801783561706543, | |
| "learning_rate": 8.802029828000156e-05, | |
| "loss": 66.3638, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.005078935116603885, | |
| "grad_norm": 2.5052285194396973, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 66.2984, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005332881872434079, | |
| "grad_norm": 2.5191738605499268, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 66.3049, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.005586828628264274, | |
| "grad_norm": 2.384291887283325, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 66.2243, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.005840775384094468, | |
| "grad_norm": 2.3815808296203613, | |
| "learning_rate": 7.612492823579745e-05, | |
| "loss": 66.3124, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0060947221399246625, | |
| "grad_norm": 2.601182222366333, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 66.2157, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0060947221399246625, | |
| "eval_loss": 11.026150703430176, | |
| "eval_runtime": 18.1547, | |
| "eval_samples_per_second": 274.034, | |
| "eval_steps_per_second": 68.522, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.006348668895754857, | |
| "grad_norm": 2.959272861480713, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 66.0543, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.006602615651585051, | |
| "grad_norm": 2.5673084259033203, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 66.0834, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.006856562407415245, | |
| "grad_norm": 2.866518259048462, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 66.044, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.00711050916324544, | |
| "grad_norm": 2.417178153991699, | |
| "learning_rate": 5.782172325201155e-05, | |
| "loss": 66.1386, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.007364455919075634, | |
| "grad_norm": 2.504648447036743, | |
| "learning_rate": 5.392295478639225e-05, | |
| "loss": 66.046, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.007618402674905828, | |
| "grad_norm": 2.539602279663086, | |
| "learning_rate": 5e-05, | |
| "loss": 66.0429, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.007618402674905828, | |
| "eval_loss": 11.006031036376953, | |
| "eval_runtime": 18.2105, | |
| "eval_samples_per_second": 273.194, | |
| "eval_steps_per_second": 68.312, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.007872349430736022, | |
| "grad_norm": 2.809628963470459, | |
| "learning_rate": 4.607704521360776e-05, | |
| "loss": 65.9401, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.008126296186566217, | |
| "grad_norm": 2.533236026763916, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 66.0943, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.00838024294239641, | |
| "grad_norm": 2.7511136531829834, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 65.9569, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.008634189698226605, | |
| "grad_norm": 2.529318332672119, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 65.9841, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.008888136454056799, | |
| "grad_norm": 2.60366153717041, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 65.9559, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.009142083209886994, | |
| "grad_norm": 2.6384119987487793, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 65.9892, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.009142083209886994, | |
| "eval_loss": 10.992709159851074, | |
| "eval_runtime": 18.2216, | |
| "eval_samples_per_second": 273.028, | |
| "eval_steps_per_second": 68.271, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.009396029965717189, | |
| "grad_norm": 2.68752121925354, | |
| "learning_rate": 2.3875071764202563e-05, | |
| "loss": 65.8811, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.009649976721547382, | |
| "grad_norm": 2.529193162918091, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 65.97, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.009903923477377577, | |
| "grad_norm": 2.684138059616089, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 65.8963, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.01015787023320777, | |
| "grad_norm": 2.5320022106170654, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 65.9401, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.010411816989037965, | |
| "grad_norm": 2.516324281692505, | |
| "learning_rate": 1.1979701719998453e-05, | |
| "loss": 65.9055, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.010665763744868158, | |
| "grad_norm": 2.543747901916504, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 65.8852, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.010665763744868158, | |
| "eval_loss": 10.98641300201416, | |
| "eval_runtime": 18.1929, | |
| "eval_samples_per_second": 273.459, | |
| "eval_steps_per_second": 68.378, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.010919710500698353, | |
| "grad_norm": 2.3728582859039307, | |
| "learning_rate": 7.367991782295391e-06, | |
| "loss": 66.1291, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.011173657256528548, | |
| "grad_norm": 2.4906511306762695, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 65.9421, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.011427604012358742, | |
| "grad_norm": 2.665292978286743, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 65.9262, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.011681550768188937, | |
| "grad_norm": 2.6886563301086426, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 65.881, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.01193549752401913, | |
| "grad_norm": 2.69474196434021, | |
| "learning_rate": 1.3815039801161721e-06, | |
| "loss": 65.8305, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.012189444279849325, | |
| "grad_norm": 2.3172616958618164, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 65.9682, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.012189444279849325, | |
| "eval_loss": 10.984763145446777, | |
| "eval_runtime": 18.4652, | |
| "eval_samples_per_second": 269.425, | |
| "eval_steps_per_second": 67.37, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.01244339103567952, | |
| "grad_norm": 2.542539119720459, | |
| "learning_rate": 1.5413331334360182e-07, | |
| "loss": 66.0153, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.012697337791509713, | |
| "grad_norm": 2.630923271179199, | |
| "learning_rate": 0.0, | |
| "loss": 65.7818, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7145835724800.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |