| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.09416195856873823, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0018832391713747645, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0018832391713747645, | |
| "eval_loss": NaN, | |
| "eval_runtime": 157.4836, | |
| "eval_samples_per_second": 5.683, | |
| "eval_steps_per_second": 2.845, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003766478342749529, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005649717514124294, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007532956685499058, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 11523.8467, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.009416195856873822, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.011299435028248588, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.013182674199623353, | |
| "grad_norm": NaN, | |
| "learning_rate": 7e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.015065913370998116, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.01694915254237288, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.018832391713747645, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02071563088512241, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.98458666866564e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.022598870056497175, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.02448210922787194, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.861849601988383e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.02448210922787194, | |
| "eval_loss": NaN, | |
| "eval_runtime": 22.1489, | |
| "eval_samples_per_second": 40.408, | |
| "eval_steps_per_second": 20.227, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.026365348399246705, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.02824858757062147, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.030131826741996232, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.45503262094184e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.032015065913371, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.263200821770461e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.03389830508474576, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.035781544256120526, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.802029828000156e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.03766478342749529, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03954802259887006, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.04143126177024482, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.04331450094161959, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.612492823579745e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.04519774011299435, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.047080979284369114, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04896421845574388, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.04896421845574388, | |
| "eval_loss": NaN, | |
| "eval_runtime": 22.1505, | |
| "eval_samples_per_second": 40.405, | |
| "eval_steps_per_second": 20.225, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.05084745762711865, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.05273069679849341, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.782172325201155e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.054613935969868174, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.392295478639225e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.05649717514124294, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0583804143126177, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.607704521360776e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.060263653483992465, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.062146892655367235, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.064030131826742, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.06591337099811675, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.06779661016949153, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 2.7555, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0696798493408663, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3875071764202563e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.07156308851224105, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.07344632768361582, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.07344632768361582, | |
| "eval_loss": NaN, | |
| "eval_runtime": 22.1351, | |
| "eval_samples_per_second": 40.434, | |
| "eval_steps_per_second": 20.239, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.07532956685499058, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07721280602636535, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1979701719998453e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.07909604519774012, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.08097928436911488, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.367991782295391e-06, | |
| "loss": 619.3525, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.08286252354048965, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0847457627118644, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.08662900188323917, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.08851224105461393, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3815039801161721e-06, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0903954802259887, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.09227871939736347, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5413331334360182e-07, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.09416195856873823, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "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": 3.467078640913613e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |