| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04873294346978557, | |
| "eval_steps": 4, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009746588693957114, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009746588693957114, | |
| "eval_loss": NaN, | |
| "eval_runtime": 573.1563, | |
| "eval_samples_per_second": 2.263, | |
| "eval_steps_per_second": 0.567, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001949317738791423, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0029239766081871343, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003898635477582846, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003898635477582846, | |
| "eval_loss": NaN, | |
| "eval_runtime": 573.0692, | |
| "eval_samples_per_second": 2.263, | |
| "eval_steps_per_second": 0.567, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004873294346978557, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005847953216374269, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00682261208576998, | |
| "grad_norm": NaN, | |
| "learning_rate": 7e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.007797270955165692, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.007797270955165692, | |
| "eval_loss": NaN, | |
| "eval_runtime": 573.3908, | |
| "eval_samples_per_second": 2.262, | |
| "eval_steps_per_second": 0.567, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.008771929824561403, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.009746588693957114, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.010721247563352826, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.98458666866564e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.011695906432748537, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.011695906432748537, | |
| "eval_loss": NaN, | |
| "eval_runtime": 574.3045, | |
| "eval_samples_per_second": 2.258, | |
| "eval_steps_per_second": 0.566, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.012670565302144249, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.861849601988383e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01364522417153996, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.014619883040935672, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.015594541910331383, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.45503262094184e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.015594541910331383, | |
| "eval_loss": NaN, | |
| "eval_runtime": 575.7606, | |
| "eval_samples_per_second": 2.253, | |
| "eval_steps_per_second": 0.564, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.016569200779727095, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.263200821770461e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.017543859649122806, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.018518518518518517, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.802029828000156e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.01949317738791423, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01949317738791423, | |
| "eval_loss": NaN, | |
| "eval_runtime": 573.4225, | |
| "eval_samples_per_second": 2.262, | |
| "eval_steps_per_second": 0.567, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02046783625730994, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.021442495126705652, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.022417153996101363, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.612492823579745e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.023391812865497075, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.023391812865497075, | |
| "eval_loss": NaN, | |
| "eval_runtime": 573.2007, | |
| "eval_samples_per_second": 2.263, | |
| "eval_steps_per_second": 0.567, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.024366471734892786, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.025341130604288498, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.02631578947368421, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.02729044834307992, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.782172325201155e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.02729044834307992, | |
| "eval_loss": NaN, | |
| "eval_runtime": 573.2103, | |
| "eval_samples_per_second": 2.263, | |
| "eval_steps_per_second": 0.567, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.028265107212475632, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.392295478639225e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.029239766081871343, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.030214424951267055, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.607704521360776e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.031189083820662766, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.031189083820662766, | |
| "eval_loss": NaN, | |
| "eval_runtime": 572.9542, | |
| "eval_samples_per_second": 2.264, | |
| "eval_steps_per_second": 0.567, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.03216374269005848, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.03313840155945419, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0341130604288499, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03508771929824561, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.03508771929824561, | |
| "eval_loss": NaN, | |
| "eval_runtime": 572.9072, | |
| "eval_samples_per_second": 2.264, | |
| "eval_steps_per_second": 0.567, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.036062378167641324, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3875071764202563e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.037037037037037035, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.038011695906432746, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.03898635477582846, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03898635477582846, | |
| "eval_loss": NaN, | |
| "eval_runtime": 572.7858, | |
| "eval_samples_per_second": 2.264, | |
| "eval_steps_per_second": 0.567, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03996101364522417, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1979701719998453e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.04093567251461988, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.04191033138401559, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.367991782295391e-06, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.042884990253411304, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.042884990253411304, | |
| "eval_loss": NaN, | |
| "eval_runtime": 573.1049, | |
| "eval_samples_per_second": 2.263, | |
| "eval_steps_per_second": 0.567, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.043859649122807015, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.04483430799220273, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.04580896686159844, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3815039801161721e-06, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.04678362573099415, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.04678362573099415, | |
| "eval_loss": NaN, | |
| "eval_runtime": 572.8438, | |
| "eval_samples_per_second": 2.264, | |
| "eval_steps_per_second": 0.567, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.04775828460038986, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5413331334360182e-07, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.04873294346978557, | |
| "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": 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": 1.972183618289664e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |