| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.027597626604112045, | |
| "eval_steps": 5, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005519525320822409, | |
| "eval_loss": 14.079300880432129, | |
| "eval_runtime": 236.8521, | |
| "eval_samples_per_second": 12.886, | |
| "eval_steps_per_second": 1.613, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016558575962467227, | |
| "grad_norm": 11.275343894958496, | |
| "learning_rate": 3e-05, | |
| "loss": 13.7022, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0027597626604112047, | |
| "eval_loss": 11.587545394897461, | |
| "eval_runtime": 238.722, | |
| "eval_samples_per_second": 12.785, | |
| "eval_steps_per_second": 1.6, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0033117151924934455, | |
| "grad_norm": 10.630936622619629, | |
| "learning_rate": 6e-05, | |
| "loss": 12.5022, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004967572788740169, | |
| "grad_norm": 13.811830520629883, | |
| "learning_rate": 9e-05, | |
| "loss": 8.3067, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005519525320822409, | |
| "eval_loss": 4.47538423538208, | |
| "eval_runtime": 238.5953, | |
| "eval_samples_per_second": 12.792, | |
| "eval_steps_per_second": 1.601, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006623430384986891, | |
| "grad_norm": 8.562952995300293, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 5.0006, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.008279287981233613, | |
| "grad_norm": 8.945141792297363, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.0773, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.008279287981233613, | |
| "eval_loss": 2.7493247985839844, | |
| "eval_runtime": 238.5337, | |
| "eval_samples_per_second": 12.795, | |
| "eval_steps_per_second": 1.601, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.009935145577480337, | |
| "grad_norm": 5.252676010131836, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 2.5857, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.011039050641644819, | |
| "eval_loss": 2.3519887924194336, | |
| "eval_runtime": 238.4533, | |
| "eval_samples_per_second": 12.799, | |
| "eval_steps_per_second": 1.602, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01159100317372706, | |
| "grad_norm": 4.178547382354736, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 2.3626, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.013246860769973782, | |
| "grad_norm": 5.464514255523682, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 2.2085, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.013798813302056023, | |
| "eval_loss": 2.240475654602051, | |
| "eval_runtime": 238.4465, | |
| "eval_samples_per_second": 12.8, | |
| "eval_steps_per_second": 1.602, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.014902718366220506, | |
| "grad_norm": 3.492499589920044, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 2.2668, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.016558575962467226, | |
| "grad_norm": 3.7871546745300293, | |
| "learning_rate": 5e-05, | |
| "loss": 2.2683, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.016558575962467226, | |
| "eval_loss": 2.201204776763916, | |
| "eval_runtime": 238.6246, | |
| "eval_samples_per_second": 12.79, | |
| "eval_steps_per_second": 1.601, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.018214433558713952, | |
| "grad_norm": 3.5724196434020996, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 2.2155, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.019318338622878434, | |
| "eval_loss": 2.1538922786712646, | |
| "eval_runtime": 238.5447, | |
| "eval_samples_per_second": 12.794, | |
| "eval_steps_per_second": 1.601, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.019870291154960674, | |
| "grad_norm": 2.8825461864471436, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 2.0547, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.021526148751207397, | |
| "grad_norm": 3.1408188343048096, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 2.1018, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.022078101283289638, | |
| "eval_loss": 2.116506814956665, | |
| "eval_runtime": 238.6838, | |
| "eval_samples_per_second": 12.787, | |
| "eval_steps_per_second": 1.6, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02318200634745412, | |
| "grad_norm": 2.7910170555114746, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 2.2127, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.02483786394370084, | |
| "grad_norm": 1.919623613357544, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.0587, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02483786394370084, | |
| "eval_loss": 2.096043586730957, | |
| "eval_runtime": 238.579, | |
| "eval_samples_per_second": 12.792, | |
| "eval_steps_per_second": 1.601, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.026493721539947564, | |
| "grad_norm": 2.80169415473938, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 2.0101, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.027597626604112045, | |
| "eval_loss": 2.0936098098754883, | |
| "eval_runtime": 238.6294, | |
| "eval_samples_per_second": 12.79, | |
| "eval_steps_per_second": 1.601, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.54256789372928e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |