| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.4319654427645788, | |
| "eval_steps": 5, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008639308855291577, | |
| "eval_loss": NaN, | |
| "eval_runtime": 46.7932, | |
| "eval_samples_per_second": 4.167, | |
| "eval_steps_per_second": 0.534, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02591792656587473, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.04319654427645788, | |
| "eval_loss": NaN, | |
| "eval_runtime": 46.134, | |
| "eval_samples_per_second": 4.227, | |
| "eval_steps_per_second": 0.542, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05183585313174946, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07775377969762419, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08639308855291576, | |
| "eval_loss": NaN, | |
| "eval_runtime": 46.1495, | |
| "eval_samples_per_second": 4.225, | |
| "eval_steps_per_second": 0.542, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10367170626349892, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.12958963282937366, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.12958963282937366, | |
| "eval_loss": NaN, | |
| "eval_runtime": 46.1367, | |
| "eval_samples_per_second": 4.227, | |
| "eval_steps_per_second": 0.542, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.15550755939524838, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.17278617710583152, | |
| "eval_loss": NaN, | |
| "eval_runtime": 46.1372, | |
| "eval_samples_per_second": 4.227, | |
| "eval_steps_per_second": 0.542, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.18142548596112312, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.20734341252699784, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2159827213822894, | |
| "eval_loss": NaN, | |
| "eval_runtime": 46.1547, | |
| "eval_samples_per_second": 4.225, | |
| "eval_steps_per_second": 0.542, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.23326133909287258, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.2591792656587473, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2591792656587473, | |
| "eval_loss": NaN, | |
| "eval_runtime": 46.1658, | |
| "eval_samples_per_second": 4.224, | |
| "eval_steps_per_second": 0.542, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.28509719222462204, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.3023758099352052, | |
| "eval_loss": NaN, | |
| "eval_runtime": 46.1477, | |
| "eval_samples_per_second": 4.226, | |
| "eval_steps_per_second": 0.542, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.31101511879049676, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.3369330453563715, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.34557235421166305, | |
| "eval_loss": NaN, | |
| "eval_runtime": 46.189, | |
| "eval_samples_per_second": 4.222, | |
| "eval_steps_per_second": 0.541, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.36285097192224625, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.38876889848812096, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.38876889848812096, | |
| "eval_loss": NaN, | |
| "eval_runtime": 46.1915, | |
| "eval_samples_per_second": 4.222, | |
| "eval_steps_per_second": 0.541, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.4146868250539957, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.4319654427645788, | |
| "eval_loss": NaN, | |
| "eval_runtime": 46.1915, | |
| "eval_samples_per_second": 4.222, | |
| "eval_steps_per_second": 0.541, | |
| "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": 2.6077781720825856e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |