| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.024752475247524754, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004950495049504951, | |
| "eval_loss": 2.6221022605895996, | |
| "eval_runtime": 27.7766, | |
| "eval_samples_per_second": 30.637, | |
| "eval_steps_per_second": 15.337, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0024752475247524753, | |
| "grad_norm": 0.7501001358032227, | |
| "learning_rate": 5e-05, | |
| "loss": 2.548, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0049504950495049506, | |
| "grad_norm": 0.6144944429397583, | |
| "learning_rate": 0.0001, | |
| "loss": 2.5697, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0049504950495049506, | |
| "eval_loss": 2.592329978942871, | |
| "eval_runtime": 27.7412, | |
| "eval_samples_per_second": 30.676, | |
| "eval_steps_per_second": 15.356, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007425742574257425, | |
| "grad_norm": 0.8921784162521362, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.6192, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.009900990099009901, | |
| "grad_norm": 0.547026515007019, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.5644, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.009900990099009901, | |
| "eval_loss": 2.4996721744537354, | |
| "eval_runtime": 27.6222, | |
| "eval_samples_per_second": 30.809, | |
| "eval_steps_per_second": 15.422, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.012376237623762377, | |
| "grad_norm": 0.717430591583252, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.4506, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01485148514851485, | |
| "grad_norm": 0.6969410181045532, | |
| "learning_rate": 5e-05, | |
| "loss": 2.4852, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01485148514851485, | |
| "eval_loss": 2.4748666286468506, | |
| "eval_runtime": 27.7477, | |
| "eval_samples_per_second": 30.669, | |
| "eval_steps_per_second": 15.353, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.017326732673267328, | |
| "grad_norm": 0.5595166683197021, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.5691, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.019801980198019802, | |
| "grad_norm": 0.6102985739707947, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.3449, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.019801980198019802, | |
| "eval_loss": 2.467658281326294, | |
| "eval_runtime": 27.8329, | |
| "eval_samples_per_second": 30.575, | |
| "eval_steps_per_second": 15.306, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.022277227722772276, | |
| "grad_norm": 0.7228185534477234, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.4674, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.024752475247524754, | |
| "grad_norm": 0.6576347947120667, | |
| "learning_rate": 0.0, | |
| "loss": 2.5014, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.024752475247524754, | |
| "eval_loss": 2.466404438018799, | |
| "eval_runtime": 27.709, | |
| "eval_samples_per_second": 30.712, | |
| "eval_steps_per_second": 15.374, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "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": 1624279061889024.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |