| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 73, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0136986301369863, | |
| "grad_norm": 34.118116953889675, | |
| "learning_rate": 2.5e-06, | |
| "loss": 1.6188, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0684931506849315, | |
| "grad_norm": 22.031220286938318, | |
| "learning_rate": 1.25e-05, | |
| "loss": 1.4509, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.136986301369863, | |
| "grad_norm": 24.48163441863143, | |
| "learning_rate": 1.995331634717649e-05, | |
| "loss": 1.2597, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2054794520547945, | |
| "grad_norm": 11.150240837844573, | |
| "learning_rate": 1.9433118132577432e-05, | |
| "loss": 1.1326, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.273972602739726, | |
| "grad_norm": 8.921910132125255, | |
| "learning_rate": 1.8364701380102267e-05, | |
| "loss": 0.9593, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3424657534246575, | |
| "grad_norm": 6.052782930210205, | |
| "learning_rate": 1.6810158587867973e-05, | |
| "loss": 0.8129, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.410958904109589, | |
| "grad_norm": 3.3107891470106945, | |
| "learning_rate": 1.485983413242606e-05, | |
| "loss": 0.7322, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4794520547945205, | |
| "grad_norm": 2.3012558972151784, | |
| "learning_rate": 1.262707378198587e-05, | |
| "loss": 0.6999, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.547945205479452, | |
| "grad_norm": 1.8947726613242064, | |
| "learning_rate": 1.0241637452361323e-05, | |
| "loss": 0.69, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6164383561643836, | |
| "grad_norm": 1.5853235499915497, | |
| "learning_rate": 7.84215803232194e-06, | |
| "loss": 0.6727, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.684931506849315, | |
| "grad_norm": 1.5065446031084813, | |
| "learning_rate": 5.5680845440075885e-06, | |
| "loss": 0.6636, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7534246575342466, | |
| "grad_norm": 1.3520067897284647, | |
| "learning_rate": 3.5515778726382967e-06, | |
| "loss": 0.6567, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.821917808219178, | |
| "grad_norm": 1.3134996516029416, | |
| "learning_rate": 1.9098300562505266e-06, | |
| "loss": 0.6475, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.8904109589041096, | |
| "grad_norm": 1.280976980177563, | |
| "learning_rate": 7.382535104222366e-07, | |
| "loss": 0.6376, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.958904109589041, | |
| "grad_norm": 1.1704055019653765, | |
| "learning_rate": 1.0493600548948879e-07, | |
| "loss": 0.6372, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.811073899269104, | |
| "eval_runtime": 0.7099, | |
| "eval_samples_per_second": 18.314, | |
| "eval_steps_per_second": 1.409, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 73, | |
| "total_flos": 30464739901440.0, | |
| "train_loss": 0.8270750029446328, | |
| "train_runtime": 794.5, | |
| "train_samples_per_second": 46.905, | |
| "train_steps_per_second": 0.092 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 73, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 30464739901440.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |