| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.10989010989010989, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005494505494505495, | |
| "grad_norm": 0.027151547372341156, | |
| "learning_rate": 1e-05, | |
| "loss": 11.9328, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005494505494505495, | |
| "eval_loss": 11.931960105895996, | |
| "eval_runtime": 18.0294, | |
| "eval_samples_per_second": 34.055, | |
| "eval_steps_per_second": 17.028, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01098901098901099, | |
| "grad_norm": 0.027643978595733643, | |
| "learning_rate": 2e-05, | |
| "loss": 11.9319, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.016483516483516484, | |
| "grad_norm": 0.028413433581590652, | |
| "learning_rate": 3e-05, | |
| "loss": 11.9315, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02197802197802198, | |
| "grad_norm": 0.03067416325211525, | |
| "learning_rate": 4e-05, | |
| "loss": 11.9323, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.027472527472527472, | |
| "grad_norm": 0.02727838046848774, | |
| "learning_rate": 5e-05, | |
| "loss": 11.932, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.027472527472527472, | |
| "eval_loss": 11.931900024414062, | |
| "eval_runtime": 18.2244, | |
| "eval_samples_per_second": 33.691, | |
| "eval_steps_per_second": 16.846, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03296703296703297, | |
| "grad_norm": 0.02454882673919201, | |
| "learning_rate": 6e-05, | |
| "loss": 11.932, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.038461538461538464, | |
| "grad_norm": 0.02835436351597309, | |
| "learning_rate": 7e-05, | |
| "loss": 11.9315, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.04395604395604396, | |
| "grad_norm": 0.026226777583360672, | |
| "learning_rate": 8e-05, | |
| "loss": 11.9322, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04945054945054945, | |
| "grad_norm": 0.027679918333888054, | |
| "learning_rate": 9e-05, | |
| "loss": 11.9327, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.054945054945054944, | |
| "grad_norm": 0.025617027655243874, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9329, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.054945054945054944, | |
| "eval_loss": 11.931732177734375, | |
| "eval_runtime": 18.2319, | |
| "eval_samples_per_second": 33.677, | |
| "eval_steps_per_second": 16.839, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06043956043956044, | |
| "grad_norm": 0.02739313431084156, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 11.9323, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.06593406593406594, | |
| "grad_norm": 0.024653950706124306, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 11.9318, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.07142857142857142, | |
| "grad_norm": 0.027017774060368538, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 11.931, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.07692307692307693, | |
| "grad_norm": 0.028646156191825867, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 11.9311, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.08241758241758242, | |
| "grad_norm": 0.028420699760317802, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9325, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.08241758241758242, | |
| "eval_loss": 11.931500434875488, | |
| "eval_runtime": 18.4245, | |
| "eval_samples_per_second": 33.325, | |
| "eval_steps_per_second": 16.663, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.08791208791208792, | |
| "grad_norm": 0.028067054226994514, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 11.9316, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.09340659340659341, | |
| "grad_norm": 0.029327698051929474, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 11.9319, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0989010989010989, | |
| "grad_norm": 0.02734130434691906, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 11.9326, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1043956043956044, | |
| "grad_norm": 0.030583491548895836, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 11.933, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.10989010989010989, | |
| "grad_norm": 0.023537058383226395, | |
| "learning_rate": 0.0, | |
| "loss": 11.9314, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.10989010989010989, | |
| "eval_loss": 11.931438446044922, | |
| "eval_runtime": 18.4207, | |
| "eval_samples_per_second": 33.332, | |
| "eval_steps_per_second": 16.666, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 20, | |
| "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": 239830302720.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |