| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.007855874910299505, | |
| "eval_steps": 13, | |
| "global_step": 13, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006042980700230389, | |
| "grad_norm": 0.5589237809181213, | |
| "learning_rate": 1e-05, | |
| "loss": 3.1692, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006042980700230389, | |
| "eval_loss": 3.1913259029388428, | |
| "eval_runtime": 229.6838, | |
| "eval_samples_per_second": 12.134, | |
| "eval_steps_per_second": 6.069, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012085961400460777, | |
| "grad_norm": 0.4362795948982239, | |
| "learning_rate": 2e-05, | |
| "loss": 2.8003, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0018128942100691166, | |
| "grad_norm": 0.4628395438194275, | |
| "learning_rate": 3e-05, | |
| "loss": 3.3741, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0024171922800921555, | |
| "grad_norm": 0.4753565788269043, | |
| "learning_rate": 4e-05, | |
| "loss": 2.9939, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003021490350115194, | |
| "grad_norm": 0.5600993037223816, | |
| "learning_rate": 5e-05, | |
| "loss": 3.2337, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0036257884201382332, | |
| "grad_norm": 0.4630330801010132, | |
| "learning_rate": 6e-05, | |
| "loss": 2.8722, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004230086490161272, | |
| "grad_norm": 0.551735520362854, | |
| "learning_rate": 7e-05, | |
| "loss": 3.0785, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004834384560184311, | |
| "grad_norm": 0.5148279666900635, | |
| "learning_rate": 8e-05, | |
| "loss": 2.8164, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00543868263020735, | |
| "grad_norm": 0.7112084627151489, | |
| "learning_rate": 9e-05, | |
| "loss": 3.3676, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006042980700230388, | |
| "grad_norm": 0.5696298480033875, | |
| "learning_rate": 0.0001, | |
| "loss": 2.7856, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006647278770253427, | |
| "grad_norm": 0.6853129863739014, | |
| "learning_rate": 9.98458666866564e-05, | |
| "loss": 3.1526, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0072515768402764665, | |
| "grad_norm": 0.6386879086494446, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 2.706, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.007855874910299505, | |
| "grad_norm": 0.7042403817176819, | |
| "learning_rate": 9.861849601988383e-05, | |
| "loss": 2.5668, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.007855874910299505, | |
| "eval_loss": 2.8041810989379883, | |
| "eval_runtime": 78.0564, | |
| "eval_samples_per_second": 35.705, | |
| "eval_steps_per_second": 17.859, | |
| "step": 13 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.1937056915718144e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |