| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.008376963350785341, | |
| "eval_steps": 13, | |
| "global_step": 13, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006443817962142569, | |
| "grad_norm": 4.898526668548584, | |
| "learning_rate": 1e-05, | |
| "loss": 8.2457, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006443817962142569, | |
| "eval_loss": 7.802831649780273, | |
| "eval_runtime": 47.5305, | |
| "eval_samples_per_second": 54.996, | |
| "eval_steps_per_second": 27.498, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012887635924285139, | |
| "grad_norm": 3.692995548248291, | |
| "learning_rate": 2e-05, | |
| "loss": 8.3769, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0019331453886427708, | |
| "grad_norm": 4.796352386474609, | |
| "learning_rate": 3e-05, | |
| "loss": 8.6187, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0025775271848570277, | |
| "grad_norm": 3.221654176712036, | |
| "learning_rate": 4e-05, | |
| "loss": 8.0322, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003221908981071285, | |
| "grad_norm": 2.433626174926758, | |
| "learning_rate": 5e-05, | |
| "loss": 7.9877, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0038662907772855416, | |
| "grad_norm": 2.0175940990448, | |
| "learning_rate": 6e-05, | |
| "loss": 7.9417, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004510672573499798, | |
| "grad_norm": 2.2974374294281006, | |
| "learning_rate": 7e-05, | |
| "loss": 8.3393, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0051550543697140554, | |
| "grad_norm": 1.9051103591918945, | |
| "learning_rate": 8e-05, | |
| "loss": 7.4193, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005799436165928313, | |
| "grad_norm": 2.320819616317749, | |
| "learning_rate": 9e-05, | |
| "loss": 8.0907, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00644381796214257, | |
| "grad_norm": 1.9515935182571411, | |
| "learning_rate": 0.0001, | |
| "loss": 7.6772, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007088199758356826, | |
| "grad_norm": 1.723854899406433, | |
| "learning_rate": 9.98458666866564e-05, | |
| "loss": 7.4406, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.007732581554571083, | |
| "grad_norm": 3.2257795333862305, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 7.8407, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.008376963350785341, | |
| "grad_norm": 2.5419061183929443, | |
| "learning_rate": 9.861849601988383e-05, | |
| "loss": 8.0091, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.008376963350785341, | |
| "eval_loss": 7.61268949508667, | |
| "eval_runtime": 23.5679, | |
| "eval_samples_per_second": 110.914, | |
| "eval_steps_per_second": 55.457, | |
| "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": 28235500879872.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |