| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.014199503017394392, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0014199503017394391, | |
| "grad_norm": 2.71122407913208, | |
| "learning_rate": 2e-05, | |
| "loss": 3.4024, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0014199503017394391, | |
| "eval_loss": 4.24873161315918, | |
| "eval_runtime": 18.9832, | |
| "eval_samples_per_second": 15.645, | |
| "eval_steps_per_second": 7.849, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0028399006034788782, | |
| "grad_norm": 2.185009717941284, | |
| "learning_rate": 4e-05, | |
| "loss": 2.5114, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004259850905218318, | |
| "grad_norm": 2.2500784397125244, | |
| "learning_rate": 6e-05, | |
| "loss": 2.9047, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004259850905218318, | |
| "eval_loss": 4.236300945281982, | |
| "eval_runtime": 19.0254, | |
| "eval_samples_per_second": 15.611, | |
| "eval_steps_per_second": 7.832, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0056798012069577564, | |
| "grad_norm": 2.796581268310547, | |
| "learning_rate": 8e-05, | |
| "loss": 2.3501, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.007099751508697196, | |
| "grad_norm": 2.2836456298828125, | |
| "learning_rate": 0.0001, | |
| "loss": 3.2729, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008519701810436636, | |
| "grad_norm": 2.491248369216919, | |
| "learning_rate": 0.00012, | |
| "loss": 2.1742, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008519701810436636, | |
| "eval_loss": 4.0644426345825195, | |
| "eval_runtime": 19.0229, | |
| "eval_samples_per_second": 15.613, | |
| "eval_steps_per_second": 7.833, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009939652112176074, | |
| "grad_norm": 3.573564052581787, | |
| "learning_rate": 0.00014, | |
| "loss": 3.9925, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.011359602413915513, | |
| "grad_norm": 2.61667537689209, | |
| "learning_rate": 0.00016, | |
| "loss": 3.8804, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.012779552715654952, | |
| "grad_norm": 2.5469532012939453, | |
| "learning_rate": 0.00018, | |
| "loss": 3.4361, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.012779552715654952, | |
| "eval_loss": 3.613114356994629, | |
| "eval_runtime": 19.0203, | |
| "eval_samples_per_second": 15.615, | |
| "eval_steps_per_second": 7.834, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.014199503017394392, | |
| "grad_norm": 1.9056304693222046, | |
| "learning_rate": 0.0002, | |
| "loss": 2.2443, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 277675172167680.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |