| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004926836478297285, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 9.853672956594571e-05, | |
| "eval_loss": 5.315885066986084, | |
| "eval_runtime": 80.4404, | |
| "eval_samples_per_second": 53.12, | |
| "eval_steps_per_second": 26.566, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004926836478297285, | |
| "grad_norm": 4.895656585693359, | |
| "learning_rate": 5e-05, | |
| "loss": 5.2609, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.000985367295659457, | |
| "grad_norm": 3.6341326236724854, | |
| "learning_rate": 0.0001, | |
| "loss": 4.9677, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.000985367295659457, | |
| "eval_loss": 4.6846604347229, | |
| "eval_runtime": 80.6705, | |
| "eval_samples_per_second": 52.969, | |
| "eval_steps_per_second": 26.49, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0014780509434891855, | |
| "grad_norm": 2.931530714035034, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 4.336, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.001970734591318914, | |
| "grad_norm": 3.130262851715088, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.6173, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.001970734591318914, | |
| "eval_loss": 3.208744525909424, | |
| "eval_runtime": 80.8453, | |
| "eval_samples_per_second": 52.854, | |
| "eval_steps_per_second": 26.433, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0024634182391486425, | |
| "grad_norm": 4.077453136444092, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.9028, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.002956101886978371, | |
| "grad_norm": 5.219675540924072, | |
| "learning_rate": 5e-05, | |
| "loss": 2.5896, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.002956101886978371, | |
| "eval_loss": 2.277921199798584, | |
| "eval_runtime": 81.8017, | |
| "eval_samples_per_second": 52.236, | |
| "eval_steps_per_second": 26.124, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0034487855348081, | |
| "grad_norm": 4.284224987030029, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.2228, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.003941469182637828, | |
| "grad_norm": 3.1860170364379883, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.9985, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.003941469182637828, | |
| "eval_loss": 1.819312334060669, | |
| "eval_runtime": 80.008, | |
| "eval_samples_per_second": 53.407, | |
| "eval_steps_per_second": 26.71, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.004434152830467557, | |
| "grad_norm": 3.8627407550811768, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.1064, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.004926836478297285, | |
| "grad_norm": 2.9635887145996094, | |
| "learning_rate": 0.0, | |
| "loss": 1.8765, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.004926836478297285, | |
| "eval_loss": 1.784060001373291, | |
| "eval_runtime": 80.2157, | |
| "eval_samples_per_second": 53.269, | |
| "eval_steps_per_second": 26.641, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 273483887542272.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |