| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0031392246115209545, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003139224611520954, | |
| "grad_norm": 6.569947719573975, | |
| "learning_rate": 2e-05, | |
| "loss": 17.9941, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003139224611520954, | |
| "eval_loss": 17.898242950439453, | |
| "eval_runtime": 37.6944, | |
| "eval_samples_per_second": 35.602, | |
| "eval_steps_per_second": 17.801, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006278449223041908, | |
| "grad_norm": 5.329532623291016, | |
| "learning_rate": 4e-05, | |
| "loss": 18.9901, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0009417673834562863, | |
| "grad_norm": 7.4519219398498535, | |
| "learning_rate": 6e-05, | |
| "loss": 17.3253, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0009417673834562863, | |
| "eval_loss": 17.875743865966797, | |
| "eval_runtime": 36.9655, | |
| "eval_samples_per_second": 36.304, | |
| "eval_steps_per_second": 18.152, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0012556898446083817, | |
| "grad_norm": 8.001363754272461, | |
| "learning_rate": 8e-05, | |
| "loss": 17.8501, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0015696123057604772, | |
| "grad_norm": 7.333746433258057, | |
| "learning_rate": 0.0001, | |
| "loss": 19.9848, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0018835347669125726, | |
| "grad_norm": 8.180486679077148, | |
| "learning_rate": 0.00012, | |
| "loss": 16.195, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0018835347669125726, | |
| "eval_loss": 17.218795776367188, | |
| "eval_runtime": 37.143, | |
| "eval_samples_per_second": 36.131, | |
| "eval_steps_per_second": 18.065, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002197457228064668, | |
| "grad_norm": 8.934775352478027, | |
| "learning_rate": 0.00014, | |
| "loss": 16.1994, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0025113796892167633, | |
| "grad_norm": 13.129068374633789, | |
| "learning_rate": 0.00016, | |
| "loss": 14.0295, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.002825302150368859, | |
| "grad_norm": 12.230052947998047, | |
| "learning_rate": 0.00018, | |
| "loss": 15.3188, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.002825302150368859, | |
| "eval_loss": 14.17167854309082, | |
| "eval_runtime": 37.137, | |
| "eval_samples_per_second": 36.136, | |
| "eval_steps_per_second": 18.068, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0031392246115209545, | |
| "grad_norm": 14.406098365783691, | |
| "learning_rate": 0.0002, | |
| "loss": 12.8901, | |
| "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": 1742636046090240.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |