| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.10820559062218214, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0036068530207394047, | |
| "eval_loss": 3.203338623046875, | |
| "eval_runtime": 5.1794, | |
| "eval_samples_per_second": 22.589, | |
| "eval_steps_per_second": 11.391, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010820559062218215, | |
| "grad_norm": 39.52641296386719, | |
| "learning_rate": 3e-05, | |
| "loss": 13.3074, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.018034265103697024, | |
| "eval_loss": 3.1665093898773193, | |
| "eval_runtime": 5.1705, | |
| "eval_samples_per_second": 22.628, | |
| "eval_steps_per_second": 11.411, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02164111812443643, | |
| "grad_norm": 3.889744520187378, | |
| "learning_rate": 6e-05, | |
| "loss": 13.6562, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.032461677186654644, | |
| "grad_norm": 33.33908462524414, | |
| "learning_rate": 9e-05, | |
| "loss": 12.7744, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03606853020739405, | |
| "eval_loss": 3.003424644470215, | |
| "eval_runtime": 5.202, | |
| "eval_samples_per_second": 22.491, | |
| "eval_steps_per_second": 11.342, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04328223624887286, | |
| "grad_norm": 2.9499218463897705, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 11.876, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.05410279531109107, | |
| "grad_norm": 177.76881408691406, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 12.124, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05410279531109107, | |
| "eval_loss": 2.8049392700195312, | |
| "eval_runtime": 5.2024, | |
| "eval_samples_per_second": 22.489, | |
| "eval_steps_per_second": 11.341, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.06492335437330929, | |
| "grad_norm": 3.8371005058288574, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 11.5471, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0721370604147881, | |
| "eval_loss": 2.6382529735565186, | |
| "eval_runtime": 5.2174, | |
| "eval_samples_per_second": 22.425, | |
| "eval_steps_per_second": 11.308, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0757439134355275, | |
| "grad_norm": 571.6266479492188, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 10.7429, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.08656447249774572, | |
| "grad_norm": 35.94160842895508, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 10.1588, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.09017132551848513, | |
| "eval_loss": 2.5596375465393066, | |
| "eval_runtime": 5.1868, | |
| "eval_samples_per_second": 22.557, | |
| "eval_steps_per_second": 11.375, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.09738503155996393, | |
| "grad_norm": 6.185794353485107, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 9.787, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.10820559062218214, | |
| "grad_norm": 64.7603530883789, | |
| "learning_rate": 0.0, | |
| "loss": 10.0356, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.10820559062218214, | |
| "eval_loss": 2.549482822418213, | |
| "eval_runtime": 5.202, | |
| "eval_samples_per_second": 22.491, | |
| "eval_steps_per_second": 11.342, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 750843196342272.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |