| { | |
| "best_metric": 0.008739800192415714, | |
| "best_model_checkpoint": "./teapotllm/checkpoint-4585", | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 4585, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.768095850944519, | |
| "learning_rate": 4e-05, | |
| "loss": 1.4227, | |
| "step": 917 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.03158193826675415, | |
| "eval_runtime": 118.9713, | |
| "eval_samples_per_second": 15.415, | |
| "eval_steps_per_second": 1.933, | |
| "step": 917 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.1604224592447281, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0372, | |
| "step": 1834 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.02036420628428459, | |
| "eval_runtime": 118.953, | |
| "eval_samples_per_second": 15.418, | |
| "eval_steps_per_second": 1.934, | |
| "step": 1834 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 0.21215090155601501, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0267, | |
| "step": 2751 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.013773798942565918, | |
| "eval_runtime": 118.9298, | |
| "eval_samples_per_second": 15.421, | |
| "eval_steps_per_second": 1.934, | |
| "step": 2751 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.42151540517807007, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0206, | |
| "step": 3668 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.010322099551558495, | |
| "eval_runtime": 118.9446, | |
| "eval_samples_per_second": 15.419, | |
| "eval_steps_per_second": 1.934, | |
| "step": 3668 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 0.2254112809896469, | |
| "learning_rate": 0.0, | |
| "loss": 0.0171, | |
| "step": 4585 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.008739800192415714, | |
| "eval_runtime": 118.8656, | |
| "eval_samples_per_second": 15.429, | |
| "eval_steps_per_second": 1.935, | |
| "step": 4585 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 4585, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.113472210927616e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |