| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0013500685581689694, | |
| "eval_steps": 2, | |
| "global_step": 4, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00033751713954224236, | |
| "grad_norm": 0.986964762210846, | |
| "learning_rate": 1e-05, | |
| "loss": 3.0624, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00033751713954224236, | |
| "eval_loss": 3.013227939605713, | |
| "eval_runtime": 309.0158, | |
| "eval_samples_per_second": 16.148, | |
| "eval_steps_per_second": 8.074, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006750342790844847, | |
| "grad_norm": 0.970856249332428, | |
| "learning_rate": 2e-05, | |
| "loss": 2.8018, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0006750342790844847, | |
| "eval_loss": 2.9928829669952393, | |
| "eval_runtime": 321.9429, | |
| "eval_samples_per_second": 15.5, | |
| "eval_steps_per_second": 7.75, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0010125514186267272, | |
| "grad_norm": 1.0419691801071167, | |
| "learning_rate": 3e-05, | |
| "loss": 2.8588, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0013500685581689694, | |
| "grad_norm": 0.9941425323486328, | |
| "learning_rate": 4e-05, | |
| "loss": 2.9969, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0013500685581689694, | |
| "eval_loss": 2.965714454650879, | |
| "eval_runtime": 324.536, | |
| "eval_samples_per_second": 15.376, | |
| "eval_steps_per_second": 7.688, | |
| "step": 4 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2959302797033472.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |