| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.08376963350785341, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.016753926701570682, | |
| "grad_norm": 4.339742183685303, | |
| "learning_rate": 1e-05, | |
| "loss": 10.2919, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.016753926701570682, | |
| "eval_loss": 10.821194648742676, | |
| "eval_runtime": 132.1781, | |
| "eval_samples_per_second": 0.764, | |
| "eval_steps_per_second": 0.386, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.033507853403141365, | |
| "grad_norm": 4.162316799163818, | |
| "learning_rate": 2e-05, | |
| "loss": 11.0619, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.033507853403141365, | |
| "eval_loss": 10.688663482666016, | |
| "eval_runtime": 2.1225, | |
| "eval_samples_per_second": 47.585, | |
| "eval_steps_per_second": 24.028, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.050261780104712044, | |
| "grad_norm": 4.636246681213379, | |
| "learning_rate": 3e-05, | |
| "loss": 10.3999, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.06701570680628273, | |
| "grad_norm": 4.28396463394165, | |
| "learning_rate": 4e-05, | |
| "loss": 10.7777, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06701570680628273, | |
| "eval_loss": 10.500483512878418, | |
| "eval_runtime": 2.1441, | |
| "eval_samples_per_second": 47.106, | |
| "eval_steps_per_second": 23.786, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.08376963350785341, | |
| "grad_norm": 4.292745113372803, | |
| "learning_rate": 5e-05, | |
| "loss": 10.1211, | |
| "step": 5 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 819422772068352.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |