| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.9902912621359223, |
| "eval_steps": 500, |
| "global_step": 51, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.1941747572815534, |
| "grad_norm": 4.664066413285674, |
| "learning_rate": 4.973358420187776e-06, |
| "loss": 0.7795, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.3883495145631068, |
| "grad_norm": 1.9822347336414026, |
| "learning_rate": 4.099182553897228e-06, |
| "loss": 0.2484, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.5825242718446602, |
| "grad_norm": 1.5984451911406743, |
| "learning_rate": 2.408694942355853e-06, |
| "loss": 0.1545, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.7766990291262136, |
| "grad_norm": 1.4874861508376533, |
| "learning_rate": 7.648145119484152e-07, |
| "loss": 0.1388, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.970873786407767, |
| "grad_norm": 1.3943333378740448, |
| "learning_rate": 6.66929084112089e-09, |
| "loss": 0.1317, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.9902912621359223, |
| "step": 51, |
| "total_flos": 9087886688256.0, |
| "train_loss": 0.2873636951633528, |
| "train_runtime": 208.0579, |
| "train_samples_per_second": 15.784, |
| "train_steps_per_second": 0.245 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 51, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 1000, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 9087886688256.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
