| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 52, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.019417475728155338, |
| "grad_norm": 0.6309196949005127, |
| "learning_rate": 0.0, |
| "loss": 1.007138967514038, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.1941747572815534, |
| "grad_norm": 0.6809913516044617, |
| "learning_rate": 9.524135262330098e-05, |
| "loss": 0.9641060299343533, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.3883495145631068, |
| "grad_norm": 0.6508110761642456, |
| "learning_rate": 7.408768370508576e-05, |
| "loss": 0.9679458618164063, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.5825242718446602, |
| "grad_norm": 0.6529077887535095, |
| "learning_rate": 4.373333832178478e-05, |
| "loss": 0.956454086303711, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.7766990291262136, |
| "grad_norm": 0.6825394630432129, |
| "learning_rate": 1.5772644703565565e-05, |
| "loss": 0.9437665939331055, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.970873786407767, |
| "grad_norm": 0.6889418959617615, |
| "learning_rate": 8.856374635655695e-07, |
| "loss": 0.9414969444274902, |
| "step": 50 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 52, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 50, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 6769733296422912.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
