| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.00199352105656616, |
| "eval_steps": 3, |
| "global_step": 6, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.00033225350942769335, |
| "grad_norm": 1.0361193418502808, |
| "learning_rate": 2e-05, |
| "loss": 1.3271, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.00033225350942769335, |
| "eval_loss": 1.3564280271530151, |
| "eval_runtime": 37.1559, |
| "eval_samples_per_second": 34.126, |
| "eval_steps_per_second": 17.063, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.0006645070188553867, |
| "grad_norm": 1.0444221496582031, |
| "learning_rate": 4e-05, |
| "loss": 1.2539, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.00099676052828308, |
| "grad_norm": 1.0711370706558228, |
| "learning_rate": 6e-05, |
| "loss": 1.2959, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.00099676052828308, |
| "eval_loss": 1.3421787023544312, |
| "eval_runtime": 37.2185, |
| "eval_samples_per_second": 34.069, |
| "eval_steps_per_second": 17.035, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.0013290140377107734, |
| "grad_norm": 0.9208881258964539, |
| "learning_rate": 8e-05, |
| "loss": 1.1699, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.0016612675471384666, |
| "grad_norm": 1.0633083581924438, |
| "learning_rate": 0.0001, |
| "loss": 1.2754, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.00199352105656616, |
| "grad_norm": 1.0281527042388916, |
| "learning_rate": 0.00012, |
| "loss": 1.2609, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.00199352105656616, |
| "eval_loss": 1.1824383735656738, |
| "eval_runtime": 37.281, |
| "eval_samples_per_second": 34.012, |
| "eval_steps_per_second": 17.006, |
| "step": 6 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 10, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 3, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 300058398425088.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
