| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.0029331964508322946, |
| "eval_steps": 3, |
| "global_step": 10, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.00029331964508322946, |
| "grad_norm": 1.1542128324508667, |
| "learning_rate": 2e-05, |
| "loss": 1.6672, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.0005866392901664589, |
| "grad_norm": 0.8581305742263794, |
| "learning_rate": 4e-05, |
| "loss": 1.3434, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.0008799589352496884, |
| "grad_norm": 0.9822282791137695, |
| "learning_rate": 6e-05, |
| "loss": 1.3971, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.0008799589352496884, |
| "eval_loss": 1.5251803398132324, |
| "eval_runtime": 133.4372, |
| "eval_samples_per_second": 10.762, |
| "eval_steps_per_second": 5.381, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.0011732785803329178, |
| "grad_norm": 1.1366212368011475, |
| "learning_rate": 8e-05, |
| "loss": 1.5729, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.0014665982254161473, |
| "grad_norm": 0.9662085175514221, |
| "learning_rate": 0.0001, |
| "loss": 1.4449, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.0017599178704993767, |
| "grad_norm": 0.8611655235290527, |
| "learning_rate": 0.00012, |
| "loss": 1.4187, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.0017599178704993767, |
| "eval_loss": 1.4484795331954956, |
| "eval_runtime": 132.2383, |
| "eval_samples_per_second": 10.859, |
| "eval_steps_per_second": 5.43, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.002053237515582606, |
| "grad_norm": 0.9230878949165344, |
| "learning_rate": 0.00014, |
| "loss": 1.5278, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.0023465571606658357, |
| "grad_norm": 1.190510869026184, |
| "learning_rate": 0.00016, |
| "loss": 1.4455, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.002639876805749065, |
| "grad_norm": 0.8905510902404785, |
| "learning_rate": 0.00018, |
| "loss": 1.34, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.002639876805749065, |
| "eval_loss": 1.3201472759246826, |
| "eval_runtime": 132.1601, |
| "eval_samples_per_second": 10.866, |
| "eval_steps_per_second": 5.433, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.0029331964508322946, |
| "grad_norm": 0.8329473733901978, |
| "learning_rate": 0.0002, |
| "loss": 1.3695, |
| "step": 10 |
| } |
| ], |
| "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": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 500097330708480.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
