| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.00847816871555744, |
| "eval_steps": 500, |
| "global_step": 10, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.000847816871555744, |
| "grad_norm": 2.349783182144165, |
| "learning_rate": 4e-05, |
| "loss": 0.9317, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.001695633743111488, |
| "grad_norm": 2.0340960025787354, |
| "learning_rate": 8e-05, |
| "loss": 0.8988, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.002543450614667232, |
| "grad_norm": 1.6518803834915161, |
| "learning_rate": 0.00012, |
| "loss": 0.8603, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.003391267486222976, |
| "grad_norm": 1.065405011177063, |
| "learning_rate": 0.00016, |
| "loss": 0.9058, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.00423908435777872, |
| "grad_norm": 1.4169495105743408, |
| "learning_rate": 0.0002, |
| "loss": 0.874, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.005086901229334464, |
| "grad_norm": 1.1625155210494995, |
| "learning_rate": 0.00016, |
| "loss": 0.8301, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.005934718100890208, |
| "grad_norm": 1.6043394804000854, |
| "learning_rate": 0.00012, |
| "loss": 0.6536, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.006782534972445952, |
| "grad_norm": 0.9761970639228821, |
| "learning_rate": 8e-05, |
| "loss": 0.7176, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.007630351844001695, |
| "grad_norm": 0.8356990218162537, |
| "learning_rate": 4e-05, |
| "loss": 0.6041, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.00847816871555744, |
| "grad_norm": 0.7568296194076538, |
| "learning_rate": 0.0, |
| "loss": 0.6684, |
| "step": 10 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 10, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 4222873804283904.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
