| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 5.769230769230769, |
| "eval_steps": 500, |
| "global_step": 18, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.2564102564102564, |
| "grad_norm": 6.0152716636657715, |
| "learning_rate": 5.0000000000000004e-08, |
| "loss": 2.0502, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.5128205128205128, |
| "grad_norm": 6.146883487701416, |
| "learning_rate": 1.0000000000000001e-07, |
| "loss": 2.0636, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.7692307692307693, |
| "grad_norm": 6.148375988006592, |
| "learning_rate": 1.5000000000000002e-07, |
| "loss": 2.0664, |
| "step": 3 |
| }, |
| { |
| "epoch": 1.2564102564102564, |
| "grad_norm": 10.523953437805176, |
| "learning_rate": 2.0000000000000002e-07, |
| "loss": 4.1446, |
| "step": 4 |
| }, |
| { |
| "epoch": 1.5128205128205128, |
| "grad_norm": 6.099686145782471, |
| "learning_rate": 2.5000000000000004e-07, |
| "loss": 2.0812, |
| "step": 5 |
| }, |
| { |
| "epoch": 1.7692307692307692, |
| "grad_norm": 6.2565131187438965, |
| "learning_rate": 3.0000000000000004e-07, |
| "loss": 2.0717, |
| "step": 6 |
| }, |
| { |
| "epoch": 2.2564102564102564, |
| "grad_norm": 10.179949760437012, |
| "learning_rate": 3.5000000000000004e-07, |
| "loss": 4.0799, |
| "step": 7 |
| }, |
| { |
| "epoch": 2.5128205128205128, |
| "grad_norm": 6.111963748931885, |
| "learning_rate": 4.0000000000000003e-07, |
| "loss": 2.076, |
| "step": 8 |
| }, |
| { |
| "epoch": 2.769230769230769, |
| "grad_norm": 6.185149192810059, |
| "learning_rate": 4.5000000000000003e-07, |
| "loss": 2.076, |
| "step": 9 |
| }, |
| { |
| "epoch": 3.2564102564102564, |
| "grad_norm": 10.27457046508789, |
| "learning_rate": 5.000000000000001e-07, |
| "loss": 4.1004, |
| "step": 10 |
| }, |
| { |
| "epoch": 3.5128205128205128, |
| "grad_norm": 6.015860080718994, |
| "learning_rate": 5.5e-07, |
| "loss": 2.0349, |
| "step": 11 |
| }, |
| { |
| "epoch": 3.769230769230769, |
| "grad_norm": 6.001443862915039, |
| "learning_rate": 6.000000000000001e-07, |
| "loss": 2.0509, |
| "step": 12 |
| }, |
| { |
| "epoch": 4.256410256410256, |
| "grad_norm": 8.41840934753418, |
| "learning_rate": 6.5e-07, |
| "loss": 3.9985, |
| "step": 13 |
| }, |
| { |
| "epoch": 4.512820512820513, |
| "grad_norm": 5.706866264343262, |
| "learning_rate": 7.000000000000001e-07, |
| "loss": 2.0218, |
| "step": 14 |
| }, |
| { |
| "epoch": 4.769230769230769, |
| "grad_norm": 5.490438461303711, |
| "learning_rate": 7.5e-07, |
| "loss": 1.9837, |
| "step": 15 |
| }, |
| { |
| "epoch": 5.256410256410256, |
| "grad_norm": 8.871084213256836, |
| "learning_rate": 8.000000000000001e-07, |
| "loss": 3.9086, |
| "step": 16 |
| }, |
| { |
| "epoch": 5.512820512820513, |
| "grad_norm": 5.151674270629883, |
| "learning_rate": 8.500000000000001e-07, |
| "loss": 1.9257, |
| "step": 17 |
| }, |
| { |
| "epoch": 5.769230769230769, |
| "grad_norm": 4.78213357925415, |
| "learning_rate": 9.000000000000001e-07, |
| "loss": 1.9045, |
| "step": 18 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 18, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 6, |
| "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": 1.4560929338150093e+17, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
