| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.1, |
| "eval_steps": 500, |
| "global_step": 100, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.01, |
| "grad_norm": 80.67810821533203, |
| "learning_rate": 4.55e-05, |
| "loss": 4.5136, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.02, |
| "grad_norm": 3.765883684158325, |
| "learning_rate": 4.05e-05, |
| "loss": 1.3464, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.03, |
| "grad_norm": 2.644195079803467, |
| "learning_rate": 3.55e-05, |
| "loss": 0.8144, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.04, |
| "grad_norm": 1.5590925216674805, |
| "learning_rate": 3.05e-05, |
| "loss": 0.4968, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.05, |
| "grad_norm": 2.227367401123047, |
| "learning_rate": 2.5500000000000003e-05, |
| "loss": 0.5272, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.06, |
| "grad_norm": 1.6742937564849854, |
| "learning_rate": 2.05e-05, |
| "loss": 0.4726, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.07, |
| "grad_norm": 1.2793476581573486, |
| "learning_rate": 1.55e-05, |
| "loss": 0.4769, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.08, |
| "grad_norm": 1.4974271059036255, |
| "learning_rate": 1.05e-05, |
| "loss": 0.5827, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.09, |
| "grad_norm": 1.951063871383667, |
| "learning_rate": 5.500000000000001e-06, |
| "loss": 0.3509, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.1, |
| "grad_norm": 1.4510406255722046, |
| "learning_rate": 5.000000000000001e-07, |
| "loss": 0.4969, |
| "step": 100 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 100, |
| "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": 121791578112000.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
