| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.9, |
| "eval_steps": 500, |
| "global_step": 6, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.15, |
| "grad_norm": 35.73806381225586, |
| "learning_rate": 5.0000000000000004e-08, |
| "loss": 3.2839, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.3, |
| "grad_norm": 35.236732482910156, |
| "learning_rate": 1.0000000000000001e-07, |
| "loss": 3.2281, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.45, |
| "grad_norm": 35.85063171386719, |
| "learning_rate": 1.5000000000000002e-07, |
| "loss": 3.2521, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 35.62168884277344, |
| "learning_rate": 2.0000000000000002e-07, |
| "loss": 3.2824, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.75, |
| "grad_norm": 36.429351806640625, |
| "learning_rate": 2.5000000000000004e-07, |
| "loss": 3.3533, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.9, |
| "grad_norm": 36.30988311767578, |
| "learning_rate": 3.0000000000000004e-07, |
| "loss": 3.3279, |
| "step": 6 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 36, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 6, |
| "save_steps": 6, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3.859909958141215e+17, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
