| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.11835194910866188, |
| "eval_steps": 100, |
| "global_step": 1000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.00011835194910866188, |
| "grad_norm": 3.050482988357544, |
| "learning_rate": 0.001, |
| "loss": 11.2196, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.011835194910866188, |
| "grad_norm": 0.32114312052726746, |
| "learning_rate": 0.001, |
| "loss": 7.1872, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.023670389821732377, |
| "grad_norm": 0.2564636170864105, |
| "learning_rate": 0.001, |
| "loss": 6.1443, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.035505584732598565, |
| "grad_norm": 0.5633418560028076, |
| "learning_rate": 0.001, |
| "loss": 5.8111, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.04734077964346475, |
| "grad_norm": 0.45185068249702454, |
| "learning_rate": 0.001, |
| "loss": 5.57, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.05917597455433094, |
| "grad_norm": 0.41621828079223633, |
| "learning_rate": 0.001, |
| "loss": 5.4025, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.07101116946519713, |
| "grad_norm": 0.5600417852401733, |
| "learning_rate": 0.001, |
| "loss": 5.2789, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.08284636437606333, |
| "grad_norm": 0.3999986946582794, |
| "learning_rate": 0.001, |
| "loss": 5.1787, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.0946815592869295, |
| "grad_norm": 0.9927613735198975, |
| "learning_rate": 0.001, |
| "loss": 5.1012, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.1065167541977957, |
| "grad_norm": 0.76481032371521, |
| "learning_rate": 0.001, |
| "loss": 5.0373, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.11835194910866188, |
| "grad_norm": 0.8310058116912842, |
| "learning_rate": 0.001, |
| "loss": 4.9801, |
| "step": 1000 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 30000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 4, |
| "save_steps": 1000, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 4.2154567139328e+16, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
