| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.6, |
| "eval_steps": 200, |
| "global_step": 400, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0, |
| "eval_runtime": 17.4243, |
| "eval_samples_per_second": 0.287, |
| "eval_steps_per_second": 0.057, |
| "step": 0 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 10.4270658493042, |
| "learning_rate": 1.9600000000000002e-05, |
| "loss": 6.4004, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 9.59022331237793, |
| "learning_rate": 1.8968421052631582e-05, |
| "loss": 5.1737, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.8, |
| "eval_runtime": 5.1058, |
| "eval_samples_per_second": 0.979, |
| "eval_steps_per_second": 0.196, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.2, |
| "grad_norm": 16.000308990478516, |
| "learning_rate": 1.7915789473684214e-05, |
| "loss": 4.7286, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.6, |
| "grad_norm": 12.360644340515137, |
| "learning_rate": 1.6863157894736844e-05, |
| "loss": 4.442, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.6, |
| "eval_runtime": 5.1817, |
| "eval_samples_per_second": 0.965, |
| "eval_steps_per_second": 0.193, |
| "step": 400 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 2000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 8, |
| "save_steps": 400, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 0.0, |
| "train_batch_size": 20, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
