| { |
| "best_global_step": 589, |
| "best_metric": 2.197453737258911, |
| "best_model_checkpoint": "./xo_model/checkpoint-589", |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 589, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.1697792869269949, |
| "grad_norm": 0.19476668536663055, |
| "learning_rate": 4.831918505942275e-05, |
| "loss": 2.197429504394531, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.3395585738539898, |
| "grad_norm": 0.2964541018009186, |
| "learning_rate": 4.6621392190152803e-05, |
| "loss": 2.1973367309570313, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.5093378607809848, |
| "grad_norm": 0.24343813955783844, |
| "learning_rate": 4.4923599320882855e-05, |
| "loss": 2.197264862060547, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.6791171477079796, |
| "grad_norm": 0.272930771112442, |
| "learning_rate": 4.322580645161291e-05, |
| "loss": 2.1971003723144533, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.8488964346349746, |
| "grad_norm": 0.2310926616191864, |
| "learning_rate": 4.152801358234296e-05, |
| "loss": 2.196432342529297, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.11714080803251255, |
| "eval_loss": 2.197453737258911, |
| "eval_runtime": 0.7848, |
| "eval_samples_per_second": 5330.075, |
| "eval_steps_per_second": 84.099, |
| "step": 589 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 2945, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 16220443986.0, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
