| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.003125, |
| "eval_steps": 100, |
| "global_step": 400, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.00078125, |
| "grad_norm": 0.548005223274231, |
| "learning_rate": 0.00066, |
| "loss": 7.392943725585938, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.00078125, |
| "eval_loss": 6.319089889526367, |
| "eval_runtime": 7.0241, |
| "eval_samples_per_second": 82.003, |
| "eval_steps_per_second": 20.501, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.0015625, |
| "grad_norm": 0.6282612085342407, |
| "learning_rate": 0.0009999996375647776, |
| "loss": 5.802936401367187, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.0015625, |
| "eval_loss": 5.66627836227417, |
| "eval_runtime": 6.87, |
| "eval_samples_per_second": 83.843, |
| "eval_steps_per_second": 20.961, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.00234375, |
| "grad_norm": 0.39866289496421814, |
| "learning_rate": 0.0009999966487228837, |
| "loss": 5.2531396484375, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.00234375, |
| "eval_loss": 5.31585693359375, |
| "eval_runtime": 6.8076, |
| "eval_samples_per_second": 84.612, |
| "eval_steps_per_second": 21.153, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.003125, |
| "grad_norm": 0.4630204141139984, |
| "learning_rate": 0.0009999906408667911, |
| "loss": 4.958253784179687, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.003125, |
| "eval_loss": 5.078152179718018, |
| "eval_runtime": 6.8409, |
| "eval_samples_per_second": 84.2, |
| "eval_steps_per_second": 21.05, |
| "step": 400 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 128000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 9223372036854775807, |
| "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": 9965832398438400.0, |
| "train_batch_size": 22, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
