| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.0007768593034970807, |
| "eval_steps": 2, |
| "global_step": 4, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.00019421482587427018, |
| "grad_norm": 606.1136474609375, |
| "learning_rate": 1e-05, |
| "loss": 44.9038, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.00019421482587427018, |
| "eval_loss": 2.784213066101074, |
| "eval_runtime": 331.9237, |
| "eval_samples_per_second": 26.126, |
| "eval_steps_per_second": 13.063, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.00038842965174854037, |
| "grad_norm": 616.8704833984375, |
| "learning_rate": 2e-05, |
| "loss": 44.8379, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.00038842965174854037, |
| "eval_loss": 2.322169065475464, |
| "eval_runtime": 345.8513, |
| "eval_samples_per_second": 25.074, |
| "eval_steps_per_second": 12.537, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.0005826444776228106, |
| "grad_norm": 299.1457824707031, |
| "learning_rate": 3e-05, |
| "loss": 37.8144, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.0007768593034970807, |
| "grad_norm": 277.48291015625, |
| "learning_rate": 4e-05, |
| "loss": 31.9779, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.0007768593034970807, |
| "eval_loss": 1.6035250425338745, |
| "eval_runtime": 288.7068, |
| "eval_samples_per_second": 30.037, |
| "eval_steps_per_second": 15.019, |
| "step": 4 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 5, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 2, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2804274878742528.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
