| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.9976905311778291, |
| "eval_steps": 500, |
| "global_step": 243, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.10264305876315115, |
| "grad_norm": 0.47805914282798767, |
| "learning_rate": 0.00018553191489361704, |
| "loss": 1.2392, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.2052861175263023, |
| "grad_norm": 0.28673839569091797, |
| "learning_rate": 0.00016425531914893618, |
| "loss": 0.8265, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.30792917628945343, |
| "grad_norm": 0.268703818321228, |
| "learning_rate": 0.00014297872340425532, |
| "loss": 0.786, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.4105722350526046, |
| "grad_norm": 0.2763696014881134, |
| "learning_rate": 0.00012170212765957448, |
| "loss": 0.7836, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.5132152938157557, |
| "grad_norm": 0.30008208751678467, |
| "learning_rate": 0.00010042553191489362, |
| "loss": 0.7712, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.6158583525789069, |
| "grad_norm": 0.28837621212005615, |
| "learning_rate": 7.914893617021277e-05, |
| "loss": 0.7763, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.718501411342058, |
| "grad_norm": 0.28170982003211975, |
| "learning_rate": 5.787234042553191e-05, |
| "loss": 0.7512, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.8211444701052092, |
| "grad_norm": 0.298803448677063, |
| "learning_rate": 3.6595744680851066e-05, |
| "loss": 0.756, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.9237875288683602, |
| "grad_norm": 0.28528884053230286, |
| "learning_rate": 1.5319148936170214e-05, |
| "loss": 0.7626, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.9976905311778291, |
| "eval_loss": 0.7545520663261414, |
| "eval_runtime": 432.6562, |
| "eval_samples_per_second": 1.898, |
| "eval_steps_per_second": 0.238, |
| "step": 243 |
| } |
| ], |
| "logging_steps": 25, |
| "max_steps": 243, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.549109544769618e+17, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
