| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.6, |
| "eval_steps": 5, |
| "global_step": 20, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.08, |
| "grad_norm": 0.7405178384640212, |
| "learning_rate": 0.0001, |
| "loss": 1.0732, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 0.8403334341079279, |
| "learning_rate": 0.00018660254037844388, |
| "loss": 0.865, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.4, |
| "eval_loss": 0.7255128622055054, |
| "eval_runtime": 3.1356, |
| "eval_samples_per_second": 6.378, |
| "eval_steps_per_second": 1.595, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 0.46504703007968234, |
| "learning_rate": 0.00011736481776669306, |
| "loss": 0.6956, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.8, |
| "eval_loss": 0.630705714225769, |
| "eval_runtime": 1.9072, |
| "eval_samples_per_second": 10.486, |
| "eval_steps_per_second": 2.622, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.2, |
| "grad_norm": 0.41977051641880375, |
| "learning_rate": 3.5721239031346066e-05, |
| "loss": 0.5421, |
| "step": 15 |
| }, |
| { |
| "epoch": 1.2, |
| "eval_loss": 0.6072101593017578, |
| "eval_runtime": 1.9054, |
| "eval_samples_per_second": 10.497, |
| "eval_steps_per_second": 2.624, |
| "step": 15 |
| }, |
| { |
| "epoch": 1.6, |
| "grad_norm": 0.42132802092200616, |
| "learning_rate": 0.0, |
| "loss": 0.5015, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.6, |
| "eval_loss": 0.6025974750518799, |
| "eval_runtime": 1.8831, |
| "eval_samples_per_second": 10.621, |
| "eval_steps_per_second": 2.655, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.6, |
| "step": 20, |
| "total_flos": 1368128028672.0, |
| "train_loss": 0.66145840883255, |
| "train_runtime": 82.9739, |
| "train_samples_per_second": 1.928, |
| "train_steps_per_second": 0.241 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 20, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 1000, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1368128028672.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
