| { |
| "best_metric": 0.5641857385635376, |
| "best_model_checkpoint": "./beans_outputs/checkpoint-51", |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 51, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.5882352941176471, |
| "grad_norm": 1.3421605825424194, |
| "learning_rate": 1.607843137254902e-05, |
| "loss": 0.9886, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.924812030075188, |
| "eval_loss": 0.7757352590560913, |
| "eval_runtime": 8.5619, |
| "eval_samples_per_second": 15.534, |
| "eval_steps_per_second": 0.35, |
| "step": 17 |
| }, |
| { |
| "epoch": 1.1764705882352942, |
| "grad_norm": 1.1954083442687988, |
| "learning_rate": 1.215686274509804e-05, |
| "loss": 0.8266, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.7647058823529411, |
| "grad_norm": 1.1710609197616577, |
| "learning_rate": 8.23529411764706e-06, |
| "loss": 0.7223, |
| "step": 30 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9548872180451128, |
| "eval_loss": 0.6193692088127136, |
| "eval_runtime": 9.1501, |
| "eval_samples_per_second": 14.535, |
| "eval_steps_per_second": 0.328, |
| "step": 34 |
| }, |
| { |
| "epoch": 2.3529411764705883, |
| "grad_norm": 1.2411857843399048, |
| "learning_rate": 4.313725490196079e-06, |
| "loss": 0.6419, |
| "step": 40 |
| }, |
| { |
| "epoch": 2.9411764705882355, |
| "grad_norm": 1.1404906511306763, |
| "learning_rate": 3.921568627450981e-07, |
| "loss": 0.6036, |
| "step": 50 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9699248120300752, |
| "eval_loss": 0.5641857385635376, |
| "eval_runtime": 9.221, |
| "eval_samples_per_second": 14.424, |
| "eval_steps_per_second": 0.325, |
| "step": 51 |
| }, |
| { |
| "epoch": 3.0, |
| "step": 51, |
| "total_flos": 2.4038230623573197e+17, |
| "train_loss": 0.7540177586031895, |
| "train_runtime": 260.6448, |
| "train_samples_per_second": 11.901, |
| "train_steps_per_second": 0.196 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 51, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "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": 2.4038230623573197e+17, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
