| { |
| "best_metric": 0.5654206275939941, |
| "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": 1.3444452285766602, |
| "learning_rate": 1.607843137254902e-05, |
| "loss": 0.9886, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.924812030075188, |
| "eval_loss": 0.7760084271430969, |
| "eval_runtime": 1.8302, |
| "eval_samples_per_second": 72.67, |
| "eval_steps_per_second": 1.639, |
| "step": 17 |
| }, |
| { |
| "epoch": 1.1764705882352942, |
| "grad_norm": 1.1995707750320435, |
| "learning_rate": 1.215686274509804e-05, |
| "loss": 0.8267, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.7647058823529411, |
| "grad_norm": 1.1789577007293701, |
| "learning_rate": 8.23529411764706e-06, |
| "loss": 0.7227, |
| "step": 30 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9548872180451128, |
| "eval_loss": 0.6204721331596375, |
| "eval_runtime": 1.9888, |
| "eval_samples_per_second": 66.876, |
| "eval_steps_per_second": 1.508, |
| "step": 34 |
| }, |
| { |
| "epoch": 2.3529411764705883, |
| "grad_norm": 1.2507354021072388, |
| "learning_rate": 4.313725490196079e-06, |
| "loss": 0.6427, |
| "step": 40 |
| }, |
| { |
| "epoch": 2.9411764705882355, |
| "grad_norm": 1.1395034790039062, |
| "learning_rate": 3.921568627450981e-07, |
| "loss": 0.6045, |
| "step": 50 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9699248120300752, |
| "eval_loss": 0.5654206275939941, |
| "eval_runtime": 1.9197, |
| "eval_samples_per_second": 69.282, |
| "eval_steps_per_second": 1.563, |
| "step": 51 |
| }, |
| { |
| "epoch": 3.0, |
| "step": 51, |
| "total_flos": 2.4038230623573197e+17, |
| "train_loss": 0.0, |
| "train_runtime": 0.3673, |
| "train_samples_per_second": 8444.655, |
| "train_steps_per_second": 138.839 |
| } |
| ], |
| "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 |
| } |
|
|
