| { |
| "best_metric": 0.34387466311454773, |
| "best_model_checkpoint": "./beans_outputs/checkpoint-85", |
| "epoch": 5.0, |
| "eval_steps": 500, |
| "global_step": 85, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.5882352941176471, |
| "grad_norm": 1.3442401885986328, |
| "learning_rate": 1.7647058823529414e-05, |
| "loss": 0.9867, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.924812030075188, |
| "eval_loss": 0.7572791576385498, |
| "eval_runtime": 14.3345, |
| "eval_samples_per_second": 9.278, |
| "eval_steps_per_second": 0.209, |
| "step": 17 |
| }, |
| { |
| "epoch": 1.1764705882352942, |
| "grad_norm": 1.1912851333618164, |
| "learning_rate": 1.5294117647058822e-05, |
| "loss": 0.8134, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.7647058823529411, |
| "grad_norm": 1.3143070936203003, |
| "learning_rate": 1.2941176470588238e-05, |
| "loss": 0.6896, |
| "step": 30 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9624060150375939, |
| "eval_loss": 0.5535997748374939, |
| "eval_runtime": 13.8121, |
| "eval_samples_per_second": 9.629, |
| "eval_steps_per_second": 0.217, |
| "step": 34 |
| }, |
| { |
| "epoch": 2.3529411764705883, |
| "grad_norm": 1.235939860343933, |
| "learning_rate": 1.0588235294117648e-05, |
| "loss": 0.5754, |
| "step": 40 |
| }, |
| { |
| "epoch": 2.9411764705882355, |
| "grad_norm": 1.0637030601501465, |
| "learning_rate": 8.23529411764706e-06, |
| "loss": 0.498, |
| "step": 50 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9699248120300752, |
| "eval_loss": 0.4194970428943634, |
| "eval_runtime": 14.2589, |
| "eval_samples_per_second": 9.328, |
| "eval_steps_per_second": 0.21, |
| "step": 51 |
| }, |
| { |
| "epoch": 3.5294117647058822, |
| "grad_norm": 1.221981167793274, |
| "learning_rate": 5.882352941176471e-06, |
| "loss": 0.4537, |
| "step": 60 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9699248120300752, |
| "eval_loss": 0.36039993166923523, |
| "eval_runtime": 14.1856, |
| "eval_samples_per_second": 9.376, |
| "eval_steps_per_second": 0.211, |
| "step": 68 |
| }, |
| { |
| "epoch": 4.117647058823529, |
| "grad_norm": 1.0668258666992188, |
| "learning_rate": 3.529411764705883e-06, |
| "loss": 0.3909, |
| "step": 70 |
| }, |
| { |
| "epoch": 4.705882352941177, |
| "grad_norm": 1.3315623998641968, |
| "learning_rate": 1.1764705882352942e-06, |
| "loss": 0.3927, |
| "step": 80 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9699248120300752, |
| "eval_loss": 0.34387466311454773, |
| "eval_runtime": 13.7327, |
| "eval_samples_per_second": 9.685, |
| "eval_steps_per_second": 0.218, |
| "step": 85 |
| }, |
| { |
| "epoch": 5.0, |
| "step": 85, |
| "total_flos": 4.006371770595533e+17, |
| "train_loss": 0.5856448944877176, |
| "train_runtime": 608.2336, |
| "train_samples_per_second": 8.5, |
| "train_steps_per_second": 0.14 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 85, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "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": 4.006371770595533e+17, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
