| { |
| "best_global_step": 50, |
| "best_metric": 0.04152026027441025, |
| "best_model_checkpoint": "generate_file_results/checkpoint-50", |
| "epoch": 3.0, |
| "eval_steps": 50, |
| "global_step": 90, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.3333333333333333, |
| "grad_norm": 0.054440299517241095, |
| "learning_rate": 0.0003951219512195122, |
| "loss": 0.2185, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.6666666666666666, |
| "grad_norm": 0.047532583033039, |
| "learning_rate": 0.00034634146341463415, |
| "loss": 0.0871, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.04808583812696361, |
| "learning_rate": 0.0002975609756097561, |
| "loss": 0.0658, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.3333333333333333, |
| "grad_norm": 0.0784136249003354, |
| "learning_rate": 0.0002487804878048781, |
| "loss": 0.052, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.6666666666666665, |
| "grad_norm": 0.02814910996414792, |
| "learning_rate": 0.0002, |
| "loss": 0.0399, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.6666666666666665, |
| "eval_accuracy": 0.9893731967355441, |
| "eval_loss": 0.04152026027441025, |
| "eval_runtime": 572.9007, |
| "eval_samples_per_second": 0.703, |
| "eval_steps_per_second": 0.089, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.036182324351060564, |
| "learning_rate": 0.00015121951219512197, |
| "loss": 0.0318, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.3333333333333335, |
| "grad_norm": 0.03317433845649314, |
| "learning_rate": 0.0001024390243902439, |
| "loss": 0.0223, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.6666666666666665, |
| "grad_norm": 0.031335770809866416, |
| "learning_rate": 5.365853658536586e-05, |
| "loss": 0.0238, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.02036822272401154, |
| "learning_rate": 4.8780487804878055e-06, |
| "loss": 0.016, |
| "step": 90 |
| }, |
| { |
| "epoch": 3.0, |
| "step": 90, |
| "total_flos": 56092224651264.0, |
| "train_loss": 0.061904317802853055, |
| "train_runtime": 9015.3076, |
| "train_samples_per_second": 0.317, |
| "train_steps_per_second": 0.01 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 90, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 50, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 56092224651264.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
