| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 4.444444444444445, |
| "eval_steps": 500, |
| "global_step": 1000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.2222222222222222, |
| "grad_norm": 9.446490287780762, |
| "learning_rate": 2.45e-05, |
| "loss": 35.94, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.4444444444444444, |
| "grad_norm": 14.75452709197998, |
| "learning_rate": 4.9500000000000004e-05, |
| "loss": 32.7746, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.6666666666666666, |
| "grad_norm": 9.099113464355469, |
| "learning_rate": 4.727777777777778e-05, |
| "loss": 23.1808, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.8888888888888888, |
| "grad_norm": 8.02777099609375, |
| "learning_rate": 4.4500000000000004e-05, |
| "loss": 12.6258, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.1111111111111112, |
| "grad_norm": 1.2070741653442383, |
| "learning_rate": 4.172222222222222e-05, |
| "loss": 4.7374, |
| "step": 250 |
| }, |
| { |
| "epoch": 1.3333333333333333, |
| "grad_norm": 0.9106131792068481, |
| "learning_rate": 3.894444444444444e-05, |
| "loss": 3.7523, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.5555555555555556, |
| "grad_norm": 1.4430468082427979, |
| "learning_rate": 3.6166666666666674e-05, |
| "loss": 3.3539, |
| "step": 350 |
| }, |
| { |
| "epoch": 1.7777777777777777, |
| "grad_norm": 1.2814528942108154, |
| "learning_rate": 3.338888888888889e-05, |
| "loss": 2.8322, |
| "step": 400 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 1.6435903310775757, |
| "learning_rate": 3.061111111111111e-05, |
| "loss": 2.373, |
| "step": 450 |
| }, |
| { |
| "epoch": 2.2222222222222223, |
| "grad_norm": 1.2958321571350098, |
| "learning_rate": 2.7833333333333333e-05, |
| "loss": 1.9407, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.4444444444444446, |
| "grad_norm": 1.1333638429641724, |
| "learning_rate": 2.5055555555555555e-05, |
| "loss": 1.628, |
| "step": 550 |
| }, |
| { |
| "epoch": 2.6666666666666665, |
| "grad_norm": 0.9968857169151306, |
| "learning_rate": 2.2277777777777778e-05, |
| "loss": 1.378, |
| "step": 600 |
| }, |
| { |
| "epoch": 2.888888888888889, |
| "grad_norm": 1.1652404069900513, |
| "learning_rate": 1.9500000000000003e-05, |
| "loss": 1.1885, |
| "step": 650 |
| }, |
| { |
| "epoch": 3.111111111111111, |
| "grad_norm": 0.9605540037155151, |
| "learning_rate": 1.6722222222222222e-05, |
| "loss": 1.0439, |
| "step": 700 |
| }, |
| { |
| "epoch": 3.3333333333333335, |
| "grad_norm": 1.0064235925674438, |
| "learning_rate": 1.3944444444444446e-05, |
| "loss": 0.942, |
| "step": 750 |
| }, |
| { |
| "epoch": 3.5555555555555554, |
| "grad_norm": 0.8710888028144836, |
| "learning_rate": 1.1166666666666668e-05, |
| "loss": 0.8673, |
| "step": 800 |
| }, |
| { |
| "epoch": 3.7777777777777777, |
| "grad_norm": 1.5614680051803589, |
| "learning_rate": 8.38888888888889e-06, |
| "loss": 0.8063, |
| "step": 850 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.7509825825691223, |
| "learning_rate": 5.611111111111112e-06, |
| "loss": 0.7722, |
| "step": 900 |
| }, |
| { |
| "epoch": 4.222222222222222, |
| "grad_norm": 0.8249015212059021, |
| "learning_rate": 2.8333333333333335e-06, |
| "loss": 0.7549, |
| "step": 950 |
| }, |
| { |
| "epoch": 4.444444444444445, |
| "grad_norm": 1.181272029876709, |
| "learning_rate": 5.555555555555556e-08, |
| "loss": 0.7358, |
| "step": 1000 |
| }, |
| { |
| "epoch": 4.444444444444445, |
| "step": 1000, |
| "total_flos": 5499802091520000.0, |
| "train_loss": 6.681387321472168, |
| "train_runtime": 1879.5247, |
| "train_samples_per_second": 8.513, |
| "train_steps_per_second": 0.532 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 1000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "save_steps": 200, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 5499802091520000.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
