| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 154, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.13071895424836602, |
| "grad_norm": 3.0212894456325223, |
| "learning_rate": 9.982228267815644e-06, |
| "loss": 0.8424, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.26143790849673204, |
| "grad_norm": 1.5504173887408619, |
| "learning_rate": 9.783744310203492e-06, |
| "loss": 0.2984, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.39215686274509803, |
| "grad_norm": 1.3025130977963952, |
| "learning_rate": 9.373382449457305e-06, |
| "loss": 0.1945, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.5228758169934641, |
| "grad_norm": 1.3126636926970239, |
| "learning_rate": 8.76931811573033e-06, |
| "loss": 0.1272, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.6535947712418301, |
| "grad_norm": 1.4783348034718067, |
| "learning_rate": 7.998306059295302e-06, |
| "loss": 0.1076, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.7843137254901961, |
| "grad_norm": 1.2662492065258457, |
| "learning_rate": 7.094495349838093e-06, |
| "loss": 0.0866, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.9150326797385621, |
| "grad_norm": 0.9604154117157047, |
| "learning_rate": 6.097916872274815e-06, |
| "loss": 0.0626, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.0392156862745099, |
| "grad_norm": 0.8148848444623922, |
| "learning_rate": 5.052710309757899e-06, |
| "loss": 0.0409, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.1699346405228759, |
| "grad_norm": 0.449331412391344, |
| "learning_rate": 4.005169142968503e-06, |
| "loss": 0.0228, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.3006535947712419, |
| "grad_norm": 0.7194440458120613, |
| "learning_rate": 3.0016902550745896e-06, |
| "loss": 0.0203, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.4313725490196079, |
| "grad_norm": 0.37349790664171545, |
| "learning_rate": 2.086718956866024e-06, |
| "loss": 0.0134, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.5620915032679739, |
| "grad_norm": 0.3466622137831237, |
| "learning_rate": 1.3007804494240478e-06, |
| "loss": 0.0104, |
| "step": 120 |
| }, |
| { |
| "epoch": 1.6928104575163399, |
| "grad_norm": 0.6638993120244377, |
| "learning_rate": 6.786849132580841e-07, |
| "loss": 0.0064, |
| "step": 130 |
| }, |
| { |
| "epoch": 1.8235294117647058, |
| "grad_norm": 0.3940188227042054, |
| "learning_rate": 2.479857227135685e-07, |
| "loss": 0.006, |
| "step": 140 |
| }, |
| { |
| "epoch": 1.954248366013072, |
| "grad_norm": 0.8092707549615061, |
| "learning_rate": 2.77590732258326e-08, |
| "loss": 0.0098, |
| "step": 150 |
| }, |
| { |
| "epoch": 2.0, |
| "step": 154, |
| "total_flos": 4.848298683583693e+16, |
| "train_loss": 0.1206096943903279, |
| "train_runtime": 1241.7384, |
| "train_samples_per_second": 1.971, |
| "train_steps_per_second": 0.124 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 154, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "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": 4.848298683583693e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
