| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.5614035087719298, |
| "eval_steps": 500, |
| "global_step": 1000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.056140350877192984, |
| "grad_norm": 3.546875, |
| "learning_rate": 2.4750000000000002e-05, |
| "loss": 3.1684613037109375, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.11228070175438597, |
| "grad_norm": 2.625, |
| "learning_rate": 4.975e-05, |
| "loss": 2.9828875732421873, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.16842105263157894, |
| "grad_norm": 2.75, |
| "learning_rate": 4.38125e-05, |
| "loss": 2.9039926147460937, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.22456140350877193, |
| "grad_norm": 2.703125, |
| "learning_rate": 3.75625e-05, |
| "loss": 2.862659912109375, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.2807017543859649, |
| "grad_norm": 2.46875, |
| "learning_rate": 3.13125e-05, |
| "loss": 2.8550177001953125, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.2807017543859649, |
| "eval_loss": 2.695997476577759, |
| "eval_runtime": 112.3251, |
| "eval_samples_per_second": 13.354, |
| "eval_steps_per_second": 1.674, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.3368421052631579, |
| "grad_norm": 2.5625, |
| "learning_rate": 2.50625e-05, |
| "loss": 2.8371957397460936, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.3929824561403509, |
| "grad_norm": 2.453125, |
| "learning_rate": 1.88125e-05, |
| "loss": 2.83647705078125, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.44912280701754387, |
| "grad_norm": 2.546875, |
| "learning_rate": 1.2562499999999999e-05, |
| "loss": 2.8517510986328123, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.5052631578947369, |
| "grad_norm": 2.28125, |
| "learning_rate": 6.3125e-06, |
| "loss": 2.8428424072265623, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.5614035087719298, |
| "grad_norm": 2.421875, |
| "learning_rate": 6.250000000000001e-08, |
| "loss": 2.8378897094726563, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.5614035087719298, |
| "eval_loss": 2.6861302852630615, |
| "eval_runtime": 111.8875, |
| "eval_samples_per_second": 13.406, |
| "eval_steps_per_second": 1.68, |
| "step": 1000 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 1000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "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": 4180672512000000.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
