| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 5.0, |
| "eval_steps": 500, |
| "global_step": 295, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.847457627118644, |
| "grad_norm": 3.6365857124328613, |
| "learning_rate": 4.152542372881356e-05, |
| "loss": 8.5103, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 1.4866021871566772, |
| "eval_runtime": 5.4305, |
| "eval_samples_per_second": 19.335, |
| "eval_steps_per_second": 1.289, |
| "step": 59 |
| }, |
| { |
| "epoch": 1.694915254237288, |
| "grad_norm": 3.137465715408325, |
| "learning_rate": 3.305084745762712e-05, |
| "loss": 1.7098, |
| "step": 100 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 1.2273037433624268, |
| "eval_runtime": 5.362, |
| "eval_samples_per_second": 19.582, |
| "eval_steps_per_second": 1.305, |
| "step": 118 |
| }, |
| { |
| "epoch": 2.542372881355932, |
| "grad_norm": 1.6243258714675903, |
| "learning_rate": 2.457627118644068e-05, |
| "loss": 1.5421, |
| "step": 150 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 1.1611202955245972, |
| "eval_runtime": 5.348, |
| "eval_samples_per_second": 19.634, |
| "eval_steps_per_second": 1.309, |
| "step": 177 |
| }, |
| { |
| "epoch": 3.389830508474576, |
| "grad_norm": 1.7812302112579346, |
| "learning_rate": 1.6101694915254237e-05, |
| "loss": 1.4875, |
| "step": 200 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 1.153254508972168, |
| "eval_runtime": 5.347, |
| "eval_samples_per_second": 19.637, |
| "eval_steps_per_second": 1.309, |
| "step": 236 |
| }, |
| { |
| "epoch": 4.237288135593221, |
| "grad_norm": 2.1582489013671875, |
| "learning_rate": 7.627118644067798e-06, |
| "loss": 1.3883, |
| "step": 250 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 1.1216797828674316, |
| "eval_runtime": 5.3095, |
| "eval_samples_per_second": 19.776, |
| "eval_steps_per_second": 1.318, |
| "step": 295 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 295, |
| "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": 9279085168558080.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
