| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 4.0, |
| "eval_steps": 1, |
| "global_step": 144, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.3582516312599182, |
| "eval_runtime": 4.9392, |
| "eval_samples_per_second": 51.627, |
| "eval_steps_per_second": 6.479, |
| "step": 36 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.12783880531787872, |
| "eval_runtime": 4.4185, |
| "eval_samples_per_second": 57.711, |
| "eval_steps_per_second": 7.242, |
| "step": 72 |
| }, |
| { |
| "epoch": 2.7777777777777777, |
| "grad_norm": 0.24191316962242126, |
| "learning_rate": 2.7137883834768073e-05, |
| "loss": 0.4019, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 0.05018627643585205, |
| "eval_runtime": 4.4037, |
| "eval_samples_per_second": 57.906, |
| "eval_steps_per_second": 7.267, |
| "step": 108 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 0.039800360798835754, |
| "eval_runtime": 4.4427, |
| "eval_samples_per_second": 57.397, |
| "eval_steps_per_second": 7.203, |
| "step": 144 |
| }, |
| { |
| "epoch": 4.0, |
| "step": 144, |
| "total_flos": 6.116937949616538e+17, |
| "train_loss": 0.2839497621688578, |
| "train_runtime": 414.9456, |
| "train_samples_per_second": 22.104, |
| "train_steps_per_second": 0.347 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 144, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 4, |
| "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": 6.116937949616538e+17, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
