| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "eval_steps": 1000, |
| "global_step": 3586, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0005577244841048522, |
| "grad_norm": 4.318717956542969, |
| "learning_rate": 0.0, |
| "loss": 2.0553, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.5577244841048522, |
| "eval_cosine_accuracy": 0.9485750198364258, |
| "eval_loss": 1.015312671661377, |
| "eval_runtime": 23.0042, |
| "eval_samples_per_second": 413.359, |
| "eval_steps_per_second": 1.652, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 3.6185929775238037, |
| "learning_rate": 6.2469480292989195e-06, |
| "loss": 1.8693, |
| "step": 1793 |
| }, |
| { |
| "epoch": 1.1154489682097044, |
| "eval_cosine_accuracy": 0.9525712728500366, |
| "eval_loss": 0.936602771282196, |
| "eval_runtime": 23.1454, |
| "eval_samples_per_second": 410.837, |
| "eval_steps_per_second": 1.642, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.6731734523145567, |
| "eval_cosine_accuracy": 0.9576190710067749, |
| "eval_loss": 0.914821207523346, |
| "eval_runtime": 22.9469, |
| "eval_samples_per_second": 414.391, |
| "eval_steps_per_second": 1.656, |
| "step": 3000 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 7.962277889251709, |
| "learning_rate": 8.824204657264677e-06, |
| "loss": 1.5407, |
| "step": 3586 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 8965, |
| "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": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 0.0, |
| "train_batch_size": 256, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
