| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 1000, |
| "global_step": 4329, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.000231000231000231, |
| "grad_norm": 9.206714630126953, |
| "learning_rate": 0.0, |
| "loss": 3.4724, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.231000231000231, |
| "grad_norm": 5.799774169921875, |
| "learning_rate": 4.602587800369686e-06, |
| "loss": 2.5331, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.231000231000231, |
| "eval_cosine_accuracy": 0.9410836696624756, |
| "eval_loss": 1.3405522108078003, |
| "eval_runtime": 33.7089, |
| "eval_samples_per_second": 281.973, |
| "eval_steps_per_second": 2.225, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.462000462000462, |
| "grad_norm": 5.877671718597412, |
| "learning_rate": 9.223659889094271e-06, |
| "loss": 2.034, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.462000462000462, |
| "eval_cosine_accuracy": 0.9490794539451599, |
| "eval_loss": 1.2312276363372803, |
| "eval_runtime": 33.4533, |
| "eval_samples_per_second": 284.128, |
| "eval_steps_per_second": 2.242, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.693000693000693, |
| "grad_norm": 6.145458698272705, |
| "learning_rate": 1.3844731977818856e-05, |
| "loss": 1.8227, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.693000693000693, |
| "eval_cosine_accuracy": 0.9502367377281189, |
| "eval_loss": 1.179374098777771, |
| "eval_runtime": 33.5332, |
| "eval_samples_per_second": 283.451, |
| "eval_steps_per_second": 2.237, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.924000924000924, |
| "grad_norm": 6.466739177703857, |
| "learning_rate": 1.846580406654344e-05, |
| "loss": 1.681, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.924000924000924, |
| "eval_cosine_accuracy": 0.9523409008979797, |
| "eval_loss": 1.1233179569244385, |
| "eval_runtime": 33.5285, |
| "eval_samples_per_second": 283.49, |
| "eval_steps_per_second": 2.237, |
| "step": 4000 |
| } |
| ], |
| "logging_steps": 1000, |
| "max_steps": 21645, |
| "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": 128, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
