| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.5361930294906166, |
| "eval_steps": 10, |
| "global_step": 50, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.010723860589812333, |
| "eval_loss": 3.1138010025024414, |
| "eval_runtime": 2.8307, |
| "eval_samples_per_second": 14.131, |
| "eval_steps_per_second": 7.065, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.05361930294906166, |
| "grad_norm": 3.256532907485962, |
| "learning_rate": 5e-05, |
| "loss": 3.3114, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.10723860589812333, |
| "grad_norm": 4.2412004470825195, |
| "learning_rate": 0.0001, |
| "loss": 3.0516, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.10723860589812333, |
| "eval_loss": 2.308056592941284, |
| "eval_runtime": 2.8594, |
| "eval_samples_per_second": 13.989, |
| "eval_steps_per_second": 6.994, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.16085790884718498, |
| "grad_norm": 3.9154632091522217, |
| "learning_rate": 9.619397662556435e-05, |
| "loss": 2.0048, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.21447721179624665, |
| "grad_norm": 4.083313941955566, |
| "learning_rate": 8.535533905932738e-05, |
| "loss": 1.6609, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.21447721179624665, |
| "eval_loss": 1.6054365634918213, |
| "eval_runtime": 2.8835, |
| "eval_samples_per_second": 13.872, |
| "eval_steps_per_second": 6.936, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.2680965147453083, |
| "grad_norm": 5.57961368560791, |
| "learning_rate": 6.91341716182545e-05, |
| "loss": 1.6185, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.32171581769436997, |
| "grad_norm": 5.112281799316406, |
| "learning_rate": 5e-05, |
| "loss": 1.4831, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.32171581769436997, |
| "eval_loss": 1.5044453144073486, |
| "eval_runtime": 2.9189, |
| "eval_samples_per_second": 13.704, |
| "eval_steps_per_second": 6.852, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.3753351206434316, |
| "grad_norm": 4.7476091384887695, |
| "learning_rate": 3.086582838174551e-05, |
| "loss": 1.5744, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.4289544235924933, |
| "grad_norm": 5.524008750915527, |
| "learning_rate": 1.4644660940672627e-05, |
| "loss": 1.3467, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.4289544235924933, |
| "eval_loss": 1.4648765325546265, |
| "eval_runtime": 2.9269, |
| "eval_samples_per_second": 13.666, |
| "eval_steps_per_second": 6.833, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.48257372654155495, |
| "grad_norm": 4.456066608428955, |
| "learning_rate": 3.8060233744356633e-06, |
| "loss": 1.5109, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.5361930294906166, |
| "grad_norm": 4.297540664672852, |
| "learning_rate": 0.0, |
| "loss": 1.453, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.5361930294906166, |
| "eval_loss": 1.4569414854049683, |
| "eval_runtime": 2.8819, |
| "eval_samples_per_second": 13.88, |
| "eval_steps_per_second": 6.94, |
| "step": 50 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 50, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 13, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 9247821240729600.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
