| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.0030440473653770054, |
| "eval_steps": 10, |
| "global_step": 50, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 6.08809473075401e-05, |
| "eval_loss": 6.931131362915039, |
| "eval_runtime": 656.8644, |
| "eval_samples_per_second": 10.529, |
| "eval_steps_per_second": 5.264, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.00030440473653770055, |
| "grad_norm": 45.05469512939453, |
| "learning_rate": 5e-05, |
| "loss": 27.2097, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.0006088094730754011, |
| "grad_norm": 40.21764373779297, |
| "learning_rate": 0.0001, |
| "loss": 19.0893, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.0006088094730754011, |
| "eval_loss": 2.306489944458008, |
| "eval_runtime": 658.2084, |
| "eval_samples_per_second": 10.507, |
| "eval_steps_per_second": 5.254, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.0009132142096131016, |
| "grad_norm": 13.2877779006958, |
| "learning_rate": 9.619397662556435e-05, |
| "loss": 3.675, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.0012176189461508022, |
| "grad_norm": 7.806561470031738, |
| "learning_rate": 8.535533905932738e-05, |
| "loss": 0.4316, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.0012176189461508022, |
| "eval_loss": 0.07837376743555069, |
| "eval_runtime": 656.503, |
| "eval_samples_per_second": 10.535, |
| "eval_steps_per_second": 5.267, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.0015220236826885027, |
| "grad_norm": 2.9194090366363525, |
| "learning_rate": 6.91341716182545e-05, |
| "loss": 0.9073, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.0018264284192262032, |
| "grad_norm": 23.289958953857422, |
| "learning_rate": 5e-05, |
| "loss": 0.6673, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.0018264284192262032, |
| "eval_loss": 0.07907278090715408, |
| "eval_runtime": 658.9663, |
| "eval_samples_per_second": 10.495, |
| "eval_steps_per_second": 5.248, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.002130833155763904, |
| "grad_norm": 13.350411415100098, |
| "learning_rate": 3.086582838174551e-05, |
| "loss": 0.3659, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.0024352378923016044, |
| "grad_norm": 2.5347867012023926, |
| "learning_rate": 1.4644660940672627e-05, |
| "loss": 0.2356, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.0024352378923016044, |
| "eval_loss": 0.0975862666964531, |
| "eval_runtime": 658.7808, |
| "eval_samples_per_second": 10.498, |
| "eval_steps_per_second": 5.249, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.002739642628839305, |
| "grad_norm": 1.3288694620132446, |
| "learning_rate": 3.8060233744356633e-06, |
| "loss": 0.2834, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.0030440473653770054, |
| "grad_norm": 12.975996971130371, |
| "learning_rate": 0.0, |
| "loss": 0.3669, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.0030440473653770054, |
| "eval_loss": 0.07795499265193939, |
| "eval_runtime": 657.4379, |
| "eval_samples_per_second": 10.52, |
| "eval_steps_per_second": 5.26, |
| "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": 1.4260472119296e+16, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
