| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.04008016032064128, |
| "eval_steps": 5, |
| "global_step": 20, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.002004008016032064, |
| "grad_norm": 0.9981935024261475, |
| "learning_rate": 1e-05, |
| "loss": 3.6274, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.002004008016032064, |
| "eval_loss": 3.705083131790161, |
| "eval_runtime": 67.9972, |
| "eval_samples_per_second": 24.722, |
| "eval_steps_per_second": 12.368, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.004008016032064128, |
| "grad_norm": 1.0312002897262573, |
| "learning_rate": 2e-05, |
| "loss": 3.7344, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.006012024048096192, |
| "grad_norm": 1.0591121912002563, |
| "learning_rate": 3e-05, |
| "loss": 3.6015, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.008016032064128256, |
| "grad_norm": 1.0240955352783203, |
| "learning_rate": 4e-05, |
| "loss": 3.7196, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.01002004008016032, |
| "grad_norm": 1.0419278144836426, |
| "learning_rate": 5e-05, |
| "loss": 3.7358, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.01002004008016032, |
| "eval_loss": 3.6875150203704834, |
| "eval_runtime": 66.7319, |
| "eval_samples_per_second": 25.19, |
| "eval_steps_per_second": 12.603, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.012024048096192385, |
| "grad_norm": 1.075563669204712, |
| "learning_rate": 6e-05, |
| "loss": 3.6583, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.014028056112224449, |
| "grad_norm": 1.0435458421707153, |
| "learning_rate": 7e-05, |
| "loss": 3.6918, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.01603206412825651, |
| "grad_norm": 0.9885270595550537, |
| "learning_rate": 8e-05, |
| "loss": 3.6284, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.018036072144288578, |
| "grad_norm": 1.0842863321304321, |
| "learning_rate": 9e-05, |
| "loss": 3.6854, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.02004008016032064, |
| "grad_norm": 1.0496262311935425, |
| "learning_rate": 0.0001, |
| "loss": 3.5911, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.02004008016032064, |
| "eval_loss": 3.535064935684204, |
| "eval_runtime": 66.7323, |
| "eval_samples_per_second": 25.19, |
| "eval_steps_per_second": 12.603, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.022044088176352707, |
| "grad_norm": 1.0535022020339966, |
| "learning_rate": 9.755282581475769e-05, |
| "loss": 3.4243, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.02404809619238477, |
| "grad_norm": 1.0760126113891602, |
| "learning_rate": 9.045084971874738e-05, |
| "loss": 3.4287, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.026052104208416832, |
| "grad_norm": 1.047857403755188, |
| "learning_rate": 7.938926261462366e-05, |
| "loss": 3.4245, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.028056112224448898, |
| "grad_norm": 0.9840763807296753, |
| "learning_rate": 6.545084971874738e-05, |
| "loss": 3.2842, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.03006012024048096, |
| "grad_norm": 0.9731857180595398, |
| "learning_rate": 5e-05, |
| "loss": 3.2958, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.03006012024048096, |
| "eval_loss": 3.302708148956299, |
| "eval_runtime": 66.7476, |
| "eval_samples_per_second": 25.184, |
| "eval_steps_per_second": 12.6, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.03206412825651302, |
| "grad_norm": 0.9710604548454285, |
| "learning_rate": 3.4549150281252636e-05, |
| "loss": 3.2329, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.03406813627254509, |
| "grad_norm": 0.9070257544517517, |
| "learning_rate": 2.061073738537635e-05, |
| "loss": 3.1751, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.036072144288577156, |
| "grad_norm": 0.9331132769584656, |
| "learning_rate": 9.549150281252633e-06, |
| "loss": 3.1826, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.03807615230460922, |
| "grad_norm": 0.9252903461456299, |
| "learning_rate": 2.4471741852423237e-06, |
| "loss": 3.1469, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.04008016032064128, |
| "grad_norm": 0.9361170530319214, |
| "learning_rate": 0.0, |
| "loss": 3.2011, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.04008016032064128, |
| "eval_loss": 3.241048812866211, |
| "eval_runtime": 66.7398, |
| "eval_samples_per_second": 25.187, |
| "eval_steps_per_second": 12.601, |
| "step": 20 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 20, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 5, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 4442802754682880.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
