| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.10465116279069768, |
| "eval_steps": 3, |
| "global_step": 9, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0, |
| "eval_loss": 1.5762042999267578, |
| "eval_runtime": 6.5489, |
| "eval_samples_per_second": 5.65, |
| "eval_steps_per_second": 2.901, |
| "step": 0 |
| }, |
| { |
| "epoch": 0.011627906976744186, |
| "grad_norm": 0.7823610901832581, |
| "learning_rate": 0.0, |
| "loss": 1.3599, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.023255813953488372, |
| "grad_norm": 0.6125471591949463, |
| "learning_rate": 2e-05, |
| "loss": 1.3481, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.03488372093023256, |
| "grad_norm": 0.7715550065040588, |
| "learning_rate": 4e-05, |
| "loss": 1.607, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.03488372093023256, |
| "eval_loss": 1.575430154800415, |
| "eval_runtime": 6.3129, |
| "eval_samples_per_second": 5.861, |
| "eval_steps_per_second": 3.01, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.046511627906976744, |
| "grad_norm": 1.3339767456054688, |
| "learning_rate": 6e-05, |
| "loss": 2.2903, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.05813953488372093, |
| "grad_norm": 0.8708456158638, |
| "learning_rate": 8e-05, |
| "loss": 1.7924, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.06976744186046512, |
| "grad_norm": 0.6723288297653198, |
| "learning_rate": 0.0001, |
| "loss": 1.2308, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.06976744186046512, |
| "eval_loss": 1.567781686782837, |
| "eval_runtime": 6.2826, |
| "eval_samples_per_second": 5.889, |
| "eval_steps_per_second": 3.024, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.08139534883720931, |
| "grad_norm": 0.6576961278915405, |
| "learning_rate": 0.00012, |
| "loss": 1.5055, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.09302325581395349, |
| "grad_norm": 1.104688286781311, |
| "learning_rate": 0.00014, |
| "loss": 1.7391, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.10465116279069768, |
| "grad_norm": 0.8543928265571594, |
| "learning_rate": 0.00016, |
| "loss": 1.9635, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.10465116279069768, |
| "eval_loss": 1.546512246131897, |
| "eval_runtime": 6.2614, |
| "eval_samples_per_second": 5.909, |
| "eval_steps_per_second": 3.034, |
| "step": 9 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 10, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 3, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 216490963894272.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
