| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.030518819938962362, |
| "eval_steps": 5, |
| "global_step": 30, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.00508646998982706, |
| "grad_norm": 1.604354739189148, |
| "learning_rate": 1.6666666666666667e-05, |
| "loss": 0.6612, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.00508646998982706, |
| "eval_loss": 1.3870973587036133, |
| "eval_runtime": 40.4847, |
| "eval_samples_per_second": 1.976, |
| "eval_steps_per_second": 1.976, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.01017293997965412, |
| "grad_norm": 1.077487826347351, |
| "learning_rate": 3.3333333333333335e-05, |
| "loss": 0.673, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.01017293997965412, |
| "eval_loss": 1.022403359413147, |
| "eval_runtime": 40.7798, |
| "eval_samples_per_second": 1.962, |
| "eval_steps_per_second": 1.962, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.015259409969481181, |
| "grad_norm": 0.9661844968795776, |
| "learning_rate": 5e-05, |
| "loss": 0.585, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.015259409969481181, |
| "eval_loss": 0.7474928498268127, |
| "eval_runtime": 40.5424, |
| "eval_samples_per_second": 1.973, |
| "eval_steps_per_second": 1.973, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.02034587995930824, |
| "grad_norm": 0.7049635648727417, |
| "learning_rate": 6.666666666666667e-05, |
| "loss": 0.4706, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.02034587995930824, |
| "eval_loss": 0.5938583612442017, |
| "eval_runtime": 40.5754, |
| "eval_samples_per_second": 1.972, |
| "eval_steps_per_second": 1.972, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.0254323499491353, |
| "grad_norm": 0.8921922445297241, |
| "learning_rate": 8.333333333333334e-05, |
| "loss": 0.4607, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.0254323499491353, |
| "eval_loss": 0.4904526174068451, |
| "eval_runtime": 40.7325, |
| "eval_samples_per_second": 1.964, |
| "eval_steps_per_second": 1.964, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.030518819938962362, |
| "grad_norm": 0.8781003355979919, |
| "learning_rate": 0.0001, |
| "loss": 0.4215, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.030518819938962362, |
| "eval_loss": 0.44746941328048706, |
| "eval_runtime": 39.9542, |
| "eval_samples_per_second": 2.002, |
| "eval_steps_per_second": 2.002, |
| "step": 30 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 983, |
| "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": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3594709185736704.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
