| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 10, |
| "global_step": 42, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.24390243902439024, |
| "grad_norm": 12.817821502685547, |
| "learning_rate": 5e-06, |
| "loss": 7.3316, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.24390243902439024, |
| "eval_runtime": 3.5066, |
| "eval_samples_per_second": 0.285, |
| "eval_steps_per_second": 0.285, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.4878048780487805, |
| "grad_norm": 16.391746520996094, |
| "learning_rate": 1e-05, |
| "loss": 6.9911, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.4878048780487805, |
| "eval_runtime": 3.2411, |
| "eval_samples_per_second": 0.309, |
| "eval_steps_per_second": 0.309, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.7317073170731707, |
| "grad_norm": 9.750876426696777, |
| "learning_rate": 1.5e-05, |
| "loss": 6.5763, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.7317073170731707, |
| "eval_runtime": 3.5499, |
| "eval_samples_per_second": 0.282, |
| "eval_steps_per_second": 0.282, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.975609756097561, |
| "grad_norm": 10.722237586975098, |
| "learning_rate": 2e-05, |
| "loss": 6.7204, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.975609756097561, |
| "eval_runtime": 3.263, |
| "eval_samples_per_second": 0.306, |
| "eval_steps_per_second": 0.306, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.0, |
| "step": 41, |
| "total_flos": 0.0, |
| "train_loss": 6.902664324132408, |
| "train_runtime": 216.0042, |
| "train_samples_per_second": 0.19, |
| "train_steps_per_second": 0.19 |
| }, |
| { |
| "epoch": 1.0, |
| "step": 42, |
| "total_flos": 0.0, |
| "train_loss": 0.14258025941394625, |
| "train_runtime": 36.0127, |
| "train_samples_per_second": 1.166, |
| "train_steps_per_second": 1.166 |
| }, |
| { |
| "epoch": 1.0, |
| "step": 42, |
| "total_flos": 0.0, |
| "train_loss": 0.0, |
| "train_runtime": 0.0249, |
| "train_samples_per_second": 1689.727, |
| "train_steps_per_second": 1689.727 |
| }, |
| { |
| "epoch": 1.0, |
| "step": 42, |
| "total_flos": 0.0, |
| "train_loss": 0.0, |
| "train_runtime": 0.0082, |
| "train_samples_per_second": 5120.208, |
| "train_steps_per_second": 5120.208 |
| }, |
| { |
| "epoch": 1.0, |
| "step": 42, |
| "total_flos": 0.0, |
| "train_loss": 0.0, |
| "train_runtime": 0.0078, |
| "train_samples_per_second": 5412.171, |
| "train_steps_per_second": 5412.171 |
| }, |
| { |
| "epoch": 1.0, |
| "step": 42, |
| "total_flos": 0.0, |
| "train_loss": 0.0, |
| "train_runtime": 0.0113, |
| "train_samples_per_second": 3718.512, |
| "train_steps_per_second": 3718.512 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 42, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 0.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
