| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.425531914893617, |
| "eval_steps": 20, |
| "global_step": 40, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.010638297872340425, |
| "eval_loss": 2.7702033519744873, |
| "eval_runtime": 32.7713, |
| "eval_samples_per_second": 45.802, |
| "eval_steps_per_second": 5.737, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.10638297872340426, |
| "grad_norm": 5.4375, |
| "learning_rate": 8e-05, |
| "loss": 2.0564, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.2127659574468085, |
| "grad_norm": 5.375, |
| "learning_rate": 0.00016, |
| "loss": 2.073, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.2127659574468085, |
| "eval_loss": 2.1077733039855957, |
| "eval_runtime": 29.718, |
| "eval_samples_per_second": 50.508, |
| "eval_steps_per_second": 6.326, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.3191489361702128, |
| "grad_norm": 6.875, |
| "learning_rate": 0.00019994532573409262, |
| "loss": 2.4864, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.425531914893617, |
| "grad_norm": 7.84375, |
| "learning_rate": 0.00019950829025450114, |
| "loss": 2.6708, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.425531914893617, |
| "eval_loss": 2.5071871280670166, |
| "eval_runtime": 46.4512, |
| "eval_samples_per_second": 32.314, |
| "eval_steps_per_second": 4.047, |
| "step": 40 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 500, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 6, |
| "save_steps": 20, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.9510565671993344e+16, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
