| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.225806451612903, |
| "eval_steps": 20, |
| "global_step": 100, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.03225806451612903, |
| "eval_loss": 2.4278130531311035, |
| "eval_runtime": 20.4099, |
| "eval_samples_per_second": 73.543, |
| "eval_steps_per_second": 3.087, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.3225806451612903, |
| "grad_norm": 7.0625, |
| "learning_rate": 8e-05, |
| "loss": 2.1532, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.6451612903225806, |
| "grad_norm": 7.0625, |
| "learning_rate": 0.00016, |
| "loss": 2.1913, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.6451612903225806, |
| "eval_loss": 2.176056146621704, |
| "eval_runtime": 20.5017, |
| "eval_samples_per_second": 73.214, |
| "eval_steps_per_second": 3.073, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.967741935483871, |
| "grad_norm": 8.9375, |
| "learning_rate": 0.00019994532573409262, |
| "loss": 2.3976, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.2903225806451613, |
| "grad_norm": 9.875, |
| "learning_rate": 0.00019950829025450114, |
| "loss": 2.4629, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.2903225806451613, |
| "eval_loss": 2.5420961380004883, |
| "eval_runtime": 20.3055, |
| "eval_samples_per_second": 73.921, |
| "eval_steps_per_second": 3.103, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.6129032258064515, |
| "grad_norm": 3.9375, |
| "learning_rate": 0.00019863613034027224, |
| "loss": 2.6415, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.935483870967742, |
| "grad_norm": 76.5, |
| "learning_rate": 0.0001973326597248006, |
| "loss": 3.0008, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.935483870967742, |
| "eval_loss": 2.800191879272461, |
| "eval_runtime": 20.2683, |
| "eval_samples_per_second": 74.057, |
| "eval_steps_per_second": 3.108, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.258064516129032, |
| "grad_norm": 7.15625, |
| "learning_rate": 0.00019560357815343577, |
| "loss": 2.776, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.5806451612903225, |
| "grad_norm": 39.5, |
| "learning_rate": 0.0001934564464599461, |
| "loss": 2.3915, |
| "step": 80 |
| }, |
| { |
| "epoch": 2.5806451612903225, |
| "eval_loss": 2.7726891040802, |
| "eval_runtime": 20.3002, |
| "eval_samples_per_second": 73.94, |
| "eval_steps_per_second": 3.103, |
| "step": 80 |
| }, |
| { |
| "epoch": 2.903225806451613, |
| "grad_norm": 32.25, |
| "learning_rate": 0.00019090065350491626, |
| "loss": 2.4592, |
| "step": 90 |
| }, |
| { |
| "epoch": 3.225806451612903, |
| "grad_norm": 61.25, |
| "learning_rate": 0.0001879473751206489, |
| "loss": 2.3718, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.225806451612903, |
| "eval_loss": 2.7737066745758057, |
| "eval_runtime": 20.2807, |
| "eval_samples_per_second": 74.011, |
| "eval_steps_per_second": 3.106, |
| "step": 100 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 500, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 17, |
| "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": 7.791231950965965e+16, |
| "train_batch_size": 6, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
