| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004377006127808579, | |
| "eval_steps": 2, | |
| "global_step": 15, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002918004085205719, | |
| "grad_norm": 0.9763444662094116, | |
| "learning_rate": 2e-05, | |
| "loss": 1.2075, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002918004085205719, | |
| "eval_loss": 1.429457187652588, | |
| "eval_runtime": 163.3614, | |
| "eval_samples_per_second": 8.833, | |
| "eval_steps_per_second": 4.42, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005836008170411438, | |
| "grad_norm": 1.0415689945220947, | |
| "learning_rate": 4e-05, | |
| "loss": 1.4158, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0005836008170411438, | |
| "eval_loss": 1.4282734394073486, | |
| "eval_runtime": 162.055, | |
| "eval_samples_per_second": 8.904, | |
| "eval_steps_per_second": 4.455, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008754012255617158, | |
| "grad_norm": 1.0212147235870361, | |
| "learning_rate": 6e-05, | |
| "loss": 1.2149, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0011672016340822876, | |
| "grad_norm": 0.8775227069854736, | |
| "learning_rate": 8e-05, | |
| "loss": 1.0194, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0011672016340822876, | |
| "eval_loss": 1.4084514379501343, | |
| "eval_runtime": 161.6261, | |
| "eval_samples_per_second": 8.928, | |
| "eval_steps_per_second": 4.467, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0014590020426028597, | |
| "grad_norm": 1.1688672304153442, | |
| "learning_rate": 0.0001, | |
| "loss": 1.3914, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0017508024511234317, | |
| "grad_norm": 1.005053997039795, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 1.2212, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0017508024511234317, | |
| "eval_loss": 1.3211736679077148, | |
| "eval_runtime": 161.7504, | |
| "eval_samples_per_second": 8.921, | |
| "eval_steps_per_second": 4.464, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0020426028596440037, | |
| "grad_norm": 1.3174978494644165, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.2575, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0023344032681645753, | |
| "grad_norm": 0.9882346391677856, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 1.1226, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0023344032681645753, | |
| "eval_loss": 1.2546484470367432, | |
| "eval_runtime": 161.6417, | |
| "eval_samples_per_second": 8.927, | |
| "eval_steps_per_second": 4.467, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0026262036766851473, | |
| "grad_norm": 1.0995094776153564, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 1.2479, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0029180040852057193, | |
| "grad_norm": 0.9760543704032898, | |
| "learning_rate": 5e-05, | |
| "loss": 1.2593, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0029180040852057193, | |
| "eval_loss": 1.2201802730560303, | |
| "eval_runtime": 162.0614, | |
| "eval_samples_per_second": 8.904, | |
| "eval_steps_per_second": 4.455, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0032098044937262913, | |
| "grad_norm": 1.1419090032577515, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 1.4679, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0035016049022468633, | |
| "grad_norm": 1.2634228467941284, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 1.243, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0035016049022468633, | |
| "eval_loss": 1.194502353668213, | |
| "eval_runtime": 161.9542, | |
| "eval_samples_per_second": 8.91, | |
| "eval_steps_per_second": 4.458, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.003793405310767435, | |
| "grad_norm": 0.995550274848938, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.9366, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.004085205719288007, | |
| "grad_norm": 1.1408365964889526, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 1.3171, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.004085205719288007, | |
| "eval_loss": 1.18353271484375, | |
| "eval_runtime": 161.9389, | |
| "eval_samples_per_second": 8.911, | |
| "eval_steps_per_second": 4.458, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.004377006127808579, | |
| "grad_norm": 0.9548996090888977, | |
| "learning_rate": 0.0, | |
| "loss": 0.974, | |
| "step": 15 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 15, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.0912429064060928e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |