| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03499562554680665, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011665208515602217, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 3.5729, | |
| "eval_samples_per_second": 101.04, | |
| "eval_steps_per_second": 50.66, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003499562554680665, | |
| "grad_norm": 6.78294018143788e-05, | |
| "learning_rate": 3e-05, | |
| "loss": 46.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00699912510936133, | |
| "grad_norm": 7.048947009025142e-05, | |
| "learning_rate": 6e-05, | |
| "loss": 46.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009332166812481774, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 3.5169, | |
| "eval_samples_per_second": 102.646, | |
| "eval_steps_per_second": 51.465, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.010498687664041995, | |
| "grad_norm": 9.457429405301809e-05, | |
| "learning_rate": 9e-05, | |
| "loss": 46.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01399825021872266, | |
| "grad_norm": 0.00011205866030650213, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 46.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.017497812773403325, | |
| "grad_norm": 9.639419295126572e-05, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 46.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.018664333624963548, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 3.5697, | |
| "eval_samples_per_second": 101.129, | |
| "eval_steps_per_second": 50.705, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.02099737532808399, | |
| "grad_norm": 6.34350799373351e-05, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 46.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.024496937882764653, | |
| "grad_norm": 6.672402378171682e-05, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 46.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02799650043744532, | |
| "grad_norm": 6.043924076948315e-05, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 46.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02799650043744532, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 3.5986, | |
| "eval_samples_per_second": 100.316, | |
| "eval_steps_per_second": 50.297, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.031496062992125984, | |
| "grad_norm": 5.254306961433031e-05, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 46.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03499562554680665, | |
| "grad_norm": 7.944657409098e-05, | |
| "learning_rate": 0.0, | |
| "loss": 46.0, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1196882657280.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |