| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.038314176245210725, | |
| "eval_steps": 3, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0019157088122605363, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0019157088122605363, | |
| "eval_loss": NaN, | |
| "eval_runtime": 25.1045, | |
| "eval_samples_per_second": 8.763, | |
| "eval_steps_per_second": 4.382, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0038314176245210726, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005747126436781609, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005747126436781609, | |
| "eval_loss": NaN, | |
| "eval_runtime": 24.8834, | |
| "eval_samples_per_second": 8.841, | |
| "eval_steps_per_second": 4.421, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007662835249042145, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.009578544061302681, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.011494252873563218, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011494252873563218, | |
| "eval_loss": NaN, | |
| "eval_runtime": 24.832, | |
| "eval_samples_per_second": 8.86, | |
| "eval_steps_per_second": 4.43, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.013409961685823755, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01532567049808429, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.45503262094184e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.017241379310344827, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.017241379310344827, | |
| "eval_loss": NaN, | |
| "eval_runtime": 24.885, | |
| "eval_samples_per_second": 8.841, | |
| "eval_steps_per_second": 4.42, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.019157088122605363, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0210727969348659, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.022988505747126436, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.022988505747126436, | |
| "eval_loss": NaN, | |
| "eval_runtime": 24.9093, | |
| "eval_samples_per_second": 8.832, | |
| "eval_steps_per_second": 4.416, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.02490421455938697, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.02681992337164751, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.782172325201155e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.028735632183908046, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.028735632183908046, | |
| "eval_loss": NaN, | |
| "eval_runtime": 24.7137, | |
| "eval_samples_per_second": 8.902, | |
| "eval_steps_per_second": 4.451, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03065134099616858, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.032567049808429116, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.034482758620689655, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.034482758620689655, | |
| "eval_loss": NaN, | |
| "eval_runtime": 24.7147, | |
| "eval_samples_per_second": 8.902, | |
| "eval_steps_per_second": 4.451, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03639846743295019, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.038314176245210725, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6572656904110080.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |