| { | |
| "best_metric": 0.4118092954158783, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-20", | |
| "epoch": 0.0935672514619883, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004678362573099415, | |
| "grad_norm": 1.2035468816757202, | |
| "learning_rate": 2e-05, | |
| "loss": 2.9851, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004678362573099415, | |
| "eval_loss": 0.8073704838752747, | |
| "eval_runtime": 11.4055, | |
| "eval_samples_per_second": 7.891, | |
| "eval_steps_per_second": 3.945, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00935672514619883, | |
| "grad_norm": 1.2121034860610962, | |
| "learning_rate": 4e-05, | |
| "loss": 3.3131, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.014035087719298246, | |
| "grad_norm": 1.1608259677886963, | |
| "learning_rate": 6e-05, | |
| "loss": 3.4206, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01871345029239766, | |
| "grad_norm": 1.0278185606002808, | |
| "learning_rate": 8e-05, | |
| "loss": 3.0533, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.023391812865497075, | |
| "grad_norm": 1.076200246810913, | |
| "learning_rate": 0.0001, | |
| "loss": 2.9734, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.023391812865497075, | |
| "eval_loss": 0.7855624556541443, | |
| "eval_runtime": 11.3916, | |
| "eval_samples_per_second": 7.901, | |
| "eval_steps_per_second": 3.95, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.028070175438596492, | |
| "grad_norm": 1.3230271339416504, | |
| "learning_rate": 0.00012, | |
| "loss": 2.8725, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03274853801169591, | |
| "grad_norm": 1.2319637537002563, | |
| "learning_rate": 0.00014, | |
| "loss": 3.1528, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03742690058479532, | |
| "grad_norm": 1.1680997610092163, | |
| "learning_rate": 0.00016, | |
| "loss": 3.197, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.042105263157894736, | |
| "grad_norm": 1.0301086902618408, | |
| "learning_rate": 0.00018, | |
| "loss": 2.4583, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04678362573099415, | |
| "grad_norm": 1.1154131889343262, | |
| "learning_rate": 0.0002, | |
| "loss": 2.7852, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04678362573099415, | |
| "eval_loss": 0.6406313180923462, | |
| "eval_runtime": 11.4034, | |
| "eval_samples_per_second": 7.892, | |
| "eval_steps_per_second": 3.946, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05146198830409357, | |
| "grad_norm": 1.1888481378555298, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 2.736, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.056140350877192984, | |
| "grad_norm": 1.0447313785552979, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 2.1931, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0608187134502924, | |
| "grad_norm": 0.9865492582321167, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 1.8405, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.06549707602339182, | |
| "grad_norm": 1.2127184867858887, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 2.1726, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.07017543859649122, | |
| "grad_norm": 1.2068496942520142, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 2.1146, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07017543859649122, | |
| "eval_loss": 0.47981786727905273, | |
| "eval_runtime": 11.2776, | |
| "eval_samples_per_second": 7.98, | |
| "eval_steps_per_second": 3.99, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07485380116959064, | |
| "grad_norm": 1.0533158779144287, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.5592, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.07953216374269007, | |
| "grad_norm": 1.02470064163208, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 2.0986, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.08421052631578947, | |
| "grad_norm": 1.0912792682647705, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 1.8195, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.08888888888888889, | |
| "grad_norm": 1.276378870010376, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 1.7657, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0935672514619883, | |
| "grad_norm": 1.306107759475708, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.8758, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0935672514619883, | |
| "eval_loss": 0.4118092954158783, | |
| "eval_runtime": 11.3147, | |
| "eval_samples_per_second": 7.954, | |
| "eval_steps_per_second": 3.977, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2845655470964736.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |