| { | |
| "best_metric": 3.286402940750122, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.11554015020219527, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00462160600808781, | |
| "grad_norm": 1.288442611694336, | |
| "learning_rate": 5e-05, | |
| "loss": 3.8012, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00462160600808781, | |
| "eval_loss": 4.563611030578613, | |
| "eval_runtime": 3.8296, | |
| "eval_samples_per_second": 13.056, | |
| "eval_steps_per_second": 3.395, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00924321201617562, | |
| "grad_norm": 1.4787236452102661, | |
| "learning_rate": 0.0001, | |
| "loss": 3.8921, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01386481802426343, | |
| "grad_norm": 1.387248158454895, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 3.8362, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01848642403235124, | |
| "grad_norm": 1.3118922710418701, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 3.9026, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.023108030040439053, | |
| "grad_norm": 1.4238702058792114, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 3.7385, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02772963604852686, | |
| "grad_norm": 1.970743179321289, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 3.5772, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.032351242056614674, | |
| "grad_norm": 2.0607903003692627, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 3.6214, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03697284806470248, | |
| "grad_norm": 2.0753731727600098, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 3.5682, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0415944540727903, | |
| "grad_norm": 1.5874611139297485, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 3.4393, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.046216060080878106, | |
| "grad_norm": 1.3372491598129272, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 3.2608, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.050837666088965915, | |
| "grad_norm": 1.390437364578247, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 3.2361, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.05545927209705372, | |
| "grad_norm": 1.6799904108047485, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 3.5205, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.06008087810514154, | |
| "grad_norm": 1.0265284776687622, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 3.304, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.06470248411322935, | |
| "grad_norm": 0.8137627243995667, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 3.1193, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.06932409012131716, | |
| "grad_norm": 0.8473964929580688, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 3.2364, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07394569612940496, | |
| "grad_norm": 0.8334770798683167, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 3.2009, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.07856730213749277, | |
| "grad_norm": 0.8550782203674316, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 3.1538, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0831889081455806, | |
| "grad_norm": 0.9399331212043762, | |
| "learning_rate": 7.75e-05, | |
| "loss": 3.1042, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0878105141536684, | |
| "grad_norm": 0.9655375480651855, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 3.2021, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.09243212016175621, | |
| "grad_norm": 0.9604383111000061, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 3.1207, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09705372616984402, | |
| "grad_norm": 1.1175299882888794, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 3.2179, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.10167533217793183, | |
| "grad_norm": 1.1890922784805298, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 3.2145, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.10629693818601964, | |
| "grad_norm": 1.2423139810562134, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 3.1882, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.11091854419410745, | |
| "grad_norm": 1.3063606023788452, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 3.1189, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.11554015020219527, | |
| "grad_norm": 1.6099401712417603, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 3.4779, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11554015020219527, | |
| "eval_loss": 3.286402940750122, | |
| "eval_runtime": 3.5029, | |
| "eval_samples_per_second": 14.274, | |
| "eval_steps_per_second": 3.711, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "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": 2.984041808658432e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |