| { | |
| "best_metric": 0.38498401641845703, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.7782101167315175, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0311284046692607, | |
| "grad_norm": 57.044677734375, | |
| "learning_rate": 5e-05, | |
| "loss": 8.1101, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0311284046692607, | |
| "eval_loss": 8.996267318725586, | |
| "eval_runtime": 1.0309, | |
| "eval_samples_per_second": 48.5, | |
| "eval_steps_per_second": 12.61, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0622568093385214, | |
| "grad_norm": 56.805782318115234, | |
| "learning_rate": 0.0001, | |
| "loss": 8.6173, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0933852140077821, | |
| "grad_norm": 35.73737335205078, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 8.0013, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1245136186770428, | |
| "grad_norm": 15.80854606628418, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 6.644, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.1556420233463035, | |
| "grad_norm": 19.536319732666016, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 5.9673, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1867704280155642, | |
| "grad_norm": 11.583967208862305, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 5.3271, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2178988326848249, | |
| "grad_norm": 10.30289077758789, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 4.6635, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.2490272373540856, | |
| "grad_norm": 12.086468696594238, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 4.0123, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.2801556420233463, | |
| "grad_norm": 13.472044944763184, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 4.113, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.311284046692607, | |
| "grad_norm": 10.922317504882812, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 3.5306, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3424124513618677, | |
| "grad_norm": 9.1859712600708, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 3.1866, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.3735408560311284, | |
| "grad_norm": 13.324037551879883, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 2.7438, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.4046692607003891, | |
| "grad_norm": 10.161223411560059, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 2.4045, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.4357976653696498, | |
| "grad_norm": 8.690367698669434, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.9267, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.4669260700389105, | |
| "grad_norm": 8.615327835083008, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.4874, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.4980544747081712, | |
| "grad_norm": 9.89849853515625, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.1637, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.5291828793774319, | |
| "grad_norm": 8.404136657714844, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.3743, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.5603112840466926, | |
| "grad_norm": 7.384093761444092, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.245, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.5914396887159533, | |
| "grad_norm": 5.8040008544921875, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.9046, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.622568093385214, | |
| "grad_norm": 5.213988780975342, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.7418, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6536964980544747, | |
| "grad_norm": 3.9535512924194336, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.5878, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.6848249027237354, | |
| "grad_norm": 4.355014801025391, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.5048, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.7159533073929961, | |
| "grad_norm": 3.732577323913574, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.4554, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.7470817120622568, | |
| "grad_norm": 5.051167011260986, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.4403, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.7782101167315175, | |
| "grad_norm": 7.252755641937256, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.5283, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.7782101167315175, | |
| "eval_loss": 0.38498401641845703, | |
| "eval_runtime": 0.5755, | |
| "eval_samples_per_second": 86.875, | |
| "eval_steps_per_second": 22.587, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 4.16708196040704e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |