| { | |
| "best_metric": 2.094454526901245, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.008320852055250457, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003328340822100183, | |
| "grad_norm": 11.368162155151367, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 9.6351, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003328340822100183, | |
| "eval_loss": 2.190483570098877, | |
| "eval_runtime": 450.2477, | |
| "eval_samples_per_second": 2.81, | |
| "eval_steps_per_second": 1.406, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006656681644200366, | |
| "grad_norm": 10.272940635681152, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 6.9149, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.000998502246630055, | |
| "grad_norm": 9.002182006835938, | |
| "learning_rate": 6e-06, | |
| "loss": 8.5981, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0013313363288400732, | |
| "grad_norm": 9.59417724609375, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 9.5408, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0016641704110500915, | |
| "grad_norm": 10.173685073852539, | |
| "learning_rate": 1e-05, | |
| "loss": 9.2569, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0016641704110500915, | |
| "eval_loss": 2.1854708194732666, | |
| "eval_runtime": 169.6684, | |
| "eval_samples_per_second": 7.456, | |
| "eval_steps_per_second": 3.731, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00199700449326011, | |
| "grad_norm": 9.6666898727417, | |
| "learning_rate": 1.2e-05, | |
| "loss": 8.8402, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002329838575470128, | |
| "grad_norm": 9.618661880493164, | |
| "learning_rate": 1.4e-05, | |
| "loss": 9.2091, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0026626726576801465, | |
| "grad_norm": 9.527913093566895, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 9.2478, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0029955067398901645, | |
| "grad_norm": 9.185748100280762, | |
| "learning_rate": 1.8e-05, | |
| "loss": 8.5159, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.003328340822100183, | |
| "grad_norm": 8.950668334960938, | |
| "learning_rate": 2e-05, | |
| "loss": 7.6605, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003328340822100183, | |
| "eval_loss": 2.1534292697906494, | |
| "eval_runtime": 168.9136, | |
| "eval_samples_per_second": 7.489, | |
| "eval_steps_per_second": 3.747, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0036611749043102015, | |
| "grad_norm": 8.140580177307129, | |
| "learning_rate": 1.9781476007338058e-05, | |
| "loss": 8.3768, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00399400898652022, | |
| "grad_norm": 6.66556453704834, | |
| "learning_rate": 1.913545457642601e-05, | |
| "loss": 7.6198, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.004326843068730238, | |
| "grad_norm": 8.427690505981445, | |
| "learning_rate": 1.8090169943749477e-05, | |
| "loss": 9.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.004659677150940256, | |
| "grad_norm": 11.37745189666748, | |
| "learning_rate": 1.6691306063588583e-05, | |
| "loss": 9.6437, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.004992511233150275, | |
| "grad_norm": 8.17237377166748, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 8.5021, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004992511233150275, | |
| "eval_loss": 2.121389389038086, | |
| "eval_runtime": 167.9606, | |
| "eval_samples_per_second": 7.532, | |
| "eval_steps_per_second": 3.769, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005325345315360293, | |
| "grad_norm": 10.338920593261719, | |
| "learning_rate": 1.3090169943749475e-05, | |
| "loss": 9.3378, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.005658179397570311, | |
| "grad_norm": 12.773215293884277, | |
| "learning_rate": 1.1045284632676535e-05, | |
| "loss": 8.3154, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.005991013479780329, | |
| "grad_norm": 10.358263969421387, | |
| "learning_rate": 8.954715367323468e-06, | |
| "loss": 8.038, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.006323847561990348, | |
| "grad_norm": 9.670676231384277, | |
| "learning_rate": 6.909830056250527e-06, | |
| "loss": 8.7551, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.006656681644200366, | |
| "grad_norm": 10.703207015991211, | |
| "learning_rate": 5.000000000000003e-06, | |
| "loss": 8.5689, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.006656681644200366, | |
| "eval_loss": 2.099368095397949, | |
| "eval_runtime": 167.8502, | |
| "eval_samples_per_second": 7.536, | |
| "eval_steps_per_second": 3.771, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.006989515726410384, | |
| "grad_norm": 7.785707950592041, | |
| "learning_rate": 3.308693936411421e-06, | |
| "loss": 8.0961, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.007322349808620403, | |
| "grad_norm": 9.827231407165527, | |
| "learning_rate": 1.9098300562505266e-06, | |
| "loss": 8.7015, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.007655183890830421, | |
| "grad_norm": 14.5091552734375, | |
| "learning_rate": 8.645454235739903e-07, | |
| "loss": 10.2516, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.00798801797304044, | |
| "grad_norm": 6.723724365234375, | |
| "learning_rate": 2.1852399266194312e-07, | |
| "loss": 6.4744, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.008320852055250457, | |
| "grad_norm": 8.817569732666016, | |
| "learning_rate": 0.0, | |
| "loss": 7.7032, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.008320852055250457, | |
| "eval_loss": 2.094454526901245, | |
| "eval_runtime": 169.3455, | |
| "eval_samples_per_second": 7.47, | |
| "eval_steps_per_second": 3.738, | |
| "step": 25 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4469307954167808.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |