| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.00990099009901, | |
| "eval_steps": 25, | |
| "global_step": 38, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07920792079207921, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07920792079207921, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.0819, | |
| "eval_samples_per_second": 46.217, | |
| "eval_steps_per_second": 12.016, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.15841584158415842, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.2376237623762376, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.982876141412856e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.31683168316831684, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.931634888554937e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.39603960396039606, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.4752475247524752, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.728616793536588e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.5544554455445545, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.578385041664925e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.6336633663366337, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.7128712871287128, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.186184199300464e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.7920792079207921, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.947199994035401e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.8712871287128713, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.9504950495049505, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.392544243589427e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.0297029702970297, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.081093963579707e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.108910891089109, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.188118811881188, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.401782177833148e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.2673267326732673, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.03909064496551e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.3465346534653464, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.4257425742574257, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.281416799501188e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.504950495049505, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.8922008423644624e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.5841584158415842, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.6633663366336635, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.107799157635538e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.7425742574257426, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.718583200498814e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.8217821782178216, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.900990099009901, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.960909355034491e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.9801980198019802, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.598217822166854e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.9801980198019802, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.5738, | |
| "eval_samples_per_second": 87.138, | |
| "eval_steps_per_second": 22.656, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.0594059405940595, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.1386138613861387, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9189060364202943e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.217821782178218, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6074557564105727e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.297029702970297, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.376237623762376, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0528000059645997e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.4554455445544554, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8138158006995364e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.5346534653465347, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.613861386138614, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4216149583350754e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.693069306930693, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2713832064634126e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.772277227722772, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.8514851485148514, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0683651114450641e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.9306930693069306, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.017123858587145e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 3.00990099009901, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 38, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.2442869360951296e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |