| { | |
| "best_metric": 0.8934311866760254, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.04434589800443459, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0017738359201773836, | |
| "grad_norm": 1.6331450939178467, | |
| "learning_rate": 2e-05, | |
| "loss": 2.1491, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0017738359201773836, | |
| "eval_loss": 2.156221389770508, | |
| "eval_runtime": 34.1792, | |
| "eval_samples_per_second": 6.963, | |
| "eval_steps_per_second": 3.482, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003547671840354767, | |
| "grad_norm": 2.142427444458008, | |
| "learning_rate": 4e-05, | |
| "loss": 2.2744, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005321507760532151, | |
| "grad_norm": 1.335496425628662, | |
| "learning_rate": 6e-05, | |
| "loss": 1.8577, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007095343680709534, | |
| "grad_norm": 1.5356032848358154, | |
| "learning_rate": 8e-05, | |
| "loss": 1.9983, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.008869179600886918, | |
| "grad_norm": 1.8492310047149658, | |
| "learning_rate": 0.0001, | |
| "loss": 2.2588, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008869179600886918, | |
| "eval_loss": 2.057093858718872, | |
| "eval_runtime": 32.7002, | |
| "eval_samples_per_second": 7.278, | |
| "eval_steps_per_second": 3.639, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.010643015521064302, | |
| "grad_norm": 1.8534923791885376, | |
| "learning_rate": 0.00012, | |
| "loss": 2.068, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.012416851441241685, | |
| "grad_norm": 2.1694960594177246, | |
| "learning_rate": 0.00014, | |
| "loss": 1.8945, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.014190687361419069, | |
| "grad_norm": 1.7592840194702148, | |
| "learning_rate": 0.00016, | |
| "loss": 1.7782, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.015964523281596452, | |
| "grad_norm": 2.2886457443237305, | |
| "learning_rate": 0.00018, | |
| "loss": 1.5152, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.017738359201773836, | |
| "grad_norm": 1.9047895669937134, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3502, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.017738359201773836, | |
| "eval_loss": 1.2971845865249634, | |
| "eval_runtime": 33.0416, | |
| "eval_samples_per_second": 7.203, | |
| "eval_steps_per_second": 3.602, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01951219512195122, | |
| "grad_norm": 1.956074833869934, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 1.3962, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.021286031042128603, | |
| "grad_norm": 1.7686818838119507, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 1.1724, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.023059866962305987, | |
| "grad_norm": 1.6020398139953613, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 1.0728, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.02483370288248337, | |
| "grad_norm": 1.6922051906585693, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 0.9902, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.026607538802660754, | |
| "grad_norm": 2.132755756378174, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.9552, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.026607538802660754, | |
| "eval_loss": 1.0003092288970947, | |
| "eval_runtime": 34.7928, | |
| "eval_samples_per_second": 6.84, | |
| "eval_steps_per_second": 3.42, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.028381374722838137, | |
| "grad_norm": 1.8932487964630127, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.0874, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.03015521064301552, | |
| "grad_norm": 2.181488037109375, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 1.0457, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.031929046563192905, | |
| "grad_norm": 2.006877899169922, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 1.0567, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03370288248337029, | |
| "grad_norm": 1.926302433013916, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.9321, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.03547671840354767, | |
| "grad_norm": 1.6763228178024292, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.141, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03547671840354767, | |
| "eval_loss": 0.9107561111450195, | |
| "eval_runtime": 35.8064, | |
| "eval_samples_per_second": 6.647, | |
| "eval_steps_per_second": 3.323, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03725055432372506, | |
| "grad_norm": 1.6538779735565186, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 0.8503, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.03902439024390244, | |
| "grad_norm": 1.8892109394073486, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 0.9907, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.040798226164079826, | |
| "grad_norm": 2.003721237182617, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 0.7393, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.042572062084257206, | |
| "grad_norm": 1.7759606838226318, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 1.0311, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.04434589800443459, | |
| "grad_norm": 1.840668797492981, | |
| "learning_rate": 0.0, | |
| "loss": 0.7071, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04434589800443459, | |
| "eval_loss": 0.8934311866760254, | |
| "eval_runtime": 32.808, | |
| "eval_samples_per_second": 7.254, | |
| "eval_steps_per_second": 3.627, | |
| "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": 601363788595200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |