| { | |
| "best_metric": 0.0008776781032793224, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.027204407113952462, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0010881762845580984, | |
| "grad_norm": 8.488767623901367, | |
| "learning_rate": 5e-05, | |
| "loss": 5.2384, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010881762845580984, | |
| "eval_loss": 0.4561319053173065, | |
| "eval_runtime": 4.1709, | |
| "eval_samples_per_second": 11.988, | |
| "eval_steps_per_second": 3.117, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0021763525691161968, | |
| "grad_norm": 12.473525047302246, | |
| "learning_rate": 0.0001, | |
| "loss": 7.3057, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0032645288536742954, | |
| "grad_norm": 13.172096252441406, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 8.1381, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0043527051382323935, | |
| "grad_norm": 12.740236282348633, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 6.7608, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005440881422790492, | |
| "grad_norm": 10.972394943237305, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 4.3499, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006529057707348591, | |
| "grad_norm": 9.73342227935791, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.7862, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.007617233991906689, | |
| "grad_norm": 8.87482738494873, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.4533, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.008705410276464787, | |
| "grad_norm": 7.187124729156494, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.5967, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.009793586561022886, | |
| "grad_norm": 3.336824655532837, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.1768, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.010881762845580983, | |
| "grad_norm": 1.0351998805999756, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.0488, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.011969939130139082, | |
| "grad_norm": 1.6404157876968384, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.0692, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.013058115414697181, | |
| "grad_norm": 1.8609697818756104, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.07, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.014146291699255279, | |
| "grad_norm": 5.1143269538879395, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.2308, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.015234467983813378, | |
| "grad_norm": 2.8937344551086426, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.0796, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.016322644268371475, | |
| "grad_norm": 0.8888844847679138, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.0157, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.017410820552929574, | |
| "grad_norm": 1.7481740713119507, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.0342, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.018498996837487673, | |
| "grad_norm": 2.1718719005584717, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.0169, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.019587173122045772, | |
| "grad_norm": 0.21131518483161926, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.005, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02067534940660387, | |
| "grad_norm": 0.1480499505996704, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.0027, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.021763525691161967, | |
| "grad_norm": 0.09550140798091888, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.0029, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.022851701975720066, | |
| "grad_norm": 0.039920106530189514, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.0013, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.023939878260278165, | |
| "grad_norm": 0.11236383020877838, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.0016, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.025028054544836264, | |
| "grad_norm": 0.13724114000797272, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.0021, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.026116230829394363, | |
| "grad_norm": 0.007396350614726543, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.0007, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.027204407113952462, | |
| "grad_norm": 0.028984805569052696, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.0011, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.027204407113952462, | |
| "eval_loss": 0.0008776781032793224, | |
| "eval_runtime": 4.1329, | |
| "eval_samples_per_second": 12.098, | |
| "eval_steps_per_second": 3.145, | |
| "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": 2.6303741225336832e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |