| { | |
| "best_metric": 1.2333778142929077, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.06532745386248572, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0026130981544994283, | |
| "grad_norm": 30.899654388427734, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1267, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0026130981544994283, | |
| "eval_loss": 1.8499661684036255, | |
| "eval_runtime": 167.2588, | |
| "eval_samples_per_second": 15.413, | |
| "eval_steps_per_second": 1.931, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005226196308998857, | |
| "grad_norm": 33.87411880493164, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2228, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007839294463498285, | |
| "grad_norm": 18.999311447143555, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.1836, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010452392617997713, | |
| "grad_norm": 21.47573471069336, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.1927, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.013065490772497142, | |
| "grad_norm": 21.85623550415039, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.2051, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01567858892699657, | |
| "grad_norm": 17.990365982055664, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.2142, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.018291687081496, | |
| "grad_norm": 14.827211380004883, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.1788, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.020904785235995427, | |
| "grad_norm": 22.092012405395508, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.2685, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.023517883390494855, | |
| "grad_norm": 32.1710319519043, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.4338, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.026130981544994283, | |
| "grad_norm": 45.76557540893555, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.566, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02874407969949371, | |
| "grad_norm": 45.74945068359375, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.6296, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03135717785399314, | |
| "grad_norm": 52.03664016723633, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.812, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03397027600849257, | |
| "grad_norm": 54.32783126831055, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.5289, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.036583374162992, | |
| "grad_norm": 25.161073684692383, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.1103, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.039196472317491425, | |
| "grad_norm": 24.294761657714844, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.1767, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04180957047199085, | |
| "grad_norm": 19.136260986328125, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.109, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04442266862649028, | |
| "grad_norm": 15.456122398376465, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.1021, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04703576678098971, | |
| "grad_norm": 12.054083824157715, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.1288, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04964886493548914, | |
| "grad_norm": 11.738526344299316, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.1676, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.05226196308998857, | |
| "grad_norm": 14.183579444885254, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.1864, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.054875061244487995, | |
| "grad_norm": 18.19736099243164, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.2671, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05748815939898742, | |
| "grad_norm": 25.0335693359375, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.3673, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.06010125755348685, | |
| "grad_norm": 36.76613235473633, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.5454, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.06271435570798628, | |
| "grad_norm": 45.20155715942383, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.5598, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06532745386248572, | |
| "grad_norm": 76.99732971191406, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.9044, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06532745386248572, | |
| "eval_loss": 1.2333778142929077, | |
| "eval_runtime": 167.251, | |
| "eval_samples_per_second": 15.414, | |
| "eval_steps_per_second": 1.931, | |
| "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": 2.829010669142016e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |