| { | |
| "best_metric": 1.4860926866531372, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.3325020781379884, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.013300083125519535, | |
| "grad_norm": 0.30807769298553467, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5989, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013300083125519535, | |
| "eval_loss": 1.8170369863510132, | |
| "eval_runtime": 4.4482, | |
| "eval_samples_per_second": 113.979, | |
| "eval_steps_per_second": 14.388, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02660016625103907, | |
| "grad_norm": 0.33670011162757874, | |
| "learning_rate": 0.0001, | |
| "loss": 1.6635, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0399002493765586, | |
| "grad_norm": 0.35574978590011597, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.639, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05320033250207814, | |
| "grad_norm": 0.43438073992729187, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.7603, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06650041562759768, | |
| "grad_norm": 0.4591783583164215, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.7698, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0798004987531172, | |
| "grad_norm": 0.3775702118873596, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.6717, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.09310058187863675, | |
| "grad_norm": 0.40178415179252625, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.6908, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.10640066500415628, | |
| "grad_norm": 0.39939138293266296, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.6511, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.11970074812967581, | |
| "grad_norm": 0.4064088761806488, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.6223, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.13300083125519535, | |
| "grad_norm": 0.42422300577163696, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.6776, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14630091438071488, | |
| "grad_norm": 0.4172786474227905, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.6897, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1596009975062344, | |
| "grad_norm": 0.4498286247253418, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.7711, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.17290108063175394, | |
| "grad_norm": 0.2242169827222824, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.5764, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1862011637572735, | |
| "grad_norm": 0.220079705119133, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.4311, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.19950124688279303, | |
| "grad_norm": 0.2502831816673279, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.5599, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.21280133000831256, | |
| "grad_norm": 0.27619630098342896, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.5565, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.22610141313383209, | |
| "grad_norm": 0.2701985239982605, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.5664, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.23940149625935161, | |
| "grad_norm": 0.24903272092342377, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.596, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.25270157938487114, | |
| "grad_norm": 0.2547197937965393, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.4784, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2660016625103907, | |
| "grad_norm": 0.22915960848331451, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.4753, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2793017456359102, | |
| "grad_norm": 0.2612093985080719, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.5629, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.29260182876142976, | |
| "grad_norm": 0.26348868012428284, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.412, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3059019118869493, | |
| "grad_norm": 0.28813788294792175, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.5054, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3192019950124688, | |
| "grad_norm": 0.31999000906944275, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.5242, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3325020781379884, | |
| "grad_norm": 0.4172128736972809, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.499, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3325020781379884, | |
| "eval_loss": 1.4860926866531372, | |
| "eval_runtime": 4.4333, | |
| "eval_samples_per_second": 114.363, | |
| "eval_steps_per_second": 14.436, | |
| "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": 4.16708196040704e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |