| { | |
| "best_metric": 1.4154735803604126, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.26999662504218697, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.010799865001687479, | |
| "grad_norm": 10.750555992126465, | |
| "learning_rate": 5e-05, | |
| "loss": 7.3972, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010799865001687479, | |
| "eval_loss": 11.61225700378418, | |
| "eval_runtime": 3.1573, | |
| "eval_samples_per_second": 15.836, | |
| "eval_steps_per_second": 4.117, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.021599730003374958, | |
| "grad_norm": 7.2301530838012695, | |
| "learning_rate": 0.0001, | |
| "loss": 6.3948, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03239959500506244, | |
| "grad_norm": 6.079974174499512, | |
| "learning_rate": 9.958086757163489e-05, | |
| "loss": 5.553, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.043199460006749915, | |
| "grad_norm": 7.805851459503174, | |
| "learning_rate": 9.833127793065098e-05, | |
| "loss": 4.8825, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0539993250084374, | |
| "grad_norm": 7.568227291107178, | |
| "learning_rate": 9.627450856774539e-05, | |
| "loss": 3.5244, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06479919001012488, | |
| "grad_norm": 8.064841270446777, | |
| "learning_rate": 9.3448873204592e-05, | |
| "loss": 2.5025, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07559905501181235, | |
| "grad_norm": 4.945073127746582, | |
| "learning_rate": 8.990700808169889e-05, | |
| "loss": 1.8287, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.08639892001349983, | |
| "grad_norm": 6.004214286804199, | |
| "learning_rate": 8.571489144483944e-05, | |
| "loss": 1.7489, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0971987850151873, | |
| "grad_norm": 4.8912177085876465, | |
| "learning_rate": 8.095061449516903e-05, | |
| "loss": 1.4673, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1079986500168748, | |
| "grad_norm": 4.171592712402344, | |
| "learning_rate": 7.570292669790186e-05, | |
| "loss": 1.4987, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11879851501856227, | |
| "grad_norm": 4.042658805847168, | |
| "learning_rate": 7.006958254769438e-05, | |
| "loss": 1.4552, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.12959838002024976, | |
| "grad_norm": 4.8983049392700195, | |
| "learning_rate": 6.415552058736854e-05, | |
| "loss": 1.3836, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.14039824502193723, | |
| "grad_norm": 2.738255023956299, | |
| "learning_rate": 5.80709086014102e-05, | |
| "loss": 1.3718, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1511981100236247, | |
| "grad_norm": 2.700366258621216, | |
| "learning_rate": 5.192909139858981e-05, | |
| "loss": 1.218, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.16199797502531219, | |
| "grad_norm": 1.7999701499938965, | |
| "learning_rate": 4.584447941263149e-05, | |
| "loss": 1.2752, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.17279784002699966, | |
| "grad_norm": 1.684377908706665, | |
| "learning_rate": 3.9930417452305626e-05, | |
| "loss": 1.2584, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.18359770502868714, | |
| "grad_norm": 1.7270563840866089, | |
| "learning_rate": 3.4297073302098156e-05, | |
| "loss": 1.2766, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1943975700303746, | |
| "grad_norm": 1.4821616411209106, | |
| "learning_rate": 2.9049385504830985e-05, | |
| "loss": 1.0553, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2051974350320621, | |
| "grad_norm": 2.4013428688049316, | |
| "learning_rate": 2.4285108555160577e-05, | |
| "loss": 1.249, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2159973000337496, | |
| "grad_norm": 2.2816715240478516, | |
| "learning_rate": 2.0092991918301108e-05, | |
| "loss": 1.154, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.22679716503543706, | |
| "grad_norm": 2.194995403289795, | |
| "learning_rate": 1.6551126795408016e-05, | |
| "loss": 1.2416, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.23759703003712454, | |
| "grad_norm": 2.089994430541992, | |
| "learning_rate": 1.3725491432254624e-05, | |
| "loss": 1.2542, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.24839689503881202, | |
| "grad_norm": 2.76861572265625, | |
| "learning_rate": 1.1668722069349041e-05, | |
| "loss": 1.3554, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2591967600404995, | |
| "grad_norm": 2.7466013431549072, | |
| "learning_rate": 1.0419132428365116e-05, | |
| "loss": 1.1405, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.26999662504218697, | |
| "grad_norm": 3.3321781158447266, | |
| "learning_rate": 1e-05, | |
| "loss": 0.987, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.26999662504218697, | |
| "eval_loss": 1.4154735803604126, | |
| "eval_runtime": 3.1946, | |
| "eval_samples_per_second": 15.651, | |
| "eval_steps_per_second": 4.069, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.984041808658432e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |