| { | |
| "best_metric": 0.16951684653759003, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.01198196713945512, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004792786855782048, | |
| "grad_norm": 0.41401901841163635, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1018, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004792786855782048, | |
| "eval_loss": 1.1791296005249023, | |
| "eval_runtime": 6.5989, | |
| "eval_samples_per_second": 7.577, | |
| "eval_steps_per_second": 7.577, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009585573711564096, | |
| "grad_norm": 0.3986301124095917, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0824, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0014378360567346145, | |
| "grad_norm": 0.2979283034801483, | |
| "learning_rate": 9.958086757163489e-05, | |
| "loss": 0.0761, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0019171147423128192, | |
| "grad_norm": 0.20421022176742554, | |
| "learning_rate": 9.833127793065098e-05, | |
| "loss": 0.037, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002396393427891024, | |
| "grad_norm": 0.1535191684961319, | |
| "learning_rate": 9.627450856774539e-05, | |
| "loss": 0.0234, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002875672113469229, | |
| "grad_norm": 0.1266649067401886, | |
| "learning_rate": 9.3448873204592e-05, | |
| "loss": 0.0158, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0033549507990474335, | |
| "grad_norm": 0.14331640303134918, | |
| "learning_rate": 8.990700808169889e-05, | |
| "loss": 0.0096, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0038342294846256384, | |
| "grad_norm": 0.17804047465324402, | |
| "learning_rate": 8.571489144483944e-05, | |
| "loss": 0.0084, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004313508170203843, | |
| "grad_norm": 0.23399387300014496, | |
| "learning_rate": 8.095061449516903e-05, | |
| "loss": 0.008, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004792786855782048, | |
| "grad_norm": 0.13882753252983093, | |
| "learning_rate": 7.570292669790186e-05, | |
| "loss": 0.0047, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005272065541360253, | |
| "grad_norm": 0.059140030294656754, | |
| "learning_rate": 7.006958254769438e-05, | |
| "loss": 0.003, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.005751344226938458, | |
| "grad_norm": 0.11627905070781708, | |
| "learning_rate": 6.415552058736854e-05, | |
| "loss": 0.004, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.006230622912516663, | |
| "grad_norm": 0.07218436151742935, | |
| "learning_rate": 5.80709086014102e-05, | |
| "loss": 0.002, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.006709901598094867, | |
| "grad_norm": 0.04201905429363251, | |
| "learning_rate": 5.192909139858981e-05, | |
| "loss": 0.0011, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.007189180283673072, | |
| "grad_norm": 0.04355667158961296, | |
| "learning_rate": 4.584447941263149e-05, | |
| "loss": 0.0019, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007668458969251277, | |
| "grad_norm": 0.08100510388612747, | |
| "learning_rate": 3.9930417452305626e-05, | |
| "loss": 0.0021, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.008147737654829481, | |
| "grad_norm": 0.05518050864338875, | |
| "learning_rate": 3.4297073302098156e-05, | |
| "loss": 0.0018, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.008627016340407686, | |
| "grad_norm": 0.06182258576154709, | |
| "learning_rate": 2.9049385504830985e-05, | |
| "loss": 0.0007, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.009106295025985891, | |
| "grad_norm": 0.025211133062839508, | |
| "learning_rate": 2.4285108555160577e-05, | |
| "loss": 0.0009, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.009585573711564096, | |
| "grad_norm": 0.01755666919052601, | |
| "learning_rate": 2.0092991918301108e-05, | |
| "loss": 0.0005, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0100648523971423, | |
| "grad_norm": 0.03852513059973717, | |
| "learning_rate": 1.6551126795408016e-05, | |
| "loss": 0.0007, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.010544131082720506, | |
| "grad_norm": 0.01072454173117876, | |
| "learning_rate": 1.3725491432254624e-05, | |
| "loss": 0.0003, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01102340976829871, | |
| "grad_norm": 0.18533989787101746, | |
| "learning_rate": 1.1668722069349041e-05, | |
| "loss": 0.004, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.011502688453876916, | |
| "grad_norm": 0.1925441175699234, | |
| "learning_rate": 1.0419132428365116e-05, | |
| "loss": 0.0018, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01198196713945512, | |
| "grad_norm": 0.03919576108455658, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0011, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01198196713945512, | |
| "eval_loss": 0.16951684653759003, | |
| "eval_runtime": 6.5411, | |
| "eval_samples_per_second": 7.644, | |
| "eval_steps_per_second": 7.644, | |
| "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": 2.0462436807081984e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |