| { | |
| "best_metric": 10.378490447998047, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.10077519379845, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.12403100775193798, | |
| "grad_norm": 0.05493992939591408, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3799, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.12403100775193798, | |
| "eval_loss": 10.383469581604004, | |
| "eval_runtime": 0.1123, | |
| "eval_samples_per_second": 445.052, | |
| "eval_steps_per_second": 115.714, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.24806201550387597, | |
| "grad_norm": 0.06447719037532806, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3793, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.37209302325581395, | |
| "grad_norm": 0.05459710955619812, | |
| "learning_rate": 9.958086757163489e-05, | |
| "loss": 10.3809, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.49612403100775193, | |
| "grad_norm": 0.06451790034770966, | |
| "learning_rate": 9.833127793065098e-05, | |
| "loss": 10.3814, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.6201550387596899, | |
| "grad_norm": 0.05665484443306923, | |
| "learning_rate": 9.627450856774539e-05, | |
| "loss": 10.3801, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.7441860465116279, | |
| "grad_norm": 0.06074388697743416, | |
| "learning_rate": 9.3448873204592e-05, | |
| "loss": 10.3798, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.8682170542635659, | |
| "grad_norm": 0.06343019008636475, | |
| "learning_rate": 8.990700808169889e-05, | |
| "loss": 10.3779, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.9922480620155039, | |
| "grad_norm": 0.0629330575466156, | |
| "learning_rate": 8.571489144483944e-05, | |
| "loss": 10.3792, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.1162790697674418, | |
| "grad_norm": 0.13291753828525543, | |
| "learning_rate": 8.095061449516903e-05, | |
| "loss": 20.3343, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.2403100775193798, | |
| "grad_norm": 0.07112114876508713, | |
| "learning_rate": 7.570292669790186e-05, | |
| "loss": 10.5189, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.3643410852713178, | |
| "grad_norm": 0.057202767580747604, | |
| "learning_rate": 7.006958254769438e-05, | |
| "loss": 10.183, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.4883720930232558, | |
| "grad_norm": 0.06450869888067245, | |
| "learning_rate": 6.415552058736854e-05, | |
| "loss": 10.6021, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.6124031007751938, | |
| "grad_norm": 0.05808200687170029, | |
| "learning_rate": 5.80709086014102e-05, | |
| "loss": 10.1293, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.7364341085271318, | |
| "grad_norm": 0.07130399346351624, | |
| "learning_rate": 5.192909139858981e-05, | |
| "loss": 10.6434, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.8604651162790697, | |
| "grad_norm": 0.06081729382276535, | |
| "learning_rate": 4.584447941263149e-05, | |
| "loss": 10.0963, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.9844961240310077, | |
| "grad_norm": 0.0815894678235054, | |
| "learning_rate": 3.9930417452305626e-05, | |
| "loss": 10.6551, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 2.108527131782946, | |
| "grad_norm": 0.11529082804918289, | |
| "learning_rate": 3.4297073302098156e-05, | |
| "loss": 20.0197, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 2.2325581395348837, | |
| "grad_norm": 0.0764957144856453, | |
| "learning_rate": 2.9049385504830985e-05, | |
| "loss": 10.8299, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 2.356589147286822, | |
| "grad_norm": 0.06253160536289215, | |
| "learning_rate": 2.4285108555160577e-05, | |
| "loss": 9.9145, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 2.4806201550387597, | |
| "grad_norm": 0.07881199568510056, | |
| "learning_rate": 2.0092991918301108e-05, | |
| "loss": 10.7975, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.604651162790698, | |
| "grad_norm": 0.056578364223241806, | |
| "learning_rate": 1.6551126795408016e-05, | |
| "loss": 9.9555, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 2.7286821705426356, | |
| "grad_norm": 0.07633749395608902, | |
| "learning_rate": 1.3725491432254624e-05, | |
| "loss": 10.8105, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.8527131782945734, | |
| "grad_norm": 0.062091290950775146, | |
| "learning_rate": 1.1668722069349041e-05, | |
| "loss": 9.8987, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.9767441860465116, | |
| "grad_norm": 0.08738675713539124, | |
| "learning_rate": 1.0419132428365116e-05, | |
| "loss": 10.8077, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 3.10077519379845, | |
| "grad_norm": 0.11702527105808258, | |
| "learning_rate": 1e-05, | |
| "loss": 19.8316, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 3.10077519379845, | |
| "eval_loss": 10.378490447998047, | |
| "eval_runtime": 0.113, | |
| "eval_samples_per_second": 442.645, | |
| "eval_steps_per_second": 115.088, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "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": 21384029798400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |