| { | |
| "best_metric": 1.0087976455688477, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.06720430107526881, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002688172043010753, | |
| "grad_norm": 0.5243517756462097, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3564, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002688172043010753, | |
| "eval_loss": 2.6512537002563477, | |
| "eval_runtime": 3.0315, | |
| "eval_samples_per_second": 16.493, | |
| "eval_steps_per_second": 4.288, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005376344086021506, | |
| "grad_norm": 0.586245596408844, | |
| "learning_rate": 0.0001, | |
| "loss": 1.135, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.008064516129032258, | |
| "grad_norm": 0.7690654993057251, | |
| "learning_rate": 9.958086757163489e-05, | |
| "loss": 1.1266, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010752688172043012, | |
| "grad_norm": 1.0103049278259277, | |
| "learning_rate": 9.833127793065098e-05, | |
| "loss": 1.1685, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.013440860215053764, | |
| "grad_norm": 1.226269006729126, | |
| "learning_rate": 9.627450856774539e-05, | |
| "loss": 1.1974, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.016129032258064516, | |
| "grad_norm": 1.2247505187988281, | |
| "learning_rate": 9.3448873204592e-05, | |
| "loss": 1.0919, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01881720430107527, | |
| "grad_norm": 1.4154307842254639, | |
| "learning_rate": 8.990700808169889e-05, | |
| "loss": 1.1176, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.021505376344086023, | |
| "grad_norm": 1.6466119289398193, | |
| "learning_rate": 8.571489144483944e-05, | |
| "loss": 1.0627, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.024193548387096774, | |
| "grad_norm": 2.3295235633850098, | |
| "learning_rate": 8.095061449516903e-05, | |
| "loss": 1.1398, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.026881720430107527, | |
| "grad_norm": 1.398525357246399, | |
| "learning_rate": 7.570292669790186e-05, | |
| "loss": 1.2629, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02956989247311828, | |
| "grad_norm": 3.2756099700927734, | |
| "learning_rate": 7.006958254769438e-05, | |
| "loss": 1.4204, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03225806451612903, | |
| "grad_norm": 10.254135131835938, | |
| "learning_rate": 6.415552058736854e-05, | |
| "loss": 3.0618, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03494623655913978, | |
| "grad_norm": 2.216543197631836, | |
| "learning_rate": 5.80709086014102e-05, | |
| "loss": 1.5946, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03763440860215054, | |
| "grad_norm": 0.9413918852806091, | |
| "learning_rate": 5.192909139858981e-05, | |
| "loss": 0.6634, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.04032258064516129, | |
| "grad_norm": 0.8472892045974731, | |
| "learning_rate": 4.584447941263149e-05, | |
| "loss": 0.6219, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.043010752688172046, | |
| "grad_norm": 0.8010571599006653, | |
| "learning_rate": 3.9930417452305626e-05, | |
| "loss": 0.594, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0456989247311828, | |
| "grad_norm": 0.7249171733856201, | |
| "learning_rate": 3.4297073302098156e-05, | |
| "loss": 0.588, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04838709677419355, | |
| "grad_norm": 0.9256644248962402, | |
| "learning_rate": 2.9049385504830985e-05, | |
| "loss": 0.6124, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.051075268817204304, | |
| "grad_norm": 1.1914323568344116, | |
| "learning_rate": 2.4285108555160577e-05, | |
| "loss": 0.7214, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.053763440860215055, | |
| "grad_norm": 1.3401687145233154, | |
| "learning_rate": 2.0092991918301108e-05, | |
| "loss": 0.7451, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.056451612903225805, | |
| "grad_norm": 1.589096188545227, | |
| "learning_rate": 1.6551126795408016e-05, | |
| "loss": 0.7814, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05913978494623656, | |
| "grad_norm": 1.599652647972107, | |
| "learning_rate": 1.3725491432254624e-05, | |
| "loss": 0.8536, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.06182795698924731, | |
| "grad_norm": 2.6867475509643555, | |
| "learning_rate": 1.1668722069349041e-05, | |
| "loss": 1.034, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.06451612903225806, | |
| "grad_norm": 2.4770703315734863, | |
| "learning_rate": 1.0419132428365116e-05, | |
| "loss": 1.4655, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06720430107526881, | |
| "grad_norm": 5.324666500091553, | |
| "learning_rate": 1e-05, | |
| "loss": 1.822, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06720430107526881, | |
| "eval_loss": 1.0087976455688477, | |
| "eval_runtime": 3.0723, | |
| "eval_samples_per_second": 16.274, | |
| "eval_steps_per_second": 4.231, | |
| "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": 2.66009604784128e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |