| { | |
| "best_metric": 11.071593284606934, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.008, | |
| "eval_steps": 25, | |
| "global_step": 47, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.064, | |
| "grad_norm": 2.7551679611206055, | |
| "learning_rate": 5e-05, | |
| "loss": 11.0895, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.064, | |
| "eval_loss": 11.088528633117676, | |
| "eval_runtime": 0.1013, | |
| "eval_samples_per_second": 1046.436, | |
| "eval_steps_per_second": 138.209, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.128, | |
| "grad_norm": 3.356942653656006, | |
| "learning_rate": 0.0001, | |
| "loss": 11.0903, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.192, | |
| "grad_norm": 3.378460168838501, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 11.0944, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.256, | |
| "grad_norm": 3.729534149169922, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 11.0861, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 3.094676971435547, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 11.0922, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.384, | |
| "grad_norm": 3.3166348934173584, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 11.0921, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.448, | |
| "grad_norm": 3.6665329933166504, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 11.0857, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.512, | |
| "grad_norm": 4.133778095245361, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 11.0874, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.576, | |
| "grad_norm": 3.0725619792938232, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 11.0896, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 3.256758451461792, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 11.0865, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.704, | |
| "grad_norm": 3.9415805339813232, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 11.0848, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.768, | |
| "grad_norm": 3.417839288711548, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 11.0847, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.832, | |
| "grad_norm": 3.2900781631469727, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 11.0839, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.896, | |
| "grad_norm": 3.490720748901367, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 11.0831, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 3.946263074874878, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 11.0783, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.024, | |
| "grad_norm": 3.4524974822998047, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 11.0873, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.088, | |
| "grad_norm": 3.8025898933410645, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 11.0816, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.152, | |
| "grad_norm": 3.968613386154175, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 11.0806, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.216, | |
| "grad_norm": 4.949509143829346, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 11.0765, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 4.188719272613525, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 11.0805, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.3439999999999999, | |
| "grad_norm": 3.8235926628112793, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 11.0809, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.408, | |
| "grad_norm": 4.225762844085693, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 11.077, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.472, | |
| "grad_norm": 5.48159122467041, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 11.076, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.536, | |
| "grad_norm": 3.7110719680786133, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 11.0746, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 4.030111312866211, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 11.0775, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_loss": 11.071593284606934, | |
| "eval_runtime": 0.1012, | |
| "eval_samples_per_second": 1047.442, | |
| "eval_steps_per_second": 138.341, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.6640000000000001, | |
| "grad_norm": 4.809144020080566, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 11.0729, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.728, | |
| "grad_norm": 5.203744888305664, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 11.078, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.792, | |
| "grad_norm": 3.483856678009033, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 11.0775, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.8559999999999999, | |
| "grad_norm": 4.308492660522461, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 11.0724, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 4.462175369262695, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 11.0692, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.984, | |
| "grad_norm": 4.674779891967773, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 11.0758, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.048, | |
| "grad_norm": 4.3319244384765625, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 11.0778, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.112, | |
| "grad_norm": 4.53694486618042, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 11.078, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.176, | |
| "grad_norm": 4.895163536071777, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 11.0718, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "grad_norm": 6.260696887969971, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 11.0733, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.304, | |
| "grad_norm": 3.851774215698242, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 11.0782, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.368, | |
| "grad_norm": 4.45391845703125, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 11.0703, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.432, | |
| "grad_norm": 5.240525722503662, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 11.0769, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.496, | |
| "grad_norm": 5.4221577644348145, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 11.0718, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "grad_norm": 4.008364200592041, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 11.0728, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.624, | |
| "grad_norm": 4.672859191894531, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 11.0769, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.6879999999999997, | |
| "grad_norm": 5.85573148727417, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 11.0651, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.752, | |
| "grad_norm": 5.035050868988037, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 11.0731, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.816, | |
| "grad_norm": 4.608683109283447, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 11.0689, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "grad_norm": 5.071901321411133, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 11.0771, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.944, | |
| "grad_norm": 6.193559169769287, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 11.0724, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 3.008, | |
| "grad_norm": 3.6927578449249268, | |
| "learning_rate": 0.0, | |
| "loss": 11.0724, | |
| "step": 47 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 47, | |
| "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": 3950531051520.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |