| { | |
| "best_metric": 1.8598170280456543, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.7476635514018691, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.029906542056074768, | |
| "grad_norm": 49.44677734375, | |
| "learning_rate": 5e-05, | |
| "loss": 6.1776, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.029906542056074768, | |
| "eval_loss": 6.561771869659424, | |
| "eval_runtime": 0.5288, | |
| "eval_samples_per_second": 94.549, | |
| "eval_steps_per_second": 24.583, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.059813084112149535, | |
| "grad_norm": 48.1866455078125, | |
| "learning_rate": 0.0001, | |
| "loss": 6.4729, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.08971962616822429, | |
| "grad_norm": 24.752422332763672, | |
| "learning_rate": 9.958086757163489e-05, | |
| "loss": 6.1342, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.11962616822429907, | |
| "grad_norm": 13.249516487121582, | |
| "learning_rate": 9.833127793065098e-05, | |
| "loss": 5.533, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.14953271028037382, | |
| "grad_norm": 8.379961013793945, | |
| "learning_rate": 9.627450856774539e-05, | |
| "loss": 5.0388, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.17943925233644858, | |
| "grad_norm": 7.7612175941467285, | |
| "learning_rate": 9.3448873204592e-05, | |
| "loss": 4.4187, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.20934579439252338, | |
| "grad_norm": 14.856832504272461, | |
| "learning_rate": 8.990700808169889e-05, | |
| "loss": 4.0229, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.23925233644859814, | |
| "grad_norm": 7.255392551422119, | |
| "learning_rate": 8.571489144483944e-05, | |
| "loss": 3.7519, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.2691588785046729, | |
| "grad_norm": 7.870395660400391, | |
| "learning_rate": 8.095061449516903e-05, | |
| "loss": 3.3613, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.29906542056074764, | |
| "grad_norm": 6.900554180145264, | |
| "learning_rate": 7.570292669790186e-05, | |
| "loss": 2.9486, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.32897196261682243, | |
| "grad_norm": 6.168272972106934, | |
| "learning_rate": 7.006958254769438e-05, | |
| "loss": 2.6565, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.35887850467289717, | |
| "grad_norm": 6.26072883605957, | |
| "learning_rate": 6.415552058736854e-05, | |
| "loss": 2.5059, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.38878504672897196, | |
| "grad_norm": 8.628870964050293, | |
| "learning_rate": 5.80709086014102e-05, | |
| "loss": 2.5369, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.41869158878504675, | |
| "grad_norm": 5.468209266662598, | |
| "learning_rate": 5.192909139858981e-05, | |
| "loss": 2.2559, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.4485981308411215, | |
| "grad_norm": 3.7481510639190674, | |
| "learning_rate": 4.584447941263149e-05, | |
| "loss": 2.0657, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.4785046728971963, | |
| "grad_norm": 2.8451316356658936, | |
| "learning_rate": 3.9930417452305626e-05, | |
| "loss": 2.3289, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.508411214953271, | |
| "grad_norm": 3.321988582611084, | |
| "learning_rate": 3.4297073302098156e-05, | |
| "loss": 2.3133, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.5383177570093458, | |
| "grad_norm": 2.810992956161499, | |
| "learning_rate": 2.9049385504830985e-05, | |
| "loss": 1.8864, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.5682242990654206, | |
| "grad_norm": 3.204352378845215, | |
| "learning_rate": 2.4285108555160577e-05, | |
| "loss": 1.7406, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.5981308411214953, | |
| "grad_norm": 2.5864105224609375, | |
| "learning_rate": 2.0092991918301108e-05, | |
| "loss": 1.7143, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6280373831775701, | |
| "grad_norm": 2.159916639328003, | |
| "learning_rate": 1.6551126795408016e-05, | |
| "loss": 1.6913, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.6579439252336449, | |
| "grad_norm": 1.9388976097106934, | |
| "learning_rate": 1.3725491432254624e-05, | |
| "loss": 1.7191, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.6878504672897197, | |
| "grad_norm": 2.578171491622925, | |
| "learning_rate": 1.1668722069349041e-05, | |
| "loss": 1.7615, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.7177570093457943, | |
| "grad_norm": 2.8211517333984375, | |
| "learning_rate": 1.0419132428365116e-05, | |
| "loss": 1.7873, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.7476635514018691, | |
| "grad_norm": 4.201313018798828, | |
| "learning_rate": 1e-05, | |
| "loss": 2.1359, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.7476635514018691, | |
| "eval_loss": 1.8598170280456543, | |
| "eval_runtime": 0.5258, | |
| "eval_samples_per_second": 95.095, | |
| "eval_steps_per_second": 24.725, | |
| "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": 4.16708196040704e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |